[go: up one dir, main page]

US20060281980A1 - Apparatus and method for determining a physiological condition - Google Patents

Apparatus and method for determining a physiological condition Download PDF

Info

Publication number
US20060281980A1
US20060281980A1 US11/401,993 US40199306A US2006281980A1 US 20060281980 A1 US20060281980 A1 US 20060281980A1 US 40199306 A US40199306 A US 40199306A US 2006281980 A1 US2006281980 A1 US 2006281980A1
Authority
US
United States
Prior art keywords
look
physiological
parameters
physiological parameters
received
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.)
Abandoned
Application number
US11/401,993
Other languages
English (en)
Inventor
Jette Randlov
Jon Hansen
Jens Poulsen
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.)
Novo Nordisk AS
Original Assignee
Novo Nordisk AS
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
Priority claimed from PCT/DK2004/000697 external-priority patent/WO2005037092A1/en
Application filed by Novo Nordisk AS filed Critical Novo Nordisk AS
Assigned to NOVO NORDISK A/S reassignment NOVO NORDISK A/S ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: HANSEN, JON ULRICH, POULSEN, JENS ULRIK, RANDLOV, JETTE
Publication of US20060281980A1 publication Critical patent/US20060281980A1/en
Priority to US14/055,508 priority Critical patent/US10524669B2/en
Abandoned legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass
    • 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
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue
    • A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue for measuring glucose, e.g. by tissue impedance measurement
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation

