TA-RNN-Medical-Hybrid: A Time-Aware and Interpretable Framework for Mortality Risk Prediction

TL;DR

This paper introduces TA-RNN-Medical-Hybrid, a deep learning framework that models irregular clinical data over time to predict mortality risk in ICUs, providing both high accuracy and interpretability grounded in medical knowledge.

Contribution

It presents a novel time-aware, knowledge-enriched RNN model with hierarchical attention for mortality prediction that offers transparent, clinically meaningful explanations.

Findings

Improves predictive performance over baselines in AUC, accuracy, and F2-score.

Provides interpretable insights into disease progression and risk factors.

Effectively decomposes mortality risk across time and clinical concepts.

Abstract

Accurate and interpretable mortality risk prediction in intensive care units (ICUs) remains a critical challenge due to the irregular temporal structure of electronic health records (EHRs), the complexity of longitudinal disease trajectories, and the lack of clinically grounded explanations in many data-driven models. To address these challenges, we propose \textit{TA-RNN-Medical-Hybrid}, a time-aware and knowledge-enriched deep learning framework that jointly models longitudinal clinical sequences and irregular temporal dynamics through explicit continuous-time encoding, along with standardized medical concept representations. The proposed framework extends time-aware recurrent modeling by integrating explicit continuous-time embeddings that operate independently of visit indexing, SNOMED-based disease representations, and a hierarchical dual-level attention mechanism that captures both visit-level temporal importance and feature/concept-level clinical relevance. This design enables accurate mortality risk estimation while providing transparent and clinically meaningful explanations aligned with established medical knowledge. We evaluate the proposed approach on the MIMIC-III critical care dataset and compare it against strong time-aware and sequential baselines. Experimental results demonstrate that TA-RNN-Medical-Hybrid consistently improves predictive performance in terms of AUC, accuracy, and recall-oriented F$_2$-score. Moreover, qualitative analysis shows that the model effectively decomposes mortality risk across time and clinical concepts, yielding interpretable insights into disease severity, chronicity, and temporal progression. Overall, the proposed framework bridges the gap between predictive accuracy and clinical interpretability, offering a scalable and transparent solution for high-stakes ICU decision support systems.