Method and system for assessing mental state

• US 10,039,485 B2
• Filed: 01/11/2017
• Issued: 08/07/2018
• 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): Wu, Eugene T
• Application Number:
  US15/403,494
• Publication Number:
  US 20170119297A1
• Time in Patent Office: 573 Days
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• 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 5/4812 Detecting sleep stages or cycles
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G16H 10/65 stored on portable record carriers, e.g. on smartcards, RFID tags or CD
• CPC Class Codes: G16H 40/63 for local operation

Abstract

A computer-implemented method of assessing a mental state 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 mental state 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 mental state of the subject, and to generate an indication of mental state based upon the metric. The indication of mental state is provided (310) as output.

Claims

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

a) receiving, as input, a heartbeat record of the subject, which comprises a sequence of heartbeat data samples obtained over a time span which includes a pre-sleep period, a sleep period having a sleep onset time and a sleep conclusion time, and a post-sleep period;

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

c) computing metrics of the subject from the heartbeat record, the metrics including;

i) a mean awake heart rate calculated as an average heart rate during the pre-sleep and post-sleep periods;

ii) a ratio of a mean awake heart rate and a mean asleep heart rate;

iii) a first slope metric indicative of a change over time of the subject'"'"'s heart rate during a first half of the sleep period; and

,

iv) a second slope metric indicative of a change over time of the subject'"'"'s heart rate during a second half of the sleep period;

d) accessing a knowledge base which comprises data obtained via expert evaluation of a training set of subjects and which embodies a computational model of a relationship between mental state and said metrics, the computational model comprising data structures representing classification trees obtained by applying a decision tree learning algorithm over said metrics computed by processing heartbeat records of a training set of subjects and the classification trees including;

i) a first classification tree data structure that classifies metrics computed from the heartbeat record of the subject into ‘

normal’

or ‘

not normal’

; and

ii) a second classification tree data structure that classifies the metrics computed from the heartbeat record of the subject into ‘

depressed’ and

‘

not depressed;

e) applying the metrics of the subject to the computational model to generate an indication of mental state by;

i) classifying the subject as ‘

normal’

or ‘

not normal’

by executing the first classification tree; and

ii) in the event that the subject is classified as ‘

not normal’

, classifying the subject as ‘

depressed’

or ‘

not depressed’

by executing the second classification tree; and

f) providing, as output, the indication of mental state.

2. The method of claim 1 wherein the method comprises:

l) partitioning the training set of subjects as ‘

normal’ and

‘

not normal’

;

m) generating the first classification tree data structure using the ‘

normal’ and

‘

not normal’

partitioning;

n) partitioning the training set of subjects as ‘

depressed’ and

‘

not depressed’

; and

,

o) generating the second classification tree data structure using the ‘

depressed’ and

‘

not depressed’

partitioning.

3. The method of claim 1 wherein the method comprises automatically identifying the sleep period using a record of activity of the subject measured using an activity monitor.

4. The method of claim 1 wherein the method comprises automatically identifying the sleep period by processing the heartbeat record.

5. The method of claim 1 wherein the method comprises storing results of assessment of the mental state of the subject within secure storage of a server and making the results accessible to a clinician via a secure access interface.

6. The method of claim 1 wherein the method comprises repeating the assessment while treatment is ongoing to provide a continuing objective measurement of the effectiveness of treatment.

7. The method of claim 1 wherein the method comprises adjusting a treatment, and repeating the assessment to assess the effectiveness of the adjustment in treatment.

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

g) at least one microprocessor;

h) at least one non-volatile storage device containing a knowledge base which comprises data obtained via expert evaluation of a training set of subjects and which embodies a computational model of a relationship between mental state and metrics computed from a heartbeat record, the computational model comprising data structures representing classification trees obtained by applying a decision tree learning algorithm over said metrics computed by processing heartbeat records of a training set of subjects and the classification trees including;

i) a first classification tree data structure that classifies metrics computed from the heartbeat record of the subject into ‘

normal’

or ‘

not normal’

; and

ii) a second classification tree data structure that classifies the metrics computed from the heartbeat record of the subject into ‘

depressed’ and

‘

not depressed;

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

j) an input/output interface operatively associated with the microprocessor,

k) 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;

i) receiving, via the input/output interface, a heartbeat record of the subject, which comprises a sequence of heartbeat data samples obtained 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;

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

iii) computing metrics of the subject from the heartbeat record, the metrics including;

(1) a mean awake heart rate calculated as an average heart rate during the pre-sleep and post-sleep periods;

(2) a ratio of a mean awake heart rate and a mean asleep heart rate;

(3) a first slope metric indicative of a change over time of the subject'"'"'s heart rate during a first half of the sleep period;

(4) a second slope metric indicative of a change over time of the subject'"'"'s heart rate during a second half of the sleep period;

iv) applying the metrics of the subject to the computational model to generate an indication of mental state by;

(1) classifying the subject as ‘

normal’

or ‘

not normal’

by executing the first classification tree; and

(2) in the event that the subject is classified as ‘

not normal’

, classifying the subject as ‘

depressed’

or ‘

not depressed’

by executing the second classification tree; and

v) providing, via the input/output interface, the indication of the mental state of the subject.

9. The system of claim 8 wherein the system further comprises a heart rate monitor device configured to be worn by the subject during the timespan including the pre-sleep period, the sleep period and the post-sleep period.

10. The system of claim 9 wherein the heartbeat monitor comprises a communications interface configured for communication with a network-connected device.

11. The system of claim 10 wherein the input/output interface comprises a network interface providing access to a wide area network, and the heartbeat record is received via the wide area network from the network-connected device of the subject.

12. The system of claim 8 wherein the microprocessor:

p) partitioning the training set of subjects as ‘

normal’ and

‘

not normal’

;

q) generating the first classification tree data structure using the ‘

normal’ and

‘

not normal’

partitioning;

r) partitioning the training set of subjects as ‘

depressed’ and

‘

not depressed’

; and

,

s) generating the second classification tree data structure using the ‘

depressed’ and

‘

not depressed’

partitioning.

13. The system of claim 8 wherein the microprocessor automatically identifies the sleep period using a record of activity of the subject measured using an activity monitor.

14. The system of claim 8 wherein the microprocessor automatically identifies the sleep period by processing the heartbeat record.

15. The system of claim 8 wherein the system includes a server having a secure store and wherein the system stores results of the assessment of the mental state of the subject within the secure storage of the server and makes the results accessible to a clinician via a secure access interface.

16. The system of claim 8 wherein the microprocessor repeats the assessment while treatment is ongoing to provide a continuing objective measurement of the effectiveness of treatment.