Alertness prediction system and method

• US 10,238,335 B2
• Filed: 02/17/2017
• Issued: 03/26/2019
• Est. Priority Date: 02/18/2016
• Status: Expired due to Fees

• Current Assignee: Curgroup Incorporated
• Original Assignee: CurAegis Technologies, Inc.
• Inventors: Kenyon, Matt, Payne-Rogers, Colin, Jones, Josh
• Primary Examiner(s): Ghulamali, Qutbuddin
• Application Number:
  US15/436,039
• Publication Number:
  US 20170238868A1
• Time in Patent Office: 767 Days
• Field of Search: 34053912
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/01 Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue clinical contact thermometers G01K13/20
• 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 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• 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 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/4809 Sleep detection, i.e. determining whether a subject is asleep or not
• CPC Class Codes: A61B 5/4857 Indicating the phase of biorhythm clocks or watches with indicators for biological cycles G04B19/264
• 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: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G16H 20/00 ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/50 : for simulation or modelling of medical disorders

Abstract

An alertness prediction bio-mathematical model for use in devices such as a wearable device that improves upon previous models of predicting fatigue and alertness by gathering data from the individual being monitored to create a more accurate estimation of alertness levels. The bio-mathematical model may be a two-process algorithm which incorporates a sleep-wake homeostasis aspect and a circadian rhythm aspect. The sleep-wake homeostasis aspect of the model is improved by using actigraphy measures in conjunction with distal skin, ambient light and heart rate measures to improve the accuracy of the sleep and wake estimations. The circadian rhythm model aspect improves fatigue prediction and estimation by using distal skin, heart rate and actigraphy data. The sleep-wake homeostasis and circadian rhythm aspects may also be combined with additional objective and subjective measures as well as information from a user to improve the accuracy of the alertness estimation even further.

Claims

1. A wearable device for monitoring and predicting alertness of an individual, the wearable device comprising:

one or more sensors configured to obtain information signals about the individual, the sensors comprising at least one of;

a motion sensor configured to produce movement data and/or body position data of the individual,

a temperature sensor configured to produce distal skin temperature data of the individual, and

a heart rate monitor configured to produce heart rate data of the individual;

a memory configured to store;

a default circadian rhythm configured to be refined with data derived from the information signals about the individual to generate an estimated circadian rhythm for the individual, and

a bio-mathematical model configured to generate a fatigue score for the individual;

a processor coupled to the one or more sensors and to the memory, configured to;

receive the information signals about the individual including at least one of movement data, position data, distal skin temperature data, or heart rate data,

estimate a circadian rhythm of the individual by incorporating the information signals about the individual to refine the default circadian rhythm,

extract features from the information signals about the individual and the estimated circadian rhythm,

apply at least one pattern recognition algorithm or machine learning algorithm to the extracted features,

extract at least one coefficient from the extracted features using the at least one pattern recognition algorithm or machine learning algorithm,

apply a bio-mathematical model to the at least one extracted coefficient, and

generate the fatigue score for the individual from the at least one extracted coefficient using the bio-mathematical model; and

a support configured to support the one or more sensors, the memory, and the processor on the individual.

2. The wearable device of claim 1, wherein the bio-mathematical model is a two-process algorithm configured to predict alertness levels of the individual using assessments of sleep-wake homeostasis and the estimated circadian rhythm;

and wherein the processor is further configured to;

make actigraphy determinations using the movement data and/or body position data,

assess, using the two-process algorithm, the sleep-wake homeostasis of the individual, including periods of sleep and wakefulness, based on the actigraphy determinations, and

combine the sleep-wake homeostasis assessments with the estimated circadian rhythm according to the two-process algorithm into the generation of the fatigue score for the individual.

3. The wearable device of claim 2, wherein the processor is further configured to:

refine the actigraphy determinations using at least one of the distal skin temperature data or the heart rate data, and

assess the sleep-wake homeostasis of the individual further based on the refined actigraphy determinations.

4. The wearable device of claim 1, wherein the at least one coefficient includes at least one of a circadian rhythm coefficient (Φ

), a wake/sleep coefficient (τ

), a circadian rhythm weighting coefficient, or a wake/sleep weighting coefficient.

5. The wearable device of claim 1, wherein the processor is further configured to:

process the information signals about the individual by using signal processing techniques;

incorporate the processed information signals into the estimation of the circadian rhythm of the individual; and

incorporate the processed information signals into the extraction of the features.

6. The wearable device of claim 1, wherein the processor is further configured to:

obtain information signals about the movement and/or position of the individual;

determine actigraphy data for the individual using the information signals about the movement of the individual;

apply the bio-mathematical model to the actigraphy data, wherein the bio-mathematical model is chosen from one of an awake bio-mathematical sub-model and an asleep bio-mathematical sub-model; and

incorporate the actigraphy data into the generation of the fatigue score for the individual.

7. The wearable device of claim 6, wherein the processor is further configured to refine the actigraphy data using at least one of the information signals about the distal skin temperature of the individual or the heart rate of the individual.