Definitions

  • This invention relates to the detection of a physiological condition, such as hypoglycaemia, in a patient. More particularly, the invention relates to an apparatus for detecting a physiological condition in a person, and to a method of alerting a patient to the risk of the presence of a physiological condition.
  • Hypoglycaemia is a physiological condition where the blood glucose level of the patient decreases below a certain value. Blood glucose levels below approx. 2.5 mmol/L may give rise to serious symptoms and may potentially even become dangerous for a diabetic patient, in particular, if the patient does not become aware of the condition, e.g. because the patient is sleeping or preoccupied with another activity, e.g. driving a car.
  • U.S. Pat. No. 4,509,531 discloses a non-invasive watch-like monitoring device that measures body temperature and skin resistance. In the event of either a predetermined change in galvanic skin resistance or a predetermined change in peripheral skin temperature an alarm is generated which can waken a sleeper wearing the monitoring device.
  • Another watch-like device that uses perspiration and a drop in skin temperature to detect hypoglycaemia is the Sleep Sentry by Diabetes Sentry Products Inc. Studies for this device have shown that, when hypoglycaemia was confirmed to be present, the alarm was generated about 90% of the time, thereby leaving about 10 % of the occurrences undetected. Furthermore, it is not uncommon for patients to experience a false alarm.
  • International patent application WO 02/069798 discloses a method of determining the presence of a physiological condition in a person where the person's skin impedance, heart rate, QT interval and mean or peak frequency of the ⁇ wave are measured.
  • the measured input data are fed into a multilayer feedforward neural network which is trained to calculate the patient's blood glucose status.
  • the neural network is trained using the back-propagation algorithm in which synaptic strengths are systematically modified so that the response of the network approximates the blood glucose status of the patient with increasing accuracy.
  • an apparatus for detecting a physiological condition in a person comprising
  • the apparatus comprises storage means for storing a look-up table comprising a plurality of entries, each entry corresponding to a pre-calculated probability of the presence or onset of said physiological condition, the pre-calculated probabilities being determined by means of a mathematical process from previously monitored physiological parameters; and
  • the processing means is adapted to process the received at least two physiological parameters to identify one of the plurality of entries of the look-up table, and to determine said result signal from the identified entry of the look-up table.
  • the entries stored in the look-up table may systematically be validated. Since any combination of inputs is associated with an entry in the look-up table, the output generated by the device for any combination of inputs may easily be validated. Furthermore, as the entries correspond to pre-calculated probabilities of the presence of said physiological condition that are determined by means of a mathematical process from previously monitored physiological parameters, a high reliability of the detection of the physiological condition is achieved.
  • the look-up table provides a direct indication of the probability of the presence or onset of said physiological condition indexed by the input parameters. Hence, the calculation/evaluation of complex physiological models or predictions of future blood glucose levels during operation is avoided, thereby providing a simple and reliable system.
  • the apparatus automatically detects nightly hypoglycaemia for diabetic patients, sufficiently early for the patient to handle the problem himself/herself.
  • the physiological parameters are received as corresponding one or more sensor signals.
  • a patient may wear a set of sensors during the night.
  • the sensor signals may be sent to a receiver of a central unit via a wireless connection.
  • This central unit receives the signals, analyses them and sounds an acoustic alarm, if the analysis shows that the patient experiences a hypoglycaemia or is on the way to one.
  • the detection may be based on measurements of several secondary effects rather than a direct measurement of blood glucose.
  • look-up table refers to any suitable data structure for storing a plurality of entries where each entry may be identified by a suitable index.
  • detecting a physiological condition is intended to comprise the detection of the presence/absence of such a condition and/or the onset of such a condition and/or a degree or severity to which such a condition is present.
  • physiological parameter comprises any quantitatively and/or qualitatively measurable parameter related to the physiological condition to be detected.
  • the physiological parameters are parameters that may be measured by non-invasive measurements.
  • invasive measurements may be used as an input as well.
  • the parameters are measured automatically, they may be continuously or quasi-continuously monitored without the need for human interaction.
  • examples of such parameters include heart rate/pulse, heart rate variability (HRV), skin impedance/perspiration, body/skin temperature, respiration frequency, respiration effort, eye movements, muscle tonus, parameters determined by an ECG, e.g. QT interval, parameters determined by Electroencephalography (EEG), e.g. the frequency of the ⁇ wave, a measurement obtained by an electro-oculogram (EOG), an O 2 saturation measurement, blood pressure, biosensors, or the like.
  • ECG Electroencephalography
  • EOG Electroencephalography
  • EOG electro-oculogram
  • O 2 saturation measurement blood pressure
  • biosensors or the like.
  • the above parameters may be detected by any suitable known method.
  • the parameters are continuously or quasi-continuously sampled, thereby providing frequent updates of the measurements, e.g. one update every few seconds, every minute, or every few minutes.
  • a high confidence level of the detection of the physiological condition is achieved, even though each one of the sensors per se may not be a good indicator of the presence or inset of the physiological condition.
  • the combined prediction provides a high degree of significance. This combination of sensor signals having comparatively low significance to a result signal of high significance will be referred to as sensor fusion.
  • the physiological parameters further include one or more parameters measured by a third degree sensor.
  • the term third degree sensor comprises a sensor measuring a parameter that does not provide any direct information about the presence or absence of the physiological condition. Nevertheless, such a sensor may support the other sensor signals and provide an increased confidence level of the result.
  • the CO 2 content of the blood is an example of such a third degree sensor signal.
  • the CO 2 content provides an indication of whether the person is dreaming and/or sleeping restlessly, i.e. an indication of the presence of alternative causes of the other measured parameters, such as perspiration and eye movement, skin temperature, etc., thereby improving the reliability of the detection of hypoglycaemia and, in particular, reducing the number of false positive alarms.
  • a first degree sensor i.e. a sensor which directly measures a single quantity reflecting the physiological condition.
  • a non-invasive blood glucose measurement such as infrared BGM may not be sufficiently accurate per se to be used as a BGM device, especially not for low blood glucose values.
  • the infrared BGM may not be accurate enough to be used for a reliable detection of hypoglycaemia.
  • an unreliable first degree measurement may contribute to an overall reliable detection.
  • the measured sensor signals may be received as an electrical signal from the respective sensors, e.g. via wires connected to the detection device.
  • some or all of the sensor signals may be received via wireless data communication.
  • a sensor may include a radio transmitter for transmitting the measured parameter(s) via a short range radio communications link to a corresponding radio receiver in the detection device, thereby avoiding the need for wires connecting the different sensors with the detection device.
  • some or all of the sensors are integrated into the detection device, e.g. when the detection device is worn by the patient such that it has direct contact with the patient's skin, e.g. around the patient's wrist.
  • the apparatus preferably comprises suitable input means for receiving the physiological parameters, e.g. any suitable circuitry or device adapted to receive a sensor signal.
  • the device may be worn by the patient, e.g. around the patient's wrist, or the device may be positioned in the proximity of the patient or in the proximity of a person caring for the patient, e.g. on a table next to the patient's bed.
  • the term “mathematical process” is intended to comprise any suitable algorithm for analysing previously measured data to determine suitable relations between the measured input values and the corresponding probabilities of the actual presence or onset of the physiological condition.
  • the mathematical process may comprise a statistical correlation analysis and/or a pattern analysis process of the measured sensor inputs and actual detected occurrences of the physiological condition.
  • the mathematical process comprises an adaptive learning algorithm
  • the generated entries of the look-up table may be adjusted during the actual usage of the device based on feedback provided by the user.
  • the apparatus starts as pre-learned and can adapt to the user from there.
  • the adaptive learning algorithm comprises a reinforcement learning process, a particularly efficient data analysis with a high learning rate is achieved.
  • the apparatus is adaptive with a high learning rate requiring only few interactions with the user in order to get a high degree of adaptation.
  • the apparatus may be initialised with a pre-learned look-up table. Consequently, when the user uses the apparatus for the first time it already has values that suits the user fairly well. Hence, the user needs to spend less time before getting to the point, where the apparatus is fully adapted.
  • the actual function of the look-up table is much more transparent than for example multilayer neural networks, thereby facilitating a validation of the entire apparatus.
  • look-up table avoids the problem of over-fitting which may arise when using multilayer back-propagation neural networks.
  • the apparatus further comprises input means for receiving a user input indicative of the presence or absence of said physiological condition and/or input means for receiving a measured quantity indicative of the presence of the physiological condition, e.g. a measured blood glucose level. Consequently, the user may provide feedback to the apparatus indicating whether an alarm generated by the apparatus was a false alarm and/or whether an alarm should have been generated and/or the like. Hence, the adaptive learning process may be updated based on the above feedback, thereby providing an improved performance adapted to the physiology of the individual patient.
