@article{ref1,
title="Fall risk assessment in stroke survivors: a machine learning model using detailed motion data from common clinical tests and motor-cognitive dual-tasking",
journal="Sensors (Basel)",
year="2024",
author="Abdollahi, Masoud and Rashedi, Ehsan and Jahangiri, Sonia and Kuber, Pranav Madhav and Azadeh-Fard, Nasibeh and Dombovy, Mary",
volume="24",
number="3",
pages="e812-e812",
abstract="BACKGROUND: Falls are common and dangerous for stroke survivors. Current fall risk assessment methods rely on subjective scales. <br><br>OBJECTIVE sensor-based methods could improve prediction accuracy. <br><br>OBJECTIVE: Develop machine learning models using inertial sensors to objectively classify fall risk in stroke survivors. Determine optimal sensor configurations and clinical test protocols. <br><br>METHODS: 21 stroke survivors performed balance, Timed Up and Go, 10 Meter Walk, and Sit-to-Stand tests with and without dual-tasking. A total of 8 motion sensors captured lower limb and trunk kinematics, and 92 spatiotemporal gait and clinical features were extracted. Supervised models-Support Vector Machine, Logistic Regression, and Random Forest-were implemented to classify high vs. low fall risk. Sensor setups and test combinations were evaluated. <br><br>RESULTS: The Random Forest model achieved 91% accuracy using dual-task balance sway and Timed Up and Go walk time features. Single thorax sensor models performed similarly to multi-sensor models. Balance and Timed Up and Go best-predicted fall risk. <br><br>CONCLUSION: Machine learning models using minimal inertial sensors during clinical assessments can accurately quantify fall risk in stroke survivors. Single thorax sensor setups are effective. <br><br>FINDINGS demonstrate a feasible objective fall screening approach to assist rehabilitation.<p /> <p>Language: en</p>",
language="en",
issn="1424-8220",
doi="10.3390/s24030812",
url="http://dx.doi.org/10.3390/s24030812"
}