[go: up one dir, main page]

WO2017180617A1 - Mesure de stress psychologique aigu utilisant un détecteur sans fil - Google Patents

Mesure de stress psychologique aigu utilisant un détecteur sans fil Download PDF

Info

Publication number
WO2017180617A1
WO2017180617A1 PCT/US2017/026996 US2017026996W WO2017180617A1 WO 2017180617 A1 WO2017180617 A1 WO 2017180617A1 US 2017026996 W US2017026996 W US 2017026996W WO 2017180617 A1 WO2017180617 A1 WO 2017180617A1
Authority
WO
WIPO (PCT)
Prior art keywords
heart rate
stress
wireless sensor
sensor device
hrv
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.)
Ceased
Application number
PCT/US2017/026996
Other languages
English (en)
Inventor
Alexander Chan
Ravi Narasimhan
Nandakumar Selvaraj
Toai Doan
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.)
Vital Connect Inc
Original Assignee
Vital Connect 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
Priority claimed from US15/096,146 external-priority patent/US9980678B2/en
Application filed by Vital Connect Inc filed Critical Vital Connect Inc
Publication of WO2017180617A1 publication Critical patent/WO2017180617A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

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
    • A61B5/024—Measuring pulse rate or heart rate
    • A61B5/02405—Determining heart rate variability
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
    • 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
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7278—Artificial waveform generation or derivation, e.g. synthesizing signals from measured signals
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/352—Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval

