Psychiatric Profiles of eHealth Users Evaluated Using Data Mining Techniques: Cohort Study

• Published in: JMIR mental health Vol. 8; no. 1; p. e17116
• Main Authors: Lopez-Castroman, Jorge, Abad-Tortosa, Diana, Cobo Aguilera, Aurora, Courtet, Philippe, Barrigón, Maria Luisa, Artés, Antonio, Baca-García, Enrique
• Format: Journal Article
• Language: English
• Published: Canada JMIR Publications 20.01.2021
• Subjects: Behavior; Bias; Cohort analysis; Data mining; Hospitals; Human health and pathology; Life Sciences; Machine learning; Mental disorders; Mental health care; Multimedia; Original Paper; Patients; Questionnaires; Suicides & suicide attempts; Spain; suicidal ideation; suicide prevention; digital phenotyping; data mining; mental disorders
• ISSN: 2368-7959; 2368-7959
• DOI: 10.2196/17116

New technologies are changing access to medical records and the relationship between physicians and patients. Professionals can now use e-mental health tools to provide prompt and personalized responses to patients with mental illness. However, there is a lack of knowledge about the digital phenotypes of patients who use e-mental health apps. This study aimed to reveal the profiles of users of a mental health app through machine learning techniques. We applied a nonparametric model, the Sparse Poisson Factorization Model, to discover latent features in the response patterns of 2254 psychiatric outpatients to a short self-assessment on general health. The assessment was completed through a mental health app after the first login. The results showed the following four different profiles of patients: (1) all patients had feelings of worthlessness, aggressiveness, and suicidal ideas; (2) one in four reported low energy and difficulties to cope with problems; (3) less than a quarter described depressive symptoms with extremely high scores in suicidal thoughts and aggressiveness; and (4) a small number, possibly with the most severe conditions, reported a combination of all these features. User profiles did not overlap with clinician-made diagnoses. Since each profile seems to be associated with a different level of severity, the profiles could be useful for the prediction of behavioral risks among users of e-mental health apps.