Multiple Sclerosis Falls Insight Track: A Personal Health Library to Reduce Falls in Patients With Multiple Sclerosis

Falls occur in >50% patients with multiple sclerosis (MS), worsen participation in daily life and increase healthcare costs. To date there are no established, accessible, tools to evaluate and reduce fall risk. MS Falls InsightTrack is a live personal health library that combines a patient's falls-relevant clinical indicators (from the electronic health record, EHR) with patient-generated data (PGD) from commercial wearable tools and patient-reported outcomes (PROs) and community-level data (sociodemographic data from University of California, San Francisco (UCSF) Health Atlas combined with MS-specific resources from the National MS Society). The tool will track falls/near-falls in real- time and report changes in status that require intervention. It will offer customized action prompts to support fall reduction through a behaviorally informed approach. It will be accessed in the clinic and in the patient's home.

Technological features. The tool will be accessible, extensible and scalable. The investigators will use modern technologies and industry standards (e.g back-end: Python, flask framework, PostgreSQL; front-end: HTML, CSS, JavaScript and d3.js). The tool will launch from Epic via SMART on FHIR, and will communicate with patients using MyChart.

Qualifications of team and setting. The UCSF MS Center is a leading clinical research center in the digital space. Our sub-leads are experts in all aspects of the study (digital technology, human-centered design, implementation science, health literacy) with a varied and experienced Stakeholder Advisory Group.

Scientific plan. In Aim 1 (design), the investigators will use a Human-Centered Design approach, engaging 20 patients with MS, clinicians and stakeholders in a series of focus groups, to identify the critical data, devices, visualizations, resources, workflows and accessibility/digital divide considerations for the tool, and the key interventions likely to promote the COM-B model of behavioral change to reduce fall risk.

Our key outcomes will be perceived effectiveness, ease of use and likability. In Aim 2 (evaluate feasibility), investigators will deploy MS Falls Insight Track in 100 diverse adults with MS who are at risk for falls. Participants will wear a Fitbit. The tool will be used by patients in their homes and by clinicians during clinical encounters. The investigators will use an implementation science approach. Our key outcomes will be study retention, tool uptake and sustained use. The investigators will explore impact on fall risk. In Aim 3 (test generalizability) investigators will conduct focus groups with patients with other conditions where falls are common (Orthopedics, Parkinson's Disease, Geriatrics) to understand additional data and design features required to promote generalizability. Our key outcomes will parallel those in Aim 1.