Definitions

  • the present invention relates to wireless sensor devices, and more particularly, to a wireless sensor device utilized to measure psychological acute stress.
  • HR heart rate
  • HRV heart rate variability
  • a method and system for determining psychological acute stress comprises detecting a physiological signal using a wireless sensor device, determining a stress feature using a normalized heart rate and a plurality of heart rate variability (HRV) features, wherein the normalized heart rate and the plurality of heart rate variability features are calculated using the detected physiological signal, and determining a stress level using the stress feature to determine the psychological acute stress.
  • HRV heart rate variability
  • the system comprises a wireless sensor device that includes a processor and a memory device coupled to the processor, wherein the memory device stores an application which, when executed by the processor, causes the wireless sensor device to detect a physiological signal using a wireless sensor device, determine a stress feature using a normalized heart rate and a plurality of heart rate variability (HRV) features, wherein the normalized heart rate and the plurality of heart rate variability features are calculated using the detected physiological signal, and determine a stress level using the stress feature to determine the psychological acute stress.
  • HRV heart rate variability
  • Figure 1 illustrates a wireless sensor device for measuring psychological stress in accordance with an embodiment.
  • Figure 2 illustrates a method for measuring psychological stress in accordance with an embodiment.
  • Figure 3 illustrates a more detailed flow chart of a method for measuring psychological stress in accordance with an embodiment.
  • Figure 4 illustrates a more detailed flow chart of a method for adaptive function calibration in accordance with an embodiment.
  • Figure 5 illustrates a diagram of stress level calculation in accordance with an embodiment.
  • Figure 6 illustrates a method for determining psychological acute stress using a stress index (SI) metric in accordance with an embodiment.
  • SI stress index
  • Figure 7 illustrates a method for feature extraction in accordance with an embodiment.
  • Figure 8 illustrates a diagram of stress index (SI) metric calculation in accordance with an embodiment.
  • SI stress index
  • the present invention relates to wireless sensor devices, and more particularly, to a wireless sensor device utilized to measure psychological acute stress.
  • the following description is presented to enable one of ordinary skill in the art to make and use the invention and is provided in the context of a patent application and its requirements.
  • Various modifications to the preferred embodiment and the generic principles and features described herein will be readily apparent to those skilled in the art.
  • the present invention is not intended to be limited to the embodiments shown but is to be accorded the widest scope consistent with the principles and features described herein.
  • the human body regulates its internal environment by various physiological processes, and maintains at a certain state of equilibrium called homeostasis. Stress is referred to as the disruption of homeostasis leading to a perturbed state of the human body. Stress can be triggered by various factors known as stressors including physical (e.g. diseases/illness, allergy, fatigue, and poor sleep), psychological (e.g. conflicts, trauma, financial state, and work/educational demands), and environmental (e.g. noise, crowd, disasters, and pollution) influences.
  • physical e.g. diseases/illness, allergy, fatigue, and poor sleep
  • psychological e.g. conflicts, trauma, financial state, and work/educational demands
  • environmental e.g. noise, crowd, disasters, and pollution
  • HPA hypothalamic-pituitary- adrenocortical
  • SAM sympathetic-adrenal-medullary
  • HRV heart rate variability
  • Stress is helpful In managing the demands at work/school, accomplishing goals/tasks, and generating fight-or-flight responses during times of danger.
  • stress is one of the primary causes leading to major chronic health disorders including diabetes, obesity, heart disease, gastrointestinal conditions, depression, and anxiety problems.
  • Salivary-based noninvasive measurements such as salivary alpha-amylase (sAA) and salivary Cortisol (sC) can be used to objectively quantify the psychosocial stress response in individuals.
  • the sensitivity and reliability of salivary measurements are limited due to a number of factors including the sample volume, type of cotton rolls/swabs, and methodological issues such as time of sampling, assay conditions, storage, and compliance to the protocol.
  • sC measurements can vary widely with body composition, age, gender, medication/nicotine use, and genetic factors. Stress can also be objectively detected using the physiological changes in blood pressure, HR, HRV, galvanic skin responses, and pupil diameter.
  • Acute stress results in a "fight or flight" response to external stimuli. This response creates a short term increase in sympathetic tone and a decrease in parasympathetic tone. Acute stress is also characterized by an increased HR, increased low frequency HRV, decreased high frequency HRV, and a decreased galvanic skin response (GSR). Chronic stress results in long-term sympathetic overactivity. Chronic stress is also characterized by an increased baseline Cortisol production, increased sympathetic activation, increased blood pressure, potentially decreased HRV, potential changes in HR, decreased physiological response to acute stress, and decreased baroreflex sensitivity.
  • HRV is related to the regulation of the heart by the autonomic nervous system.
  • HRV is measured by a variety of time domain functions including but not limited to standard deviation of R-R intervals (SDNN), root-mean-square of successive R-R intervals (RMSSD), and a proportion of successive R-R intervals differing by a predetermined time period (e.g. >50ms).
  • An R-R interval is the interval from the peak of one QRS complex to the peak of the next as shown on an electrocardiogram.
  • HRV is measured by a variety of frequency domain functions including but not limited to low frequency (LF) power from a predetermined range (e.g. 0.04 to 0.15 Hz), high frequency (HF) power from a predetermined range (e.g. 0.15 to 0.4 Hz), and a LF/HF ratio.
  • LF low frequency
  • HF high frequency
  • the person's psychological stress is measured by determining R-R intervals from an electrocardiogram (ECG) to calculate HRV features or metrics including but not limited to standard deviation of the R-R intervals (SDNN) and instantaneous heart rate (HR), wherein a stress feature (SF) is determined using the HRV metrics including SDNN and HR.
  • ECG electrocardiogram
  • HRV features or metrics including but not limited to standard deviation of the R-R intervals (SDNN) and instantaneous heart rate (HR), wherein a stress feature (SF) is determined using the HRV metrics including SDNN and HR.
