Depression Diagnosis and Forecast based on Mobile Phone Sensor Data

TL;DR

This study demonstrates that mobile phone sensor data can be effectively used to diagnose and forecast depression, achieving promising accuracy and RMSE scores, thus enabling earlier mental health interventions.

Contribution

It introduces a novel approach combining passive mobile data features with LSTM models for both depression diagnosis and forecasting, emphasizing the potential for real-time mental health monitoring.

Findings

77.0% accuracy in depression forecasting

53.7% accuracy in depression severity prediction

RMSE score of 4.094 for PHQ-9

Abstract

Previous studies have shown the correlation between sensor data collected from mobile phones and human depression states. Compared to the traditional self-assessment questionnaires, the passive data collected from mobile phones is easier to access and less time-consuming. In particular, passive mobile phone data can be collected on a flexible time interval, thus detecting moment-by-moment psychological changes and helping achieve earlier interventions. Moreover, while previous studies mainly focused on depression diagnosis using mobile phone data, depression forecasting has not received sufficient attention. In this work, we extract four types of passive features from mobile phone data, including phone call, phone usage, user activity, and GPS features. We implement a long short-term memory (LSTM) network in a subject-independent 10-fold cross-validation setup to model both a diagnostic and a forecasting tasks. Experimental results show that the forecasting task achieves comparable results with the diagnostic task, which indicates the possibility of forecasting depression from mobile phone sensor data. Our model achieves an accuracy of 77.0 % for major depression forecasting (binary), an accuracy of 53.7 % for depression severity forecasting (5 classes), and a best RMSE score of 4.094 (PHQ-9, range from 0 to 27).