Publication

Identifying objective physiological markers and modifiable behaviors for self-reported stress and mental health status using wearable sensor

Sano, A., Taylor, S., McHill, A. W., Phillips, A. J. K., Barger, L. K., Klerman, E., and Picard, R., "Identifying objective physiological markers and modifiable behaviors for self-reported stress and mental health status using wearable sensors and Mobile Phones: Observational Study," Journal of Medical Internet Research, 2018;20(6):e210

Abstract

Background: Wearable and mobile devices that capture multimodal data have the potential to identify risk factors for self-reported high stress and poor mental health and to provide information to improve health and well-being.

Objective: We developed new tools that provide objective physiological and behavioral measures using wearable sensors and mobile phones, together with methods that improve their data integrity. The aim of this study was to examine, using machine learning (ML), how accurately these measures could identify conditions of self-reported high stress and poor mental health and which of the underlying modalities and measures were most accurate in identifying those conditions.

Methods: We designed and conducted the 1-month SNAPSHOT study that investigated how daily behaviors and social networks influence self-reported stress, mood, and other health or  well-being-related factors. We collected over 145,000 hours of data from 201 college students (age: 18-25 years, male:female=1.8:1) at one university, all recruited within self-identified social groups. Each student filled out standardized pre- and postquestionnaires on stress and mental health; during the month, completed twice-daily electronic diaries (e-diaries); wore two wrist-based sensors that recorded continuous physical activity, light exposure, and autonomic physiology; and installed an app on their mobile phone that recorded call and texting (short message service, SMS) behaviors and geolocation patterns. We developed tools to make data collection more efficient, including semiautomatic data-check systems for sensor and mobile phone data and an e-diary administrative module for study investigators to locate possible errors in the e-diaries and communicate with participants to correct their entries promptly, which reduced the time taken to clean e-diary data by 69%. We constructed features and applied ML techniques to the multimodal data to identify factors associated with self-reported stress and mental health reported at the end of the study, including behaviors that can be possibly modified by the individual to improve these measures.

Results: We identified the physiological sensor, phone, mobility, and modifiable behavior features that were best predictors for classifying self-reported high or low stress and mental health. In general, features derived from wearable wrist-worn sensors performed better than features derived from mobile phone or modifiable behaviors. Features derived from wearable sensors, including skin conductance and temperature, reached 78% accuracy for classifying students into high or low stress groups and 86% accuracy for classifying high or low mental health groups. Features derived from modifiable behaviors, including number of naps, studying duration, phone calls, mobility patterns, and phone-screen-on time, reached 74% accuracy for classifying students into high or low stress groups and 78% accuracy for classifying high or low mental health groups.

Conclusions:

New semiautomated tools improved the efficiency of long-term ambulatory data collection from wearable and mobile devices. Applying ML to the resulting data revealed a set of both objective features and modifiable behavioral features that could classify self-reported high or low stress and mental health groups in a college student population better than previous studies and showed new insights into digital phenotyping.

Related Content