  • the input means for receiving a user input may comprise a keyboard, a touch screen, a keypad, a number of push buttons or other touch-sensitive input device, a voice/sound input device, or any other suitable input device.
  • the processing means is further adapted to update at least the identified entry of the look-up table according to the adaptive process and in response to a user input indicative of the presence or absence of said physiological condition and/or a received measured quantity indicative of the presence of the physiological condition.
  • the entry selected by the current sensor signal is updated based on the received feedback to better reflect the physiology of the patient and to improve the reliability of future detections. For example, if an alarm is classified as a false alarm by the user, the probability stored in the currently selected entry of the look-up table may be decreased by a predetermined value. Likewise, if the user has indicated that an alarm should have been generated, the corresponding probability may be increased. In one embodiment, all entries selected within a predetermined period prior to an alarm are updated, thereby increasing the efficiency of the algorithm.
  • the processing means is further adapted to discretize the received physiological parameters to obtain one of a plurality of possible combinations of discrete physiological parameters, each of the plurality of combinations being associated to a corresponding one of the plurality of entries of the look-up table.
  • the processing means is adapted to discretize the received physiological parameters by identifying, for each of the received physiological parameters, one of a corresponding number of intervals in which the received physiological parameter is determined to fall; resulting in a combination of identified intervals, the combination identifying a corresponding entry in the look-up table.
  • an efficient generation of an index for the look-up table is provided which may easily be validated and which does not require many computational resources.
  • the processing of the received at least two physiological parameters to identify one of the plurality of entries of the look-up table results in a suitable index for the look-up table.
  • the measured sensor signals are discretized with respect to a small number of intervals, thereby reducing the index space of the look-up table and, thus, reducing the complexity of the detection system.
  • the number of intervals is preferably selected large enough to provide a sufficient resolution to detect changes indicative of the onset or presence of the physiological condition.
  • each measured sensor signal is assigned to one of 2-10 intervals, preferably 3-6 intervals, more preferably 3-5 intervals, most preferably 4 intervals. However, it is understood that in some embodiments larger numbers of intervals may be desirable.
  • the intervals are selected to provide a higher resolution of the discretization at ranges that are significant for the physiological condition in question than at ranges which are less significant.
  • the intervals for at least some of the sensors are distributed asymmetrically around a normal value of a given sensor signal, i.e. around a value of the sensor signal corresponding to a normal physiological condition.
  • the intervals are distributed such that there are a larger number of intervals on one side of the normal value than on the other side. It has been realised by the inventors that for many sensor signals both the frequency of occurrences as well as the degree of importance of the values for the determination of a physiological condition is asymmetrically distributed. Hence, by selecting asymmetrically distributed intervals, the number of required intervals and, consequently, the size of the look-up table are reduced.
  • the number of different sensor signals should be selected large enough to provide a reliable detection and small enough to provide a small look-up table which can easily be validated.
  • the at least two physiological parameters consist of 2-10 parameters, preferably 3-6 parameters, more preferably 4-5 parameters.
  • the apparatus further detects the rate of change of at least one of the physiological parameters, thereby further increasing the detection reliability.
  • processing means comprises any suitable circuit or device for processing data, e.g. a general- or special-purpose programmable microprocessor, a Digital Signal Processors (DSP), an Application Specific Integrated Circuits (ASIC), a central processing unit (CPU) of a computer, or the like.
  • DSP Digital Signal Processors
  • ASIC Application Specific Integrated Circuits
  • CPU central processing unit
  • the output means comprises any circuit or device for generating an output signal suitable for catching a user's or another person's attention, preferably suitable to wake up a sleeping user.
  • Examples of such output means include a sound generator, a loudspeaker, a beeper, a vibrator, a light source, e.g. for generating a strong blinking light, etc. or any combination of the above.
  • the alarm may be connected to a telecommunications system. Hence, if the physiological condition is detected, the detection apparatus may automatically dial a preselected number if there is no reaction to the alarm within a set timeframe.
  • the term storage means comprises any suitable circuit or device for storing data, for example an electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), a random access memory (RAM), magnetic storage such as a hard disk, a removable storage medium, e.g. a memory card, a PCMCIA card, a smart card, or the like.
  • EEPROM electrically erasable programmable read only memory
  • EPROM erasable programmable read only memory
  • RAM random access memory
  • magnetic storage such as a hard disk, a removable storage medium, e.g. a memory card, a PCMCIA card, a smart card, or the like.
  • the apparatus may comprise a suitably programmed and/or configured data processing device, e.g. a dedicated or multi-purpose medical device, a personal computer, a handheld computer, a PDA, a mobile terminal, or the like.
  • a suitably programmed and/or configured data processing device e.g. a dedicated or multi-purpose medical device, a personal computer, a handheld computer, a PDA, a mobile terminal, or the like.
  • the present invention can be implemented in different ways including the apparatus described above and in the following, a method, and further product means, each yielding one or more of the benefits and advantages described in connection with the first-mentioned method, and each having one or more preferred embodiments corresponding to the preferred embodiments described in connection with the first-mentioned apparatus and disclosed in the dependant claims.
  • the invention further relates to a method of alerting a patient to the risk of the presence of a physiological condition, the method comprising
  • the features of the method described above and in the following may be implemented in software and carried out in a data processing system or other processing means caused by the execution of computer-executable instructions.
  • the instructions may be program code means loaded in a memory, such as a RAM, from a storage medium or from another computer via a computer network.
  • the described features may be implemented by hardwired circuitry instead of software or in combination with software.
  • the invention further relates to a data processing system adapted to perform the method described above and in the following.
  • the invention further relates to a computer program comprising program code means for performing all the steps of the method described above and in the following when said program is run on a computer.
  • the invention further relates to a computer program product comprising program code means stored on a computer readable medium for performing the method described above and in the following when said computer program product is run on a computer.
  • FIGS. 1 a - c show block diagrams of examples of an apparatus for detecting hypoglycaemia
  • FIG. 2 shows a more detailed block diagram of the functions performed by the processing unit of an apparatus for detecting hypoglycaemia
  • FIG. 3 shows an example of a look-up table comprising probabilities for the presence or onset of hypoglycaemia
  • FIG. 4 shows a flow diagram of a method of determining the entries of the look-up table based on reinforcement learning
  • FIG. 5 shows a flow diagram of the process of a daily or nightly operation of a detection apparatus including an on-line adaptation of the entries of the look-up table.
  • FIGS. 1 a - c show block diagrams of examples of an apparatus for detecting hypoglycaemia.
  • same reference numbers refer to the same components.
  • the apparatus 101 comprises a processing unit 102 a memory 103 , a loudspeaker 108 , and a user interface 109 .
  • the apparatus further comprises or is connected to a number of sensors generally designated 104 , 105 , 106 , and 107 .
  • the apparatus 101 is connected to three sensors 104 , 105 , and 106 via cables, and the apparatus 101 further comprises an integrated sensor 107 , e.g. a pulse sensor or a skin temperature sensor integrated into a device, e.g. a device which is worn around the user's wrist.
  • the sensors 104 , 105 , 106 , and 107 may measure the pulse, the heart rate variability, the skin temperature, and the skin impedance, respectively. However it is understood that alternatively or additionally other measurements may be performed.
  • the pulse sensor may be based on any suitable method known in the art such as photoelectric measurements, e.g. as described in “The Biomedical, Engineering Handbook, CRC Press, Volume 1 (ISBN: 0-8493-0461-X), p. 86-1-86-7.
  • the pulse sensor may be a pulse oximeter, e.g. placed at the user's fingertip or ear lobe.
  • the skin impedance may be based on any suitable method known in the art.
  • the skin impedance sensor may comprise a concentric type electrode with an outer passive electrode and an inner electrode, e.g. as disclosed in WO 02/069798.
  • the measurement of the heart rate variability may be based on any suitable method known in the art, e.g. as described in “The Biomedical Engineering Handbook, CRC Press, Volume 1 (ISBN: 0-8493-0461-X), p. 13-1-13-8.
  • the HRV may be determined based on an ECG, e.g. measured via electrodes placed on the user's chest and/or arms.
  • the skin temperature may be measured based on any suitable method known in the art, e.g. by means of a thermistor-based sensor.
  • a different set of sensor signals may be used.
  • such a set of sensor signals may include respiration frequency, respiration effort, eye movements, EOG, muscle tonus, parameters determined by an ECG, e.g. QT interval, frequency of the ⁇ wave, etc., parameters determined by Electroencephalography (EEG), etc, third degree sensor signals such as the O 2 and/or CO 2 content of the blood, first degree sensor signals such as a non-invasive blood glucose measurement, etc., or any combination of the above.
  • EEG Electroencephalography
  • third degree sensor signals such as the O 2 and/or CO 2 content of the blood
  • first degree sensor signals such as a non-invasive blood glucose measurement, etc., or any combination of the above.