  • PMF probability mass function
  • SL stress level
  • the SL determination normalizes stress measurements between a value range of 0 to 1 because individual stress features (SFs) are highly variable.
  • Wearable smart sensors can capture the physiological and behavioral data in our day-to-day lives to correlate with stress.
  • clinical-grade physiological monitors wireless sensor devices
  • a method and system in accordance with the present invention quantifies the psychological acute stress using a disposable adhesive biosensor (e.g. wireless sensor device, Health Patch®, VitalPatch) worn on the chest of the user by using a stress index (SI) metric.
  • SI stress index
  • the wireless sensor device tracks day-today patterns in HR, HRV, and SI levels which is useful in many clinical applications including but not limited to post-traumatic stress disorder, depression, and insomnia.
  • the wireless sensor device in accordance with the present invention is a clinically validated disposable medical device worn on the user's chest that remotely monitors single lead ECG, HR, HRV, breathing rate, skin temperature, step counts, posture, fall detection, and continuously monitors changes in acute psychological stress levels.
  • the method and system in accordance with the present invention utilizes a combination of heart rate (HR) and heart rate variability metrics such as the SDNN and specific posture analysis to continuously measure stress levels of an individual person. Changing postures from sitting to standing and then from standing to walking increases a person's HR and decreases the HRV.
  • HR heart rate
  • SDNN heart rate variability metrics
  • the wireless sensor device utilized by the present invention to measure psychological acute stress is a disposable adhesive patch biosensor that incorporates two surface electrodes with hydrogel at the bottom side.
  • An electronic module that consists of an embedded processor, tri-axial accelerometer, and Bluetooth Low energy (BLE) transceiver is inserted into the wireless sensor device and paired with a relay device (e.g. smartphone) for wireless data collection.
  • BLE Bluetooth Low energy
  • the wireless sensor device is adhered to the chest and collects at least ECG measurements and tri-axlal accelerations of the upper torso.
  • the raw waveforms captured by the wireless sensor device is processed by embedded firmware algorithms on the electronic module thereby generating a plurality of physiological measurements including but not limited to HR, HRV, breathing rates, activity levels, energy expenditures, and psychological stress levels (via the stress index (SI) metric).
  • SI stress index
  • the changes in psychological stress levels in individuals is detected based upon the changes in HR and HRV measurements at the constraint of no activity, and mapped to SI as a stress score (range of 0-100%).
  • FIG. 1 illustrates a wireless sensor device 100 for measuring psychological stress in accordance with an embodiment.
  • the wireless sensor device 100 includes a sensor 102, a processor 104 coupled to the sensor 102, a memory 106 coupled to the processor 104, an application 108 coupled to the memory 106, and a transmitter 110 coupled to the application 108.
  • the sensor 102 obtains physiological data from the user and transmits the data to the memory 106 and in turn to the application 108.
  • the processor 104 executes the application 108 to process the physiological data of the user. The processed data is transmitted to the transmitter 110 and in turn relayed to another user or device.
  • the senor 102 comprises two electrodes to measure physiological and cardiac activity and an accelerometer to record physical activity and posture and the processor 104 comprises a microprocessor.
  • the processor 104 comprises a microprocessor.
  • One of ordinary skill in the art readily recognizes that a variety of devices can be utilized for any of the processor 104, the memory 106, the application 108, and the transmitter 110, and that would be within the spirit and scope of the present invention.
  • FIG. 2 illustrates a method 200 for measuring psychological stress in accordance with an embodiment.
  • the method 200 comprises the wireless sensor device 100 determining R-R intervals from an electrocardiogram (ECG) to calculate a standard deviation of the R-R intervals (SDNN) and a heart rate (HR), via step 202, and determining a stress feature (SF) using the SDNN and the HR, via step 204.
  • ECG electrocardiogram
  • HR heart rate
  • SF stress feature
  • the method 200 includes performing adaptation to update a probability mass function (PMF), via step 206.
  • the method 200 includes determining a stress level (SL) using the SF and the PMF to continuously measure the psychological stress, via step 208.
  • SL stress level
  • the method 200 further includes determining a posture state, wherein the psychological stress is not measured if the posture state is active.
  • the posture state comprises a variety of states including but not limited to active (e.g. walking, running, etc.), siting, and standing.
  • a separate probability mass function (PMF) is stored for each possible posture.
  • the method 200 further includes displaying the determined SL to a user or another device.
  • determining R-R intervals from the ECG to calculate the SDNN and the HR via step 202 comprises coupling the wireless sensor device 100 via at least one electrode to measure the ECG of a user and detecting R peaks from the ECG within a predetermined time period.
  • the R-R intervals are calculated using the detected R peaks.
  • determining a stress feature (SF) using the SDNN and the HR via step 204 comprises calculating a mean heart rate (HR) from the ECG within the predetermined time period and computing the SF utilizing an algorithm that includes the HR and the SDNN.
  • the wireless sensor device 100 records other relevant physiologic parameters, for example, galvanic skin response (GSR), skin temperature (TEMP), breathing rate (BR), and a square root of the mean squared difference of successive NNs (RMSSD) is utilized to compute HRV
  • GSR galvanic skin response
  • TEMP skin temperature
  • BR breathing rate
  • RMSSD square root of the mean squared difference of successive NNs
  • performing adaptation to update the PMF via step 206 comprises grouping data into a predetermined distribution, calibrating the predetermined distribution according to a detected resting heart rate, and adjusting the predetermined distribution according to additional samples received.
  • adjusting the predetermined distribution according to additional samples received comprises multiplying all bins of the predetermined distribution by 1- ⁇ in response to data arriving and adding ⁇ to a bin corresponding to the data.
  • determining the stress level (SL) using the SF and the PMF via step 208 comprises adding all bins below a bin corresponding to the SF, and computing the SL utilizing an algorithm that includes a probability mass function for a given posture (PMFp ⁇ ture), the SF, and the added bins.
