JMIR Publications

ABSTRACT

Background:

Extant studies have suggested that social media data, along with machine learning algorithms, can be used to generate computational mental health insights. Those computational insights have potential to support clinician-patient communication during psychotherapy consultations. However, it has been underexplored how clinicians would perceive and envision utilizing computational insights during consultations.

Objective:

We sought to understand clinician perspectives regarding computational mental health insights from patients’ social media. We focused on the opportunities and challenges of utilizing these insights during psychotherapy consultations.

Methods:

Following user-centered design approaches, we developed a prototype that can analyze consented patients’ Facebook data and visually represent the computational insights. We incorporated the insights into existing clinician-facing assessment tools, the Hamilton Depression Rating Scale and Global Functioning: Social Scale. The design intent is that a clinician will verbally interview a patient (e.g., How was your mood in the past week) while they review relevant insights from the patient’s social media (e.g., number of depression indicative posts.) Using the prototype, we conducted interviews (N=15) and 3 focus groups (N=13) with mental health clinicians: psychiatrists, clinical psychologists, and licensed clinical social workers. The transcribed qualitative data was analyzed using thematic analysis.

Results:

Clinicians reported the potential usefulness of the prototype as collateral information regarding collaborative agenda setting, tracking symptoms, and navigating patient verbal reports. They suggested alternative use scenarios such as collaborative use between clinicians, reviewing the prototype prior to consultations, and using the prototype when patients miss their consultations. They also shared their concerns regarding computational insights: they were not sure whether patients’ social media represent their actual behaviors; they wanted to learn how and when the machine learning algorithm can fail to set their expectations of trust; they worried about situations where they cannot properly respond to the insights, especially emergency situations outside of clinical settings. They also pointed out that reviewing computational insights may increase their workload.

Conclusions:

Our findings support the touted potential of computational mental health insights from patients’ social media data, especially in the context of psychotherapy consultations. However, sociotechnical issues, such as transparent algorithmic information and institutional support, should be addressed in future endeavors to design an implementable and sustainable technology.