# Interpretable Adaptive Graph Fusion Network for Mortality and Complication Prediction in ICUs

## TL;DR

This paper presents a new interpretable machine learning model that improves prediction of ICU patient outcomes by combining adaptive graphs and multi-horizon temporal analysis.

## Contribution

The novel Adaptive Graph Fusion Network dynamically constructs patient similarity graphs and integrates short- and long-term temporal patterns for ICU outcome prediction.

## Key findings

- The model achieved a mean AUC of 0.91 across six critical ICU outcomes.
- In-hospital mortality prediction reached an AUC of 0.96, outperforming existing models.
- Key clinical factors like lactate levels, creatinine, and vasopressor use were identified as major risk determinants.

## Abstract

Background: This study introduces the Adaptive Graph Fusion Network, an interpretable graph-based learning framework developed for large-scale prediction of intensive care outcomes. The proposed model dynamically constructs patient similarity networks through a density-aware kernel that adjusts neighborhood size based on local data distribution, thereby representing both frequent and rare clinical patterns. Methods: To characterize physiological evolution over time, the framework integrates a short-horizon convolutional encoder that captures acute variations in vital signs and laboratory results with a long-horizon recurrent memory unit that models gradual temporal trends. The approach was trained and internally validated on the publicly available eICU Collaborative Research Database, which includes more than 200,000 admissions from 208 hospitals across the United States. Results: The model achieved a mean area under the receiver operating characteristic curve of 0.91 across six critical outcomes, with in-hospital mortality reaching 0.96, outperforming logistic regression, temporal long short-term memory networks, and calibrated Transformer-based architectures. Feature attribution analysis using SHAP and temporal contribution mapping identified lactate trajectories, creatinine fluctuations, and vasopressor administration as dominant determinants of risk, consistent with established clinical understanding while revealing additional temporal dependencies overlooked by existing scoring systems. Conclusions: These findings demonstrate that adaptive graph construction combined with multi-horizon temporal reasoning improves predictive reliability and interpretability in heterogeneous intensive care populations, offering a transparent and reproducible foundation for future research in clinical machine learning.