  • the method 200 further includes adding a fraction of a current bin of the SL to improve granularity.
  • the method 200 further includes tracking both a mean and a standard deviation of a probability mass function (PMF) as the PMF adapts over time and combining the mean and standard deviation to measure long-term stress.
  • PMF stress feature probability mass function
  • FIG. 3 illustrates a more detailed flow chart of a method 300 for measuring psychological stress in accordance with an embodiment.
  • the method 300 includes determining the current posture/activity of a user, via step 302. If the posture/activity is "active", the method 300 does not compute a stress level. If the posture/activity is either "stand” or “sit", the method 300 computes a stress level.
  • the method 300 detects R- peaks within a predetermined time period, via step 304, computes R-R intervals, via step 306, computes a standard deviation of R-R intervals (SDNN), via step 308, and computes a heart rate (HR), via step 310.
  • SDNN standard deviation of R-R intervals
  • HR heart rate
  • the SF is highly variable between individuals and in one embodiment, is between a predetermined range of -20 to 160". Because of this variability, a standardized stress level with a value range between 0 and 1 is computed that is relatively normalized between people. The a value is typically negative and is the weighting that allows for combining HR and SDNN and in one embodiment, a is defaulted as -0.315.
  • the binedgeposture[i] includes the edges of the bins for the stress feature and the number of bins and spacing of bin edges is set depending upon desired granularity. In one embodiment, for 180 bins from -20 to 160, bin edges are set as -20, -19, -18..., 159, 160). The bins are used for the PMF/histogram and B is the bin that the current SF falls into.
  • PMF probability mass function
  • the stress level (SL) measures the stress of an individual on a scale from 0 to 1 , where 0 indicates no or very little stress and 1 indicates extremely high stress.
  • the method 300 computes the SL per the following equation, via step 322:
  • the method 300 determines whether the computed SL is greater than a threshold (th) for more than N minutes, via step 324. If yes, an alert is presented to the user. After the SL is computed, it is displayed via the wireless sensor device 100.
  • th a threshold for more than N minutes
  • the adaptive function comprises initializing, calibrating, and adapting steps.
  • the initializing step includes beginning with a group probability mass function (PMF) that is a discretized Gaussian distribution predetermined from group training data.
  • the calibrating step includes shifting the probability distribution according to detected resting heart rates.
  • the adapting step includes adjusting the PMF as new samples arrive or as frequently/infrequently as desired. When new data arrives, all bins are multiplied by 1- ⁇ (e.g. 0.9997) and ⁇ (e.g. 0.0003) is added to a bin corresponding to the new data.
  • This adaptation adjusts the probability distribution over the course of days to weeks to fit the particular person's average distribution of stress over the course of the day.
  • FIG. 4 illustrates a more detailed flow chart of a method 400 for adaptive function calibration in accordance with an embodiment.
  • the method 400 includes initializing a stress feature probability density function (PDF) to a predetermined group model per the following equation: PDF SF ⁇ l% SFgroup , o 2 SFgr0U p), via step 402.
  • PDF stress feature probability density function
  • the notation ⁇ ( ⁇ , ⁇ 2 ) is a normal/Gaussian distribution with mean ⁇ and variance ⁇ 2 and MsFgroup and ⁇ sFgroup are predetermined from the group training data.
  • the method 400 determines a resting heart rate (HRrest) of a user during a period of low or no activity, via step 404.
  • the HRrest is estimated from the user's data and can be during no activity or sleep periods.
  • the method 400 estimates an individual heart rate (HR) PDF per the following equation: PDFHR ⁇ N(HRrest+Y*OHRindiv , o 2 HRindiv), via step 406 and estimates an individual SDNN PDF per the following equation: PDFsDNN ⁇ N(MsDNNindiv , o ⁇ sDNNindiv), via step 408.
  • the method 400 computes a new stress feature PDF by combining the determined HR and SDNN PDFs per the following equation: PDFsF ⁇ N(HRreet+Y*OHRindlv+a*pSDNNIndw i a 2 HRin ⁇ iv+a 2 *C i SDNNirKliv) I Via Step 410.
  • the continuous PDFSF is converted to a discretized probability distribution, or probability mass function (PMFSF), via step 412.
  • PMFSF probability mass function
  • the conversion is done by sampling the PDFSF within a predetermined interval and normalizing the sum to 1.
  • the OHRindiv, osDNNindiv, usDNNindiv values are predetermined and fixed and are computed from the group training data.
  • the OHRindv and osDNNindiv values are computed as the mean of the individual standard deviations in the group training data and the MsDNNindv value is computed as the mean of the mean SDNN of all individuals in the group training data.
  • PMFSF mean stress feature probability mass function/probability distribution
  • the blocks ranged from 3 to 7 minutes in length, relaxation involved various acts including but not limited to sitting quietly or listening to classical music, and stress involved various acts including but not limited to watching a movie clip from an active/horror movie, playing tetris, performing a stroop test, performing a series of mental arithmetic problems, and playing a competitive online real-time strategy game.
  • FIG. 5 illustrates a diagram 500 of stress level calculation in accordance with an embodiment.
  • the y axis represents the stress level from 0 to 1 and the x axis represents time.
  • a predetermined window of time for computing the stress level is variable depending on the necessary time resolution and the application (e.g. gaming versus daily use). Shorter windows allow changes in stress to be detected much faster but include additional noise. During periods of stress 502, such as playing a game, the stress level increases to values closer to 1.
  • the probability mass function is adapted for each person
  • the best stress feature or the best combination of HR and SDNN is learnable for each person.
  • individual learning is done via supervised learning including but not limited to Fisher Discriminants that learn the best a, which is the weighting parameter for combining HR and SDNN for each person.
  • a semi-supervised approached is utilized to learn the best feature including but not limited to self-training where an individual performs a few minutes of a relaxation activity (e.g. metronome breathing) and a few minutes of a stressful activity (e.g. playing tetris).
  • the two data points are used to determine an initial projection line defined by the a parameter and new data is classified and the most confident data points are used by the wireless sensor device 100 to continuously and automatically adjust the a parameter.
