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

To assess whether an individual's degree of psychological resilience can be determined from physiological metrics passively collected from a wearable device. 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. 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 ( In a These findings support the further assessment of psychological characteristics from passively collected wearable data in dedicated studies.

Informations de copyright

© The Author(s) 2023. Published by Oxford University Press on behalf of the American Medical Informatics Association.

Déclaration de conflit d'intérêts

DC is a coinventor on patents filed by the Icahn School of Medicine at Mount Sinai (ISMMS) relating to the treatment for treatment-resistant depression, suicidal ideation, and other disorders. ISMMS has entered into a licensing agreement with Janssen Pharmaceuticals, Inc, and it has received and will receive payments from Janssen under the license agreement related to these patents for the treatment of treatment-resistant depression and suicidal ideation. Consistent with the ISMMS Faculty Handbook (the medical school policy), DC is entitled to a portion of the payments received by the ISMMS. Because SPRAVATO has received regulatory approval for treatment-resistant depression, through the ISMMS, DC will be entitled to additional payments beyond those already received under the license agreement. DC is a named coinventor on several patents filed by ISMMS for a cognitive training intervention to treat depression and related psychiatric disorders. The ISMMS has entered into a licensing agreement with Click Therapeutics, Inc and has received and will receive payments related to the use of this cognitive training intervention for the treatment of psychiatric disorders. In accordance with the ISMMS Faculty Handbook, DC has received a portion of these payments and is entitled to a portion of any additional payments that the medical school may receive from this license with Click Therapeutics. DC is a named coinventor on a patent application filed by the ISMMS for the use of intranasally administered Neuropeptide Y for the treatment of mood and anxiety disorders. This intellectual property has not been licensed. DC is a named coinventor on a patent application in the United States and several issued patents outside the United States filed by the ISMMS related to the use of ketamine for the treatment of posttraumatic stress disorder. This intellectual property has not been licensed. EPB reports consultancy agreements with Deloitte and Roland Berger; ownership interest in Digital Medicine E. Böttinger GmbH, EBCW GmbH, and Ontomics, Inc; receiving honoraria from Bayer, Bosch Health Campus, Sanofi, and Siemens; and serving as a scientific advisor or member of Bosch Health Campus and Seer Biosciences Inc. LK declares research funding from Abbvie and Pfizer, consulting for Abbvie and Pfizer, and equity ownership/stock options in MetaMe Health and Trellus Health. MS-F declares research support from Novartis and Allergenis. GNN reports employment with, consultancy agreements with, and ownership interest in Pensieve Health and Renalytix AI; receiving consulting fees from AstraZeneca, BioVie, GLG Consulting, and Reata; and serving as a scientific advisor or member of Pensieve Health and Renalytix AI. ZAF discloses consulting fees from Alexion, GlaxoSmithKline, and Trained Therapeutix Discovery and research funding from Daiichi Sankyo, Amgen, Bristol Myers Squibb, and Siemens Healthineers. ZAF receives financial compensation as a board member and advisor to Trained Therapeutix Discovery and owns equity in Trained Therapeutix Discovery as a cofounder. The remaining authors declare no conflicts of interest.