An interpretable data-driven approach to optimizing clinical fall risk assessment

2026-01-08

AI Summary

This study addresses the misalignment between the existing Johns Hopkins Fall Risk Assessment Tool (JHFRAT) and clinical labels in predicting inpatient fall risk, which undermines intervention efficacy. To resolve this, the authors propose a Constrained Score Optimization (CSO) model that data-drivenly recalibrates JHFRAT’s scoring weights while preserving its additive structure and clinically established thresholds. Evaluated on a retrospective cohort derived from electronic health records, the CSO model achieves an AUC-ROC of 0.91—significantly outperforming the original JHFRAT (AUC-ROC: 0.86)—and identifies 35 additional high-risk patients per week. The model demonstrates robust performance across varying risk labeling schemes and maintains both interpretability and compatibility with clinical workflows.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Optimization
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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 cohort 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 to reweight the JHFRAT scoring weights, while preserving its additive structure and clinical thresholds. Recalibration refers to adjusting item weights so that the resulting score can order encounters more consistently by the study's risk labels, and without changing the tool's form factor or deployment workflow. The model demonstrated significant improvements in predictive performance over the current JHFRAT (CSO AUC-ROC=0.91, JHFRAT AUC-ROC=0.86). This performance improvement translates to protecting an additional 35 high-risk patients per week across the Johns Hopkins Health System. 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 labeling. 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

• fall risk assessment
• clinical prediction
• interpretable modeling
• inpatient safety
• risk stratification

Innovation

• Constrained Score Optimization
• Interpretable Machine Learning
• Fall Risk Assessment
• Clinical Decision Support
• Data-driven Recalibration