[go: up one dir, main page]

WO2025219784A1 - Prédiction de pression artérielle à partir d'un signal d'impulsion implantable - Google Patents

Prédiction de pression artérielle à partir d'un signal d'impulsion implantable

Info

Publication number
WO2025219784A1
WO2025219784A1 PCT/IB2025/053082 IB2025053082W WO2025219784A1 WO 2025219784 A1 WO2025219784 A1 WO 2025219784A1 IB 2025053082 W IB2025053082 W IB 2025053082W WO 2025219784 A1 WO2025219784 A1 WO 2025219784A1
Authority
WO
WIPO (PCT)
Prior art keywords
pressure values
processing circuitry
pressure value
pulse signal
overall
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/IB2025/053082
Other languages
English (en)
Inventor
Veronica RAMOS
Todd M. Zielinski
Shantanu Sarkar
Yong K. Cho
Patrick M. HERMANS
Nicholas H. FINSTROM
Aaron B. BARTNIK
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Medtronic Inc
Original Assignee
Medtronic Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Medtronic Inc filed Critical Medtronic Inc
Publication of WO2025219784A1 publication Critical patent/WO2025219784A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A61B5/02108—Measuring pressure in heart or blood vessels from analysis of pulse wave characteristics
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7221—Determining signal validity, reliability or quality
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A61B5/0215—Measuring pressure in heart or blood vessels by means inserted into the body
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
    • A61B5/024—Measuring pulse rate or heart rate
    • A61B5/02416—Measuring pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems

