One out of every two of the 2.3 million persons with Multiple Sclerosis (PwMS) report a fall in any given three- month period. The onset of MS is often during early or middle adulthood, making MS-induced falls a significant, long-term problem in need of new preventative interventions. Here we propose to advance several components of Just-In-Time Fall Prevention ? a novel mHealth (mobile health) approach for preventing falls and to demonstrate each component in a sample of PwMS. The proposed mHealth system will be composed of wireless, wearable sensors and a mobile phone application. The wearable sensors will capture patient biomechanics and a network of statistical models, created using machine learning and deployed on the mobile phone, will predict fall risk based upon these measurements. Fall risk predictions will inform personalized interventions, delivered through the mobile application, that leverage strategies from social psychology designed to induce biomechanical and behavioral changes to immediately reduce fall risk. This approach enables real- time assessment and intervention to prevent future falls. Data to develop and pilot each component of this mHealth system will be collected in a study of N=50 PwMS that will a) capture concurrent measurements from wearable sensors, optical motion capture, force platforms, and an instrumented treadmill during functional assessments and simulated daily activities, b) track falls and objective biomechanical and behavioral measures during a 3-month in-home study, and c) assess the efficacy of point-of-choice prompts for altering fall-related biomechanics during balance-challenging daily activities. These data will be used to accomplish the following specific aims: 1) Validate wearable sensor algorithms for capturing biomechanics and behavior of PwMS, 2) Identify digital biomarkers for quantifying fall risk in real time during daily life in PwMS, and 3) Pilot point-of- choice prompts for inducing biomechanical changes in PwMS under realistic cognitive load.
These aims are the first step toward our goal of developing a paradigm-shifting mHealth system for fall prevention and lead naturally to future R01 support for a randomized, controlled clinical trial testing the efficacy of this approach.

Public Health Relevance

This project will advance several components of a novel mobile health intervention for preventing falls. If successful, this approach has the potential to shift fall preventions efforts from reactive and physician centered to preventative and patient centered improving long-term health outcomes and quality of life for those with balance and mobility impairment.

National Institute of Health (NIH)
National Institute of Biomedical Imaging and Bioengineering (NIBIB)
Exploratory/Developmental Grants (R21)
Project #
Application #
Study Section
Biomedical Computing and Health Informatics Study Section (BCHI)
Program Officer
Lash, Tiffani Bailey
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
University of Vermont & St Agric College
United States
Zip Code