  • FIG. 6 illustrates a method 600 for determining psychological acute stress using a stress index (SI) metric in accordance with an embodiment.
  • the method 600 provides a wearable sensor (wireless sensor device) attached to a user in locations including the chest, wrist, or ear, via step 602, to detect electrocardiogram (ECG) / photoplethysmogram (PPG) signals (raw waveforms), via step 604, and to detect accelerations and activity levels, via step 606.
  • ECG electrocardiogram
  • PPG photoplethysmogram
  • the wireless sensor device detects R peaks of the ECG signal or systolic peaks of the PPG signal.
  • the wireless sensor device utilizes the detected successive peaks to calculate heart rate interval series, via step 610, by determining the time intervals (HR intervals) between successive R peaks or systolic peaks.
  • the wireless sensor device detects and rejects artifact beat values (noise) from the heart rate interval series to provide pruned beat-to-beat heart rate interval values, via step 612, and the pruned beat-to-beat heart rate interval values are used to extract a plurality of HRV features, via step 614.
  • the feature extraction process, via step 614, of the plurality of features is further described below in FIG. 7.
  • the method 600 further comprises the wireless sensor device determining whether there has been any activity by the user, via step 616.
  • the wireless sensor device detects acceleration signal and activity levels of the user using embedded sensors such as an accelerometer.
  • the wireless sensor device can utilize a predetermined threshold level for the activity level to determine whether there has been any activity.
  • the method 600 returns back to step 602 and the cardiovascular and activity metrics are detected again by the wireless sensor device via steps 604 and 606. If no (the user has not been active or very minimal activity levels that are at or below the predetermined threshold level have been detected), the method 600 continues and the wireless sensor device utilizes the feature extraction output garnered from step 614 to provide a stress calculation, via step 618.
  • the stress calculation involves the previously described steps of 312-322 of FIG. 3 where the stress feature (SF) is calculated using the linear or nonlinear combination of the plurality of HRV features, the probability mass function (PMF) is retrieved for a given posture, and the stress level (SL) is calculated using both the SF and the PMF.
  • the stress level calculation of step 618 is given on a scale between 0 and 1 or 0-100%, via step 620.
  • FIG. 7 illustrates a method 700 for feature extraction in accordance with an embodiment.
  • the method 700 provides additional details regarding the feature extraction step of 614 from FIG. 6.
  • the pruned beat-to-beat heart rate interval values (output from step 612 of FIG. 6) is represented by step 702 which is first process step in method 700.
  • the pruned heart rate interval values are used to determine a continuous basal heart rate (HRt>), via step 704.
  • the continuous basal heart rate is a low-pass filtered signal of the pruned heart rate interval values (instantaneous heart rate interval values) with a constraint of inactivity that tracks a very low frequency trend in heart rate during rest conditions.
  • the pruned heart rate interval values over a number of beats (e.g., 124 beats) or a moving time window (e.g., 2 min) are used by the wireless sensor device to calculate the average heart rate, via step 706, a statistical HRV, via step 708, a frequency-domain HRV, via step 710, and a non-linear HRV, via step 712.
  • the instantaneous heart rate values are calculated as the ratio of 60 over the pruned heart rate interval values in seconds.
  • the statistical HRV features, determined via step 708, include but are not limited to the standard deviation of HR intervals (SDNN) and the root mean square successive differences of the HR intervals (RMSSD).
  • the frequency-domain HRV features, determined via step 710 include but are not limited to the absolute or normalized spectral band powers including low-frequency band (0.04-0.15 Hz) and high frequency band (0.15-0.4 Hz) and the ratio of spectral band powers (LF/HF ratio).
  • the non-linear HRV features, determined via step 712, include but are not limited to the approximate entropy that measures complexity or regularity of the HR time interval series data and Poincare plot measures including short-term HRV (SD1 ) and long-term HRV (SD2).
  • the method 700 obtains subject information from the user, via step 714, and combines the continuous basal heart rate and the average heart rate measurements from steps 704 and 706 to determine a normalized heart rate (nHR), via step 716.
  • the subject information includes a plurality of information including but not limited to age.
  • the normalization of the heart rate allows scaling the stress level (SL) uniformly across a plurality of individuals with different backgrounds (age, gender, etc) and health (athletes, smokers, diabetics, etc). Since the HR values vary widely across individuals in normal conditions, the change in HR from their baseline due to psychological stress can result in changes in stress level restricted to a particular region (low, mid, high level on a scale of 0 to 1 or 0 to 100%). For example, the wireless sensor device may determine that individuals with a low baseline HR values have a low stress level despite detecting an increase in HR from their low baseline due to psychological stress.
  • the wireless sensor device may determine that individuals with a high baseline HR values have a high stress level even though they are not stressed out.
  • the normalized heart rate (nHR) calculated via step 716 and the plurality of HRV features (statistical via step 708, frequency-domain via step 710, non-linear via step 712) are combined to determine a stress feature value, via step 718.
  • the stress feature value is either a linear or a nonlinear model as a function of the plurality of HRV features. Accordingly, the stress feature value (SF) is calculated as a weighted sum of features similar to step 312 of FIG. 3, the stress level (SL) is calculated using the stress feature value (SF) similar to step 322 of FIG. 3, and the stress index (SI) metric is the stress level (SL) given in a percentage (%) scale.
  • FIG. 8 illustrates a diagram 800 of stress index (SI) metric calculation in accordance with an embodiment.
  • the stress index (SI) metric is the stress level given in %.
  • the wireless sensor device accurately calculates an increase in the stress index (SI) metric to approximately 100% levels during when the user conducted the stressful speech and the mental arithmetic (MA) tasks.
  • the stress index (SI) metric started at a 0% level, gradually increased as the preparation started, peaked during the stressful activities, and dropped back down to the recovery period as denoted in diagram 800.
