US-12620492-B2 - Acute stressors detection for recognizing maladaptation in physiological conditions

Abstract

A method of acute stressors detection includes obtaining, by a processor, heart rate variability (HRV) data determined based on an HRV-related metric associated with an individual; determining, based on the HRV data, whether an HRV event indicative of a maladaptation risk of the individual has occurred; and responsive to determining that the HRV event indicative of the maladaptation risk of the individual has occurred, using a causal inference engine to determine at least one acute stressor as a probable cause of the HRV event based on inputs comprising the HRV event and lifestyle data associated with the individual, wherein the lifestyle data comprises at least one lifestyle event and environmental contexts associated with the at least one lifestyle event performed by the individual.

Inventors

• Hyungik Oh
• Mengfan Tang
• Kongqiao Wang

Assignees

• ZEPP, INC.
• Anhui Huami Health Technology Co., Ltd.

Dates

Publication Date

20260505

Application Date

20221128

Claims (20)

1. 1 . A method of acute stressors detection using a wearable device, comprising: obtaining, by a processor associated with the wearable device, heart rate data collected by an inward facing heart rate sensor of the wearable device facing toward or in contact with an individual's skin when the wearable device is worn by the individual; determining, by the processor, heart rate variability (HRV) data based on an HRV-related metric associated with the individual, wherein the HRV-related metric is derived from the heart rate data; determining, based on the HRV data, whether an HRV event indicative of a maladaptation risk of the individual has occurred, wherein the HRV event indicative of the maladaptation risk is determined according to at least two different parameters from the HRV data, a first one of the at least two different parameters is derived from the HRV-related metric over time; and responsive to determining that the HRV event indicative of the maladaptation risk of the individual has occurred, determining, by the processor, at least one acute stressor as a probable cause of the HRV event using causal inference techniques based on the HRV event, at least one lifestyle event performed by the individual, and environmental contexts associated with the at least one lifestyle event, wherein the at least one acute stressor is determined by comparing statistical dependencies between the HRV event and each of the at least one lifestyle event, wherein the at least one lifestyle event and the environmental contexts are extracted from sensor data collected by the wearable device, and the sensor data comprises the heart rate data and at least one other type of sensor data collected by the wearable device, wherein the HRV data further comprises an HRV baseline and a smallest worthwhile change (SWC), the HRV baseline is indicative of a moving average of the HRV data during a first number of days, and the HRV baseline is determined based on: a time window T per day, the first number of days, and the HRV-related metric, and the SWC is indicative of a value range for the HRV-related metrics during a second number of days, wherein the SWC is determined based on: a standard deviation of the HRV-related metric during the second number of days, the second number of days, and the HRV-related metric, wherein the second number of days is more than the first number of days.
2. 2 . The method of claim 1 , wherein the at least one acute stressor is determined using a causal inference engine, and using the causal inference engine comprises using a directed acyclic graph (DAG) to determine statistical dependencies between a first node representing a causally related lifestyle event and a second node representing the HRV event, wherein an edge is established from the first node to the second node upon determining that the causally related lifestyle event associated with the first node is likely to have caused the HRV event associated with the second node, wherein a weight of the edge indicates a conditional probability for the HRV event occurring based on occurrence of the causally related lifestyle event.
3. 3 . The method of claim 2 , wherein the at least one acute stressor as the probable cause of the HRV event is selected from a plurality of causally related lifestyle events, wherein each of the plurality of causally related lifestyle events is associated with a respective edge to the HRV event on the DAG.
4. 4 . The method of claim 1 , wherein the HRV-related metric comprises a root mean square of successive time differences (RMSSD) of consecutive heartbeats in a logarithm form.
5. 5 . The method of claim 1 , wherein the HRV data further comprises a daily HRV score, and the HRV event indicative of the maladaptation risk of the individual is determined to have occurred when the daily HRV score is outside of the value range of the SWC, and the HRV baseline is decreasing.
6. 6 . The method of claim 1 , wherein the lifestyle events comprise at least one of exercise events or sleep events for the individual.
7. 7 . The method of claim 1 , wherein the maladaptation risk is associated with a state of the individual indicative of at least one of: inability to respond to the at least one acute stressor, poor adaptation to work, or non-functional overreaching.
8. 8 . The method of claim 1 , wherein the HRV data further comprises a coefficient of variation (CV), the CV is indicative of a value for assessing adaptation over time to a fitness program or a lifestyle change by the individual, the CV is determined based on: a standard deviation of the HRV-related metric during a third number of days, the third number of days, and the HRV-related metric, wherein the HRV event indicative of the maladaptation risk of the individual is determined to have occurred when the baseline HRV is decreasing and the CV is increasing.
9. 9 . The method of claim 1 , wherein the environmental contexts associated with the at least one lifestyle event comprise at least one of: information extracted from workout data derived from the sensor data of the device, or at least one of exercise type, duration, timestamp, or space associated with the at least one lifestyle event.
10. 10 . The method of claim 1 , wherein the at least one acute stressor is associated with at least one lifestyle event of the individual as follows: lower than normal sleep duration, higher than normal workout, decreasing sleep duration, or higher than normal training load.
