Detecting Depression of Cancer Patients with Daily Mental Health Logs from Mobile Applications

Abstract

Mobile mental health trackers, the mobile applications that gather self-reported mental logs from users, have gained recent attention from clinicians as a tool for detecting patients’ depression. However, critics have raised questions about the validity of the data collected from mental health trackers, which ask only a few simple questions using the face emoticon scale. Our research is the first study to address this issue, and we provide theoretical discussion that leads to the following hypotheses: (1) simpler but larger datasets collected daily from mobile mental health trackers can serve as good indicators to detect patients’ depression, and (2) higher adherence to mobile mental health trackers enhances screening accuracy. We tested our hypotheses using the dataset of 5,792 sets of daily mental health logs collected from 78 breast cancer patients. Our random logistic panel regression and ROC analysis results, as well as k-means clustering analysis, provide strong supports for both hypotheses.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 2 citations exist upstream.