  • the above parameters may be detected by any suitable method known per se in the art.
  • the sensors 104 , 105 , 106 , and 107 forward the measured sensor signals to the processing unit 102 .
  • the signals are forwarded as analogue signals which are processed by the processing unit, e.g. by sampling/digitizing the analogue signal and/or averaging the signals over a predetermined time, and/or the like.
  • some or all of the sensors 104 , 105 , 106 , and 107 perform some or all of the above processing and forward a suitably sampled, averaged and digitized signal to the processing unit 102 .
  • the processing unit 102 determines an entry of a look-up table from the combination of sensor signals, retrieves the identified entry from a look-up table stored in the memory 103 , and determines, based on the retrieved entry, whether or not an alarm should be raised, as will be described in greater detail below.
  • the processing unit activates the loudspeaker 108 . It is understood that alternatively or additionally, any other suitable output device for generating an alarm may be used.
  • the apparatus further comprises a user interface 109 , e.g. one or more push buttons, a keypad, a touch screen, or the like, allowing the user to provide feedback to the apparatus.
  • the user interface may comprise a button for turning off the alarm and further buttons or a keypad for providing additional feedback, e.g. an acknowledgment that the alarm was a justified alarm or the alarm was a false alarm, i.e. whether the user actually experiences hypoglycaemia. This feedback may then be used in order to adaptively modify one or more entries in the look-up table as described in greater detail below.
  • the user interface may further allow a user to enter a measured blood glucose level, thereby providing a feedback about the degree of hypoglycaemia, if any.
  • FIG. 1 b shows another example of an apparatus for detecting hypoglycaemia.
  • the apparatus 101 receives the sensor signals from the sensors 104 , 105 , 106 , and 107 via radio communications. Consequently, the apparatus 101 further comprises a short-range radio receiver 116 , e.g. a receiver adapted to receive radio signals in an unlicensed radio frequency band. In one embodiment, the receiver is implemented according to the Bluetooth standard.
  • the sensors 104 , 105 , 106 , and 107 each comprise a corresponding radio transmitter 110 , 111 , 112 , and 113 , respectively, adapted to communicate with the receiver 116 .
  • the apparatus 101 with the receiver, the processing unit and the alarm output may be a device that may be placed on a night stand or it may be a watch-like unit worn around the user's wrist.
  • the device may optionally include a refrigerators compartment that is sufficiently large to hold some juice, a soft drink, or the like, thereby allowing the patient to immediately counterbalance a condition of hypoglycaemia in case of an alarm.
  • FIG. 1 c shows yet another example of an apparatus for detecting hypoglycaemia.
  • the apparatus 101 is connected to three sensors 104 , 105 , and 106 via cables, and the apparatus 101 further comprises an integrated sensor 107 , as in the example of FIG. 1 a .
  • the apparatus of FIG. 1 c further comprises an interface circuit 114 for receiving a signal from a blood glucose measurement device 115 .
  • the interface circuit may be a wired connection, a plug-and-socket connection or a wireless connection, e.g. an infrared or radio-based connection.
  • the interface circuit 114 allows a user to directly transfer a blood glucose value measured by the measurement device 115 to the apparatus 101 , thereby allowing the user to verify or reject an alarm raised by the apparatus 101 .
  • FIG. 2 shows a more detailed block diagram of the functions performed by the processing unit of an apparatus for detecting hypoglycaemia.
  • the processing unit 200 receives inputs from N sensors exemplified by sensors 104 , 105 , and 107 , generally designated S 1 , S 2 , . . . , SN.
  • the signal received from sensor S 1 is fed into a pre-processor module 204 where it is suitably pre-processed, e.g. averaged over a predetermined time period, e.g. a few seconds, and/or normalised and/or the like.
  • the pre-processed signal is fed into a discretizer module 205 .
  • skin temperature T may be discretized as “quite low” (corresponding to T ⁇ 23° C.), “low” (23° C. ⁇ T ⁇ 25° C.), “normal” (25° C. ⁇ T ⁇ 27° C.), and “high” (T>27° C.).
  • the normal value 26° C.
  • the discretizer outputs the number of the identified interval.
  • the pre-processed signal is also fed into a module 206 for determining a rate of change of the sensor signal S 1 .
  • the rate of change is also determined as falling within one of a number of intervals.
  • the range of change may simply be determined as a difference of two consecutive values of the sensor signal. For example, in the above example of skin temperature, the rate of change may be discretized into “rapidly decreasing”, “slowly decreasing”, “slowly increasing”, rapidly increasing.”
  • the module 206 outputs an indication of the rate of change, e.g. by outputting the number of the corresponding interval.
  • the sensor signal received from sensor S 2 is pre-processed in pre-processor 207 , discretised in discretizer module 208 , and a rate of change is determined in module 209 .
  • the sensor signal received from sensor SN is pre-processed in pre-processor 210 , discretised in discretizer module 211 , and a rate of change is determined in module 212 . hence, in this embodiment, 2 N interval numbers are generated.
  • the index numbers determined from the received sensor signals and the corresponding rates of changes are fed into the index module 213 .
  • the index module determines a corresponding entry in the look-up table 214 .
  • the look-up table is stored in a memory 103 , e.g. an EPROM, EEPROM, a hard disk, a memory card, or the like.
  • Each entry of the look-up table corresponds to an estimated probability that the patient is hypoglycaemic.
  • the index module further stores the determined index number together with a corresponding timestamp in a log table 217 stored in the memory 103 or, alternatively, in a separate memory.
  • the log table may store the index numbers selected during the past 12 hours, the last 24 hours, or the like.
  • the determined probability retrieved from the look-up table 214 is fed into the threshold module 215 , where the probability is compared to a predetermined threshold.
  • the threshold may be preset by a physician for the individual patient.
  • a single global threshold is used for all entries of the look-up table, thereby reducing the number of parameters that have to be adjusted. If the threshold module determines that the probability is below the threshold, no alarm is generated. Otherwise, if the probability is determined to be above the threshold an alarm signal is output by the processing unit controlling the loudspeaker 108 to sound an audible alarm.
  • the threshold module further forwards a signal to a reinforcement module 216 indicating that an alarm has been triggered.
  • the above process is repeated in regular time intervals, e.g. every 30 seconds, every minute, every few minutes, or the like. Consequently, in this embodiment, the sensors acquire measurements over one time interval, and the resulting signal is processed, transformed into an index for the look-up table, and from the corresponding probability it is determined whether or not an alarm is to be raised. In some embodiments, an alarm is only raised, if the determined probability is determined to be above threshold in a predetermined number of consecutive time intervals.
  • the processing unit receives a signal from the user interface relating to the actual physiological condition of the user, the received information is fed into a reinforcement learning module 216 . Based on the received input and any possible signals received from the threshold unit about any triggered alarms, the reinforcement module determines a time period such that all entries of the look-up table selected during that time period are modified. For example, if an alarm has been generated by the apparatus and if the user has indicated via the user interface 109 that the alarm was a false alarm, the reinforcement module may determined to decrease all probabilities that were selected during the last 30 minutes prior to the alarm.
  • the reinforcement module may determine to increase all probabilities that were selected during the last 30 minutes prior to the alarm.
  • the reinforcement module may determine to modify all entries of the look-up table 214 that were selected during the previous night. Consequently, the reinforcement module retrieves information from the memory 217 identifying the entries that were selected during the determined period of time and the corresponding points in time at which the entries were selected. The reinforcement module 216 then calculates modified probabilities for the identified entries and stores the modified probabilities in look-up table 214 .
  • An embodiment of the update algorithm will be described below.
  • FIG. 3 shows an example of a look-up table comprising probabilities for the presence or onset of hypoglycaemia.
  • the corresponding apparatus receives signals from two sensors S 1 and S 2 . It is further assumed that the signal from S 1 is discretized into four intervals indexed 1 , 2 , 3 , and 4 , while the signal from S 2 is discretized into three intervals indexed 1 , 2 , and 3 .
  • the rate of change of signal S 1 labelled ⁇ S 1
  • the rate of change of signal S 2 labelled ⁇ S 2
  • the rate of change of signal S 2 is discretized in two intervals indexed 1 and 2 .
  • Each row of the look-up table of FIG. 3 corresponds to one of the possible combinations of intervals of S 1 , ⁇ S 1 , S 2 , and ⁇ S 2 , and each row includes an entry comprising a probability P assigned to the corresponding combination of intervals.
  • the probability values are schematically indicated by P ijkl , where i ⁇ 1 , 2 , 3 , 4 ⁇ , j ⁇ 1 , 2 , 3 , 4 ⁇ , k ⁇ 1 , 2 , 3 , ⁇ , l ⁇ 1 , 2 ⁇ correspond to the indices of the intervals corresponding to S 1 , ⁇ S 1 , S 2 , and ⁇ S 2 , respectively.
  • the number of sensor signals and the respective numbers of intervals are selected to be small but still large enough to provide a reliable detection of the physiological condition.
  • the number of sensor signals and the respective numbers of intervals are selected to be small but still large enough to provide a reliable detection of the physiological condition.
  • the format of the data structure in which the look-up table is stored may vary depending on the actual implementation.
  • the table may be stored as a multi-dimensional array, as a hierarchical tree structure, or the like.
  • FIG. 4 shows a flow diagram of a method of determining the entries of the look-up table based on reinforcement learning.
  • the process is based on a set of experimental data comprising measured sensor signals for a patient over a predetermined period of time, e.g. a few days, a week, or even longer, and corresponding indications whether the patient was in a condition of hypoglycaemia or not.
  • the experimental data is obtained for the same patient who subsequently will use the apparatus, thereby providing an individualised look-up table.
