JMIR Publications

ABSTRACT

Background:

Recent research has emphasized a need for accessing information about patients to augment mental health patients' verbal reports in clinical settings. Even though it has not been introduced in clinical settings, computational linguistic analysis on social media has proved that it can infer mental health attributes, implying that it can be used as collateral information at the point of care. To realize this potential and to make social media insights actionable to clinical decision-making, however, the gaps between computational linguistic analysis on social media and the current work practices of mental health clinicians must be bridged.

Objective:

This study aims to identify information derived from patients' social media data, that can benefit clinicians, and develop a set of design implications, via a series of low-fidelity prototypes, on how we can deliver the information at the point of care.

Methods:

A team of clinical researchers and Human-Computer Interaction (HCI) researchers conducted a long-term co-design activity over 6 months. The needs-affordances analysis framework was used to refine the clinicians' potential needs that can be supported by patients' social media data. Based on the identified needs, the HCI researchers created 3 different low-fidelity prototypes in an iterative fashion. The prototypes were shared with both groups of researchers via a video-conferencing application for discussion and feedback. During the remote meetings, potential clinical utility, potential use of the different prototypes in a treatment setting, and areas of improvement were discussed.

Results:

Our first prototype was a card-type interface that supported treatment goal tracking. Each card included the level of the attributes: depression, anxiety, social activities, alcohol, and drug use. This version confirmed which types of information are helpful, but revealed the need for a glanceable dashboard that highlights the trends of each type of information. As a result, we next developed the second prototype, an interface that shows clinical state and trend. We found that focusing more on the changes since the last visit without visual representation can be more compatible with clinicians' work practices. Additionally, the second phase of needs-affordances analysis identified three categories of information relevant to schizophrenia patients: symptoms related psychosis, symptoms related mood/anxiety, and social functioning. Finally, we developed the third prototype, a clinical summary dashboard, that showed changes from the last visit in plain texts and contrasting colors.

Conclusions:

This exploratory co-design research confirmed that mental health attributes inferred from patient social media can be useful for clinicians, although it revealed a gap between computational social media analyses and clinicians' expectations and conceptualizations of patients' mental health states. Summarily, the iterative co-design process crystallized design directions for the future interface including how we can organize symptom-related information and provide the information in a way that minimizes the clinicians' workloads.