JMIR Publications

ABSTRACT

Background:

The mobility of an individual measured by phone-collected location data has been found to be associated with depression in several recent studies. However, the longitudinal relationships (the temporal direction of relationships) between depressive symptom severity and phone-measured mobility are yet to be fully explored.

Objective:

To explore the relationships and the direction of the relationships between depressive symptom severity and phone-measured mobility over time.

Methods:

The data used in this paper came from the major EU program, Remote Assessment of Disease and Relapse – Central Nervous System (RADAR-CNS) conducted across three European countries. Depressive symptom severity was measured by the 8-item Patient Health Questionnaire (PHQ-8) through mobile phones every two weeks. Participants’ location data was recorded by GPS and network sensors in mobile phones every 10 minutes. To measure individuals’ mobility, 11 mobility features were extracted from 2 weeks’ location data prior to each PHQ-8 record. A dynamic structural equation modeling framework was used to explore the longitudinal relationships between depressive symptom severity and phone-measured mobility.

Results:

This study included 290 participants (median [IQR] age, 50.0 (34.0, 59.0) years; 215 (74.14%) females; 149 (51.38%) employed participants) with 2341 PHQ-8 records and corresponding phone-collected location data. Significant and negative correlations were found between depressive symptom severity and phone-measured mobility, and these correlations were more significant at the within-individual level than the between-individual level. For the direction of relationships over time, mobility features of homestay (time at home), the location entropy (time distribution on different locations), and the residential location count (reflecting traveling) were significantly correlated with the subsequent changes in the PHQ-8 score, while changes in the PHQ-8 score significantly affected the subsequent periodic pattern of mobility.

Conclusions:

Our results demonstrate that several phone-derived mobility features have the potential to predict the future depressive state, which may provide support for future clinical applications of depression prediction, depressive relapse prevention, and remote mental health monitoring practice in real-world settings.