Definitions

  • This disclosure generally relates to medical devices and, more particularly, to disease state monitoring devices.
  • IMD implantable medical devices
  • cardiac, neurological, and/or other conditions of a patient may monitor physiological signals of the patient.
  • IMD may monitor an electrocardiogram (ECG) of the patient to monitor patient conditions.
  • ECG electrocardiogram
  • ECG electrocardiogram
  • such devices are configured to monitor patient conditions based on one or more physiological signals.
  • Such IMDs may process and/or transmit device data to investigate patient health.
  • the data may be transmitted to a cloud computing system, which may process the data for analysis and/or presentation to a user.
  • BP blood pressure
  • a patient may have a medical device system including one or more implantable medical devices (IMDs) that continuously monitor one or more physiological signals.
  • IMDs implantable medical devices
  • Processing circuitry of the system determines an overall systolic pressure value and an overall diastolic pressure value and provides notifications to one or both of the patient or a clinician to allow the patient and/or the clinician to address the patient’s BP.
  • the medical device system may determine a plurality of systolic pressure values and a corresponding plurality of diastolic pressure values based on a physiological signal, e.g., a pulse signal.
  • Processing circuitry of the medical device system may use the plurality of systolic pressure values and the corresponding plurality of diastolic pressure values to determine an overall systolic pressure value and an overall diastolic pressure value, i.e., an overall BP.
  • the medical device system may generate a notification of the overall BP and may send the notification to the patient and/or the clinician.
  • Hypertension is a serious condition and is associated with increased risk of cardiovascular events and other diseases. For example, uncontrolled hypertension increases risk of coronary artery disease, congestive heart failure (HF), renal failure, eyesight damage, and stroke.
  • HF congestive heart failure
  • renal failure renal failure
  • eyesight damage and stroke.
  • Hypertension can be treated by lifestyle changes, e.g., diet and exercise, and may also require medications, e.g., beta blockers, diuretics, and calcium channel blockers.
  • medications e.g., beta blockers, diuretics, and calcium channel blockers.
  • regular BP monitoring is essential to ensure BP stays within a healthy range.
  • Current methods of clinical management of hypertension mainly comprise scheduled logs of manual measurements at regular clinic visits, oftentimes using a BP cuff, and in emergencies via a more invasive procedure.
  • the techniques of this disclosure may be implemented by one or more IMDs that can continuously (e.g., on a periodic or triggered basis without human intervention) sense signals while subcutaneously implanted in a patient over months or years and perform numerous operations per second on the signals to enable the systems herein to determine an overall BP of a patient.
  • continuously monitoring e.g., monitoring daily or monitoring multiple times per day for a period of time, e.g., greater than a week, month, or year, without requiring user intervention
  • the techniques of this disclosure may facilitate the monitoring and subsequent treatment of hypertension or other related disease states. As such, the patient may be more likely to receive treatment in a timely manner, which may lead to better patient outcomes and quality of life.
  • the techniques of this disclosure may provide one or more additional technical and clinical advantages.
  • using the techniques of this disclosure with an IMD may be advantageous when a physician or other interested party cannot monitor a patient frequently enough over weeks or months to evaluate the patient.
  • Using the techniques of this disclosure with an IMD may advantageously allow continuous monitoring of patient BP without requiring subject compliance with attending clinic visits and may advantageously lower patient burden associated with clinic visits.
  • current techniques often rely on manual BP cuff measurements. Many patients experience anxiety during BP measurements and may resultingly present with artificially high BP due to their anxious state.
  • the techniques of this disclosure may prevent patient anxiety from affecting BP measurements, which may improve accuracy of patient status information, thereby improving patient outcomes.
  • the one or more IMDs include a single lead implantable cardiac monitor (ICM).
  • the ICM may be implanted via minimally invasive surgery.
  • the single lead ICM may be facilitate unobtrusive monitoring, e.g., relative to clinician visits and/or the use of BP cuffs.
  • the techniques of this disclosure may allow patients to perform daily activities more easily than with other methods of monitoring BP. For example, the patient may be able to attend fewer clinic visits. Additionally, monitoring patient BP via the single lead ICM rather than during clinic visits, the techniques of this disclosure may reduce clinician burden by reducing clinic visits.
  • BP blood pressure
  • changes in BP and health condition status between visits may go undetected.
  • Some patients may use conventional mechanical plethysmographic BP measurement devices at home, but still with relatively infrequent measurements having a quality dependent on the compliance and competence of the patient or a caregiver.
  • medical devices such as watches, patches, bands, fitness, trackers, or other external devices configured to sense BP, e.g., using photophethysmograpic techniques
  • the location and orientation, e.g., with respect to the heart, of the sensors used to sense BP values may vary between patients, and within a given patient over time, e.g., due to incorrect and/or variable device placement.
  • IMD implantable medical device
  • the continuously monitored pulse signals used by the processing circuitry to determine a BP of the patient, and in some examples, a health condition status of the patient based on trends in BP over time may improve accuracy of BP and BP trend determinations relative to BP and BP trends determined during in-office visits or by a patient manually taking BP measurements themselves.
  • improving the accuracy of BP and BP trend determinations may facilitate more accurate determinations of hypertension, cardiac wellness, and risk of sudden cardiac death, and may lead to clinical interventions to suppress hypertension such as medications and ablations.
  • the techniques may facilitate patient awareness of health issues and risks associated with high BP, which may lead patients to make lifestyle changes, such as increasing physical activity, losing weight, or limiting alcohol consumption.
  • the techniques of this disclosure may additionally include filtering out data that is deemed to be low quality or that may otherwise lead to inaccurate determinations of BP.
  • filtering out data that is low quality the techniques of this disclosure may advantageously result in more accurate determinations of BP, which may improve patient outcomes.
  • the techniques of this disclosure may include determining a patient status before analyzing pulse signal data.
  • the medical device system may determine whether to analyze the pulse signal data based on the patient status.
  • the techniques of this disclosure may prevent analysis of data that may not be representative of the patient’s BP, e.g., due to artifacts in the signal associated with, for example, a patient posture.
  • the techniques of this disclosure may include determining a pulse signal condition, e.g., a pulse signal quality, before analyzing the pulse signal data.
  • the medical device system may determine whether to analyze the pulse signal data based on the pulse signal quality. By determining whether to analyze the pulse signal data of the patient based on the pulse signal quality, the techniques of this disclosure may prevent analysis of low quality data that may not result in accurate BP measurements for the patient.
  • the techniques and systems of this disclosure may use a machine learning model to more accurately determine BP, BP trends, and/or health conditions associated with BP, e.g., hypertension.
  • Using techniques of this disclosure with an IMD may be advantageous when a physician cannot be continuously present with the patient over weeks or months to evaluate BP levels and/or where performing millions of operations on weeks or months of BP levels could not practically be performed in the mind of a physician with techniques of this disclosure, e.g., including use of a machine learning model.
  • a medical device system comprises: an optical sensor configured to sense a pulse signal; and processing circuitry configured to: determine a plurality of systolic pressure values and a corresponding plurality of diastolic pressure values based on an analysis of a predetermined length of the pulse signal, wherein the analysis comprises, for each of systolic pressure value of the plurality of systolic pressure values and each corresponding diastolic pressure value of the plurality of diastolic pressure values, applying a rolling window within the predetermined length of the pulse signal; determine an overall systolic pressure value based on the plurality of systolic pressure values and an overall diastolic pressure value based on the corresponding plurality of diastolic pressure values; and present the overall systolic pressure value and the overall diastolic pressure value to a user.
  • a method comprises: sensing, by an optical sensor of a medical device system, a pulse signal; and determining, by processing circuitry of the medical device system, a plurality of systolic pressure values and a corresponding plurality of diastolic pressure values based on an analysis of a predetermined length of the pulse signal, wherein the analysis comprises, for each of systolic pressure value of the plurality of systolic pressure values and each corresponding diastolic pressure value of the plurality of diastolic pressure values, applying a rolling window within the predetermined length of the pulse signal; determining, by the processing circuitry, an overall systolic pressure value based on the plurality of systolic pressure values and an overall diastolic pressure value based on the corresponding plurality of diastolic pressure values; and presenting, by the processing circuitry, the overall systolic pressure value and the overall diastolic pressure value to a user.
  • a non-transitory computer-readable medium stores instructions that when executed by processing circuitry cause the processing circuitry to: determine a plurality of systolic pressure values and a corresponding plurality of diastolic pressure values based on an analysis of a predetermined length of a pulse signal sensed by an optical sensor, wherein the analysis comprises, for each of systolic pressure value of the plurality of systolic pressure values and each corresponding diastolic pressure value of the plurality of diastolic pressure values, applying a rolling window within the predetermined length of the pulse signal; determine an overall systolic pressure value based on the plurality of systolic pressure values and an overall diastolic pressure value based on the corresponding plurality of diastolic pressure values; and present the overall systolic pressure value and the overall diastolic pressure value to a user.
  • FIG. 1 illustrates the environment of an example medical device system in conjunction with a patient, in accordance with one or more techniques of this disclosure.
  • FIG. 2 is a block diagram illustrating an example system configured to determine the disease state of a patient in accordance with one or more techniques of this disclosure.
  • FIGS. 3A and 3B are conceptual diagrams illustrating example implantable medical devices that operate in accordance with one or more techniques of this disclosure.
  • FIG. 4 is a block diagram illustrating an example configuration of an implantable medical device that operates in accordance with one or more techniques of this disclosure.
  • FIG. 5 is a block diagram illustrating an example configuration of an external device that operates in accordance with one or more techniques of this disclosure.
  • FIG. 6 is a flow diagram illustrating an example operation for determining an overall systolic pressure value and an overall diastolic pressure value of a patient, in accordance with one or more techniques of this disclosure.
  • FIG. 7 is a graph illustrating an optical signal, in accordance with one or more techniques of this disclosure.
  • FIG. 8 is a graph illustrating a plurality of systolic and diastolic pressure values during a predetermined length of pulse signal data, in accordance with one or more techniques of this disclosure.
  • FIG. 9 is a flow diagram illustrating an example operation for determining whether to analyze a predetermined length of pulse signal data based on a patient status, in accordance with one or more techniques of this disclosure.
  • FIG. 10A illustrates an example screen of a user interface indicative of a patient systolic and diastolic BP, in accordance with one or more techniques of this disclosure.
  • FIG. 10B illustrates an example screen of a user interface of systolic and diastolic pressure value trends, in accordance with one or more techniques of this disclosure.
  • FIG. 11 is a flow diagram illustrating an example operation for determining whether to analyze a predetermined length of pulse signal data based on one or more quality metrics, in accordance with one or more techniques of this disclosure.
  • FIG. 12 is a flow diagram illustrating an example operation for determining to cancel analysis of predetermined lengths of pulse signal data for a duration of time, in accordance with one or more techniques of this disclosure.
  • FIG. 13 is a flow diagram illustrating an example operation for determining an overall systolic pressure value and an overall diastolic pressure value based on pairs of pressure values meeting one or more criterion, in accordance with one or more techniques of this disclosure.
  • FIG. 14 is a flow diagram illustrating an example operation for determining whether to remove a pair of pressure values from a plurality of pairs of pressure values, in accordance with one or more techniques of this disclosure.
  • FIG. 15 is a conceptual diagram illustrating an example machine learning model configured to determine patient blood pressure, in accordance with one or more techniques of this disclosure.
  • FIG. 16 is a conceptual diagram illustrating an example training process for a machine learning model, in accordance with one or more techniques of this disclosure.
  • An implantable medical device may include an optical sensor to sense BP.
  • the optical sensors used by IMDs to sense BP may be integrated with a housing of the IMD and/or coupled to the IMD via one or more elongated leads.
  • Example IMDs that may be configured to monitor BP include pacemakers and implantable cardioverter-defibrillators, which may be coupled to intravascular or extravascular leads, as well as pacemakers with housings configured for implantation within the heart, which may be leadless.
  • An example of pacemaker configured for intracardiac implantation is the MicraTM Transcatheter Pacing System, available from Medtronic, Inc.
  • IMDs that do not provide therapy may be configured to sense BP.
  • IMD Reveal LINQTM and LINQ IITM Insertable Cardiac Monitors (ICMs), available from Medtronic, Inc., which may be inserted subcutaneously.
  • ICMs Reveal LINQTM and LINQ IITM Insertable Cardiac Monitors
  • Such IMDs may facilitate relatively longer-term monitoring of patients during normal daily activities and may periodically transmit collected data to a network service, such as the Medtronic CareLinkTM Network.
  • Any medical device configured to sense BP via implanted sensors may implement the techniques of this disclosure for evaluating physiological signals to determine a patient BP and/or trend in BP.
  • the techniques of this disclosure may additionally facilitate monitoring and/or identification of a health condition status of a patient, such as a degree of hypertension, may facilitate determinations of a degree of hypertension, cardiac wellness, and risk of sudden cardiac death, and may lead to clinical interventions to suppress hypertension such as medications and ablations.
  • FIG. 1 illustrates the environment of an example medical device system 2 in conjunction with a patient 4, in accordance with one or more techniques of this disclosure.
  • the example techniques may be used with one or more patient sensing devices, e.g., including an IMD 10, which may be in wireless communication with one or more computing devices, e.g., external device 12.
  • IMD 10 includes a sensor configured to sense a pulse signal, and in some examples, one or more additional sensors to sense other physiological signals of patient 4.
  • IMD 10 may collect and store one or more features of the sensed signals.
  • the sensor configured to sense the pulse signal may be an optical sensor, such as a photoplethysmography (PPG) sensor.
  • PPG photoplethysmography
  • the sensor configured to sense the pulse signal may be an accelerometer, microphone, capacitive BP sensor, etc.
  • One or more elements of system 2 may determine a BP of patient 4 based on the collected data.
  • IMD 10 may be implanted outside of a thoracic cavity of patient 4 (e.g., subcutaneously in the pectoral location illustrated in FIG. 1). IMD 10 may be positioned near the sternum near or just below the level of the heart of patient 4, e.g., at least partially within the cardiac silhouette, and be configured to sense a pulse signal, and ECG signal, and/or other physiological signals from that position.
  • IMD 10 may be configured to be implanted subcutaneously in patient 4 and may include an optical sensor(s) 358 (as shown in FIG. 3A). In some examples, IMD 10 may include additional sensor(s) 456 (as shown in FIG. 4) to the optical sensor(s) 358. Some examples of physiological signals that may be sensed by such devices may include BP signals, electrocardiogram (ECG) signals, temperature signals, respiration signals, impedance signals, and/or patient activity/posture signals. In some examples, IMD 10 may include electrodes and other sensors 456, in addition to optical sensor(s) 358 to sense physiological signals of patient 4. In some examples, the optical sensor(s) 358 of IMD 10 is a photoplethysmography (PPG) sensor. In some examples, IMD 10 takes the form of the Reveal LINQTM or LINQ II ICMTM, or another ICM similar to, e.g., a version or modification of, the LINQTM ICMs.
  • PPG photoplethys
  • IMD 10 is a single lead ICM
  • the ICM may be implanted via minimally invasive surgery.
  • the single lead ICM may facilitate unobtrusive monitoring.
  • the techniques of this disclosure may be implemented in systems including any one or more implantable or external medical devices, including monitors, pacemakers, defibrillators (e.g., subcutaneous or substernal), wearable external defibrillators (WAEDs), neurostimulators, drug pumps, patch monitors, or wearable physiological monitors, e.g., wrist or head wearable devices. Examples with multiple IMDs or other sensing devices may be able to collect different data useable by system 2 to determine a BP of patient 4.
  • External device 12 may be a computing device with a display viewable by a user, e.g., patient 4 or the clinician, and an interface for providing input to external device 12 (i.e., a user input mechanism). External device 12 is configured for wireless communication with IMD 10. External device 12 retrieves sensed physiological data from IMD 10 that was collected and stored by the IMD. In some examples, external device 12 takes the form of a personal computing device of patient 4. For example, external device 12 may take the form of a smartphone of patient 4. In some examples, external device 12 may be any computing device configured for wireless communication with IMD 10, such as a desktop, laptop, or tablet computer.
