Benchmarking Early Deterioration Prediction Across Hospital-Rich and MCI-Like Emergency Triage Under Constrained Sensing

2026-02-09

arXiv.org

AI Summary

This study addresses the challenge of early clinical deterioration prediction in emergency triage, where decisions are often made under severe information constraints. While existing models frequently rely on data unavailable at initial presentation, this work establishes a leakage-proof benchmark framework using the deduplicated MIMIC-IV-ED cohort, strictly limiting features to those obtainable within the first hour of arrival. Through systematic evaluation across multiple models, structured ablation studies, and interpretability analyses, the authors demonstrate—for the first time under both temporal and data-availability constraints—that vital signs alone retain strong predictive signal for deterioration, with only marginal performance loss compared to models using full hospital data. Respiratory and oxygenation parameters emerge as key predictors, offering a robust, deployable baseline for triage decision support in resource-limited settings.

Abstract

Emergency triage decisions are made under severe information constraints, yet most data-driven deterioration models are evaluated using signals unavailable during initial assessment. We present a leakage-aware benchmarking framework for early deterioration prediction that evaluates model performance under realistic, time-limited sensing conditions. Using a patient-deduplicated cohort derived from MIMIC-IV-ED, we compare hospital-rich triage with a vitals-only, MCI-like setting, restricting inputs to information available within the first hour of presentation. Across multiple modeling approaches, predictive performance declines only modestly when limited to vitals, indicating that early physiological measurements retain substantial clinical signal. Structured ablation and interpretability analyses identify respiratory and oxygenation measures as the most influential contributors to early risk stratification, with models exhibiting stable, graceful degradation as sensing is reduced. This work provides a clinically grounded benchmark to support the evaluation and design of deployable triage decision-support systems in resource-constrained settings.

Problem

• emergency triage
• early deterioration prediction
• constrained sensing
• information leakage
• benchmarking

Innovation

• leakage-aware benchmarking
• early deterioration prediction
• constrained sensing
• emergency triage
• vitals-only modeling