Innovating to improve behavioral health care for patients: best practices in adaptive measurement technology
|Rona Margaret Relovaemail@example.com|
Research has shown that measurement based care (MBC) works to improve behavioral health outcomes, but its implementation in real-world environments is difficult. The VA health care system has proven no exception: MBC has been attempted at the VA, but its champions have been hampered by challenges in usability and insufficiency of sophisticated technology.
A cloud technology platform that automatically administers and interprets measures, uses advanced data analytics to produce insights, and programmatically triages patient needs may overcome many of these obstacles. Mirah's software-as-a-service (SaaS), designed to augment clinical best practice with digital patient assessments and machine-learning analytics, has this platform. Mirah’s virtual clinical assistant functionality is built on the concept that adoption is a crucial and fragile component, automatically initiating computer-adaptive sessions with patients on behalf of the directing clinician.
The purpose of this project is to validate the usefulness of the Mirah platform through end-user (patients, providers, administrators) testing and evaluation at the VA health care setting.
This study will use mixed qualitative and quantitative methods to assess the feasibility of the Mirah platform with a select group of behavioral health providers at the VA Palo Alto Outpatient Mental Health setting. Investigators will consult with each patient’s treatment provider to determine eligibility (i.e. capacity to provide informed consent among other criteria). After obtaining consent, participants complete questionnaires on kiosks/laptops/tablets prior to each clinical session. Mirah’s assessments take 5-10 minutes and include adaptive psychometric measures as well as standard instruments. Mirah’s platform automatically interprets symptom characteristics and facilitates patient triage. Providers receive the completed reports and machine interpretations, which can guide the treatment session and be shared with the patient directly.
Quantitative measures of study outcome include (a) pre- and post-implementation surveys of providers’ attitudes to MFS, (b) automatically generated implementation information including rates of questionnaire completion and feedback viewing, and (c) session-based surveys of Veteran perceptions of the MFS. Qualitative methods will include (a) training notes and observations from implementation support activities and (b) a semi-structured focus group with participating Veterans, providers and administrators.
By enabling providers to better identify risks to treatment (including treatment non-response, status decline, occurrence of critical events, etc.), the MFS could improve outcomes for Veterans with serious mental illness and increase the efficiency of resource allocation.