11. 11 . An apparatus for acute stressors detection, comprising: a non-transitory memory; a heart rate sensor comprising an inward facing heart rate sensor facing toward or in contact with an individual's skin when the apparatus is worn by the individual; and a processor, wherein the non-transitory memory includes instructions executable by the processor to: obtain heart rate data collected by the heart rate sensor when the apparatus is worn by the individual; determine heart rate variability (HRV) data based on an HRV-related metric associated with the individual, wherein the HRV-related metric is derived from the heart rate data; determine, based on the HRV data, whether an HRV event indicative of a maladaptation risk of the individual has occurred, wherein the HRV event indicative of the maladaptation risk is determined according to at least two different parameters from the HRV data, a first one of the at least two different parameters is derived from the HRV-related metric over time; and responsive to determining that the HRV event indicative of the maladaptation risk of the individual has occurred, determine at least one acute stressor as a probable cause of the HRV event using causal inference techniques based on the HRV event, at least one lifestyle event performed by the individual, and environmental contexts associated with the at least one lifestyle event, wherein the at least one acute stressor is determined by comparing statistical dependencies between the HRV event and each of the at least one lifestyle event, wherein the at least one lifestyle event and the environmental contexts are extracted from sensor data collected by the apparatus, and the sensor data comprises the heart rate data and at least one other type of sensor data collected by the apparatus, wherein the HRV data further comprises an HRV baseline and a smallest worthwhile change (SWC), the HRV baseline is indicative of a moving average of the HRV data during a first number of days, and the HRV baseline is determined based on: a time window T per day, the first number of days, and the HRV-related metric, and the SWC is indicative of a value range for the HRV-related metrics during a second number of days, wherein the SWC is determined based on: a standard deviation of the HRV-related metric during the second number of days, the second number of days, and the HRV-related metric, wherein the second number of days is more than the first number of days.
12. 12 . The apparatus of claim 11 , wherein the at least one acute stressor is determined using a causal inference engine, and using the causal inference engine comprises using a directed acyclic graph (DAG) to determine statistical dependencies between a first node representing a causally related lifestyle event and a second node representing the HRV event, wherein an edge is established between the first node and the second node upon determining that the causally related lifestyle event associated with the first node is likely to have caused the HRV event associated with the second node, wherein a weight of the edge indicates a conditional probability for the HRV event occurring based on occurrence of the causally related lifestyle event.
13. 13 . The apparatus of claim 12 , wherein the at least one acute stressor as the probable cause of the HRV event is selected from a plurality of causally related lifestyle events, wherein each of the plurality of causally related lifestyle events is associated with a respective edge to the HRV event on the DAG.
14. 14 . The apparatus of claim 11 , wherein the HRV-related metric comprises a root mean square of successive time differences (RMSSD) of consecutive heartbeats in a logarithm form.
15. 15 . The apparatus of claim 11 , wherein the HRV data further comprises a daily HRV score, and the HRV event indicative of the maladaptation risk of the individual is determined to have occurred when the daily HRV score is outside of the value range of the SWC, and the HRV baseline is decreasing.
16. 16 . The apparatus of claim 11 , wherein the lifestyle events comprise at least one of exercise events or sleep events for the individual, and the environmental contexts associated with the at least one lifestyle event comprise at least one of: information extracted from workout data derived from the sensor data of the apparatus, or at least one of exercise type, duration, timestamp, or space associated with the at least one lifestyle event.
17. 17 . The apparatus of claim 11 , wherein the maladaptation risk is associated with a state of the individual indicative of at least one of: inability to respond to the at least one acute stressor, poor adaptation to work, or non-functional overreaching, and the at least one acute stressor is associated with at least one lifestyle event of the individual as follows: lower than normal sleep duration, higher than normal workout, decreasing sleep duration, or higher than normal training load.
18. 18 . The apparatus of claim 11 , wherein the HRV data further comprises a coefficient of variation (CV), the CV is indicative of a value for assessing adaptation over time to a fitness program or a lifestyle change by the individual, the CV is determined based on: a standard deviation of the HRV-related metric during a third number of days, the third number of days, and the HRV-related metric, wherein the HRV event indicative of the maladaptation risk of the individual is determined to have occurred when the baseline HRV is decreasing and the CV is increasing.
19. 19 . A non-transitory computer-readable storage medium configured to store computer programs for acute stressors detection, the computer programs comprising instructions executable by a processor to perform the method of claim 1 .
20. 20 . The non-transitory computer-readable storage medium of claim 19 , wherein the at least one acute stressor is determined using a causal inference engine, and using the causal inference engine comprises using a directed acyclic graph (DAG) to determine statistical dependencies between a first node representing a causally related lifestyle event and a second node representing the HRV event, wherein an edge is established from the first node to the second node upon determining that the causally related lifestyle event associated with the first node is likely to have caused the HRV event associated with the second node, wherein a weight of the edge indicates a conditional probability for the HRV event occurring based on occurrence of the causally related lifestyle event.

