Explainable Siamese Neural Networks for Detection of High Fall Risk Older Adults in the Community Based on Gait Analysis
Authors:
- Christos KokkotisChristos Kokkotis
- Kyriakos ApostolidisKAKyriakos Apostolidis
- Dimitrios MenychtasDMDimitrios Menychtas
- Ioannis KansizoglouIoannis Kansizoglou
- Evangeli KarampinaEKEvangeli Karampina
- Maria KarageorgopoulouMaria Karageorgopoulou
- Athanasios GkrekidisAGAthanasios Gkrekidis
- Serafeim MoustakidisSerafeim Moustakidis
- Evangelos KarakasisEKEvangelos Karakasis
- Erasmia GiannakouEGErasmia Giannakou
- Maria MichalopoulouMMMaria Michalopoulou
- Georgios Ch SirakoulisGSGeorgios Ch Sirakoulis
Open Access
- 22 February 2025
- journal article
- research article
- Published by MDPI AG in Journal of Functional Morphology and Kinesiology
- Vol. 10 (1) , 73
Abstract
Background/Objectives: Falls among the older adult population represent a significant public health concern, often leading to diminished quality of life and serious injuries that escalate healthcare costs, and they may even prove fatal. Accurate fall risk prediction is therefore crucial for implementing timely preventive measures. However, to date, there is no definitive metric to identify individuals with high risk of experiencing a fall. To address this, the present study proposes a novel approach that transforms biomechanical time-series data, derived from gait analysis, into visual representations to facilitate the application of deep learning (DL) methods for fall risk assessment. Methods: By leveraging convolutional neural networks (CNNs) and Siamese neural networks (SNNs), the proposed framework effectively addresses the challenges of limited datasets and delivers robust predictive capabilities. Results: Through the extraction of distinctive gait-related features and the generation of class-discriminative activation maps using Grad-CAM, the random forest (RF) machine learning (ML) model not only achieves commendable accuracy (83.29%) but also enhances explainability. Conclusions: Ultimately, this study underscores the potential of advanced computational tools and machine learning algorithms to improve fall risk prediction, reduce healthcare burdens, and promote greater independence and well-being among the older adults.Keywords
Funding Information
- Study, Design, Development and Implementation of a Holistic System for Upgrading the Quality of Life and Activity of the Elderly (MIS 5047294, NSRF 2014–2020)
- Operational Program “Competitiveness, Entrepreneurship and Innovation” (MIS 5047294, NSRF 2014–2020)
- Greece and the European Union (European Regional Development Fund) (MIS 5047294, NSRF 2014–2020)
This publication has 36 references indexed in Scilit:
- Automatic fall risk assessment with Siamese network for stroke survivors using inertial sensor‐based signalsInternational Journal of Intelligent Systems, 2022
- XGBoost based machine learning approach to predict the risk of fall in older adults using gait outcomesScientific Reports, 2021
- New horizons in falls prevention and management for older adults: a global initiativeAge and Ageing, 2021
- Center of pressure displacement characteristics differentiate fall risk in older people: A systematic review with meta-analysisAgeing Research Reviews, 2020
- Explaining the unique nature of individual gait patterns with deep learningScientific Reports, 2019
- Learning Efficient Spatial-Temporal Gait Features with Deep Learning for Human IdentificationNeuroinformatics, 2018
- Validity and reliability of the modified John Hopkins Fall Risk Assessment Tool for elderly patients in home health careGeriatric Nursing, 2013
- Support vector machine for classification of walking conditions of persons after stroke with dropped footHuman Movement Science, 2009
- Postural orientation and equilibrium: what do we need to know about neural control of balance to prevent falls?Age and Ageing, 2006
- Random ForestsMachine Learning, 2001