  • the look-up table may be pre-trained based on generic patient data, thereby avoiding a data acquisition for each individual patient.
  • the data is represented as a sequence of data records, each data record comprising a time t, a set of measured sensor signals ⁇ S t ⁇ at time t, e.g.
  • the sensor signals averaged over a time period around the time t, and an indication whether the patient at time t was in a state of hypoglycaemia or not.
  • MAX corresponds to the number of records in the data set.
  • the above data may be obtained during an overnight monitoring of a patient under supervision. It is understood that a different time increment may be used instead, e.g. any increment between a few seconds and several minutes.
  • P i 0.5 for probabilities P i .
  • the probabilities are assumed to be indexed by i.
  • step 402 an iteration is started.
  • step 403 the time t is incremented, i.e. t ⁇ t+1.
  • step 404 the process retrieves the sensor signals ⁇ S t ⁇ for time t from memory and, in step 405 , the corresponding index i(t) identifying one of the entries of the look-up table is determined as was described above. From the look-up table, the corresponding probability P i(t) is retrieved from the look-up table stored in the memory 103 . The identified index i(t) and the corresponding time t are stored in a suitable data record in memory 103 for later use.
  • the process enters a loop.
  • the loop comprises the steps from step 412 through step 415 and performs an update of the probabilities of all the entries of the look-up table that have been identified during a predetermined period prior to the current time t.
  • the correction depends on the probabilities at time ⁇ and at time ⁇ 1.
  • the parameter ⁇ determines the relative weight of the probabilities at time ⁇ and at time ⁇ 1.
  • the value of ⁇ is selected according to the sampling rate and the length of the time period. For example for a time period of 30 minutes and a sampling once a minute as in the current example, values of ⁇ between 0.97 and 0.98 are preferred. However, other values may be used as well.
  • the parameter ⁇ is referred to as the learning rate and determines the overall strength of the correction. For example, the learning rate may be selected to be between 0.4 and 0.6. However, other values may be selected as well.
  • the learning rate is multiplied with the factor ⁇ , thereby causing the most recent entries prior to the false positive or false negative result to be corrected by the largest correction factors.
  • the parameter r is the reinforcement parameter determined in steps 406 - 408 .
  • the term ⁇ P i( ⁇ ) ⁇ P i( ⁇ 1) is a small negative number.
  • the correction ⁇ P ⁇ is a small negative number
  • the correction ⁇ P ⁇ is a positive number.
  • step 414 the parameter T is incremented, and at step 415 it is tested whether ⁇ >t, i.e. whether the correction loop is completed. If ⁇ >t, the process continues at step 416 , otherwise the process returns to step 412 .
  • a process for determining an initial set of probabilities for the entries of the look-up table of an apparatus is disclosed.
  • the entries of the look-up table are subsequently updated during operation based on feedback received from the patient, thereby providing an adaptive detection apparatus where the probabilities in the look-up table are both adaptive with respect to the individual patient and with respect to a development of the patient over time.
  • a statistical correlation-analysis on the experimental data may be performed, e.g. using a statistics software package like SAS or MatLab.
  • the analysis may be started with any pair of two sensor signals of the set of sensor signals. Starting with the pair that caries most information, additional signals from any of the other sensors or trends of the sensor signals may be added one by one in order to identify a set of signals with a high correlation to the observed hypoglycaemia events. This is an efficient but rather time consuming solution.
  • one, more or all the sensor data and possibly also the trends from the experimental data set are analysed with a conventional pattern analysis software.
  • the mapping from sensor signals to the presence or absence of a hypoglycaemia condition is saved and used without subsequent user adaptation.
  • FIG. 5 shows a flow diagram of the process of a daily or nightly operation of a detection apparatus including an on-line adaptation of the entries of the look-up table.
  • the apparatus is initialised. After placing the sensors at the correct positions on the patient's body and connecting any wires if necessary, the apparatus is put in an initialisation state, e.g. by powering on the apparatus. Preferably, during the first couple of minutes while the patient is wearing the sensors, the patient should not have hypoglycaemia. During this period, the apparatus may check whether all sensor signals are received correctly, and acquire initial sensor signals, e.g. by sampling data over an initial time interval, thereby adapting to the physiology of the user.
  • the sensor signals are continuously or periodically acquired and analysed:
  • the sensor signals are acquired by the sensors and forwarded to the apparatus, e.g. by sampling the sensor signals over a predetermined period, e.g. one minute.
  • step 503 the acquired sensor signals are analysed by the apparatus, i.e. the sensor signals are discretized, the rates of change of the sensor signals are determined and discretized, and the entry of the look-up table that corresponds to the resulting combination of discretized sensor signals and rates of changes is identified, as was described in greater detail above.
  • the index of the identified entry of the look-up table is stored in memory 103 .
  • step 504 the process compares the identified entry of the look-up table with a predetermined threshold and determines whether an alarm should be raised. If the probability is below threshold, no alarm is raised, and the process returns to step 502 starting the next sampling interval. If the probability is above threshold, the process continues at step 505 .
  • an alarm is raised only if the probability is higher than the threshold during a predetermined number of consecutive intervals, e.g. 2-5 intervals, thereby reducing the risk of false alarms due to isolated erroneous measurements. For example, the number of consecutive intervals required may be selected by a physician or the user.
  • step 505 the alarm is raised, e.g. by sounding an audible alarm and/or activating a vibrator and/or the like, thereby alerting the patient to a potential condition of hypoglycaemia.
  • the process receives an acknowledgment from the patient.
  • the patient may press a button on the apparatus to stop the alarm.
  • the process may increase the severity of the alarm, e.g. by increasing the volume of the alarm sound, by sending a control signal to a different device, e.g. in order to invoke an alarm in a different room of the house, or by causing a modem to dial a predetermined telephone number e.g. of a hospital, or the like, in order provide help to the patient.
  • the patient may either provide an affirmative acknowledgment confirming that the patient experiences a condition of hypoglycaemia, or the patient may provide a rejection of the alarm.
  • the patient may merely switch off the alarm without providing any feedback, thereby preventing the entries of the look-up table from being updated. In this case, the process would simply continue at step 502 after the alarm has been switched off.
  • the apparatus may comprise three buttons “Switch off alarm”, “confirm alarm”, and “reject alarm”, thereby allowing the patient to decide whether or not to provide feedback for a given alarm.
  • the apparatus may be operated in two modes, an adaptive mode where feedback from the patient is accepted, and a stationary mode without adaptation of the probabilities.
  • step 506 the process has received a confirmation of the alarm
  • the patient may measure the blood glucose level and enter the measured blood glucose level into the apparatus via a suitable user interface or via a data connection between the blood glucose measurement device and the hypoglycaemia detection apparatus.
  • the confirmation or rejection of the alarm may be replaced or supplemented with a measured blood glucose level.
  • the reinforcement parameter may be determined from the measured blood glucose level BG, if such a measurement is provided.
  • a continuous reinforcement parameter is determined.
  • the learning rate ⁇ , the parameter ⁇ , and the relative weight factor ⁇ are determined as described in connection with FIG. 4 above.
  • step 502 the process continues at step 502 , i.e. by continuing the data acquisition and analysis.
  • the discretized sensor data in memory 520 is saved for an entire night. For example, assuming a storage requirement of one byte per discretized sensor signal, 12 hours data of signals from 5 sensors and their corresponding discretized rates of changes with a sampling frequency of 1 sample/minute requires 2*5*60*12 bytes, i.e. approximately 8 kilobyte of data. If the apparatus receives a feedback from a patient indicating that an undetected hypoglycaemia has occurred during a predetermined period, e.g. at an unspecified time during the past six hours, or at an unspecified time during the last night, the apparatus may update all entries of the look-up table that were selected during that period of time, i.e. in a predetermined time interval [t 0 ;t 1 ].
  • all the probabilities in the predetermined time period are updated with the same relative strength, since the exact time within the time period at which the hypoglycaemia occurred is unknown.
  • the patient may initiate the above update, e.g. by indicating the time interval via a suitable user interface.
  • the invention has mainly been described in connection with hypoglycaemia and the sensors relevant for the detection of hypoglycaemia. However, it is understood that the invention may also be applied to the detection of other physiological conditions, possibly based on other types of measurements.
  • the bed sheets be part of the device, e.g. by placing some of the sensors, for example the sweat and temperature sensor, in the sheet.
  • Some of the wires can also be placed in the sheet.
  • a heart rate variability analysis requires two connected sensors. The wire connecting these sensors may advantageously be put in the sheet.
  • the detection apparatus may send a signal to the glucagon dosing device that injects the patient.
  • the signal may be sent via a wireless connection. The possibility of this depends on the development of durability of ready-to-use glucagon.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Surgery (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Molecular Biology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biophysics (AREA)
  • Cardiology (AREA)
  • Physiology (AREA)
  • Optics & Photonics (AREA)
  • Emergency Medicine (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Pulmonology (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
US11/401,993 2003-10-13 2006-04-11 Apparatus and method for determining a physiological condition Abandoned US20060281980A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US14/055,508 US10524669B2 (en) 2003-10-13 2013-10-16 Apparatus and method for determining a physiological condition

