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

TL;DR

This paper presents an interpretable, data-driven approach using constrained score optimization to improve inpatient fall risk assessment, outperforming traditional tools and maintaining robustness, thereby enhancing patient safety and resource allocation.

Contribution

The study introduces a novel constrained score optimization model that enhances fall risk prediction accuracy while preserving interpretability and robustness over existing methods.

Findings

CSO model achieves higher AUC-ROC (0.91) than JHFRAT (0.86)

CSO performs similarly with or without EHR variables

Black-box XGBoost model has higher AUC-ROC (0.94) but less robustness

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.