Optimizing Clinical Fall Risk Prediction: A Data-Driven Integration of EHR Variables with the Johns Hopkins Fall Risk Assessment Tool

2025-10-23

AI Summary

To address insufficient predictive accuracy and poor clinical interpretability in inpatient fall risk assessment, this study proposes a Constraint-based Scoring Optimization (CSO) method that integrates domain knowledge with data-driven learning. Building upon the Johns Hopkins Fall Risk Assessment Tool (JHFRAT), the CSO framework incorporates clinically meaningful variables from electronic health records to construct an interpretable and robust risk prediction model. Unlike black-box models (e.g., XGBoost) and the original JHFRAT, CSO preserves the transparency and clinical intuitiveness of score-based decision-making while improving AUC-ROC from 0.86 to 0.91. The model demonstrates consistent performance across multi-level risk stratifications, confirming its stability and generalizability. This work delivers a clinically deployable tool that balances high predictive performance with decision transparency, thereby enabling precision fall prevention and optimized allocation of nursing resources.

Technology Category

• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

In this study we aim to better align fall risk prediction from the Johns Hopkins Fall Risk Assessment Tool (JHFRAT) with additional clinically meaningful measures via a data-driven modelling approach. We conducted a retrospective analysis of 54,209 inpatient admissions from three Johns Hopkins Health System hospitals between March 2022 and October 2023. A total of 20,208 admissions were included as high fall risk encounters, and 13,941 were included as low fall risk encounters. To incorporate clinical knowledge and maintain interpretability, we employed constrained score optimization (CSO) models on JHFRAT assessment data and additional electronic health record (EHR) variables. The model demonstrated significant improvements in predictive performance over the current JHFRAT (CSO AUC-ROC=0.91, JHFRAT AUC-ROC=0.86). The constrained score optimization models performed similarly with and without the EHR variables. Although the benchmark black-box model (XGBoost), improves upon the performance metrics of the knowledge-based constrained logistic regression (AUC-ROC=0.94), the CSO demonstrates more robustness to variations in risk labelling. This evidence-based approach provides a robust foundation for health systems to systematically enhance inpatient fall prevention protocols and patient safety using data-driven optimization techniques, contributing to improved risk assessment and resource allocation in healthcare settings.

Problem

• Enhancing fall risk prediction by integrating EHR variables with JHFRAT
• Improving predictive accuracy while maintaining model interpretability
• Developing robust fall prevention protocols through data-driven optimization

Innovation

• Integrating EHR variables with JHFRAT via data-driven modeling
• Employing constrained score optimization for interpretable risk prediction
• Enhancing fall risk assessment robustness with data-driven techniques