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
DKPA200301510 2003-10-13
DKPA200301510 2003-10-13
PCT/DK2004/000697 WO2005037092A1 (en) 2003-10-13 2004-10-12 Apparatus and method for determining a physiological condition

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
PCT/DK2004/000697 Continuation WO2005037092A1 (en) 2003-10-13 2004-10-12 Apparatus and method for determining a physiological condition

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14/055,508 Division US10524669B2 (en) 2003-10-13 2013-10-16 Apparatus and method for determining a physiological condition

Publications (1)

Publication Number Publication Date
US20060281980A1 true US20060281980A1 (en) 2006-12-14

Family

ID=37524979

Family Applications (2)

Application Number Title Priority Date Filing Date
US11/401,993 Abandoned US20060281980A1 (en) 2003-10-13 2006-04-11 Apparatus and method for determining a physiological condition
US14/055,508 Expired - Fee Related US10524669B2 (en) 2003-10-13 2013-10-16 Apparatus and method for determining a physiological condition

Family Applications After (1)

Application Number Title Priority Date Filing Date
US14/055,508 Expired - Fee Related US10524669B2 (en) 2003-10-13 2013-10-16 Apparatus and method for determining a physiological condition

Country Status (3)

Country Link
US (2) US20060281980A1 (da)
DK (1) DK1677668T3 (da)
ES (1) ES2349174T3 (da)

Cited By (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070112261A1 (en) * 2005-08-24 2007-05-17 Medtronic Minimed, Inc. Automobile Glucose Sensor Monitoring System and Method for Using the Same
US20080068932A1 (en) * 2006-09-14 2008-03-20 Bennie Mosley Wrist watch for monitoring diabetes
US20080161701A1 (en) * 2006-12-28 2008-07-03 Bullens Roland W M Event Registration for Automatic Threshold Setting
US20090048500A1 (en) * 2005-04-20 2009-02-19 Respimetrix, Inc. Method for using a non-invasive cardiac and respiratory monitoring system
US20090093686A1 (en) * 2007-10-08 2009-04-09 Xiao Hu Multi Automated Severity Scoring
US20090270705A1 (en) * 2008-04-28 2009-10-29 Medtronic Minimed, Inc. Automobile Physiological Monitoring System and Method for Using the Same
US20100261982A1 (en) * 2007-12-06 2010-10-14 Norbert Noury Method and apparatus for detecting a critical situation of a subject
US8115635B2 (en) 2005-02-08 2012-02-14 Abbott Diabetes Care Inc. RF tag on test strips, test strip vials and boxes
US20120165695A1 (en) * 2009-06-26 2012-06-28 Widex A/S Eeg monitoring apparatus and method for presenting messages therein
US8287495B2 (en) 2009-07-30 2012-10-16 Tandem Diabetes Care, Inc. Infusion pump system with disposable cartridge having pressure venting and pressure feedback
US20140228655A1 (en) * 2009-05-18 2014-08-14 Empire Technology Development, Llc Touch-sensitive device and method
WO2015025187A1 (en) * 2013-08-23 2015-02-26 Medicus Engineering Aps Method and device for improving prediction and detection of change in a physiological condition
US20160066826A1 (en) * 2013-11-14 2016-03-10 Dexcom, Inc. Devices and methods for continuous analyte monitoring
US20160071403A1 (en) * 2014-09-08 2016-03-10 Verizon Patent And Licensing Inc. Method, apparatus and system for broadcasting an alarm for an alarm group
US9962486B2 (en) 2013-03-14 2018-05-08 Tandem Diabetes Care, Inc. System and method for detecting occlusions in an infusion pump
US20180242875A1 (en) * 2017-02-28 2018-08-30 Zoll Medical Corporation Configuring a cardiac monitoring device
US10258736B2 (en) 2012-05-17 2019-04-16 Tandem Diabetes Care, Inc. Systems including vial adapter for fluid transfer
US10303971B2 (en) * 2015-06-03 2019-05-28 Innereye Ltd. Image classification by brain computer interface
US10405757B2 (en) 2014-02-25 2019-09-10 Icu Medical, Inc. Patient monitoring system with gatekeeper signal
US10456078B2 (en) * 2016-03-03 2019-10-29 Chandrasekaran Jayaraman Wearable device and system for preventative health care for repetitive strain injuries
US11049614B2 (en) 2013-03-15 2021-06-29 Tandem Diabetes Care, Inc. Field update of an ambulatory infusion pump system
US20210275089A1 (en) * 2018-09-25 2021-09-09 Koninklijke Philips N.V. Deriving information about a person's sleep and wake states from a sequence of video frames
US11270792B2 (en) 2015-10-19 2022-03-08 Icu Medical, Inc. Hemodynamic monitoring system with detachable display unit
US11273283B2 (en) 2017-12-31 2022-03-15 Neuroenhancement Lab, LLC Method and apparatus for neuroenhancement to enhance emotional response
US11364361B2 (en) 2018-04-20 2022-06-21 Neuroenhancement Lab, LLC System and method for inducing sleep by transplanting mental states
US11452839B2 (en) 2018-09-14 2022-09-27 Neuroenhancement Lab, LLC System and method of improving sleep
US20220346676A1 (en) * 2019-08-30 2022-11-03 The University Of Warwick Electrocardiogram-based blood glucose level monitoring
US11717686B2 (en) 2017-12-04 2023-08-08 Neuroenhancement Lab, LLC Method and apparatus for neuroenhancement to facilitate learning and performance
US11723579B2 (en) 2017-09-19 2023-08-15 Neuroenhancement Lab, LLC Method and apparatus for neuroenhancement
US11786694B2 (en) 2019-05-24 2023-10-17 NeuroLight, Inc. Device, method, and app for facilitating sleep
US12280219B2 (en) 2017-12-31 2025-04-22 NeuroLight, Inc. Method and apparatus for neuroenhancement to enhance emotional response
US12484809B2 (en) * 2019-08-30 2025-12-02 The University Of Warwick Electrocardiogram-based blood glucose level monitoring

