Temporal and Type Correlation in Digital Phenotyping for Bipolar Disorder State Prediction Using Multitask Self-Supervised Learning

Bipolar disorder is a prevalent mental illness characterized by a high relapse rate. In this study, we propose an early warning system that utilizes digital phenotyping to collect various data points from bipolar patients, including location information, self-assessment scales, daily mood reports, sleep patterns, and multimedia records, through a mobile application. These collected data are utilized to develop a predictive model for assessing the risk state of bipolar disorder. Compared to traditional recurrence prediction methods, this study incorporates medical records, medication data, and emergency records, as suggested by medical professionals, to define the five states of bipolar disorder, leading to enhanced accuracy. To account for data type correlation and temporal correlation, we employ a multitask self-supervised learning mechanism. The proposed method is trained on a Gated recurrent unit and demonstrates an improved prediction accuracy of 88.2% on the collected test data, as compared to the baseline accuracy of 85.1%. These findings highlight the significant importance of considering data type and temporal correlations in digital phenotyping for predicting the state of bipolar disorder.

I. Introduction

Bipolar disorder (BD) is a chronic psychiatric condition characterized by episodes of depression, mania, or mixed states. It is estimated that BD affects approximately 435-544 million individuals worldwide, with a prevalence rate of 0.7% (0.6%-0.8%) [1]. Alarmingly, 25% - 50% of BD patients have attempted suicide, leading to significant social and economic consequences [2]. The World Health Organization recommends a psychiatrist-patient ratio of 1 doctor per 10,000 patients [3]. However, many regions struggle to meet this staffing requirement. While long-term monitoring can aid in managing BD [4], it also consumes substantial medical resources and personnel. Therefore, the objective of this study is to develop an early warning system to assist healthcare professionals in predicting the state of BD.