Sepsis Prediction Using Graph Convolutional Networks over Patient-Feature-Value Triplets

TL;DR

This paper introduces Triplet-GCN, a graph convolutional model that encodes EHR data as patient-feature-value triplets, improving early sepsis detection by leveraging graph-based patient representations.

Contribution

The paper presents a novel triplet-based graph convolutional approach for EHR data, enhancing sepsis prediction accuracy over traditional tabular models.

Findings

Triplet-GCN outperforms baseline models in discrimination metrics.

The model achieves better sensitivity-specificity balance.

Graph-based patient representations improve early warning utility.

Abstract

In the intensive care setting, sepsis continues to be a major contributor to patient illness and death; however, its timely detection is hindered by the complex, sparse, and heterogeneous nature of electronic health record (EHR) data. We propose Triplet-GCN, a single-branch graph convolutional model that represents each encounter as patient-feature-value triplets, constructs a bipartite EHR graph, and learns patient embeddings via a Graph Convolutional Network (GCN) followed by a lightweight multilayer perceptron (MLP). The pipeline applies type-specific preprocessing -- median imputation and standardization for numeric variables, effect coding for binary features, and mode imputation with low-dimensional embeddings for rare categorical attributes -- and initializes patient nodes with summary statistics, while retaining measurement values on edges to preserve "who measured what and by how much". In a retrospective, multi-center Chinese cohort (N = 648; 70/30 train-test split) drawn from three tertiary hospitals, Triplet-GCN consistently outperforms strong tabular baselines (KNN, SVM, XGBoost, Random Forest) across discrimination and balanced error metrics, yielding a more favorable sensitivity-specificity trade-off and improved overall utility for early warning. These findings indicate that encoding EHR as triplets and propagating information over a patient-feature graph produce more informative patient representations than feature-independent models, offering a simple, end-to-end blueprint for deployable sepsis risk stratification.