Understanding Falls Risk Profiles in Older Adults: Clinical Subgroups Informed by Machine Learning and Clinician Insight

Tuesday, October 28, 2025

5:15 PM - 5:30 PM

Location: ROOM: Astoria Room >>> DIRECTIONS: Third Floor >>> From the Main Elevator Bank, proceed left toward the Williford and Waldorf Rooms. Astoria is located beyond the Waldorf along the south corridor.

Presenting Author(s)

Brittany Samulski, DPT, PhD

Assistant Professor
Old Dominion University
Virginia Beach, VA, United States

Slides Slides

Non-presenting Author(s)

Neda Moghim

Research Assistant Professor
Old Dominion Univerisity
Suffolk, Virginia, United States
Ashwini Kulkarni, PT, PhD (she/her/hers)

Assistant Professor
Old Dominion University
Norfolk, VA, United States
PS

Pooyan Salavati

Independent Researcher
Formerly with Department of Computer Engineering, University of Isfahan, Isfahan, Iran
Suffolk, United States
Ross Gore

Research Associate Professor
Old Dominion University
Suffolk, Virginia, United States
Soumya Banerjee

Research Assistant Professor
Old Dominion University
Suffolk, Virginia, United States
Christopher K. Rhea

Associate Dean for Research and Innovation
Old Dominion University
Norfolk, VA, United States

This presentation identifies data-driven and clinically meaningful subgroups of older adults at risk of falling by applying dimensionality reduction and clustering techniques, and the extent to which the identified groupings align with established clinical falls risk classifications.

Learning Objectives:

Describe the process and rationale for using dimensionality reduction and clustering techniques to identify fall risk subgroups in older adults.
Interpret the clinical characteristics of five identified subgroups and discuss their implications for individualized fall prevention strategies.
Evaluate the potential for integrating machine learning with clinical judgment to enhance fall risk assessment and intervention planning.