  • a method and system for determining psychological acute stress of a user of a wireless sensor device comprises detecting a physiological signal using the wireless sensor device, determining a stress feature using a normalized heart rate and a plurality of heart rate variability (HRV) features, wherein the normalized heart rate and the plurality of HRV features are calculated using the detected physiological signal, and determining a stress level using the stress feature to determine the psychological acute stress.
  • HRV heart rate variability
  • the plurality of HRV features include statistical HRV features, frequency- domain HRV features, and non-linear HRV features.
  • the statistical HRV features include but are not limited to any of a standard deviation of HR intervals (SDNN) and a root mean square successive differences of HR intervals (RMSSD)
  • the frequency- domain HRV features include but are not limited to any of absolute or normalized spectral band powers and a ratio of spectral band powers (LF/HF ratio)
  • the nonlinear HRV features include any of an approximate entropy measuring complexity of HR time interval series data of the physiological signal and Poincare plot measures.
  • the method further comprises determining whether an activity level threshold is reached (e.g., a low activity level to ensure stress level calculations are only carried out when the user is not active) and wherein if the activity level threshold is reached, detecting another physiological signal prior to the determining of the stress feature.
  • an activity level threshold e.g., a low activity level to ensure stress level calculations are only carried out when the user is not active
  • the plurality of HRV features are calculated by performing peak detection on the physiological signal to provide a plurality of successive peaks, calculating a heart rate interval series using the plurality of successive peaks, removing artifacts from the heart rate interval series to provide beat-to-beat pruned heart rate interval values, and extracting features from the pruned beat-to-beat plurality of HRV features to provide the plurality of HRV features.
  • the physiological signal is any of an electrocardioagram (ECG) signal and a photoplethysmogram (PPG) signal.
  • ECG electrocardioagram
  • PPG photoplethysmogram
  • the extracting of the features from the pruned beat-to-beat plurality of HRV features step further comprises determining a continuous basal heart rate using the pruned beat-to- beat plurality of HRV features, determining an average heart rate using the pruned beat- to-beat plurality of HRV features, and a calculation of the continuous basal heart rate over a predetermined time period, and determining the plurality of HRV features using a calculation of the continuous basal heart rate over a predetermined time period (e.g., a number of beats such as 124 beats or a moving time window such as 2 minutes).
  • a predetermined time period e.g., a number of beats such as 124 beats or a moving time window such as 2 minutes.
  • the determining of the stress level step further comprises determining a probability mass function (PMF) for a detected posture, calculating the stress level using both the stress feature and the probability mass function, and providing the stress level as a stress index (SI) metric on a predetermined scale (e.g., 0 to 1 or 0 to 100%).
  • PMF probability mass function
  • SI stress index
  • the system comprises a wireless sensor device (e.g., Health Patch®) for determining the psychological acute stress.
  • the wireless sensor device includes a processor and a memory device coupled to the processor, wherein the memory device stores an application which, when executed by the processor, causes the wireless sensor device to carry out the aforementioned steps of the method.
  • the method and system allow for measuring psychological acute stress of a user using a wireless sensor device.
  • determining current posture detecting R-peaks from an ECG or systolic peaks from a PPG within a predetermined window of time to calculate a plurality of HRV features or metrics, combining the plurality of HRV metrics with a normalized heart rate to calculate a stress feature (SF) that is highly variable between different people, determining a current bin that the SF falls into within a predetermined bin range, determining a latest probability mass function (PMF), and summing all bins of the PMF below the current bin, a cost-effective and continuous stress level (SL) measurement system is achieved.
  • SF stress feature
  • PMF latest probability mass function
  • the predetermined window of time includes but is not limited to 120 seconds and the predetermined bin range includes but is not limited to -20 to 160 with a width of 1. If a threshold time period has passed since last adaptation, the method and system perform adaptation of the probability mass function (PMF)/probability distribution using the current SF.
  • the current stress level (SL) of the user is either displayed to the user via the wireless sensor device and/or triggers a warning alert if the SL is above a threshold (th) longer than a predetermined time period of N minutes.
  • the wireless sensor device utilizes the vital/physiological measurements of HR and HRV to determine a normalized HR and a stress feature vector and then calculates the stress index (SI) metric to provide feedback about the patient's stress levels, offer awareness about his/her state of mind, and help prevent and detect cardiac and stress related diseases.
  • SI stress index
  • Embodiments described herein can take the form of an entirely hardware implementation, an entirely software implementation, or an implementation containing both hardware and software elements.
  • Embodiments may be implemented in software, which includes, but is not limited to, application software, firmware, resident software, microcode, etc.
  • the steps described herein may be implemented using any suitable controller or processor, and software application, which may be stored on any suitable storage location or computer-readable medium.
  • the software application provides instructions that enable the processor to cause the receiver to perform the functions described herein.
  • embodiments may take the form of a computer program product accessible from a computer-usable or computer-readable storage medium providing program code or program instructions for use by or in connection with a computer or any instruction execution system.
  • a computer- usable or computer-readable storage medium can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
  • the computer-readable storage medium may be an electronic, magnetic, optical, electromagnetic, infrared, semiconductor system (or apparatus or device), or a propagation medium.
  • Examples of a computer-readable storage medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, a random access memory (RAM), a read-only memory (ROM), a rigid magnetic disk, and an optical disk.
  • Current examples of optical disks include DVD, compact disk-read-only memory (CD-ROM), and compact disk - read/write (CD-R/W).