  • External device 12 may communicate with IMD 10 via near-field communication technologies e.g., inductive coupling, NFC, pulsed light communications, e.g., light fidelity (Li-Fi), or other communication technologies operable at ranges less than 10-20 cm, and far-field communication technologies, e.g., radiofrequency telemetry according to the Bluetooth® or Bluetooth® Low Energy (BLE) protocols, or other communication technologies operable at ranges greater than near-field communication technologies.
  • near-field communication technologies e.g., inductive coupling, NFC, pulsed light communications, e.g., light fidelity (Li-Fi), or other communication technologies operable at ranges less than 10-20 cm
  • far-field communication technologies e.g., radiofrequency telemetry according to the Bluetooth® or Bluetooth® Low Energy (BLE) protocols, or other communication technologies operable at ranges greater than near-field communication technologies.
  • BLE Bluetooth® Low Energy
  • external device 12 may be used to transmit instructions to IMD 10.
  • the clinician may also configure and store operational
  • External device 12 may be used to retrieve data from IMD 10.
  • the retrieved data may include signal data and/or one or more features of the signal data determined by IMD 10 based on signals sensed by IMD 10.
  • external device 12 may retrieve physiological signal data, e.g., pulse signal data, on a regular transmission schedule, e.g., daily, due to IMD 10 determining that the patient is at a particular activity level or posture, or in response to a request to record the segment from patient 4 or another user.
  • IMD 10 may include a sensor configured to sense motion, vibration, and/or orientation with respect to earth gravity, such as an accelerometer configured to sense activity of patient 4.
  • external device 12 may retrieve data indicative of one or more features and/or a plurality of systolic pressure values and a plurality of diastolic pressure values determined by IMD 10 based on the signals.
  • Processing circuitry of system 2 may be configured to perform the example techniques described herein for determining overall BP based on data collected by IMD 10.
  • one or more of the sensors, e.g., of IMD 10 may be implanted within patient 4, that is, implanted at least subcutaneously.
  • one or more of the sensors of IMD 10 may be located externally to patient 4, for example as part of a cuff or as a wearable device.
  • IMD 10 transmits data to an external device 12, e.g., a smartphone of the patient, configured with an application (e.g., the Medtronic My CareLinkTM Heart application), which may include an artificial intelligence (Al) application, to process the data, track any changes, and notify the clinician and the patient when a visit to clinic is advised or recommended.
  • the Al application comprises a machine learning (ML) model.
  • the ML model may be configured to process device data, e.g., based on a pulse signal and/or one or more other physiological signals. The ML model may process the data to determine the patient BP.
  • IMD 10 transmits data, e.g., via tissue conductive communication, to a second IMD (not depicted), e.g., an IMD with higher processing power and/or battery capacity, to process the data.
  • the second IMD may process the data to determine patient 4’s BP. Additionally, or alternatively, the second IMD may utilize the data as part of detecting episodes, e.g., arrhythmia episodes, of patient 4.
  • the second IMD may be configured to deliver therapy, e.g., to administer shocks.
  • the second IMD may increase an accuracy of arrhythmia episode detection, thereby preventing inappropriate shocks.
  • FIG. 2 is a block diagram illustrating an example system that includes an access point 210, a network 220, external computing devices, such as server 230, and one or more other computing devices 240A-240N, which may be coupled to IMD 10, and external device 12 via network 220, in accordance with one or more techniques described herein.
  • IMD 10 may communicate with external device 12 via a first wireless connection and may communicate with an access point 210 via a second wireless connection.
  • access point 210, external device 12, server 230, and computing devices 240A-240N are interconnected and may communicate with each other through network 220.
  • Access point 210 may include a device that connects to network 220 via any of a variety of connections, such as telephone dial-up, digital subscriber line (DSL), or cable modem connections. In other examples, access point 210 may be coupled to network 220 through different forms of connections, including wired or wireless connections.
  • access point 90 may be a user device, such as a tablet or smartphone, that may be co-located with the patient.
  • IMD 10 may be configured to transmit physiological data to external device 12.
  • access point 210 may interrogate IMD 10, such as periodically or in response to a command from the patient or network 220, in order to retrieve patient data from IMD 10. Access point 210 may be communicate the retrieved data to server 230 via network 220.
  • server 230 may be configured to provide a secure storage site for data that has been collected from IMD 10, and/or external device 12. In some cases, server 230 may assemble data for viewing by clinicians via computing devices 240 A- 240N.
  • One or more aspects of the illustrated system of FIG. 2 may be implemented with general network technology and functionality, which may be similar to that provided by the Medtronic CareLinkTM Network developed by Medtronic, Inc.
  • Server 230 may include processing circuitry 234.
  • Processing circuitry 234 may include fixed function circuitry and/or programmable processing circuitry.
  • Processing circuitry 234 may include any one or more of a microprocessor, a controller, digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), graphics processing unit (GPU), tensor processing unit (TPU), or equivalent discrete or analog logic circuitry.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field-programmable gate array
  • GPU graphics processing unit
  • TPU tensor processing unit
  • processing circuitry 234 may include multiple components, such as any combination of one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, or one or more FGPAs, one or more GPUs, one or more TPUs, as well as other discrete or integrated logic circuitry.
  • the functions attributed to processing circuitry 234 may be embodied as software, firmware, hardware, or any combination thereof.
  • processing circuitry 234 may perform one or more techniques described herein to determine BP based on a pulse signal, one or more other physiological signals, and/or features determined based on such signals and received from IMD 10, as examples.
  • Server 230 may include storage device 232.
  • Storage device 232 includes computer-readable instructions that, when executed by processing circuitry 234, cause IMD 10 and processing circuitry 234 to perform various functions attributed to IMD 10 and processing circuitry 234 herein.
  • Storage device 232 may include any volatile, nonvolatile, magnetic, optical, or electrical media, such as random access memory (RAM), read only memory (ROM), non-volatile RAM (NVRAM), electronically erasable programmable ROM (EEPROM), flash memory, or any other digital media.
  • RAM random access memory
  • ROM read only memory
  • NVRAM non-volatile RAM
  • EEPROM electronically erasable programmable ROM
  • flash memory or any other digital media.
  • one or more of computing devices 240A-240N may be a tablet or other smart device located with a clinician, by which the clinician may program, receive alerts from, and/or interrogate IMD 10.
  • the clinician may access data corresponding to a pulse signal, one or more other physiological signals, and/or features based on the signals collected by IMD 10, or disease state updates determined by IMD 10 based on such features and/or signals, through device 240A, such as when patient 4 is in between clinician visits, to check on a status of patient 4.
  • the clinician may enter instructions for medical intervention for patient 4 into an application in computing device 240A, such as based on a status of a patient condition determined by IMD 10, external device 12, or the combination thereof, or based on other patient data known to the clinician.
  • Computing device 240A may then transmit the instructions for medical intervention to another of computing devices 240, e.g., computing device 240B, located with patient 4 or a caregiver of patient 4.
  • such instructions for medical intervention may include an instruction to change a drug dosage, timing, or selection, to make a lifestyle modification, e.g., to engage in relaxation and stress-reducing activities, to increase activity level, to limit sodium intake, or to limit alcohol consumption, to schedule a visit with the clinician, or to seek medical attention.
  • patient 4 may be empowered to take action, as needed, to address his or her medical status, which may help improve clinical outcomes for patient 4.
  • FIG. 3 A is a perspective drawing illustrating an IMD 10A, which may be an example configuration of IMD 10 of FIG. 1 as an ICM.
  • IMD 10A may be embodied as a monitoring device having housing 312, proximal electrode 316A, distal electrode 316B, and optical sensor(s) 358.
  • the optical sensor(s) 358 may be positioned at various locations on IMD 10A.
  • Housing 312 may further comprise first major surface 314, second major surface 318, proximal end 320, and distal end 322. Housing 312 encloses electronic circuitry located inside the IMD 10A and protects the circuitry contained therein from body fluids. Housing 312 may be hermetically sealed and configured for subcutaneous implantation. Electrical feedthroughs provide electrical connection of electrodes 316A and 316B.
  • IMD 10A is defined by a length /., a width W and thickness or depth D and is in the form of an elongated rectangular prism wherein the length L is much larger than the width W, which in turn is larger than the depth D.
  • the geometry of the IMD 10A - in particular a width W greater than the depth D - is selected to allow IMD 10A to be inserted under the skin of the patient using a minimally invasive procedure and to remain in the desired orientation during insertion.
  • the device shown in FIG. 3 A includes radial asymmetries (notably, the rectangular shape) along the longitudinal axis that maintains the device in the proper orientation following insertion.
  • the spacing between proximal electrode 316A and distal electrode 316B may range from 5 millimeters (mm) to 55 mm, 30 mm to 55 mm, 35 mm to 55 mm, and from 40 mm to 55 mm and may be any range or individual spacing from 5 mm to 60 mm.
  • IMD 10A may have a length L that ranges from 30 mm to about 70 mm. In other examples, the length L may range from 5 mm to 60 mm, 40 mm to 60 mm, 45 mm to 60 mm and may be any length or range of lengths between about 30 mm and about 70 mm.
  • the width W of major surface 314 may range from 3 mm to 15, mm, from 3 mm to 10 mm, or from 5 mm to 15 mm, and may be any single or range of widths between 3 mm and 15 mm.
  • the thickness of depth D of IMD 10A may range from 2 mm to 15 mm, from 2 mm to 9 mm, from 2 mm to 5 mm, from 5 mm to 15 mm, and may be any single or range of depths between 2 mm and 15 mm.
  • IMD 10A according to an example of the present disclosure is has a geometry and size designed for ease of implant and patient comfort. Examples of IMD 10A described in this disclosure may have a volume of three cubic centimeters (cm) or less, 1.5 cubic cm or less or any volume between three and 1.5 cubic centimeters.
  • proximal end 320 and distal end 322 are rounded to reduce discomfort and irritation to surrounding tissue once inserted under the skin of the patient.
  • IMD 10A including instrument and method for inserting IMD 10A is described, for example, in U.S. Patent Publication No. 2014/0276928, incorporated herein by reference in its entirety.
  • Proximal electrode 316A is at or proximate to proximal end 320, and distal electrode 16B is at or proximate to distal end 322.
  • Proximal electrode 316A and distal electrode 316B are used to sense ECG signals thoracically outside the ribcage, which may be implanted sub-muscularly or subcutaneously.
  • ECG signals may be stored in a memory of IMD 10 A, and data may be transmitted via integrated antenna 330A to another device, which may be another implantable device or an external device, such as external device 312.
  • electrodes 316A and 316B may additionally or alternatively be used for sensing any bio-potential signal of interest, which may be, for example, an electroencephalogram (EEG), electromyogram (EMG), or a nerve signal, or for measuring impedance, from any implanted location.
  • EEG electroencephalogram
  • EMG electromyogram
  • nerve signal or for measuring impedance, from any implanted location.
  • proximal electrode 316A is at or in close proximity to the proximal end 320 and distal electrode 316B is at or in close proximity to distal end 322.
  • distal electrode 316B is not limited to a flattened, outward facing surface, but may extend from first major surface 314 around rounded edges 324 and/or end surface 326 and onto the second major surface 318 so that the electrode 316B has a three-dimensional curved configuration.
  • electrode 316B is an uninsulated portion of a metallic, e.g., titanium, part of housing 312.
  • proximal electrode 316A is located on first major surface 314 and is substantially flat, and outward facing.
  • proximal electrode 316A may utilize the three-dimensional curved configuration of distal electrode 316B, providing a three dimensional proximal electrode (not shown in this example).
  • distal electrode 316B may utilize a substantially flat, outward facing electrode located on first major surface 314 similar to that shown with respect to proximal electrode 316A.
  • proximal electrode 316A and distal electrode 316B are located on both first major surface 314 and second major surface 318.
  • proximal electrode 316A and distal electrode 316B are located on both major surfaces 314 and 318.
  • both proximal electrode 316A and distal electrode 316B are located on one of the first major surface 314 or the second major surface 318 (e.g., proximal electrode 316A located on first major surface 314 while distal electrode 316B is located on second major surface 318).
  • IMD 10A may include electrodes on both major surface 314 and 318 at or near the proximal and distal ends of the device, such that a total of four electrodes are included on IMD 10A.
  • Electrodes 316A and 316B may be formed of a plurality of different types of biocompatible conductive material, e.g., stainless steel, titanium, platinum, iridium, or alloys thereof, and may utilize one or more coatings such as titanium nitride or fractal titanium nitride.
  • proximal end 320 includes a header assembly 328 that includes one or more of proximal electrode 316A, integrated antenna 330A, anti-migration projections 332, and/or suture hole 334.
  • Integrated antenna 330A is located on the same major surface (i.e., first major surface 314) as proximal electrode 316A and is also included as part of header assembly 328.
  • Integrated antenna 330A allows IMD 10A to transmit and/or receive data.
  • integrated antenna 330A may be formed on the opposite major surface as proximal electrode 316A or may be incorporated within the housing 312 of IMD 10A. In the example shown in FIG.
  • antimigration projections 332 are located adjacent to integrated antenna 330A and protrude away from first major surface 314 to prevent longitudinal movement of the device.
  • anti-migration projections 332 include a plurality of small bumps or protrusions (e.g., nine) extending away from first major surface 314.
  • anti-migration projections 332 may be located on the opposite major surface as proximal electrode 316A and/or integrated antenna 330A.
  • header assembly 328 includes suture hole 334, which provides another means of securing IMD 10A to the patient to prevent movement following insertion.
  • header assembly 328 is a molded header assembly made from a polymeric or plastic material, which may be integrated or separable from the main portion of IMD 10 A.
  • FIG. 3B is a perspective drawing illustrating another IMD 10B, which may be another example configuration of IMD 10 from FIG. 1 as an ICM.
  • IMD 10B of FIG. 3B may be configured substantially similarly to IMD lOA of FIG. 3 A, with differences between them discussed herein.
  • IMD 10B may include a leadless, subcutaneously-implantable monitoring device, e.g., an ICM.
  • IMD 10B includes housing having a base 340 and an insulative cover 342.
  • Proximal electrode 316C, distal electrode 316D, and optical sensor(s) 358 may be formed or placed on an outer surface of cover 342.
  • Various circuitries and components of IMD 10B may be formed or placed on an inner surface of cover 342, or within base 340.
  • a battery or other power source of IMD 10B may be included within base 340.
  • antenna 330B is formed or placed on the outer surface of cover 342 but may be formed or placed on the inner surface in some examples.
  • insulative cover 342 may be positioned over an open base 340 such that base 340 and cover 342 enclose the circuitries and other components and protect them from fluids such as body fluids.
  • the housing including base 370 and insulative cover 372 may be hermetically sealed and configured for subcutaneous implantation.
  • Circuitries and components may be formed on the inner side of insulative cover 342, such as by using flip-chip technology.
  • Insulative cover 342 may be flipped onto a base 340. When flipped and placed onto base 340, the components of IMD 10B formed on the inner side of insulative cover 342 may be positioned in a gap 344 defined by base 340. Electrodes 316C and 316D and antenna 330B may be electrically connected to circuitry formed on the inner side of insulative cover 342 through one or more vias (not shown) formed through insulative cover 342.
  • Insulative cover 342 may be formed of sapphire (i.e., corundum), glass, parylene, and/or any other suitable insulating material.
  • Base 340 may be formed from titanium or any other suitable material (e.g., a biocompatible material). Electrodes 316C and 316D may be formed from any of stainless steel, titanium, platinum, iridium, or alloys thereof. In addition, electrodes 316C and 316D may be coated with a material such as titanium nitride or fractal titanium nitride, although other suitable materials and coatings for such electrodes may be used.
  • a material such as titanium nitride or fractal titanium nitride, although other suitable materials and coatings for such electrodes may be used.
  • the housing of IMD 10B defines a length I., a width W and thickness or depth D and is in the form of an elongated rectangular prism wherein the length L is much larger than the width W, which in turn is larger than the depth D, similar to IMD 10A of FIG. 3 A.
  • the spacing between proximal electrode 316C and distal electrode 316D may range from 5 mm to 50 mm, from 30 mm to 50 mm, from 35 mm to 45 mm, and may be any single spacing or range of spacings from 5 mm to 50 mm, such as approximately 40 mm.
  • IMD 10B may have a length L that ranges from 5 mm to about 70 mm.
  • the length L may range from 30 mm to 70 mm, 40 mm to 60 mm, 45 mm to 55 mm, and may be any single length or range of lengths from 5 mm to 50 mm, such as approximately 45 mm.
  • the width may range from 3 mm to 15 mm, 5 mm to 15 mm, 5 mm to 10 mm, and may be any single width or range of widths from 3 mm to 15 mm, such as approximately 8 mm.
  • the thickness or depth D of IMD 10B may range from 2 mm to 15 mm, from 5 mm to 15 mm, or from 3 mm to 5 mm, and may be any single depth or range of depths between 2 mm and 15 mm, such as approximately 4 mm.
  • IMD 10B may have a volume of three cubic centimeters (cm) or less, or 1.5 cubic cm or less, such as approximately 1.4 cubic cm.
  • outer surface of cover 342 faces outward, toward the skin of the patient.
  • proximal end 346 and distal end 348 are rounded to reduce discomfort and irritation to surrounding tissue once inserted under the skin of the patient.
  • edges of IMD 10B may be rounded.
  • FIG. 4 is a block diagram illustrating an example configuration of an IMD 10 in accordance with one or more techniques described herein.
  • IMD 10 may correspond to either of IMDs 10A and 10B, or another configuration of an IMD.
  • IMD 10 includes electrodes 316 (which may correspond to any of electrodes 316A-316D), processing circuitry 450, sensing circuitry 454, sensor(s) 456, communication circuitry 460, power source 482, and memory 452.
  • the illustrated example includes two electrodes 316, IMDs including or coupled to more than two electrodes may implement the techniques of this disclosure in some examples. Additionally, IMDs without electrodes may implement the techniques of this disclosure in some examples.
  • Processing circuitry 450 may include fixed function circuitry and/or programmable processing circuitry. Processing circuitry 450 may include any one or more of a microprocessor, a controller, a DSP, an ASIC, a FPGA, a GPU, a TPU, or equivalent discrete or analog logic circuitry.
  • processing circuitry 450 may include multiple components, such as any combination of one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, or one or more FPGAs, one or more GPUs, one or more TPUs, as well as other discrete or integrated logic circuitry.
  • the functions attributed to processing circuitry 450 herein may be embodied as software, firmware, hardware, or any combination thereof.
  • Sensing circuitry 454 may be coupled to electrodes 316 to sense electrical signals of the heart of patient 4, for example by selecting electrodes 316 and polarity, used to sense an ECG as controlled by processing circuitry 450. Sensing circuitry 454 may sense the ECG from electrodes 316 in order to facilitate monitoring the electrical activity of the heart. In some examples, sensing circuitry 454 may include one or more filters and amplifiers for filtering and amplifying signals received from electrodes 316 and/or sensor(s) 456. Sensing circuitry 454 and processing circuitry 450 may store ECG data in memory 452.
  • Sensing circuitry 454 may additionally be coupled to optical sensor(s) 358 of sensor(s) 456 to sense a pulse signal of patient 4, e.g., via emitter(s) 462 and detector(s) 464.
  • One or more optical sensor(s) 358 may include one or more light detector(s) 464 configured to receive and/or detect light signals, such as reflected light signals originating from light emitter(s) 462.
  • optical emitter(s) 462 may be configured to emit light signals belonging to a particular wavelength spectrum. Some examples of a particular wavelength spectrum may be an amber wavelength spectrum, a green wavelength spectrum, yellow wavelength spectrum, blue wavelength spectrum, or other wavelength spectrums.
  • Optical detector(s) 464 may be configured to receive optical signals of the corresponding particular wavelength spectrum, e.g., facilitated by filtering, masking, or photodiode material selection, such as an amber wavelength spectrum, a green wavelength spectrum, yellow wavelength spectrum, blue wavelength spectrum, or other wavelength spectrum.
  • Light signals received and/or detected by optical sensor(s) 358 may be referred to as optical signals.
  • one or more of optical sensor(s) 358 may be configured as a PPG sensor, e.g., by being configured to receive light reflected by blood in one or more blood vessels.
  • an optical sensor(s) 358 may be included in a same sensor package and/or may be implemented using the same transducer(s).
  • IMD 10 may, in some cases, include one or more optical sensor(s) 358 including two or more light emitters 464 and one or more light detectors 464.
  • processing circuitry 450 may apply the optical signals and/or the levels or features described herein to a machine learning model to determine the health condition status of the patient.
  • processing circuitry 450 may be configured to identify a wavelength spectrum of the optical signals.
  • processing circuitry 450 may select a machine learning model trained on training data having a wavelength spectrum that corresponds to the wavelength spectrum of the optical signals and apply the selected machine learning model, that corresponds to the wavelength spectrum of the optical signals, to the optical signals.
  • the pulse signal may be sensed by a plurality of other sensors, such as an accelerometer or a capacitive BP sensor and is not limited to an optical sensor.
  • Optical sensor(s) 358 serves merely as an example.
  • Communication circuitry 460 may include any suitable hardware, firmware, software, or any combination thereof for communicating with another device, such as external device 12, another networked computing device, or another IMD or sensor. Under the control of processing circuitry 450, communication circuitry 460 may receive downlink telemetry from, as well as send uplink telemetry to external device 12. In addition, processing circuitry 450 may communicate with a networked computing device via an external device (e.g., external device 12) and a computer network, such as the Medtronic CareLinkTM Network. Communication circuitry 460 may be configured to transmit and/or receive signals via inductive coupling, electromagnetic coupling, Near Field Communication (NFC), Radio Frequency (RF) communication, Bluetooth, Wi-Fi, or other proprietary or non-proprietary wireless communication schemes.
  • NFC Near Field Communication
  • RF Radio Frequency
  • One or more memory devices 452 may be configured to store information within IMD 10 during operation.
  • Memory device 452 in some examples, is described as a computer-readable storage medium.
  • memory device 452 is a temporary memory, meaning that a primary purpose of memory device 452 is not longterm storage.
  • Memory device 452, in some examples, is described as a volatile memory, meaning that memory device 452 does not maintain stored contents when the computer is turned off. Examples of volatile memories include RAM, dynamic RAM (DRAM), static RAM (SRAM), and other forms of volatile memories known in the art.
  • memory device 452 is used to store program instructions for execution by processing circuitry 450.
  • Storage device 452 in one example, is used by software or applications 470 running on IMD 10A to temporarily store information during program execution.
  • Memory device 452 also includes one or more non- transitory computer-readable storage media.
  • Memory device 452 may be configured to store larger amounts of information than volatile memory.
  • Memory devices 452 may further be configured for long-term storage of information.
  • memory devices 452 includes non-volatile storage elements. Examples of such non-volatile storage elements include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or EEPROM memories.
  • memory 452 may be configured to store physiological data, e.g., pulse signal data.
  • Memory 452 may additionally be configured to store one or more applications including program instructions and/or data that are executable by processing circuitry 450.
  • the one or more applications may be configured to determine one or more features of the physiological signals, and, in some examples, a plurality of systolic pressure values, a plurality of corresponding diastolic values, and/or overall BP based on the one or more features.
  • the one or more applications may implement a machine learning model to determine the one or more features, the plurality of systolic pressure values, the plurality of corresponding diastolic values, and/or to determine the overall BP.
  • processing circuitry 450 may control communication circuitry 460 to transmit signal data, e.g., the one or more features used to determine BP to another device, e.g., external device 12 or a cloud computing system comprising one or more computing devices, for analysis to determine BP according to the techniques of this disclosure.
  • sensor(s) 456 may additionally include one or more additional sensors to sense one or more additional signals, such as BP signals, ECG signals, temperature signals, respiration signals, and/or patient activity/posture signals.
  • processing circuitry 450 may use one or more features based on the one or more additional signals to determine patient BP, such as one or more pulse transit time (PTT) features and/or one or more pulse wave velocity features based on the pulse signal and an ECG signal. Additionally, or alternatively, processing circuitry 450 may determine the one or more features of the one or more additional signals to determine whether to determine patient BP using the pulse signal. As an example, processing circuitry 450 may determine not to determine patient BP using a captured segment, e.g., a 10 second segment, of pulse signal data when the patient activity/posture signal does not meet one or more criteria.
  • a captured segment e.g., a 10 second segment
  • processing circuitry 450 may determine a pulse signal condition indicative of the pulse signal quality.
  • ambient light interference e.g., through the skin and to the optical sensor, can reduce pulse signal quality.
  • Processing circuitry 450 may determine whether to determine patient BP based on the pulse signal condition. As an example, processing circuitry 450 may determine not to determine patient BP using a captured segment, e.g., a 10 second segment, of pulse signal data when the pulse signal quality does not meet one or more criteria.
  • FIG. 5 is a block diagram illustrating an example configuration of external device 12.
  • external device 12 takes the form of a smartphone, a laptop, a tablet computer, a personal digital assistant (PDA), a smartwatch or other wearable computing device.
  • computing devices 240 and/or server 230 may be configured similarly to the configuration of external device 12 illustrated in FIG. 5.
  • external device 12 may be logically divided into user space 502, kernel space 504, and hardware 506.
  • Hardware 506 may include one or more hardware components that provide an operating environment for components executing in user space 502 and kernel space 504.
  • kernel space 504 may represent different sections or segmentations of memory, where kernel space 504 provides higher privileges to processes and threads than user space 502.
  • kernel space 504 may include operating system 520, which operates with higher privileges than components executing in user space 502.
  • hardware 506 includes processing circuitry 530, memory 532, one or more input devices 534, one or more output devices 536, one or more sensors 538, and communication circuitry 540.
  • external device 12 may be any component or system that includes processing circuitry or other suitable computing environment for executing software instructions and, for example, need not necessarily include one or more elements shown in FIG. 5.
  • Processing circuitry 530 is configured to implement functionality and/or process instructions for execution within external device 12.
  • processing circuitry 530 may be configured to receive and process instructions stored in memory 532 that provide functionality of components included in kernel space 504 and user space 502 to perform one or more operations in accordance with techniques of this disclosure.
  • Examples of processing circuitry 530 may include, any one or more microprocessors, controllers, GPUs, TPUs, DSPs, ASICs, FPGAs, or equivalent discrete or integrated logic circuitry.
  • Memory 532 may be configured to store information within external device 12, for processing during operation of external device 12.
  • Memory 532 in some examples, is described as a computer-readable storage medium.
  • memory 532 includes a temporary memory or a volatile memory. Examples of volatile memories include RAM, DRAM, SRAM, and other forms of volatile memories known in the art.
  • Memory 532 in some examples, also includes one or more memories configured for longterm storage of information, e.g. including non-volatile storage elements. Examples of such non-volatile storage elements include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories.
  • EPROM electrically programmable memories
  • EEPROM electrically erasable and programmable
  • memory 532 includes cloud-associated storage.
  • One or more input devices 534 of external device 12 may receive input, e.g., from patient 4, a clinician, or another user. Examples of input are tactile, audio, kinetic, and optical input. Input devices 534 may include, as examples, a mouse, keyboard, voice responsive system, camera, buttons, control pad, microphone, presence-sensitive or touch- sensitive component (e.g., screen), or any other device for detecting input from a user or a machine.
  • One or more output devices 536 of external device 12 may generate output, e.g., to patient 4 or another user. Examples of output are tactile, haptic, audio, and visual output.
  • Output devices 536 of external device 12 may include a presence-sensitive screen, sound card, video graphics adapter card, speaker, cathode ray tube monitor, liquid crystal display (LCD), light emitting diodes (LEDs), or any type of device for generating tactile, audio, and/or visual output.
  • One or more sensors 538 of external device 12 may sense physiological parameters or signals of patient 4.
  • Sensor(s) 538 may include electrodes, an optical sensor, accelerometers (e.g., 3-axis accelerometers), impedance sensors, temperature sensors, pressure sensors, heart sound sensors (e.g., microphones or accelerometers), and other sensors, and sensing circuitry (e.g., including an ADC), similar to those described above with respect to IMD 10.
  • accelerometers e.g., 3-axis accelerometers
  • impedance sensors e.g., impedance sensors
  • temperature sensors e.g., pressure sensors
  • heart sound sensors e.g., microphones or accelerometers
  • other sensors e.g., microphones or accelerometers
  • Communication circuitry 540 of external device 12 may communicate with other devices by transmitting and receiving data.
  • Communication circuitry 540 may receive physiological data from IMD 10, such as pulse signal data, and/or accelerometer signal data, from communication circuitry in IMD 10.
  • Communication circuitry 540 may include a network interface card, such as an Ethernet card, an optical transceiver, a radio frequency transceiver, or any other type of device that can send and receive information.
  • communication circuitry 540 may include a radio transceiver configured for communication according to standards or protocols, such as 3G, 4G, 5G, WiFi (e.g., 802.11 or 802.15 ZigBee), Bluetooth®, or Bluetooth® Low Energy (BLE).
  • health monitoring application 550 executes in user space 502 of external device 12.
  • Health monitoring application 550 may be logically divided into presentation layer 552, application layer 554, and data layer 556.
  • Presentation layer 552 may include a user interface (UI) component 560, which generates and renders user interfaces of health monitoring application 550.
  • UI user interface
  • Data layer 556 may include pressure value data 590 and signal data 592, which may be received from IMD 10 via communication circuitry 540 and stored in memory 532 by processing circuitry 530.
  • Application layer 554 may include, but is not limited to, status analyzer 570, and model configuration application 572.
  • Status analyzer 570 may determine one or more features, a plurality of systolic BP values, a plurality of diastolic BP values, and/or an overall BP using pressure value data 590 based on signal data 592, which may be generated by IMD 10, as described herein.
  • processing circuitry 530 processes signal data 592, e.g., optical signal data associated with a certain number of cardiac cycles, into a matrix with multiple time series, e.g., one series per feature, and provides the matrix as input to the CNN to determine overall BP.
  • Status analyzer 570 may determine the health condition status based on application of the data as inputs one or more model(s) 594, which may include one or more machine learning models, algorithms, decision trees, and/or thresholds. In examples in which models 594 include one or more machine learning models, status analyzer 570 may apply feature vectors derived from the data to the model(s).
  • Model configuration component 572 may be configured to develop models 594 based on machine learning.
  • Example machine learning techniques that may be employed to generate model(s) 594 can include various learning styles, such as supervised learning, unsupervised learning, and semi-supervised learning.
  • Example types of algorithms include Bayesian algorithms, Markov models, Hawkes processes, Clustering algorithms, decisiontree algorithms, regularization algorithms, regression algorithms, instance-based algorithms, artificial neural network algorithms, deep learning algorithms, dimensionality reduction algorithms and the like.
  • Various examples of specific algorithms include Bayesian Linear Regression, Boosted Decision Tree Regression, and Neural Network Regression, Back Propagation Neural Networks, Convolution Neural Networks (CNN), Long Short Term Networks (LSTM), the Apriori algorithm, K-Means Clustering, k- Nearest Neighbour (kNN), Learning Vector Quantization (LVQ), Self-Organizing Map (SOM), Locally Weighted Learning (LWL), Ridge Regression, Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net, and Least-Angle Regression (LARS), Principal Component Analysis (PCA) and Principal Component Regression (PCR).
  • Bayesian Linear Regression Boosted Decision Tree Regression
  • Neural Network Regression Back Propagation Neural Networks
  • CNN Convolution Neural Networks
  • LSTM Long Short Term Networks
  • K-Means Clustering K-Means Clustering
  • kNN Learning Vector Quantization
  • SOM Self-Organizing Map
  • FIG. 6 is a flow diagram illustrating an example operation for determining an overall systolic pressure value and an overall diastolic pressure value, i.e., an overall BP, of a patient, in accordance with one or more techniques of this disclosure.
  • Processing circuitry e.g., processing circuitry 450 of IMD 10, processing circuitry 530 of external device 12, processing circuitry 234 of server 230, or any other processing circuitry of FIG. 2, determines a plurality of systolic pressure values and a corresponding plurality of diastolic pressure values based on an analysis of a predetermined length of a pulse signal (602).
  • Processing circuitry may capture the predetermined length of the pulse signal on a periodic schedule, in response to identifying one or more flags in the signal data, e.g., signal data 592, or on-demand.
  • the periodic schedule may be, as examples, an hourly, daily, weekly, biweekly, or monthly schedule.
  • the predetermined length of the pulse signal may be 10 seconds of pulse signal.
  • the predetermined length of pulse signal may be a specific number of samples, e.g., 800 samples or 1000 samples, or range of samples, e.g., 800-1000 samples.
  • the predetermined length of the pulse signal may correspond to one or more cardiac cycles, e.g., 10 cardiac cycles.
  • the techniques of this disclosure may conserve battery life.
  • processing circuitry may apply a rolling window to the predetermined length of data.
  • processing circuitry determines one or more features of the predetermined length of the pulse signal, and based on the one or more features, determines the plurality of systolic pressure values and the corresponding plurality of diastolic pressure values.
  • processing circuitry may implement a machine learning model to determine one or more of the one or more features, the plurality of systolic pressure values, or the plurality of diastolic pressure values.
  • Processing circuitry determines an overall systolic pressure value based on the plurality of systolic pressure values and an overall diastolic pressure value based on the plurality of diastolic pressure values (604). In some examples, to determine the overall systolic and corresponding diastolic pressure values, processing circuitry determines a statistical representation, e.g., a median or average, of the plurality of systolic pressure values and a statistical representation of the corresponding plurality of diastolic pressure values. Processing circuitry may implement a machine learning model to determine the overall systolic and corresponding diastolic pressure values, i.e., the overall BP.
  • a statistical representation e.g., a median or average
  • Processing circuitry generates an indication of the overall systolic pressure value and the overall diastolic pressure value for presentation to a user, e.g., patient 4 or the clinician, e.g., via UI component 560 of computing device 12 (606).
  • the indication of the overall systolic and diastolic pressure values is presented as an overall BP.
  • the indication may additionally, or alternatively, include a BP level, e.g., low, moderate, or high.
  • the indication may include an indication of whether BP increased or decreased relative to one or more prior measurements.
  • FIG. 7 is a graph illustrating an optical signal 706, in accordance with one or more techniques of this disclosure.
  • Window 702 is a window, e.g., a 10 second window or a predetermined number of datapoints, containing the predetermined length of pulse signal 706 and respiration signal 704.
  • pulse signal 706 and respiration signal 704 may be based on a PPG signal.
  • Respiration signal 704 may, in some examples, correspond to at least one respiration cycle.
  • processing circuitry may be configured to determine one or more features based on respiration signal 704 as part of determining overall BP.
  • Pulse signal 706 includes feature information indicative of BP.
  • processing circuitry e.g., processing circuitry 450 of IMD 10, processing circuitry 530 of external device 12, processing circuitry 234 of server 230, or any other processing circuitry of FIG.
  • ⁇ extracts one or more features from the predetermined length of pulse signal data, such as one or more of a peak-to-peak interval, a systolic peak, a time to systolic peak, a systolic area, a systolic slope trajectory, a diastolic peak, a diastolic area, a diastolic slope trajectory, diastolic peak/systolic peak ratio, a Boolean dicrotic notch, a height of dicrotic notch, a mean value, a standard deviation value, a kurtosis value, and/or a skewness value.
  • a peak-to-peak interval such as one or more of a peak-to-peak interval, a systolic peak, a time to systolic peak, a systolic area, a systolic slope trajectory, a diastolic peak, a dias
  • a dicrotic notch is a nadir point of a waveform, such as a pressure waveform, that indicates the end of systole.
  • a dicrotic notch may occur after the closure of aortic valves and precedes the secondary dicrotic wave.
  • a systole wave is a result of the direct pressure wave traveling from the left ventricle to the periphery of the body and a systolic peak is a maximum point of the systole wave.
  • a diastolic wave is a result of reflection of the pressure wave by arteries of the lower body and a diastolic peak is a maximum point of the diastole wave.
  • the machine learning model may be more focused and spend a majority of its nodes on determining a BP, trends in BP, and/or a health condition status, e.g., a hypertension status, based on BP trends over a period of time.
  • Processing circuitry may be configured to execute an artificial intelligence (Al) engine that operates according to one or more models, such as machine learning models.
  • Machine learning models may include any number of different types of machine learning models, such as neural networks, deep neural networks, convolution neural networks, recurrent neural networks, such as long short term memory networks, dense neural networks, and the like.
  • various feature inputs to the Al engine may be fed as direct inputs to different layers in a network and not necessarily prior to the convolution layers.
  • the techniques described in this disclosure are also applicable to other types of Al models, including rule-based models, finite state machines, and the like.
  • Machine learning may generally enable a computing device to analyze input data and identify an action to be performed responsive to the input data.
  • Each machine learning model may be trained using training data that reflects likely input data.
  • the training data may include data from IMD 10 and, in some examples, may additionally include data from other BP measurement devices, e.g., watches.
  • the training data may be labeled or unlabeled (meaning that the correct action to be taken based on a sample of training data is explicitly stated or not explicitly stated, respectively).
  • the training of the machine learning model may be guided (in that a designer, such as a computer programmer, may direct the training to guide the machine learning model to identify the correct action in view of the input data) or unguided (in that the machine learning model is not guided by a designer to identify the correct action in view of the input data).
  • the machine learning model is trained through a combination of labeled and unlabeled training data, a combination of guided and unguided training, or possibly combinations thereof.
  • Processing circuitry may utilize machine learning, such as a deep learning algorithm or model (e.g., a neural network or deep belief network), to generate a score indicative BP.
  • processing circuitry of system 2 may train a deep learning model to represent a relationship of the features extracted from the received optical signal discussed above to BP. For example, processing circuitry of system 2 may train the deep learning model using optical signals from other patients.
  • processing circuitry of system 2 may train the deep leaning model by adjusting the weights of a hidden layer of a neural network model to balance the contribution of each input (e.g., characteristics of the images input) according to determining the BP.
  • processing circuitry of system 2 may train the deep learning model by also using optical signals received from patient 4 in addition to using optical signals from other patients as part of training data set. Using optical signals of patient 4 as part training data sets may result in a model that is customized for more accurate BP determinations for patient 4.
  • processing circuitry of system may obtain and apply data, such as the features extracted from the received optical signal, to the trained deep learning model.
  • the output of the deep learning model may include a score that indicates a BP.
  • processing circuitry may use the score to determine a degree of hypertension of patient 4.
  • FIG. 8 is a graph illustrating a plurality of systolic and diastolic pressure values during a predetermined length of pulse signal data, in accordance with one or more techniques of this disclosure.
  • processing circuitry e.g., processing circuitry 450 of IMD 10, processing circuitry 530 of external device 12, processing circuitry 234 of server 230, or any other processing circuitry of FIG. 2, may be configured to apply a rolling window to window 702 containing predetermined length of pulse signal 706 of FIG. 7.
  • the CNN model may be configured to make an overall BP prediction based on the predetermined length, e.g., predetermined number of datapoints, of signal data 592 of window 702.
  • Processing circuitry may process the predetermined length of signal data 592 of window 702 into an input matrix.
  • the CNN loops over the input matrix by an index value.
  • Processing circuitry determines a plurality of systolic pressure values, e.g., systolic line 806, and a corresponding plurality of diastolic pressure values, e.g., diastolic line 808.
  • Overall systolic pressure value 802 may be an average or median of the plurality of values corresponding to systolic line 806 at the conclusion of the application of the rolling window.
  • Overall diastolic pressure value 804 may be an average or median of the plurality of values corresponding to diastolic line 808 at the conclusion of the application of the rolling window.
  • processing circuitry implements a machine learning model to determine overall systolic pressure value 802 and the overall diastolic pressure value 804.
  • FIG. 9 is a flow diagram illustrating an example operation for determining whether to analyze a predetermined length of pulse signal data based on a patient status, in accordance with one or more techniques of this disclosure.
  • processing circuitry e.g., processing circuitry 450 of IMD 10, processing circuitry 530 of external device 12, processing circuitry 234 of server 230, or any other processing circuitry of FIG. 2, may be configured to determine whether to analyze the predetermined length of pulse signal data based on the patient status, e.g., to conserve battery life and/or to ensure accurate BP determinations.
  • Processing circuitry receives one or more physiological signals, such as temperature signals, respiration signals, patient posture/activity signals, and/or ECG signals (902).
  • Processing circuitry determines a patient status based on the one or more physiological signals (904). Processing circuitry compares the patient status to one or more criterion. Responsive to the patient status meeting the one or more criterion, processing circuitry determines to analyze the predetermined length of the pulse signal (906). In examples in which the patient status does not meet the one or more criterion, processing circuitry may determine to capture a new predetermined length of the pulse signal.
  • patient 4 may be performing an activity that may artificially increase their BP, such as jogging or experiencing stress. Additionally, patient 4 may be positioned such that IMD 10 is relatively susceptible to noise during certain activities.
  • one or more of the temperature signal, respiration signal, patient posture/activity signal, or ECG signal may be indicative of the patient activity. Responsive to determining patient 4 is performing an activity that may result in an inaccurate BP measurement, processing circuitry may determine not to analyze the predetermined length of the pulse signal. In some examples, processing circuitry may determine to analyze the predetermined length of data when the one or more physiological signals are indicative of certain patient activities, e.g., to determine patient BP during physically or emotionally strenuous activities.
  • processing circuitry may additionally or alternatively determine whether to analyze the predetermined length of pulse signal data based on the pulse signal condition, e.g., to conserve battery life and/or to ensure accurate BP determinations. If the pulse signal condition does not meet one or more criteria, e.g., due to ambient light interference, processing circuitry determines not to use the predetermined length of pulse signal data. If the pulse signal condition meets one or more criteria, processing circuitry determines to use the predetermined length of pulse signal data.
  • FIG. 10A illustrates an example screen 1000 of a user interface indicative of patient 4’s systolic and diastolic BP, in accordance with one or more techniques of this disclosure.
  • screen 1000 is an example screen of UI component 560 of external device 12.
  • screen 1000 may be a screen of a user interface of any of computing devices 240.
  • Systolic pressure value 1002 and diastolic pressure value 1004 indicate the overall BP to the user, e.g., patient 4 or the clinician.
  • screen 1000 may include different information based on the user. For example, screen 1000 may include more detailed information when the user is the clinician.
  • screen 1000 may additionally or alternatively include a graphical representation of the systolic pressure values and the diastolic pressure values. In some examples, the graphical representation may be similar to FIG. 8.
  • processing circuitry e.g., processing circuitry 530 of computing device 12, may determine a mode of presentation of the overall BP based on the user. As an example, processing circuitry 530 may determine to output more detailed information to the clinician than to patient 4.
  • screen 1000 may additionally include a confidence score 1005. Processing circuitry may determine a confidence score associated with the overall BP output for presentation to the user as confidence score 1005.
  • screen 1000 may additionally include an indication of a comparison of patient 4’s BP to an average BP of patient 4’s demographic (not depicted), e.g., patient 4’s age group.
  • patient 4 may be able to select a friend button of screen 1000 to connect with and “compete” with other patients, e.g., for lower BP measurements or for higher activity.
  • FIG. 10B illustrates an example screen 1010 of a user interface indicative of patient 4’s systolic and diastolic pressure value trends, in accordance with one or more techniques of this disclosure.
  • screen 1010 is an example screen of UI component 560 of external device 12.
  • screen 1010 may be a screen of a user interface of any of computing devices 240.
  • the user e.g., patient 4 or the clinician, may navigate to screen 1010 by selecting month summary box 1008.
  • Systolic trend 1012 and diastolic trend 1014 indicate overall BP changes over months.
  • the user may select note button 1016.
  • screen 1010 may additionally include an indication of a trend status 1018, e.g., stable, unstable, a number of abnormal episodes or measurements over a period of time, e.g., 30 days, for patient 4.
  • a trend status 1018 e.g., stable, unstable, a number of abnormal episodes or measurements over a period of time, e.g., 30 days, for patient 4.
  • FIG. 11 is a flow diagram illustrating an example operation for determining whether to analyze a predetermined length of pulse signal data based on one or more quality metrics, in accordance with one or more techniques of this disclosure.
  • Processing circuitry e.g., processing circuitry 450 of IMD 10, processing circuitry 530 of external device 12, processing circuitry 234 of server 230, or any other processing circuitry of FIG. 2, determines one or more quality metrics based on, e.g., signal data 592 of external device 12 (1102).
  • the one or more quality metrics may be based on one or more of an average amplitude of one or more signals of signal data 592, e.g., an average amplitude of the predetermined length of the pulse signal data, a number of cardiac cycles associated with signal data 592, or a number of samples of the predetermined length of the pulse signal data.
  • Processing circuitry compares each of the one or more quality metrics to a respective quality metric criterion (1104).
  • the respective quality metric criterion is preconfigured.
  • the clinician determines the respective quality metric criterion.
  • Processing circuitry may present one or more potential quality metric criteria to the clinician for clinician approval.
  • processing circuitry determines the respective quality metric threshold.
  • the respective quality metric threshold may, in some examples, be patient specific. In other examples, the respective quality metric threshold may be based on aggregate patient data. Based on the comparisons, processing circuitry determines a quality score (1106). In some examples, the quality score may comprise a summation of each of the one or more quality metrics and/or a difference between each quality metric and the respective quality metric criterion. In some examples, the one or more quality metrics may be weighted. Processing circuitry determines whether the quality score meets a quality score criterion (1108).
  • FIG. 12 is a flow diagram illustrating an example operation for determining whether to cancel analysis of predetermined lengths of pulse signal data for a duration of time, in accordance with one or more techniques of this disclosure.
  • processing circuitry may determine the quality score does not meeting the quality score criterion (“NO” of 1108) for more than one predetermined length of the pulse signal data.
  • Processing circuitry e.g., processing circuitry 450 of IMD 10, processing circuitry 530 of external device 12, processing circuitry 234 of server 230, or any other processing circuitry of FIG. 2, determines a number of times the quality score has failed to satisfy the quality score threshold, e.g., within a time period, e.g., 5 minutes (1202).
  • processing circuitry Based on the number of times the quality score has failed to satisfy the quality score threshold within the time period exceeding a threshold number of times, e.g., 3 times, processing circuitry cancels the analysis of the predetermined length of pulse signal data for a duration of time, e.g., 15 minutes, 30 minutes or 1 hour (1204). By canceling analysis for the duration of time, the techniques of this disclosure may conserve battery life of IMD 10.
  • FIG. 13 is a flow diagram illustrating an example operation for determining an overall systolic pressure value and an overall diastolic pressure value based on pairs of pressure values meeting one or more criterion, in accordance with one or more techniques of this disclosure.
  • Processing circuitry e.g., processing circuitry 450 of IMD 10, processing circuitry 530 of external device 12, processing circuitry 234 of server 230, or any other processing circuitry of FIG. 2, pairs each of the plurality of systolic pressure values to a corresponding diastolic pressure value of the plurality of diastolic pressure values to from a plurality of pairs of pressure values (1302).
  • Each pair of pressure values may be associated with a particular timestamp and/or a particular sample number.
  • processing circuitry determines a quality score (1304). Processing circuitry determines whether the quality score meets one or more criterion (1306). If the quality score meets the one or more criterion (“YES” of 1306), processing circuitry keeps the pair of values (1316). Processing circuitry determines a quantity of remaining pairs of pressure values and/or a quantity of removed pairs of pressure values (1310). Processing circuitry compares the quantity of remaining pairs and/or the quantity of removed pairs to a corresponding threshold (1312). In some examples, the threshold may be a percentage, e.g., 80%.
  • processing circuitry determines the overall systolic pressure value and overall diastolic pressure value (1314). If the quantity of remaining pairs and/or the quantity of removed pairs does not meet the corresponding threshold (“NO” of 1312), the process ends, and, in some examples, processing circuitry determines to attempt to determine the overall systolic pressure value and the overall diastolic pressure value using a new predetermined length of pulse signal data.
  • processing circuitry determines whether one or more of the systolic pressure value or the diastolic pressure value is an outlier, e.g., to determine the quality score associated with the pair of pressure values (1402). Processing circuitry determines whether one or more of the systolic pressure value or the diastolic pressure value is an outlier based on a statistical analysis of the plurality of systolic pressure values and diastolic pressure values over a period of time. In some examples, to determine whether one or more of the systolic pressure value or the diastolic pressure value is an outlier, processing circuitry compares the systolic pressure value to the diastolic pressure value.
  • processing circuitry may compare the systolic pressure value of the pair of pressure values to one or more other systolic pressure values of the plurality of systolic pressure values and compare the diastolic pressure value of the pair of pressure values to one or more other diastolic pressure values of the plurality of diastolic pressure values.
  • processing circuitry may compare the systolic pressure value of the pair of pressure values based on one or more of a standard deviation or an average of the plurality of systolic pressure values.
  • processing circuitry removes the pair of pressure values from the plurality of pressure values, i.e., processing circuitry excludes the pair of pressure values from the determination of the overall systolic pressure value and the overall diastolic pressure value (1408). If neither of the pressure values is an outlier, processing circuitry keeps the pair of pressure values for determining the overall systolic pressure value and the overall diastolic pressure value (1406). In some examples, processing circuitry utilizes the number of removed values as part of determining a confidence score associated with the overall BP, e.g., confidence score 1005.
