Development of a Data-Driven Digital Phenotype Profile of Distress Experience of Healthcare Workers During COVID-19 Pandemic

38 Pages Posted: 27 Oct 2022

See all articles by Binh Nguyen

Binh Nguyen

Toronto Metropolitan University (formerly Ryerson University) - Department of Electrical, Computer, and Biomedical Engineering

Andrei Torres

University of Ontario Institute of Technology

Caroline Espinola

University of Toronto

Walter Sim

St. Michael’s Hospital

D Kenny

University of Colorado

Douglas M Campbell

University of Toronto - Unity Health Toronto

Wendy Y. W. Lou

University of Toronto - Dalla Lana School of Public Health

Bill Kapralos

University of Ontario Institute of Technology

Lindsay Beavers

University of Toronto - Unity Health Toronto

Elizabeth Peter

University of Toronto

Adam Dubrowski

University of Ontario Institute of Technology

Sridhar Krishnan

Toronto Metropolitan University (formerly Ryerson University) - Department of Electrical, Computer, and Biomedical Engineering

Venkat Bhat

University of Toronto

Multiple version iconThere are 2 versions of this paper

Abstract

Due to the constraints of the COVID-19 pandemic, healthcare workers have reported acting in ways that are contrary to their moral values, which may result in moral distress and injury. The purpose of this work is to create a digital phenotype profile (DPP) tool to automate and evaluate the distress of participants in the COVID-19 VR Healthcare Simulation for Moral Distress dataset (NCT05001542). The dataset collected passive physiological signals and active mental health questionnaires. This paper focuses on correlating electrocardiogram, respiration, photoplethysmography and galvanic skin response with moral injury outcome scale (Brief MIOS). The DPP tool uses data-driven techniques to create a robust evaluation of distress among participants. To accomplish this, we applied pre-processing techniques which involved normalization, data sanitation, segmentation, and windowing. During feature analysis, we extracted statistical and heart rate variability features, followed by feature selection techniques to rank the importance of features. Prior to classification, we used k-means clustering to cluster the Brief MIOS scores to low, moderate, and high moral distress as the Brief MIOS is yet to have an established cut-off scores. We then classified the separation of the Brief MIOS scores using weighted support vector machine with leave-one-subject-out-cross-validation to achieve an accuracy of 98.67±0.87%. Various machine learning ablation tests were performed to support our results and further enhance the understanding of the predictive model. Our findings suggest that the proposed DPP tool could be used as an automated tool to examine moral distress. With further replication and validation, it could be used as a potential AI-based clinical decision-making tool to expedite and validate mental health treatments.

Note:

Funding Information: This work was supported by Department of Defense, Canada IDeAS grant, CPCA-0592. The financial support of Natural Sciences and Engineering Research Council of Canada (NSERC) RGPIN-2020-04628 and Ontario Graduate Scholarship (OGS) is gratefully acknowledged by BN. The financial support of the Ontario Trillium Scholarship program is gratefully acknowledged by AT. VB is supported by an Academic Scholar Award (University of Toronto Department of Psychiatry). This project (CPCA-0592) was funded by the Canadian Department of Defense, Innovation for Defense Excellence and Security Program.

Declaration of Interests: VB is supported by an Academic Scholar Award from the UofT Dept of Psychiatry and has received research support from CIHR, BBRF, MOH Innovation Funds, RCPSC, DND, Canada, and an investigator-initiated trial from Roche Canada. All other authors have no conflicts to declare.

Keywords: Digital phenotyping, COVID-19, Moral Distress, vr, Data-driven

Suggested Citation

Nguyen, Binh and Torres, Andrei and Espinola, Caroline and Sim, Walter and Kenny, D and Campbell, Douglas M and Lou, Wendy Y. W. and Kapralos, Bill and Beavers, Lindsay and Peter, Elizabeth and Dubrowski, Adam and Krishnan, Sridhar and Bhat, Venkat, Development of a Data-Driven Digital Phenotype Profile of Distress Experience of Healthcare Workers During COVID-19 Pandemic. Available at SSRN: https://ssrn.com/abstract=4234115 or http://dx.doi.org/10.2139/ssrn.4234115

Binh Nguyen (Contact Author)

Toronto Metropolitan University (formerly Ryerson University) - Department of Electrical, Computer, and Biomedical Engineering ( email )

Andrei Torres

University of Ontario Institute of Technology ( email )

Canada

Caroline Espinola

University of Toronto ( email )

105 St George Street
Toronto, M5S 3G8
Canada

Walter Sim

St. Michael’s Hospital ( email )

D Kenny

University of Colorado ( email )

Douglas M Campbell

University of Toronto - Unity Health Toronto ( email )

Wendy Y. W. Lou

University of Toronto - Dalla Lana School of Public Health ( email )

Toronto, Ontario
Canada

Bill Kapralos

University of Ontario Institute of Technology ( email )

Canada

Lindsay Beavers

University of Toronto - Unity Health Toronto ( email )

Elizabeth Peter

University of Toronto ( email )

105 St George Street
Toronto, M5S 3G8
Canada

Adam Dubrowski

University of Ontario Institute of Technology ( email )

Canada

Sridhar Krishnan

Toronto Metropolitan University (formerly Ryerson University) - Department of Electrical, Computer, and Biomedical Engineering ( email )

Venkat Bhat

University of Toronto ( email )

105 St George Street
Toronto, M5S 3G8
Canada

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
42
Abstract Views
273
PlumX Metrics