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Veterinary Medicine (AREA)
  • General Health & Medical Sciences (AREA)
  • Cardiology (AREA)
  • Surgery (AREA)
  • Psychiatry (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Physiology (AREA)
  • Child & Adolescent Psychology (AREA)
  • Developmental Disabilities (AREA)
  • Social Psychology (AREA)
  • Psychology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Hospice & Palliative Care (AREA)
  • Signal Processing (AREA)
  • Educational Technology (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

La présente invention décrit un procédé et un système de détermination du stress psychologique aigu. Dans un premier aspect, le procédé comprend la détection d'un signal physiologique en utilisant un dispositif détecteur sans fil, la détermination d'une caractéristique de stress en utilisant une fréquence cardiaque normalisée et une pluralité de caractéristiques de variabilité de fréquence cardiaque (HRV), la fréquence cardiaque normalisée et la pluralité des caractéristiques de variabilité de fréquence cardiaque étant calculées en utilisant le signal physiologique détecté, et la détermination d'un niveau de stress en utilisant la caractéristique de stress pour déterminer le stress psychologique aigu. Dans un second aspect, le système comprend un dispositif détecteur sans fil qui comprend un processeur et un dispositif de mémorisation couplé au processeur, où le dispositif de mémorisation stocke une application qui, lorsqu'elle est exécutée par le processeur, entraîne la conduite des étapes du procédé par le dispositif détecteur sans fil.
PCT/US2017/026996 2016-04-11 2017-04-11 Mesure de stress psychologique aigu utilisant un détecteur sans fil Ceased WO2017180617A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US15/096,146 US9980678B2 (en) 2012-10-30 2016-04-11 Psychological acute stress measurement using a wireless sensor
US15/096,146 2016-04-11