Description

FIELD The present disclosure relates generally to physical health care monitoring, and more specifically, to acute stressors detection. BACKGROUND With modern technologies, we have the ability to sense and compute upon health-related data ubiquitously and continuously, and apply this information towards improved health. A serious challenge remains in transforming this collected data to real-world improvements in individual health. Furthermore, delivering better health quality to people without excessive cost is also key to allow societal resources to go towards progress in other domains. SUMMARY Disclosed herein are implementations of methods, apparatuses, and systems for acute stressors detection. In one aspect, a method of acute stressors detection is disclosed. The method includes obtaining, by a processor, heart rate variability (HRV) data determined based on an HRV-related metric associated with an individual; determining, based on the HRV data, whether an HRV event indicative of a maladaptation risk of the individual has occurred; and responsive to determining that the HRV event indicative of the maladaptation risk of the individual has occurred, using a causal inference engine to determine at least one acute stressor as a probable cause of the HRV event based on inputs comprising the HRV event and lifestyle data associated with the individual, wherein the lifestyle data comprises at least one lifestyle event and environmental contexts associated with the at least one lifestyle event performed by the individual. In another aspect, an apparatus for acute stressors detection is disclosed. The apparatus includes a non-transitory memory; and a processor, wherein the non-transitory memory includes instructions executable by the processor to: obtain, by a processor, heart rate variability (HRV) data determined based on an HRV-related metric associated with an individual, the HRV data comprising an HRV baseline; determine, based on the HRV data, whether an HRV event indicative of a maladaptation risk of the individual has occurred; and responsive to determining that the HRV event indicative of the maladaptation risk of the individual has occurred, use a causal inference engine to determine at least one acute stressor as a probable cause of the HRV event based on inputs comprising the HRV event and lifestyle data associated with the individual, wherein the lifestyle data comprises at least one lifestyle event and environmental contexts associated with the at least one lifestyle event performed by the individual. In another aspect, a non-transitory computer-readable storage medium configured to store computer programs for acute stressors detection is disclosed. The computer programs include instructions executable by a processor to: obtain, by a processor, heart rate variability (HRV) data determined based on an HRV-related metric associated with an individual; determine, based on the HRV data, whether an HRV event indicative of a maladaptation risk of the individual has occurred; and responsive to determining that the HRV event indicative of the maladaptation risk of the individual has occurred, use a causal inference engine to determine at least one acute stressor as a probable cause of the HRV event based on inputs comprising the HRV event and lifestyle data associated with the individual, wherein the lifestyle data comprises at least one lifestyle event and environmental contexts associated with the at least one lifestyle event performed by the individual. BRIEF DESCRIPTION OF THE DRAWINGS The disclosure is best understood from the following detailed description when read in conjunction with the accompanying drawings. It is emphasized that, according to common practice, the various features of the drawings are not to-scale. On the contrary, the dimensions of the various features are arbitrarily expanded or reduced for clarity. FIG. 1 depicts a perspective view of an example wearable device according to some implementations of this disclosure. FIG. 2 depicts an example computing device according to some implementations of this disclosure. FIG. 3 is a flowchart of an example process of acute stressors detection according to some implementations of this disclosure. FIG. 4 is an example of heart rate variability (HRV) data over time according to some implementations of this disclosure. FIG. 5 is an example of using causal inference for acute stressors detection according to some implementations of this disclosure. FIG. 6 is an example of a directed acyclic graph (DAG) for acute stressors detection according to some implementations of this disclosure. DETAILED DESCRIPTION Many portable devices and systems have been developed to monitor physiological conditions of an individual. One area of interest in the use of physiological monitors is personal wellness and physical exercise for purposes of fitness training, weight loss, or monitoring general health. This can include monitoring of heart rate, glucose level, a