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8488500B2 (en) 2008-05-02 2013-07-16 Dhaani Systems Power management of networked devices
KR102335739B1 (ko) 2014-12-19 2021-12-06 삼성전자주식회사 비 침습적 혈당 측정 방법 및 이를 위한 장치
US10888281B2 (en) 2016-05-13 2021-01-12 PercuSense, Inc. System and method for disease risk assessment and treatment
US20220122735A1 (en) * 2019-10-25 2022-04-21 Wise IOT Solutions System and method for processing human related data including physiological signals to make context aware decisions with distributed machine learning at edge and cloud

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5997476A (en) * 1997-03-28 1999-12-07 Health Hero Network, Inc. Networked system for interactive communication and remote monitoring of individuals
US6572542B1 (en) * 2000-03-03 2003-06-03 Medtronic, Inc. System and method for monitoring and controlling the glycemic state of a patient
US20030199740A1 (en) * 2000-02-14 2003-10-23 Iliff Edwin C. Automated diagnostic system and method including disease timeline
US20040167418A1 (en) * 2001-02-28 2004-08-26 Hung Nguyen Non-invasive method and apparatus for determining onset of physiological conditions

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4509531A (en) 1982-07-28 1985-04-09 Teledyne Industries, Inc. Personal physiological monitor
JPH07236643A (ja) 1994-02-25 1995-09-12 Otax Kk 低血糖監視装置
US5844862A (en) 1998-07-22 1998-12-01 Cocatre-Zilgien; Jan H. Skin temperature radio telemetry and alarms
US6064898A (en) * 1998-09-21 2000-05-16 Essential Medical Devices Non-invasive blood component analyzer
US6151517A (en) 1999-01-22 2000-11-21 Futrex Inc. Method and apparatus for noninvasive quantitative measurement of blood analytes
CA2382228A1 (en) 1999-08-23 2001-03-01 University Of Virginia Patent Foundation Method and apparatus for predicting the risk of hypoglycemia
US7025425B2 (en) 2000-03-29 2006-04-11 University Of Virginia Patent Foundation Method, system, and computer program product for the evaluation of glycemic control in diabetes from self-monitoring data
EP1289601A4 (en) 2000-05-31 2008-12-10 Metacure N V ELECTROPANCREATOGRAPHIE
DE60133653T2 (de) 2000-08-18 2009-06-04 Animas Technologies Llc Vorrichtung zum vorhersagen von hypoglyecemiefällen
EP1351601A2 (en) 2001-01-03 2003-10-15 Microlife Intellectual Property GmbH A system for measuring at least one body parameter, a blood pressure monitor and a medical thermometer

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5997476A (en) * 1997-03-28 1999-12-07 Health Hero Network, Inc. Networked system for interactive communication and remote monitoring of individuals
US20030199740A1 (en) * 2000-02-14 2003-10-23 Iliff Edwin C. Automated diagnostic system and method including disease timeline
US6572542B1 (en) * 2000-03-03 2003-06-03 Medtronic, Inc. System and method for monitoring and controlling the glycemic state of a patient
US20040167418A1 (en) * 2001-02-28 2004-08-26 Hung Nguyen Non-invasive method and apparatus for determining onset of physiological conditions