  • FIG. 15 is a conceptual diagram illustrating an example machine learning model 1300 configured to determine patient BP.
  • Machine learning model 1500 is an example of a deep learning model, or deep learning algorithm, trained to determine systolic pressure values and diastolic pressure values, i.e., BP values.
  • One or more of IMD 10, external device 12, server 230, and/or other computing device(s) may train, store, and/or utilize machine learning model 1500, but other devices may apply inputs associated with a particular patient to machine learning model 1500 in other examples.
  • other types of machine learning and deep learning models or algorithms may be utilized in other examples.
  • a convolutional neural network model of ResNet- 18 may be used.
  • models that may be used for transfer learning include AlexNet, VGGNet, GoogleNet, ResNet50, or DenseNet, etc.
  • machine learning techniques include Support Vector Machines, K- Nearest Neighbor algorithm, and Multi-layer Perceptron.
  • machine learning model 1500 may include three layers. These three layers include input layer 1502, hidden layer 1504, and output layer 1506. Output layer 1506 comprises the output from the transfer function 1505 of output layer 1506. Input layer 1502 represents each of the input values XI through X4 provided to machine learning model 1500.
  • the input values may be any of the of values input into the machine learning model, as described above.
  • the input values may be one or more features extracted from the received optical signal and ECG signal, as described above.
  • input values of machine learning model 1500 may include additional data, such as accelerometer signal data relating to activity of patient 4 and/or ECG signal data.
  • Each of the input values for each node in the input layer 1502 is provided to each node of hidden layer 1504.
  • hidden layers 1504 include two layers, one layer having four nodes and the other layer having three nodes, but fewer or greater number of nodes may be used in other examples.
  • Each input from input layer 1502 is multiplied by a weight and then summed at each node of hidden layers 1504.
  • the weights for each input are adjusted to establish the relationship between the one or more features and the BP values.
  • one hidden layer may be incorporated into machine learning model 1500, or three or more hidden layers may be incorporated into machine learning model 1500, where each layer includes the same or different number of nodes.
  • the result of each node within hidden layers 1504 is applied to the transfer function of output layer 1506.
  • the transfer function may be liner or non-linear, depending on the number of layers within machine learning model 1500.
  • Example non-linear transfer functions may be a sigmoid function or a rectifier function.
  • the output 1507 of the transfer function may be a classification of the BP values, that is generated by a computing device or computing system, such as by processing circuitry 530, in response to applying the extracted cardiac features from the received optical signal to machine learning model 1500.
  • processing circuitry 530 is able to determine the overall BP of a patient with great accuracy, specificity, and sensitivity. This may facilitate determinations of cardiac wellness, and risk of sudden cardiac death, and may lead to clinical interventions to suppress hypertension such as medications and renal denervation procedures.
  • FIG. 16 is an example of the machine learning model 1602 being trained using supervised and/or reinforcement learning techniques.
  • the machine learning model 1602 may be implemented using any number of models for supervised and/or reinforcement learning, such as but not limited to, an artificial neural network, a decision tree, naive Bayes network, support vector machine, or k-nearest neighbor model, to name only a few examples.
  • one or more of IMD 10, external device 12, server 230, and/or other computing device(s) initially trains the machine learning model 1602 based on a training set of features and corresponding to a received optical signal and ECG signal.
  • the training set 1600 may include a set of feature vectors, where each feature in the feature vector represents a value for a particular feature.
  • One or more of IMD 10, external device 12, server 230, and/or other computing device(s) may select a training set comprising a set of training instances, each training instance comprising an association between one or more respective optical signal features of a respective cardiac feature and a respective pulse signal.
  • a prediction or classification by the machine learning model 1602 may be compared 1604 to the target output 1603.
  • the processing circuitry implementing a learning/training function 1605 may send or apply a modification to weights of machine learning model 1602 or otherwise modify/update the machine learning model 1602.
  • one or more of IMD 10, external device 12, server 230, and/or other computing device(s) may, for each training instance in the training set, modify, based on the respective cardiac features and the respective optical signal of the training instance, the machine learning model 1602 to change a score generated by the machine learning model 1602 in response to subsequent pulse signals applied to the machine learning model 1602.
  • Example 1 A medical device system comprising: an optical sensor configured to sense a pulse signal; and processing circuitry configured to: determine a plurality of systolic pressure values and a corresponding plurality of diastolic pressure values based on an analysis of a predetermined length of the pulse signal, wherein the analysis comprises, for each of systolic pressure value of the plurality of systolic pressure values and each corresponding diastolic pressure value of the plurality of diastolic pressure values, applying a rolling window within the predetermined length of the pulse signal; determine an overall systolic pressure value based on the plurality of systolic pressure values and an overall diastolic pressure value based on the corresponding plurality of diastolic pressure values; and present the overall systolic pressure value and the overall diastolic pressure value to a user.
  • the analysis comprises, for each of systolic pressure value of the plurality of systolic pressure values and each
  • Example 2 The system of example 1, wherein the processing circuitry is further configured to determine whether to analyze the predetermined length of the pulse signal based on a patient status, and wherein the patient status is based on one or more of a temperature signal, a respiration signal, a patient posture signal, or an electrocardiogram (ECG) signal.
  • Example 3 The system of any one or more of examples 1-2, wherein the processing circuitry is further configured to present a trend in systolic pressure value predictions and diastolic pressure value predictions over time.
  • Example 4 The system of any one or more of examples 1-3, wherein the processing circuitry is further configured to: determine one or more quality metrics; compare each of the one or more quality metrics to a respective quality metric threshold; determine a quality score based on the comparisons; responsive to the quality score failing to satisfy a quality score criterion, cancel the analysis of the predetermined length of pulse signal data.
  • Example 5 The system of any one or more of examples 1-4, wherein the one or more quality metrics comprise one or more of an average amplitude, a number of cardiac cycles, or a number of samples of the predetermined length of pulse signal data.
  • Example 6 The system of any one or more of examples 4-5, wherein the processing circuitry is further configured to: determine a number of times the quality score has failed to satisfy the quality score threshold within a time window; based on the number of times the quality score has failed to satisfy the quality score threshold within the time window meeting a time window threshold, cancelling the analysis of the predetermined length of pulse signal data for a duration of time.
  • Example 7 The system of any one or more of examples 1-6, wherein the processing circuitry is further configured to: pair each systolic pressure value of the plurality of systolic pressure values to a corresponding diastolic pressure value of the plurality of diastolic pressure values to form a plurality of pairs of pressure values; for each pair of pressure values of the plurality of pressure values, determine a quality score; responsive to the quality score of a pair of pressure values not meeting the one or more criterion, remove the pair of pressure values from the plurality of pairs of pressure values; based on at least one of a quantity of remaining pairs of pressure values or a quantity of removed pairs of pressure values from the predetermined length of pulse signal data, determine whether a threshold number of pairs of pressure values are available to determine the overall systolic pressure value and the overall diastolic pressure value.
  • Example 8 The system of example 7, wherein to determine the quality score, the processing circuitry is configured to determine whether one or more of the values of the pair is an outlier.
  • Example 9 The system of example 8, wherein to determine whether one or more of the values of the pair is an outlier, the processing circuitry is configured to one or more of: compare the systolic pressure value of the pair to the diastolic pressure value of the pair; or compare the systolic pressure value of the pair to other systolic pressure values of the plurality of systolic pressure values and compare the diastolic pressure value of the pair to other diastolic pressure values of the plurality of diastolic pressure values.
  • Example 10 The system of any one or more of examples 1-9, wherein the processing circuitry presents a graphical representation of the plurality of systolic pressure values and the plurality of diastolic pressure values.
  • Example 11 The system of any one or more of examples 1-10, wherein the user comprises a patient or a clinician.
  • Example 12 The system of any one or more of examples 1-11, wherein to determine the overall systolic pressure value and the overall diastolic pressure value the processing circuitry is configured to apply the plurality of systolic pressure values and the corresponding plurality of diastolic pressure values to a machine learning (ML model).
  • Example 13 The system of any one or more of examples 1-11, wherein to determine the overall systolic pressure value and the overall diastolic pressure value the processing circuitry is configured to apply the plurality of systolic pressure values and the corresponding plurality of diastolic pressure values to a machine learning (ML model).
  • the medical device system comprises an insertable cardiac monitor, the insertable cardiac monitor comprising the optical sensor and a housing configured for subcutaneous implantation, the housing having a length, a width, and a depth, wherein the length is greater than the width, and the width is greater than the depth, and the length is within a range from 40 millimeters (mm) to 60 mm, and wherein the insertable cardiac monitor comprises a plurality of electrodes on the housing and is configured to sense an ECG signal via the electrodes and the pulse signal via the optical sensor.
  • Example 14 The system of any one or more of examples 1-13, wherein the processing circuitry comprises processing circuitry of one or more of: an insertable cardiac monitor of the medical device system, wherein the insertable cardiac monitor comprises the optical sensor; or a computing system of the medical device system.
  • Example 15 The system of any one or more of examples 1-14, wherein the processing circuitry is further configured to determine whether to analyze the predetermined length of the pulse signal based on a pulse signal condition.
  • Example 16 A method comprising: sensing, by an optical sensor of a medical device system, a pulse signal; and determining, by processing circuitry of the medical device system, a plurality of systolic pressure values and a corresponding plurality of diastolic pressure values based on an analysis of a predetermined length of the pulse signal, wherein the analysis comprises, for each of systolic pressure value of the plurality of systolic pressure values and each corresponding diastolic pressure value of the plurality of diastolic pressure values, applying a rolling window within the predetermined length of the pulse signal; determining, by the processing circuitry, an overall systolic pressure value based on the plurality of systolic pressure values and an overall diastolic pressure value based on the corresponding plurality of diastolic pressure values; and presenting, by the processing circuitry, the overall systolic pressure value and the overall diastolic pressure value to a user.
  • Example 17 The method of example 16, further comprising: determining, by the processing circuitry, whether to analyze the predetermined length based on a patient status, wherein the patient status is based on one or more of a temperature signal, a respiration signal, a patient posture signal, or an electrocardiogram (ECG) signal.
  • ECG electrocardiogram
  • Example 18 The method of any one or more of examples 16-17, further comprising: generating for presentation, by the processing circuitry, a trend in systolic pressure value predictions and diastolic pressure value predictions over time.
  • Example 19 The method of any one or more of examples 16-18, further comprising: determining, by the processing circuitry, one or more quality metrics; comparing, by the processing circuitry, each of the one or more quality metrics to a respective quality metric threshold; determining, by the processing circuitry, a quality score based on the comparisons; responsive to the quality score failing to satisfy a quality score criterion, cancelling, by the processing circuitry, the analysis of the predetermined length of pulse signal data.
  • Example 20 The method of any one or more of examples 16-19, wherein the one or more quality metrics comprise one or more of an average amplitude, a number of cardiac cycles, or a number of samples of the predetermined length of pulse signal data.
  • Example 21 The method of any one or more of examples 19-20, further comprising: determining, by the processing circuitry, a number of times the quality score has failed to satisfy the quality score threshold within a time window; based on the number of times the quality score has failed to satisfy the quality score threshold within the time window meeting a time window threshold, cancelling, by the processing circuitry, analysis of the predetermined length of pulse signal data for a duration of time.
  • Example 22 The method of any one or more of examples 16-21, further comprising: pairing, by the processing circuitry, each systolic pressure value of the plurality of systolic pressure values to a corresponding diastolic pressure value of the plurality of diastolic pressure values to form a plurality of pairs of pressure values; for each pair of pressure values of the plurality of pressure values, determining, by the processing circuitry, a quality score; responsive to the quality score of a pair of pressure values not meeting the one or more criterion, removing, by the processing circuitry, the pair of pressure values from the plurality of pairs of pressure values; based on at least one of a quantity of remaining pairs of pressure values or a quantity of removed pairs of pressure values from the predetermined length of pulse signal data, determining, by the processing circuitry, whether a threshold number of pairs of pressure values are available to determine the overall systolic pressure value and the overall diastolic pressure value.
  • Example 23 The method of example 22, wherein determining the quality score comprises determining, by the processing circuitry, whether one or more of the values of the pair is an outlier.
  • Example 24 The method of example 23, wherein determining whether one or more of the values of the pair is an outlier comprises: comparing, by the processing circuitry, the systolic pressure value of the pair to the diastolic pressure value of the pair; or comparing, by the processing circuitry, the systolic pressure value of the pair to other systolic pressure values of the plurality of systolic pressure values and compare the diastolic pressure value of the pair to other diastolic pressure values of the plurality of diastolic pressure values.
  • Example 25 The method of any one or more of examples 16-24, further comprising: presenting, by the processing circuitry, a graphical representation of the plurality of systolic pressure values and the plurality of diastolic pressure values.
  • Example 26 The method of any one or more of examples 16-25, wherein the user comprises a patient or a clinician.
  • Example 27 The method of any one or more of examples 16-26, wherein determining the overall systolic pressure value and the overall diastolic pressure value comprises: applying, by the processing circuitry, the plurality of systolic pressure values and the corresponding plurality of diastolic pressure values to a machine learning (ML model).
  • ML model machine learning
  • Example 28 The method of any one or more of examples 16-27, wherein the medical device system comprises an insertable cardiac monitor, the insertable cardiac monitor comprising the optical sensor and a housing configured for subcutaneous implantation, the housing having a length, a width, and a depth, wherein the length is greater than the width, and the width is greater than the depth, and the length is within a range from 40 millimeters (mm) to 60 mm, and wherein the insertable cardiac monitor comprises a plurality of electrodes on the housing and is configured to sense an ECG signal via the electrodes and the pulse signal via the optical sensor.
  • the medical device system comprises an insertable cardiac monitor, the insertable cardiac monitor comprising the optical sensor and a housing configured for subcutaneous implantation, the housing having a length, a width, and a depth, wherein the length is greater than the width, and the width is greater than the depth, and the length is within a range from 40 millimeters (mm) to 60 mm
  • the insertable cardiac monitor comprises a plurality of electrodes on the
  • Example 29 The method of any one or more of examples 16-28, wherein the processing circuitry comprises processing circuitry of one or more of: an insertable cardiac monitor of the medical device system, wherein the insertable cardiac monitor comprises the optical sensor; or a computing system of the medical device system.
  • Example 30 The method of any one or more of examples 16-29, further comprising: determining, by the processing circuitry, whether to analyze the predetermined length based on a pulse signal condition.
  • Example 31 A non-transitory computer-readable medium storing instructions that when executed by processing circuitry cause the processing circuitry to: determine a plurality of systolic pressure values and a corresponding plurality of diastolic pressure values based on an analysis of a predetermined length of a pulse signal sensed by an optical sensor, wherein the analysis comprises, for each of systolic pressure value of the plurality of systolic pressure values and each corresponding diastolic pressure value of the plurality of diastolic pressure values, applying a rolling window within the predetermined length of the pulse signal; determine an overall systolic pressure value based on the plurality of systolic pressure values and an overall diastolic pressure value based on the corresponding plurality of diastolic pressure values; and present the overall systolic pressure value and the overall diastolic pressure value to a user.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Cardiology (AREA)
  • Veterinary Medicine (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Physiology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Psychiatry (AREA)
  • Vascular Medicine (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

