Predicting ICU In-Hospital Mortality Using Adaptive Transformer Layer Fusion

TL;DR

ALFIA is an attention-based model that fuses multi-layer features from BERT to predict ICU mortality, outperforming existing classifiers and aiding clinical decision-making.

Contribution

Introduces ALFIA, a novel adaptive layer fusion architecture with attention, trained on a new benchmark, enhancing ICU mortality prediction from clinical text.

Findings

ALFIA surpasses state-of-the-art classifiers in AUPRC.

Fusion embeddings improve performance across models.

ALFIA demonstrates superior early-warning capabilities.

Abstract

Early identification of high-risk ICU patients is crucial for directing limited medical resources. We introduce ALFIA (Adaptive Layer Fusion with Intelligent Attention), a modular, attention-based architecture that jointly trains LoRA (Low-Rank Adaptation) adapters and an adaptive layer-weighting mechanism to fuse multi-layer semantic features from a BERT backbone. Trained on our rigorous cw-24 (CriticalWindow-24) benchmark, ALFIA surpasses state-of-the-art tabular classifiers in AUPRC while preserving a balanced precision-recall profile. The embeddings produced by ALFIA's fusion module, capturing both fine-grained clinical cues and high-level concepts, enable seamless pairing with GBDTs (CatBoost/LightGBM) as ALFIA-boost, and deep neuro networks as ALFIA-nn, yielding additional performance gains. Our experiments confirm ALFIA's superior early-warning performance, by operating directly on routine clinical text, it furnishes clinicians with a convenient yet robust tool for risk stratification and timely intervention in critical-care settings.