Accepted for/Published in: JMIR mHealth and uHealth
Date Submitted: Jan 16, 2020
Date Accepted: Jun 3, 2020
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
An App for Classifying Personal Mental Illness at Workplace Using Fit Statistics and Convolutional Neural Networks(CNN): A Survey-Based Quantitative Study
ABSTRACT
Background:
Mental illness(MI) is common among those who work in healthcare settings. Whether MI is related to employees’ mental status at work is yet been known. An MI app is developed and proposed to help employees assess their status in hope to detect MI at an earlier stage.
Objective:
The aim of this study is to build a model using the convolutional neural networks(CNN) and fit statistics based on two aspects of measures and Outfit mean square errors(MNSQ) for automatic detection and classification of personal MI at workplace using the emotional labor and mental health(ELMH) questionnaire so as to equip the staff the ability to assess and understand their own mental status with an app on their mobile device.
Methods:
We recruited 352 respiratory therapists (RT) working in Taiwan medical centers and regional hospitals to fill out the 44-item ELMH questionnaire in March 2019. The exploratory factor analysis(EFA), Rasch analysis, and CNN were used as unsupervised and supervised learnings for (1) dividing RTs into four classes(from poor mental health to confident) and (2) building an ELMH predictive model to estimate 108 parameters. We calculated the prediction accuracy rate and created an app for classifying MI for RTs at workplace as an online assessment.
Results:
We observed that (1) eight domains in ELMH were retained by EFA; (2) four types of mental health (n = 6, 63, 265, and 18 in four quadrants) were classified by Rasch analysis; (3) the 44-item model yields a higher accuracy rate (0.92); and (4) an available MI app for RTs predicting mental health was successfully developed and demonstrated in this study.
Conclusions:
The 44-item model with the 108 parameters estimated by using CNN for improving the accuracy of mental health for RTs. An MI app developed for helping RTs self-detect work-related mental health illness at an early stage should be made more available in the future. Clinical Trial: Nil
Citation
