Home // eTELEMED 2025, The Seventeenth International Conference on eHealth, Telemedicine, and Social Medicine // View article

Enhancing Fall Prediction in Older Adults: A Data-Driven Approach to Key Parameter Selection

Authors:
Amadou M. Djiogomaye Ndiaye
Michel Harel
Laurent Billonnet
Achille Tchalla

Keywords: fall; older population; data; prevention; AI.

Abstract:
Falls significantly contribute to frailty and functional decline in elderly individuals. The Risk Of Falling (ROF) is linked to three dimensions: physical/organic, socio-environmental, and thymic/cognitive. Therefore, fall prevention protects older individuals from multiple comorbidities. The reliability of predictive studies depends on the quality and consistency of data collection. In most studies, data for model construction were collected from hospitals, research laboratories, or participants’ homes. Recent fall prediction models increasingly rely on machine learning, deep learning, and computer vision. Predictive models assist specialists in decision-making. Using home-collected data, our objective is to develop an optimized predictive model with minimal features. In this paper, we aim to identify the optimal model for predicting falls using this strategy with the objective of building a robust dataset as the entry of an AI process.

Pages: 37 to 39

Copyright: Copyright (c) IARIA, 2025

Publication date: May 18, 2025

Published in: conference

ISSN: 2308-4359

ISBN: 978-1-68558-270-8

Location: Nice, France

Dates: from May 18, 2025 to May 22, 2025