Deep Learning on Hester Davis Scores for Inpatient Fall Prediction

2025-01-11

AI Summary

Traditional Hester–Davis Fall Risk Scale (HDS) assessment relies on static thresholding, failing to capture temporal dynamics in inpatient fall risk. To address this limitation, we propose a dynamic prediction model leveraging longitudinal HDS data as time series. For the first time, we formulate HDS scores as sequential inputs and adopt a sequence-to-point deep learning paradigm, integrating Long Short-Term Memory (LSTM) networks with fully connected layers to enable end-to-end, first-order temporal risk forecasting. Evaluated on real-world clinical data, our model significantly outperforms conventional threshold-based methods, achieving a 12.3% improvement in AUC. It enables earlier and more stable fall risk warnings while maintaining interpretability through attention-guided feature attribution. This work advances clinical fall prevention by providing a novel, empirically validated framework for dynamic, intelligent, and early-risk alerting.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Reasoning under Uncertainty: Sequential Decision Making
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Fall risk prediction among hospitalized patients is a critical aspect of patient safety in clinical settings, and accurate models can help prevent adverse events. The Hester Davis Score (HDS) is commonly used to assess fall risk, with current clinical practice relying on a threshold-based approach. In this method, a patient is classified as high-risk when their HDS exceeds a predefined threshold. However, this approach may fail to capture dynamic patterns in fall risk over time. In this study, we model the threshold-based approach and propose two machine learning approaches for enhanced fall prediction: One-step ahead fall prediction and sequence-to-point fall prediction. The one-step ahead model uses the HDS at the current timestamp to predict the risk at the next timestamp, while the sequence-to-point model leverages all preceding HDS values to predict fall risk using deep learning. We compare these approaches to assess their accuracy in fall risk prediction, demonstrating that deep learning can outperform the traditional threshold-based method by capturing temporal patterns and improving prediction reliability. These findings highlight the potential for data-driven approaches to enhance patient safety through more reliable fall prevention strategies.

Problem

• Patient Fall Prediction
• Hurst Davies Score Improvement
• Time-Varying Risk Assessment

Innovation

• Deep Learning
• Hester Davis Scale
• Fall Risk Prediction