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

TL;DR

This paper introduces a realistic benchmarking framework for early deterioration prediction in emergency triage, evaluating model performance with limited initial assessment data.

Contribution

It presents a leakage-aware benchmarking framework and compares different models under constrained sensing conditions using MIMIC-IV-ED data.

Findings

Predictive performance declines modestly with vitals-only data.

Respiratory and oxygenation measures are key contributors to early risk prediction.

Models show stable performance even with reduced sensing information.

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.