Using Wearable Device and Artificial Intelligence to Predict Mood Symptoms in Bipolar Disorder (Preprint)

UNSTRUCTURED Bipolar disorder (BD) is a highly recurrent disorder. Early detection, early intervention, and prevention of recurrent bipolar mood symptoms are key for better prognosis. In this study, we build prediction models for bipolar disorder with machine learning algorithms. This study recruited 24 participants with BD. The Beck Depression Inventory (BDI) and Young Mania Rating Scale (YMRS) were used to evaluate depressive and manic episodes respectively. Using digital biomarkers collected from wearable devices as input, six machine learning algorithms (Logistic Regression, Decision Tree, K-Nearest Neighbors, Random Forest, Adaptive Boosting, and Extreme Gradient Boosting) were used to build predictive models. The prediction model for depressive symptoms achieved 83% accuracy, 0.89 Area Under the Receiver Operating Characteristic curve (AUROC), and 0.65 F1 score on testing data. The prediction model for manic symptoms achieved 91% accuracy, 0.88 AUROC, and 0.25 F1 score on testing data. With the interpretable model Shapely Additive exPlanations (SHAP), we found that relatively high resting heart rate, low activity, and lack of sleep may predict depressive symptoms. This study demonstrated that digital biomarkers could be used to predict depressive and manic symptoms. Moreover, based on the findings from the prediction model, we may provide clinical assessment and treatment earlier to prevent a recurrence.