8. The wearable device of claim 1, wherein the extracted features include one or more of:

markers indicating a shape of a circadian rhythm of the individual, information regarding sleep habits of the individual on both working days and free days, and general medical information about the individual.

9. The wearable device of claim 1, wherein the processor is further configured to incorporate individual parameters about the individual into the extraction of the features when the individual parameters are entered into the wearable device.

10. The wearable device of claim 1, wherein the processor is further configured to:

identify raw circadian data within the information signals about the individual;

identify non-circadian data caused by non-circadian events within the raw circadian data;

remove the non-circadian data from the raw circadian data to obtain refined circadian data; and

incorporate the refined circadian data into the estimation of the circadian rhythm of the individual.

11. The wearable device of claim 1, wherein the sensors of the wearable device are configured to collect environmental information signals about the individual'"'"'s environment, including at least one of ambient light level data or ambient temperature data, and wherein processor is further configured to incorporate the environmental information signals into the estimation of the circadian rhythm.

12. The wearable device of claim 11, wherein:

the sensors of the device further comprise an ambient light sensor configured to produce ambient light data from ambient light surrounding the individual,

the processor is coupled to the ambient light sensor,

and wherein the processor is further configured to refine the circadian rhythm estimation with the bio-mathematical model by incorporating the ambient light data.

13. The wearable device of claim 11, wherein the temperature sensor is further configured to produce ambient temperature data from the ambient temperature surrounding the individual, and wherein the processor is further configured to refine the circadian rhythm estimation with the bio-mathematical model by incorporating the ambient temperature data.

14. A method for producing a fatigue score for an individual, the method comprising:

obtaining, with sensors of a wearable device, information signals about the individual including at least one of movement, position, distal skin temperature, or heart rate;

estimating, with a processor of the wearable device, a circadian rhythm of the individual from the information signals about the individual;

extracting, with the processor, features from the information signals about the individual and the estimated circadian rhythm;

applying, with the processor, at least one pattern recognition algorithm or machine learning algorithm to the extracted features;

extracting, with the processor and using the at least one pattern recognition algorithm or machine learning algorithm, at least one coefficient from the extracted features;

applying, with the processor, a bio-mathematical model to the extracted coefficients; and

generating, with the processor and using the bio-mathematical model, a fatigue score for the individual from the extracted coefficients.

15. The method of claim 14, wherein the method further comprises:

processing, with the processor, the information signals about the individual, by using signal processing techniques;

incorporating, with the processor, the processed information signals into the estimation of the circadian rhythm of the individual; and

incorporating, with the processor, the processed information signals into the extraction of the features.

16. The method of claim 14, wherein the sensors of the wearable device are configured to:

collect environmental information signals about the individual'"'"'s environment, including at least one of ambient light levels or temperature; and

incorporate, with the processor, the environmental information signals into the estimation of the circadian rhythm of the individual.

17. The method of claim 14, wherein the method further comprises:

identifying, with the processor, raw circadian data within the information signals about the individual;

identifying, with the processor, non-circadian data caused by non-circadian events, within the raw circadian data;

removing, with the processor, the non-circadian data from the raw circadian data to obtain refined circadian data; and

incorporating, with the processor, the refined circadian data into the estimation of the circadian rhythm of the individual.

18. The method of claim 14, wherein the method further comprises entering, into the wearable device, individual parameters about the individual;

and

incorporating, with the processor, the individual parameters into the extraction of the features.

19. The method of claim 14, wherein the at least one coefficient includes at least one of a circadian rhythm coefficient, a wake/sleep coefficient, a circadian rhythm weighting coefficient, or a wake/sleep weighting coefficient.

20. The method of claim 14, wherein the method further comprises:

obtaining, with a motion sensor of the wearable device, information signals about the movement and/or position of the individual;

determining, with the processor, actigraphy data for the individual using the information signals about the movement of the individual;

applying, with the processor, the bio-mathematical model to the actigraphy data, wherein the bio-mathematical model is chosen from one of an awake bio-mathematical sub-model and an asleep bio-mathematical sub-model; and

incorporating, with the processor, the actigraphy data into the generation of the fatigue score for the individual.

21. The method of claim 20, wherein the method further comprises:

refining, with the processor, the actigraphy data using at least one of the information signals about the distal skin temperature of the individual or the heart rate of the individual.

22. The method of claim 20, wherein the method further comprises:

determining, with the processor and using the actigraphy data, whether the individual is awake or asleep.

23. The method of claim 22, wherein the method further comprises:

selecting, with the processor, the awake bio-mathematical sub-model when the processor determines the individual is awake.

24. The method of claim 22, wherein the method further comprises:

selecting, with the processor, the asleep bio-mathematical sub-model when the processor determines the individual is asleep.

25. The method of claim 14, wherein the extracted features include one or more of:

markers indicating a shape of a circadian rhythm of the individual, information regarding sleep habits of the individual on both working days and free days, and general medical information about the individual.