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

Abstract

Background 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. Objective This study aimed to reveal the profiles of users of a mental health app through machine learning techniques. Methods 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. Results 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. Conclusions 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.

General Demographics and Behavioral Patterns of Visitors Using a Self-help Website for Identification of and Intervention in Alcoholism and Common Mental Disorders in Suriname: Descriptive Study

“…In contrast to our findings, none of the abovementioned studies found a difference in gender use. However, a more recent Spanish study found that women used the modules more than men [27]. In accordance with our findings, the Spanish study also found that the modules for mood disorders were highest in use among the other modules [27].…”

“…The website [11] was launched on August 1, 2015, prior to the population survey in Nickerie (which was held from August [15][16][17][18][19][20][21][22][23][24][25][26][27]2015). Interest was generated in this period during the informative sessions with the doctors, district commissioners, police officers, and civil servants that helped during the survey.…”

Enhancing Feature Selection Accuracy using Butterfly and Lion Optimization Algorithm with Specific Reference to Psychiatric Disorder Detection & Diagnosis

“…Various previous research using data mining was carry doubt to deal with mental health [3,4,5]. Due to change in behavior the symptoms change in mental disorder and so it needs intelligent mechanism to classify it [6,7].…”