Efficacy of the Mobile Application for Prediction and Prevention of Mood Episode Recurrence Based on Machine Learning

The study subjects participating in this clinical trial wear wearable activity tracker 24 hours a day for a continuous period of time and run the CRM app once a day to check their conditions (feelings, vitality, sleep, etc.) in the Daily Symptom Assessment (eMoodChart). The active intervention group are provided with mood prediction results and instructions as feedback through the 'life report' and push notification in the application.

The study subjects assigned to the sham intervention group are provided with feedbacks operated by dummy algorithm. The application is visually indistinguishable from active CRM, and it is designed to minimize behavioral change.