Predicting ICU In-Hospital Mortality Using Adaptive Transformer Layer Fusion
This provides clinicians with a robust tool for risk stratification in critical-care settings, though it is incremental as it builds on existing transformer and adapter methods.
The paper tackled early identification of high-risk ICU patients by introducing ALFIA, an attention-based architecture that fuses multi-layer features from BERT, achieving state-of-the-art AUPRC on the cw-24 benchmark and enabling performance gains when paired with other models like GBDTs.
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.