Sont divulguées des techniques de surveillance de valeurs de pression artérielle d'un patient. Dans un exemple, un système de dispositif médical comprend : un capteur optique configuré pour détecter un signal d'impulsion ; et un circuit de traitement configuré pour : déterminer une pluralité de valeurs de pression systolique et une pluralité de valeurs de pression diastolique correspondantes en fonction d'une analyse d'une longueur prédéterminée du signal d'impulsion, l'analyse consistant, pour chacune de la valeur de pression systolique de la pluralité de valeurs de pression systolique et de chaque valeur de pression diastolique correspondante de la pluralité de valeurs de pression diastolique, à appliquer une fenêtre glissante dans la longueur prédéterminée du signal d'impulsion ; à déterminer une valeur de pression systolique globale en fonction de la pluralité de valeurs de pression systolique et une valeur de pression diastolique globale en fonction de la pluralité de valeurs de pression diastolique correspondantes ; et à présenter la valeur de pression systolique globale et la valeur de pression diastolique globale à un utilisateur.
PCT/IB2025/053082 2024-04-16 2025-03-24 Prédiction de pression artérielle à partir d'un signal d'impulsion implantable Pending WO2025219784A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202463634674P 2024-04-16 2024-04-16
US63/634,674 2024-04-16

Publications (1)