Cited By (63)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8115635B2 (en) 2005-02-08 2012-02-14 Abbott Diabetes Care Inc. RF tag on test strips, test strip vials and boxes
US8542122B2 (en) 2005-02-08 2013-09-24 Abbott Diabetes Care Inc. Glucose measurement device and methods using RFID
US8390455B2 (en) 2005-02-08 2013-03-05 Abbott Diabetes Care Inc. RF tag on test strips, test strip vials and boxes
US8358210B2 (en) 2005-02-08 2013-01-22 Abbott Diabetes Care Inc. RF tag on test strips, test strip vials and boxes
US8223021B2 (en) 2005-02-08 2012-07-17 Abbott Diabetes Care Inc. RF tag on test strips, test strip vials and boxes
US20090048500A1 (en) * 2005-04-20 2009-02-19 Respimetrix, Inc. Method for using a non-invasive cardiac and respiratory monitoring system
US20070112261A1 (en) * 2005-08-24 2007-05-17 Medtronic Minimed, Inc. Automobile Glucose Sensor Monitoring System and Method for Using the Same
US20080068932A1 (en) * 2006-09-14 2008-03-20 Bennie Mosley Wrist watch for monitoring diabetes
US8052610B2 (en) * 2006-12-28 2011-11-08 Medtronic, Inc. Event registration for automatic threshold setting
US20080161701A1 (en) * 2006-12-28 2008-07-03 Bullens Roland W M Event Registration for Automatic Threshold Setting
US20090093686A1 (en) * 2007-10-08 2009-04-09 Xiao Hu Multi Automated Severity Scoring
US20100261982A1 (en) * 2007-12-06 2010-10-14 Norbert Noury Method and apparatus for detecting a critical situation of a subject
US8207860B2 (en) 2008-04-28 2012-06-26 Medtronic Minimed, Inc. Automobile physiological monitoring system and method for using the same
US8207859B2 (en) 2008-04-28 2012-06-26 Medtronic Minimed, Inc. Automobile physiological monitoring system and method for using the same
US20090267775A1 (en) * 2008-04-28 2009-10-29 Medtronic Minimed, Inc. Automobile Physiological Monitoring System and Method for Using the Same
US20090267774A1 (en) * 2008-04-28 2009-10-29 Medtronic Minimed, Inc. Automobile Physiological Monitoring System and Method for Using the Same
US20090270705A1 (en) * 2008-04-28 2009-10-29 Medtronic Minimed, Inc. Automobile Physiological Monitoring System and Method for Using the Same
US20140228655A1 (en) * 2009-05-18 2014-08-14 Empire Technology Development, Llc Touch-sensitive device and method
US9427192B2 (en) * 2009-05-18 2016-08-30 Empire Technology Development Llc Touch-sensitive device and method
US20120165695A1 (en) * 2009-06-26 2012-06-28 Widex A/S Eeg monitoring apparatus and method for presenting messages therein
US10959639B2 (en) * 2009-06-26 2021-03-30 T&W Engineering A/S EEG monitoring apparatus and method for presenting messages therein
US8298184B2 (en) 2009-07-30 2012-10-30 Tandem Diabetes Care, Inc. Infusion pump system with disposable cartridge having pressure venting and pressure feedback
US11135362B2 (en) 2009-07-30 2021-10-05 Tandem Diabetes Care, Inc. Infusion pump systems and methods
US9211377B2 (en) 2009-07-30 2015-12-15 Tandem Diabetes Care, Inc. Infusion pump system with disposable cartridge having pressure venting and pressure feedback
US12144964B2 (en) 2009-07-30 2024-11-19 Tandem Diabetes Care, Inc Infusion pump system with disposable cartridge having pressure venting and pressure feedback
US12042627B2 (en) 2009-07-30 2024-07-23 Tandem Diabetes Care, Inc. Infusion pump systems and methods
US8758323B2 (en) 2009-07-30 2014-06-24 Tandem Diabetes Care, Inc. Infusion pump system with disposable cartridge having pressure venting and pressure feedback
US8926561B2 (en) 2009-07-30 2015-01-06 Tandem Diabetes Care, Inc. Infusion pump system with disposable cartridge having pressure venting and pressure feedback
US8287495B2 (en) 2009-07-30 2012-10-16 Tandem Diabetes Care, Inc. Infusion pump system with disposable cartridge having pressure venting and pressure feedback
US11285263B2 (en) 2009-07-30 2022-03-29 Tandem Diabetes Care, Inc. Infusion pump systems and methods
US10258736B2 (en) 2012-05-17 2019-04-16 Tandem Diabetes Care, Inc. Systems including vial adapter for fluid transfer
US9962486B2 (en) 2013-03-14 2018-05-08 Tandem Diabetes Care, Inc. System and method for detecting occlusions in an infusion pump
US11776689B2 (en) 2013-03-15 2023-10-03 Tandem Diabetes Care, Inc. Field update of an ambulatory infusion pump system
US11049614B2 (en) 2013-03-15 2021-06-29 Tandem Diabetes Care, Inc. Field update of an ambulatory infusion pump system
US11452457B2 (en) 2013-08-23 2022-09-27 Medicus Engineering Aps Method and device for improving prediction and detection of change in a physiological condition
WO2015025187A1 (en) * 2013-08-23 2015-02-26 Medicus Engineering Aps Method and device for improving prediction and detection of change in a physiological condition
US10555677B2 (en) 2013-08-23 2020-02-11 Medicus Engineering Aps Method and device for improving prediction and detection of change in a physiological condition
US10004436B2 (en) * 2013-11-14 2018-06-26 Dexcom, Inc. Devices and methods for continuous analyte monitoring
US20160066826A1 (en) * 2013-11-14 2016-03-10 Dexcom, Inc. Devices and methods for continuous analyte monitoring
US10405757B2 (en) 2014-02-25 2019-09-10 Icu Medical, Inc. Patient monitoring system with gatekeeper signal
US9589454B2 (en) * 2014-09-08 2017-03-07 Verizon Patent And Licensing Inc. Method, apparatus and system for broadcasting an alarm for an alarm group
US20160071403A1 (en) * 2014-09-08 2016-03-10 Verizon Patent And Licensing Inc. Method, apparatus and system for broadcasting an alarm for an alarm group
US10948990B2 (en) * 2015-06-03 2021-03-16 Innereye Ltd. Image classification by brain computer interface
US10303971B2 (en) * 2015-06-03 2019-05-28 Innereye Ltd. Image classification by brain computer interface
US11270792B2 (en) 2015-10-19 2022-03-08 Icu Medical, Inc. Hemodynamic monitoring system with detachable display unit
US10456078B2 (en) * 2016-03-03 2019-10-29 Chandrasekaran Jayaraman Wearable device and system for preventative health care for repetitive strain injuries
US11844620B2 (en) 2017-02-28 2023-12-19 Zoll Medical Corporation Configuring a cardiac monitoring device
US10912478B2 (en) * 2017-02-28 2021-02-09 Zoll Medical Corporation Configuring a cardiac monitoring device
US20180242875A1 (en) * 2017-02-28 2018-08-30 Zoll Medical Corporation Configuring a cardiac monitoring device
US11723579B2 (en) 2017-09-19 2023-08-15 Neuroenhancement Lab, LLC Method and apparatus for neuroenhancement
US11717686B2 (en) 2017-12-04 2023-08-08 Neuroenhancement Lab, LLC Method and apparatus for neuroenhancement to facilitate learning and performance
US11273283B2 (en) 2017-12-31 2022-03-15 Neuroenhancement Lab, LLC Method and apparatus for neuroenhancement to enhance emotional response
US11478603B2 (en) 2017-12-31 2022-10-25 Neuroenhancement Lab, LLC Method and apparatus for neuroenhancement to enhance emotional response
US11318277B2 (en) 2017-12-31 2022-05-03 Neuroenhancement Lab, LLC Method and apparatus for neuroenhancement to enhance emotional response
US12280219B2 (en) 2017-12-31 2025-04-22 NeuroLight, Inc. Method and apparatus for neuroenhancement to enhance emotional response
US12383696B2 (en) 2017-12-31 2025-08-12 NeuroLight, Inc. Method and apparatus for neuroenhancement to enhance emotional response
US12397128B2 (en) 2017-12-31 2025-08-26 NeuroLight, Inc. Method and apparatus for neuroenhancement to enhance emotional response
US11364361B2 (en) 2018-04-20 2022-06-21 Neuroenhancement Lab, LLC System and method for inducing sleep by transplanting mental states
US11452839B2 (en) 2018-09-14 2022-09-27 Neuroenhancement Lab, LLC System and method of improving sleep
US20210275089A1 (en) * 2018-09-25 2021-09-09 Koninklijke Philips N.V. Deriving information about a person's sleep and wake states from a sequence of video frames
US11786694B2 (en) 2019-05-24 2023-10-17 NeuroLight, Inc. Device, method, and app for facilitating sleep
US20220346676A1 (en) * 2019-08-30 2022-11-03 The University Of Warwick Electrocardiogram-based blood glucose level monitoring
US12484809B2 (en) * 2019-08-30 2025-12-02 The University Of Warwick Electrocardiogram-based blood glucose level monitoring

Also Published As

Publication number Publication date
ES2349174T3 (es) 2010-12-28
US10524669B2 (en) 2020-01-07
US20140058218A1 (en) 2014-02-27
DK1677668T3 (da) 2010-10-25

Similar Documents

Publication Publication Date Title
US10524669B2 (en) Apparatus and method for determining a physiological condition
EP1677668B1 (en) Apparatus and method for determining a physiological condition
US20100030092A1 (en) Adaptive Hypoglycaemia Alert System and Method
JP6423487B2 (ja) 痙攣の検出のためのシステムおよびその作動方法
US20190110692A1 (en) Processing a physical signal
JP5049132B2 (ja) 音声インジケータを有する移動式医療用遠隔測定装置
US7598878B2 (en) Method and device for measuring physiological parameters at the wrist
US20050075542A1 (en) System and method for automatic monitoring of the health of a user
US20080208009A1 (en) Wearable Device, System and Method for Measuring Vital Parameters
US20160066840A1 (en) System method and device for determining the risk of dehydration
CN109480861A (zh) 提供敏感且特定的警报的系统和方法
JP2004529704A (ja) 患者監視における警告限界の適応選択
EP1750585A1 (en) Method and device for measuring physiological parameters at the hand
CN102043894A (zh) 一种生理数据监测系统及方法
CN106691423B (zh) 通过心跳讯号评估心脏健康的穿戴式装置及讯号处理方法
GB2533774A (en) Data processing based on multiple inputs
EP2734105A1 (en) Health meter
CN116724361A (zh) 基于睡眠活动的对患者健康状况变化的检测
WO2025016490A1 (zh) 心电图异常监测方法、装置、设备和存储介质
GB2425180A (en) Wearable physiological monitor with wireless transmitter
US20090326398A1 (en) Sensing biological data
CN113303804A (zh) 生理讯号测量装置动态阈值调校系统
CN115798739A (zh) 多模融合智能感知预警方法和系统
EP4312228A1 (en) System for supporting a patient's health control and operating method of such system
EP4472520A1 (en) System for reproductive monitoring

Legal Events

Date Code Title Description
AS Assignment

Owner name: NOVO NORDISK A/S, DENMARK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:RANDLOV, JETTE;HANSEN, JON ULRICH;POULSEN, JENS ULRIK;REEL/FRAME:018163/0747

Effective date: 20060606

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION