Advanced Cognitive Assessment Model for Predicting Fall Risks among Elderly Patients in Hospital Environments

The increasing incidence of falls among the elderly in hospital settings necessitates the development of advanced predictive models. This paper introduces a comprehensive cognitive assessment model designed to predict fall risks among elderly patients in hospital environments. By integrating cognitive assessment scores, patient demographics, and environmental factors, the model offers a holistic approach to fall risk prediction. Three distinct machine learning algorithms, namely Neural Network-based Fall Risk Prediction (NN-FRP), Support Vector Machine-based Fall Risk Prediction (SVM-FRP), and K-Nearest Neighbors-based Fall Risk Prediction (KNNFRP), are explored. The culmination of this research is the Ensemble-based Fall Risk Prediction (E-FRP), which synergistically combines the strengths of the three individual models. Preliminary results indicate that the ensemble model outperforms its constituent models in terms of accuracy and convergence time.