Publications (1)

Publication Number Publication Date
WO2017180617A1 true WO2017180617A1 (fr) 2017-10-19

Family

ID=60042206

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2017/026996 Ceased WO2017180617A1 (fr) 2016-04-11 2017-04-11 Mesure de stress psychologique aigu utilisant un détecteur sans fil

Country Status (1)

Country Link
WO (1) WO2017180617A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112965060A (zh) * 2021-02-19 2021-06-15 加特兰微电子科技(上海)有限公司 生命特征参数的检测方法、装置和检测体征点的方法
SE2350362A1 (en) * 2023-03-29 2024-09-30 Zmartrest AB A method for monitoring the state of an individual
CN120360521A (zh) * 2025-06-26 2025-07-25 南昌航空大学 一种机上人员生理应激的预警方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009138923A1 (fr) * 2008-05-12 2009-11-19 Koninklijke Philips Electronics N.V. Procédé et appareil de mesure et de réduction du stress mental
US20110061647A1 (en) * 2003-08-18 2011-03-17 Stahmann Jeffrey E Patient Monitoring, Diagnosis, And/Or Therapy Systems and Methods
US7991458B2 (en) * 2003-12-19 2011-08-02 Aalborg Universitet System and a method for analysing ECG curvature for long QT syndrome and drug influence
US20110270049A1 (en) * 2009-10-22 2011-11-03 Corventis, Inc. Method and Apparatus for Remote Detection and Monitoring of Functional Chronotropic Incompetence
US20120136226A1 (en) * 2010-11-29 2012-05-31 Nellcor Puritan Bennett Llc Pulse Oximetry For Determining Heart Rate Variability As A Measure Of Susceptibility To Stress

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110061647A1 (en) * 2003-08-18 2011-03-17 Stahmann Jeffrey E Patient Monitoring, Diagnosis, And/Or Therapy Systems and Methods
US7991458B2 (en) * 2003-12-19 2011-08-02 Aalborg Universitet System and a method for analysing ECG curvature for long QT syndrome and drug influence
WO2009138923A1 (fr) * 2008-05-12 2009-11-19 Koninklijke Philips Electronics N.V. Procédé et appareil de mesure et de réduction du stress mental
US20110270049A1 (en) * 2009-10-22 2011-11-03 Corventis, Inc. Method and Apparatus for Remote Detection and Monitoring of Functional Chronotropic Incompetence
US20120136226A1 (en) * 2010-11-29 2012-05-31 Nellcor Puritan Bennett Llc Pulse Oximetry For Determining Heart Rate Variability As A Measure Of Susceptibility To Stress

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112965060A (zh) * 2021-02-19 2021-06-15 加特兰微电子科技(上海)有限公司 生命特征参数的检测方法、装置和检测体征点的方法
SE2350362A1 (en) * 2023-03-29 2024-09-30 Zmartrest AB A method for monitoring the state of an individual
CN120360521A (zh) * 2025-06-26 2025-07-25 南昌航空大学 一种机上人员生理应激的预警方法及系统

Similar Documents

Publication Publication Date Title
US10687757B2 (en) Psychological acute stress measurement using a wireless sensor
de Zambotti et al. Sensors capabilities, performance, and use of consumer sleep technology
Choi et al. Using heart rate monitors to detect mental stress
Radha et al. Estimating blood pressure trends and the nocturnal dip from photoplethysmography
US10383562B2 (en) Measuring psychological stress from cardiovascular and activity signals
CN106999065B (zh) 使用加速度测量术的可穿戴疼痛监测器
US10595776B1 (en) Determining energy expenditure using a wearable device
US12097049B2 (en) Methods, apparatus and systems for adaptable presentation of sensor data
US20150245777A1 (en) Detection of emotional states
CN107427267B (zh) 用于导出主体的精神状态的方法和装置
JP2018524080A (ja) 被検者の生理学的状態を監視する装置及び方法
CN109529304A (zh) 一种智能训练方法和系统
IL213004A (en) Method and mechanism for determining critical care parameters
US11075009B2 (en) System and method for sympathetic and parasympathetic activity monitoring by heartbeat
WO2022144813A1 (fr) Dispositif portable et méthode de détection du stress, de reconnaissance et de gestion des émotions
US20200359909A1 (en) Monitoring device including vital signals to identify an infection and/or candidates for autonomic neuromodulation therapy
JP2008253727A (ja) モニタ装置、モニタシステム及びモニタ方法
WO2017180617A1 (fr) Mesure de stress psychologique aigu utilisant un détecteur sans fil
Poli Measurement and processing of multimodal physiological signals in response to external stimuli by wearable devices and evaluation of parameters influencing data acquisition
Rivolta et al. Big Data and Signal Processing in mHealth
GB2512305A (en) Apparatus and method for estimating energy expenditure
KR20250160702A (ko) Ppg센서에서 측정되는 맥파정보에 기반한 혈당 관리 서비스 제공방법
KR20250160706A (ko) Ppg센서를 이용한 맥파 측정 분석에 기반한 인공지능 당화혈색소 예측방법
WO2021141572A1 (fr) Procédés et systèmes de présentation adaptables de données de capteur
Akiyama et al. A Method for Estimating Stress and Relaxed States Using a Pulse Sensor for QOL Visualization

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 17782973

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 17782973

Country of ref document: EP

Kind code of ref document: A1