Clinician Perspectives and Design Implications in Using Patient-Generated Health Data to Improve Mental Health Practices: Mixed Methods Study

Abstract

Background Patient-generated health data (PGHD) have been largely collected through mobile health (mHealth) apps and wearable devices. PGHD can be especially helpful in mental health, as patients’ illness history and symptom narratives are vital to developing diagnoses and treatment plans. However, the extent to which clinicians use mental health–related PGHD is unknown. Objective A mixed methods study was conducted to understand clinicians’ perspectives on PGHD and current mental health apps. This approach uses information gathered from semistructured interviews, workflow analysis, and user-written mental health app reviews to answer the following research questions: (1) What is the current workflow of mental health practice and how are PGHD integrated into this workflow, (2) what are clinicians’ perspectives on PGHD and how do they choose mobile apps for their patients, (3) and what are the features of current mobile apps in terms of interpreting and sharing PGHD? Methods The study consists of semistructured interviews with 12 psychiatrists and clinical psychologists from a large academic hospital. These interviews were thematically and qualitatively analyzed for common themes and workflow elements. User-posted reviews of 56 sleep and mood tracking apps were analyzed to understand app features in comparison with the information gathered from interviews. Results The results showed that PGHD have been part of the workflow, but its integration and use are not optimized. Mental health clinicians supported the use of PGHD but had concerns regarding data reliability and accuracy. They also identified challenges in selecting suitable apps for their patients. From the app review, it was discovered that mHealth apps had limited features to support personalization and collaborative care as well as data interpretation and sharing. Conclusions This study investigates clinicians’ perspectives on PGHD use and explored existing app features using the app review data in the mental health setting. A total of 3 design guidelines were generated: (1) improve data interpretation and sharing mechanisms, (2) consider clinical workflow and electronic health record integration, and (3) support personalized and collaborative care. More research is needed to demonstrate the best practices of PGHD use and to evaluate their effectiveness in improving patient outcomes.

Can the European EHR Exchange Format Support Shared Decision Making and Citizen-Driven Health Science?

“…Some studies [16,17] reported about the adaptation of standards for integration of data from wearables into EHRs, in particular HL7 Common Document Architecture (CDA). Other studies point out the limited capacity of EHRs for direct patient input [18], insufficient integration of mental health apps with EHRs [19], and EHRs being inferior at storing patient contextual data such as patients' needs, values, goals, and preferences relevant to their care [20]. This limited support for direct patient engagement was confirmed in the recent FHIR connectathon, in the Patient Empowerment track.…”

Perceptions of and Experiences with Consumer Sleep Technologies That Use Artificial Intelligence

“…When patients present CST data to clinicians, there may be disagreements on how patient-generated health data (PGHD) should be used [ 20 , 21 ]. One systematic review found that PGHD improved clinicians’ understanding of patients’ health, but clinicians had a varied interest in PGHD and encountered barriers to its use in clinical care, such as time constraints, lack of workflow integration, information overload, and lack of reimbursement [ 20 ].…”

Opportunities and Challenges of Integrating Food Practice into Clinical Decision-Making

“…These challenges include the lack of actionable data, reliability and accuracy of the data, workflow disruption, technical issues, and a lack of incentives. 8,98,99 Furthermore, food practice data need to be summarized, so that patterns can be easily visualized by health care professionals who will eventually need to rapid sense making and decision-making. 100,101 Perceived or objective problems with the reliability and accuracy of data can affect use of food practice data.…”