A machine learning approach to determine resilience utilizing wearable device data: analysis of an observational cohort

Abstract Objective To assess whether an individual’s degree of psychological resilience can be determined from physiological metrics passively collected from a wearable device. Materials and Methods Data were analyzed in this secondary analysis of the Warrior Watch Study dataset, a prospective cohor...

Full description

Saved in:
Bibliographic Details
Published in:JAMIA open 2023-07, Vol.6 (2), p.ooad029
Main Authors: Hirten, Robert P, Suprun, Maria, Danieletto, Matteo, Zweig, Micol, Golden, Eddye, Pyzik, Renata, Kaur, Sparshdeep, Helmus, Drew, Biello, Anthony, Landell, Kyle, Rodrigues, Jovita, Bottinger, Erwin P, Keefer, Laurie, Charney, Dennis, Nadkarni, Girish N, Suarez-Farinas, Mayte, Fayad, Zahi A
Format: Article
Language:English
Subjects:
Machine learning
Machinery
Magneto-electric machines
Medical personnel
Research and Applications
Surveys
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Objective To assess whether an individual’s degree of psychological resilience can be determined from physiological metrics passively collected from a wearable device. Materials and Methods Data were analyzed in this secondary analysis of the Warrior Watch Study dataset, a prospective cohort of healthcare workers enrolled across 7 hospitals in New York City. Subjects wore an Apple Watch for the duration of their participation. Surveys were collected measuring resilience, optimism, and emotional support at baseline. Results We evaluated data from 329 subjects (mean age 37.4 years, 37.1% male). Across all testing sets, gradient-boosting machines (GBM) and extreme gradient-boosting models performed best for high- versus low-resilience prediction, stratified on a median Connor-Davidson Resilience Scale-2 score of 6 (interquartile range = 5–7), with an AUC of 0.60. When predicting resilience as a continuous variable, multivariate linear models had a correlation of 0.24 (P = .029) and RMSE of 1.37 in the testing data. A positive psychological construct, comprised of resilience, optimism, and emotional support was also evaluated. The oblique random forest method performed best in estimating high- versus low-composite scores stratified on a median of 32.5, with an AUC of 0.65, a sensitivity of 0.60, and a specificity of 0.70. Discussion In a post hoc analysis, machine learning models applied to physiological metrics collected from wearable devices had some predictive ability in identifying resilience states and a positive psychological construct. Conclusions These findings support the further assessment of psychological characteristics from passively collected wearable data in dedicated studies. Lay Summary Mental health issues are common however resources for their evaluation and treatment are limited. Digital technologies, such as wearable devices, provide a possible means to automate mental health assessments. Resilience, or an individual’s ability to cope with adversity, is an important psychological feature which can improve stress and psychological well-being. The goal of this study is to see whether we are able to predict a person’s degree of resilience, and other psychological features, using the information collected from wearable devices. Using machine learning algorithms, we evaluated the changes in the time between each heartbeat, or heart rate variability, which is collected from wearable devices. Heart rate variability reflects the body’s ne
ISSN:2574-2531
2574-2531
DOI:10.1093/jamiaopen/ooad029