Method and system for monitoring stress conditions

• US 10,638,965 B2
• Filed: 06/15/2016
• Issued: 05/05/2020
• Est. Priority Date: 06/15/2015
• Status: Active Grant

• Current Assignee: Medibio Ltd.
• Original Assignee: Medibio Ltd.
• Inventors: Flax, Matthew, Wong, Aaron, Player, Michael, Jolly, Todd, Stampfer, Hans
• Primary Examiner(s): Holmes, Rex R
• Application Number:
  US15/736,445
• Publication Number:
  US 20180184960A1
• Time in Patent Office: 1,420 Days
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/4809 Sleep detection, i.e. determining whether a subject is asleep or not
• CPC Class Codes: A61B 5/4815 Sleep quality
• CPC Class Codes: A61B 5/6823 Trunk, e.g., chest, back, abdomen, hip
• CPC Class Codes: A61B 5/6831 Straps, bands or harnesses
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7278 Artificial waveform generation or derivation, e.g. synthesising signals from measured signals A61B5/327 takes precedence
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G16H 10/65 stored on portable record carriers, e.g. on smartcards, RFID tags or CD
• CPC Class Codes: G16H 20/70 relating to mental therapies, e.g. psychological therapy or autogenous training
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 70/60 : relating to pathologies
• CPC Class Codes: H04B 1/3827 : Portable transceivers
• CPC Class Codes: H04M 1/72403 : with means for local support of applications that increase the functionality
• CPC Class Codes: H04M 1/72412 : using two-way short-range wireless interfaces
• CPC Class Codes: H04M 2250/12 : including a sensor for measuring a physical value, e.g. temperature or motion telephones including GPS signal receivers H04M2250/10

Abstract

A computer-implemented method of assessing a stress condition of a subject (106) includes receiving (302), as input, a heartbeat record (200) of the subject. The heartbeat record comprises a sequence of heartbeat data samples obtained over a time span which includes a pre-sleep period (208), a sleep period (209) having a sleep onset time (224) and a sleep conclusion time (226), and a post-sleep period (210). At least the sleep onset time and the sleep conclusion time are identified (304) within the heartbeat record. A knowledge base (124) is then accessed (306), which comprises data obtained via expert evaluation of a training set of subjects and which embodies a computational model of a relationship between stress condition and heart rate characteristics. Using information in the knowledge base, the computational model is applied (308) to compute at least one metric associated with the stress condition of the subject, and to generate an indication of stress condition based upon the metric. The indication of stress condition is provided (310) as output.

Claims

1. A computer-implemented method of assessing a mental state of a subject, the method comprising:

receiving a heartbeat record indicative of a heart rate of the subject over a time span including a pre-sleep period, a sleep period having a sleep onset time and a sleep conclusion time, and a post-sleep period;

identifying, within the heartbeat record, at least the sleep onset time and the sleep conclusion time;

analysing the heartbeat record using the identified sleep onset time and the sleep conclusion time to determine at least one heart rate metric;

applying the at least one heart rate metric to a computational model of a relationship between mental state and heart rate characteristics to generate an indication of mental state based upon the at least one heart rate metric, the computation model being obtained by applying machine learning to at least one heart rate metric derived from heart rates measured for subjects in a training set who have been assessed by an expert assessor; and

providing, as output, the indication of mental state;

wherein the computational model forms part of a knowledge base including an array of (M+1) dimensional vectors, where M is the number of the plurality of heart rate metrics employed, in which each vector corresponds with a subject in the training set, and comprises values for each of the at least one heart rate metric, and a value of the corresponding expert assessment of the subject.

2. The method of claim 1 wherein the indication of mental state comprises an indication of stress levels experienced by the subject.

3. The method of claim 2 wherein the indication of mental state distinguishes between three levels of stress.

4. The method of claim 2 wherein the computational model forms part of a knowledge base, the knowledge base including a template heart rate characteristic.