Publication Number Publication Date
WO2025219784A1 true WO2025219784A1 (fr) 2025-10-23

Family

ID=95309904

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2025/053082 Pending WO2025219784A1 (fr) 2024-04-16 2025-03-24 Prédiction de pression artérielle à partir d'un signal d'impulsion implantable

Country Status (1)

Country Link
WO (1) WO2025219784A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5322069A (en) * 1991-11-12 1994-06-21 Stuart Medical Inc. Ambulatory ECG triggered blood pressure monitoring system and method therefor
US20120277602A1 (en) * 2011-04-29 2012-11-01 Bbnt Technologies Corp. Continuous blood pressure monitoring
US20140276928A1 (en) 2013-03-15 2014-09-18 Medtronic, Inc. Subcutaneous delivery tool
US20220296172A1 (en) * 2021-03-16 2022-09-22 Electronics And Telecommunication Research Institute Method and system for estimating arterial blood based on deep learning
WO2023203419A1 (fr) * 2022-04-22 2023-10-26 Medtronic, Inc. Système conçu pour la surveillance de maladies chroniques à l'aide d'informations provenant de multiples dispositifs
US20240016397A1 (en) * 2022-07-14 2024-01-18 Hill-Rom Services, Inc. Estimation of blood pressure using ballistocardiogram and peripheral photoplethysmogram

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5322069A (en) * 1991-11-12 1994-06-21 Stuart Medical Inc. Ambulatory ECG triggered blood pressure monitoring system and method therefor
US20120277602A1 (en) * 2011-04-29 2012-11-01 Bbnt Technologies Corp. Continuous blood pressure monitoring
US20140276928A1 (en) 2013-03-15 2014-09-18 Medtronic, Inc. Subcutaneous delivery tool
US20220296172A1 (en) * 2021-03-16 2022-09-22 Electronics And Telecommunication Research Institute Method and system for estimating arterial blood based on deep learning
WO2023203419A1 (fr) * 2022-04-22 2023-10-26 Medtronic, Inc. Système conçu pour la surveillance de maladies chroniques à l'aide d'informations provenant de multiples dispositifs
US20240016397A1 (en) * 2022-07-14 2024-01-18 Hill-Rom Services, Inc. Estimation of blood pressure using ballistocardiogram and peripheral photoplethysmogram

Similar Documents

Publication Publication Date Title
US20220211332A1 (en) Medical device system for monitoring patient health
EP4061207A1 (fr) Réalisation d'une ou de plusieurs mesures de temps de transit d'impulsion sur la base d'un signal d'électrogramme et d'un signal de photopléthysmographie
US20250268522A1 (en) Closed loop care system based on compliance with a prescribed medication plan
US20250268523A1 (en) A system configured for chronic illness monitoring using information from multiple devices
WO2024123547A1 (fr) Prédiction ou détection d'événements cardiaques indésirables majeurs par rupture dans une réponse sympathique
WO2025219784A1 (fr) Prédiction de pression artérielle à partir d'un signal d'impulsion implantable
CN116472585A (zh) 症状记录器
US20250262482A1 (en) Exercise tolerance using an implantable or wearable heart monitor
US20250281127A1 (en) Identification of disordered breathing during sleep
WO2025219783A1 (fr) Dispositif médical configuré pour surveiller le risque d'hypertension pulmonaire à l'aide de signaux optiques et d'électrocardiogramme
US20250248605A1 (en) Sensing and diagnosing adverse health event risk
WO2024224203A1 (fr) Système médical conçu pour déterminer un état de condition de santé sur la base de changements de pression artérielle détectés par capteur optique implantable
US20240138743A1 (en) Premature ventricular contraction (pvc) detection using an artificial intelligence model
US20250040890A1 (en) High-resolution diagnostic data system for patient recovery after heart failure intervention
US20250262362A1 (en) Configuration of a medical device system for impedance-based calibration of dialysis sessions
US20250255547A1 (en) Biochemical sensing for heart failure management
US20250255546A1 (en) Closed loop adjustment of heart failure therapy
JP2025531726A (ja) 心電図ベースの左心室機能障害及び駆出率のモニタリング
WO2024224199A1 (fr) Ludification et présentation de système médical
WO2024249414A1 (fr) Fonctionnement d'un système de dispositif médical implantable pour déterminer la probabilité de récurrence de fibrillation auriculaire
WO2025224544A1 (fr) Fonctionnement d'un système de dispositif médical pour identifier des échantillons de données cardiaques particuliers associés à un événement cardiaque
WO2025224686A1 (fr) Systèmes de détermination d'éligibilité de patient pour des soins auto-administrés avec des anticoagulants oraux
WO2025088408A1 (fr) Fonctionnement d'un système de dispositif médical pour déterminer des positions de fenêtre d'un signal de battement de bruit cardiaque pour extraire des caractéristiques de bruit cardiaque
AU2023369259A1 (en) Ambient noise detection to reduce heart disease events

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25717347

Country of ref document: EP

Kind code of ref document: A1