TY  - JOUR
AU  - Yu, Jessica
AU  - Chiu, Carter
AU  - Wang, Yajuan
AU  - Dzubur, Eldin
AU  - Lu, Wei
AU  - Hoffman, Julia
PY  - 2021
DA  - 2021/8/27
TI  - A Machine Learning Approach to Passively Informed Prediction of Mental Health Risk in People with Diabetes: Retrospective Case-Control Analysis
JO  - J Med Internet Res
SP  - e27709
VL  - 23
IS  - 8
KW  - diabetes mellitus
KW  - mental health
KW  - risk detection
KW  - passive sensing
KW  - ecological momentary assessment
KW  - machine learning
AB  - Background: Proactive detection of mental health needs among people with diabetes mellitus could facilitate early intervention, improve overall health and quality of life, and reduce individual and societal health and economic burdens. Passive sensing and ecological momentary assessment are relatively newer methods that may be leveraged for such proactive detection. Objective: The primary aim of this study was to conceptualize, develop, and evaluate a novel machine learning approach for predicting mental health risk in people with diabetes mellitus. Methods: A retrospective study was designed to develop and evaluate a machine learning model, utilizing data collected from 142,432 individuals with diabetes enrolled in the Livongo for Diabetes program. First, participants’ mental health statuses were verified using prescription and medical and pharmacy claims data. Next, four categories of passive sensing signals were extracted from the participants’ behavior in the program, including demographics and glucometer, coaching, and event data. Data sets were then assembled to create participant-period instances, and descriptive analyses were conducted to understand the correlation between mental health status and passive sensing signals. Passive sensing signals were then entered into the model to train and test its performance. The model was evaluated based on seven measures: sensitivity, specificity, precision, area under the curve, F1 score, accuracy, and confusion matrix. SHapley Additive exPlanations (SHAP) values were computed to determine the importance of individual signals. Results: In the training (and validation) and three subsequent test sets, the model achieved a confidence score greater than 0.5 for sensitivity, specificity, area under the curve, and accuracy. Signals identified as important by SHAP values included demographics such as race and gender, participant’s emotional state during blood glucose checks, time of day of blood glucose checks, blood glucose values, and interaction with the Livongo mobile app and web platform. Conclusions: Results of this study demonstrate the utility of a passively informed mental health risk algorithm and invite further exploration to identify additional signals and determine when and where such algorithms should be deployed. 
SN  - 1438-8871
UR  - https://www.jmir.org/2021/8/e27709
UR  - https://doi.org/10.2196/27709
UR  - http://www.ncbi.nlm.nih.gov/pubmed/34448707
DO  - 10.2196/27709
ID  - info:doi/10.2196/27709
ER  -