5. The method of claim 4 wherein the template characteristic heart rate is obtained by averaging scaled and normalised heart rate characteristics of the subjects in the training set who have been assessed by an expert assessor as experiencing normal or low levels of stress.

6. The method of claim 5 wherein the knowledge base further comprises a normal centroid value, comprising a measure of an average distance of the heartbeat characteristics of subjects in the training set assessed as normal from the template characteristic.

7. The method of claim 6 wherein the knowledge base further comprises a set of segmentation points, representing variations in distance from the template characteristic, relative to the normal centroid and, defining classification boundaries between different indications of mental state.

8. The method of claim 1 wherein the at least one heart rate metric comprises:

a mean-awake heart rate;

a ratio between mean-awake and -asleep heart rates;

a slope of heart rate during the first half of the sleep period; and

a slope of heart rate in the second half of the sleep period.

9. The method of claim 8 wherein the computational model forms part of a knowledge base including an array of values of the heart rate metrics corresponding with a template characteristic based upon subjects assessed by an expert as having normal or low stress levels.

10. The method of claim 9 wherein the knowledge base further comprises an array of normal centroid values, corresponding with each one of the plurality of heart rate metrics, and computed by averaging the magnitudes of the differences between the respective heart rate metrics for all subjects assessed by the expert as having normal or low stress levels, and the equivalent template characteristic heart rate metrics.

11. The method of claim 10 further comprising performing a comparison between the at least one heart rate metric for the received heartbeat record of the subject, and the corresponding normal centroid values, to compute a measure of distance of the subject'"'"'s mental state from a ‘

normal’

mental state, and wherein the knowledge base further comprises an array of segmentation values defining distance measures corresponding with boundaries between mental state classifications.

12. The method of claim 1 wherein the indication of mental state is generated using a k nearest neighbour (k-NN) computational model.

13. The method of claim 12 wherein the knowledge base further comprises an optimised value of the number of nearest-neighbours parameter K.

14. The method of claim 12 wherein the indication of mental state of the subject is generated as the most-frequently occurring mental state associated with the identified K nearest neighbours from the training set.

15. A computer-implemented system for assessing a mental state of a subject, the system comprising:

at least one microprocessor;

at least one non-volatile storage device containing a computational model of a relationship between mental state and heart rate characteristics, the computation model being obtained by applying machine learning to at least one heart rate metric derived from heart rates measured for subjects in a training set who have been assessed by an expert assessor;

at least one computer-readable memory device operatively associated with the microprocessor; and

wherein the memory device contains computer-executable instruction code which, when executed via the microprocessor, causes the microprocessor to effect a method comprising steps of;

receiving a heartbeat record indicative of a heart rate over a timespan which includes a pre-sleep period, a sleep period having a sleep onset time and a sleep conclusion time, and a post-sleep period;

identifying, within the heartbeat record, at least the sleep onset time and the sleep conclusion time;

analysing the heartbeat record using the identified sleep onset time and the sleep conclusion time to determine at least one heart rate metric;

applying the at least one heart rate metric to the computational model to generate an indication of mental state based upon the at least one heart rate metric; and

providing, via the input/output interface, the indication of the mental state of the subject;

wherein the computational model forms part of a knowledge base including an array of (M+1) dimensional vectors, where M is the number of the plurality of heart rate metrics employed, in which each vector corresponds with a subject in the training set, and comprises values for each of the at least one heart rate metric, and a value of the corresponding expert assessment of the subject.

16. The system of claim 15 wherein the heartbeat record of the subject is obtained via a heart rate monitor device worn by the subject during the timespan including the pre-sleep period, the sleep period and the post-sleep period.

17. The system of claim 16 wherein the heartbeat monitor comprises a communications interface configured for communication with a network-connected device of the subject.

18. The system of claim 17 wherein the heartbeat record is received via an input/output interface comprising a network interface providing access to a wide area network, and the next record is received via the wide area network from the network-connected device of the subject.