Early Prediction of Multi-Label Care Escalation Triggers in the Intensive Care Unit Using Electronic Health Records

2025-09-15

AI Summary

Conventional early warning systems (e.g., SOFA, MEWS) predict only a single adverse outcome and fail to capture the co-occurring, multidimensional physiological deterioration patterns characteristic of ICU patients. Method: We propose a multilabel classification framework that simultaneously forecasts four distinct clinical deterioration events—respiratory failure, hemodynamic instability, renal impairment, and neurologic deterioration—using the first 24 hours of electronic health record data upon ICU admission. Trained on 85,242 ICU admissions from MIMIC-IV, the model integrates aggregated vital signs, laboratory values, and demographic features, employing XGBoost for high interpretability and clinical transparency. Contribution/Results: Our model achieves F1-scores of 0.62–0.76 across all four tasks—significantly outperforming unilabel baselines—while identifying clinically meaningful feature importances aligned with established pathophysiological mechanisms. To our knowledge, this is the first multilabel, interpretable, and clinically deployable early warning system that requires neither temporal modeling nor natural language processing.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Intensive Care Unit (ICU) patients often present with complex, overlapping signs of physiological deterioration that require timely escalation of care. Traditional early warning systems, such as SOFA or MEWS, are limited by their focus on single outcomes and fail to capture the multi-dimensional nature of clinical decline. This study proposes a multi-label classification framework to predict Care Escalation Triggers (CETs), including respiratory failure, hemodynamic instability, renal compromise, and neurological deterioration, using the first 24 hours of ICU data. Using the MIMIC-IV database, CETs are defined through rule-based criteria applied to data from hours 24 to 72 (for example, oxygen saturation below 90, mean arterial pressure below 65 mmHg, creatinine increase greater than 0.3 mg/dL, or a drop in Glasgow Coma Scale score greater than 2). Features are extracted from the first 24 hours and include vital sign aggregates, laboratory values, and static demographics. We train and evaluate multiple classification models on a cohort of 85,242 ICU stays (80 percent training: 68,193; 20 percent testing: 17,049). Evaluation metrics include per-label precision, recall, F1-score, and Hamming loss. XGBoost, the best performing model, achieves F1-scores of 0.66 for respiratory, 0.72 for hemodynamic, 0.76 for renal, and 0.62 for neurologic deterioration, outperforming baseline models. Feature analysis shows that clinically relevant parameters such as respiratory rate, blood pressure, and creatinine are the most influential predictors, consistent with the clinical definitions of the CETs. The proposed framework demonstrates practical potential for early, interpretable clinical alerts without requiring complex time-series modeling or natural language processing.

Problem

• Predicting multiple care escalation triggers simultaneously in ICU patients
• Overcoming limitations of traditional single-outcome early warning systems
• Using first 24 hours of EHR data for early deterioration detection

Innovation

• Multi-label classification framework predicting multiple care escalation triggers
• Uses first 24 hours of ICU data with XGBoost as best-performing model
• Rule-based criteria define triggers from clinical parameters without complex modeling