Tracking Depression Dynamics in College Students Using Mobile Phone and Wearable Sensing

Abstract

There are rising rates of depression on college campuses. Mental health services on our campuses are working at full stretch. In response researchers have proposed using mobile sensing for continuous mental health assessment. Existing work on understanding the relationship between mobile sensing and depression, however, focuses on generic behavioral features that do not map to major depressive disorder symptoms defined in the standard mental disorders diagnostic manual (DSM-5). We propose a new approach to predicting depression using passive sensing data from students' smartphones and wearables. We propose a set of symptom features that proxy the DSM-5 defined depression symptoms specifically designed for college students. We present results from a study of 83 undergraduate students at Dartmouth College across two 9-week terms during the winter and spring terms in 2016. We identify a number of important new associations between symptom features and student self reported PHQ-8 and PHQ-4 depression scores. The study captures depression dynamics of the students at the beginning and end of term using a pre-post PHQ-8 and week by week changes using a weekly administered PHQ-4. Importantly, we show that symptom features derived from phone and wearable sensors can predict whether or not a student is depressed on a week by week basis with 81.5% recall and 69.1% precision.

Keywords: Applied computing → Life and medical sciences; Depression; Human-centered computing → Ubiquitous and mobile computing; Mental Health; Mobile Sensing.

Fig. 1

We continuously collect behavioral passive sensing data from Android and Apple iOS smartphones and physiological sensing data from Microsoft Band 2. We compute the symptom features from the passive sensing data. The symptom features map smartphone and wearable passive sensing to 5 depression symptoms defined in DSM-5: sleep changes, diminished ability to concentrate, diminished interest in activities, depressed mood, and fatigue or loss of energy. We look for associations between the symptom features and the PHQ8/PHQ4 depression outcomes.

Fig. 2

The distribution of the PHQ-8 and PHQ-4 responses. (a) The mean score for the pre PHQ-8 is 6.09 (N = 82, std = 4.33), where 16 students are in the depressed group (PHQ-8 ≥10). (b) The mean score for the post PHQ-8 is 6.69 (N = 71, std = 5.46), where 17 students are in the depressed group. (c) The mean score of the PHQ-4 depression subscale is 1.34 (N = 707, std = 1.50), where 108 responses are above the depressed cutoff (≥3). (d) The mean per-participant PHQ-4 depression subscale score is 1.31 (std = 1.17), where 4 participants’ mean PHQ-4 depression subscale score is above the depressed cutoff (≥3).

Fig. 3

The correlation matrix of proposed symptom features and PHQ-8 pre-post item scores. Correlations with p > 0.05 are omitted.

Fig. 4

The distribution of the time at study places, the slope of the time at study places over the term, and the unlock duration at study places of the pre-post PHQ-8 non depressed group and depressed group. Students from the depressed group

Fig. 5

The distribution of the conversation duration and the conversation duration slope of the pre-post PHQ-8 non depressed group and depressed group.

Fig. 6

The distribution of sleep duration, sleep start time standard deviation, and sleep end time standard deviation for the pre-post PHQ-8 non depressed group and depressed group. The group differences are not statistically significant according to ANOVA.

Fig. 7

The ROC curve of using lasso logistic regression to predict PHQ-4 depression states. The area under the ROC curve (AUC) is 0.809.

Fig. 8

The dynamics of a student’s PHQ-4 depression subscale score, number of conversations around, sleep duration, bed time, wake time, and number of places visited over a 9-week term. The student starts the term in a non depressed state but their PHQ-4 depression subscale score deteriorates as the term progresses and peaks during week 4 and drops to 0 in week 8. The student is around fewer conversations, sleep less, goes to bed later at night and wakes up earlier in the morning, and visit fewer places before week 4. As the term ends the student recovers showing resilience and their behavioral sensing curves sleeping earlier, getting up later and therefore sleeping longer, visiting more locations on campus during the day, and being around more conversation.