Related Experiment Video
Updated: May 17, 2026
08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
A dynamic Bayesian network for estimating the risk of falls from real gait data
German Cuaya1, Angélica Muñoz-Meléndez, Lidia Nuñez Carrera
1Computer Science Department, Instituto Nacional de Astrofsica ptica y Elctronia, Tonantzintla, PUE, Mexico. germancs@inaoep.mx
Medical & Biological Engineering & Computing
|October 16, 2012
Summary
Dynamic Bayesian networks can predict fall risk in elderly individuals using gait analysis. A computational model achieved 72.22% accuracy in predicting falls within six months, offering promising results for fall prevention strategies.
Area of Science:
- Gerontology
- Biomedical Engineering
- Data Science
Background:
- Falls are a significant risk for elderly individuals, leading to severe injuries and mortality.
- Gait analysis offers a potential method for assessing fall risk.
- Understanding longitudinal gait changes is crucial for accurate fall risk estimation.
Purpose of the Study:
- To develop and evaluate dynamic Bayesian network (DBN) models for predicting fall risk in the elderly based on gait parameters.
- To compare an expert-guided DBN model with a computationally derived DBN model.
Main Methods:
- Two DBN models were constructed using gait-derived variables.
- DBN1 was guided by domain experts.
- DBN2 utilized a feature selection algorithm for variable selection.
Main Results:
- The computationally derived DBN model (DBN2) demonstrated effectiveness in predicting falls.
- DBN2 achieved a prediction accuracy of 72.22% for falls within a 6-month period.
- The results indicate the utility of probabilistic models in pathological gait analysis.
Conclusions:
- Dynamic probabilistic models, specifically DBNs, are valuable tools for predicting fall risk in the elderly.
- Computational approaches to variable selection can enhance the predictive power of DBNs for fall risk assessment.
- This study supports the use of gait analysis and DBNs for proactive fall prevention in aging populations.
