Leveraging graph neural networks for supporting Automatic Triage of Patients

TL;DR

The paper tackles automatic triage in emergency departments by constructing a patient similarity graph from historical records and applying Graph Neural Networks to perform inductive node classification into triage levels $y \in \{Red, Orange, Yellow, Green\}$. It systematically compares graph-building strategies using cosine, Euclidean, Manhattan, and Minkowski distances and evaluates three GNNs (GCN, GAT, GraphSAGE), finding that GraphSAGE on cosine-based graphs with a threshold of $0.95$ delivers strong performance surpassing traditional triage and tabular baselines. The approach demonstrates the value of explicit similarity modeling and inductive graph learning for accurate, scalable triage with potential improvements in ED throughput and patient outcomes. The work provides data and code for reproducibility and highlights practical implications for deploying graph-based triage in diverse clinical settings.

Abstract

Patient triage plays a crucial role in emergency departments, ensuring timely and appropriate care based on correctly evaluating the emergency grade of patient conditions. Triage methods are generally performed by human operator based on her own experience and information that are gathered from the patient management process. Thus, it is a process that can generate errors in emergency level associations. Recently, Traditional triage methods heavily rely on human decisions, which can be subjective and prone to errors. Recently, a growing interest has been focused on leveraging artificial intelligence (AI) to develop algorithms able to maximize information gathering and minimize errors in patient triage processing. We define and implement an AI based module to manage patients emergency code assignments in emergency departments. It uses emergency department historical data to train the medical decision process. Data containing relevant patient information, such as vital signs, symptoms, and medical history, are used to accurately classify patients into triage categories. Experimental results demonstrate that the proposed algorithm achieved high accuracy outperforming traditional triage methods. By using the proposed method we claim that healthcare professionals can predict severity index to guide patient management processing and resource allocation.

Figures (10)

• Figure 1: Figure compares automatic vs traditional triage systems. In the traditional triage system, patients go to the Emergency Departments for admission. A set of vital signs and biochemical parameters are evaluated and an emergency code is assigned. In the scenario, we envision patient data from previous admissions are used initially to build a network representing similarity among patients. The network is then used to learn a Graph Neural Network to classify patients in a latent space (the assignment of the severity index is translated into a multiclass classification problem). Finally, each patient who enters the emergency room is automatically classified after the acquisition of clinical data.
• Figure 2: Patient data are used to build a network representing patient similarity. Each node has a previous severity index codified as a node label. The network is then used to learn a Graph Neural Network to classify patients. Therefore, the assignment of the severity index is translated into a multiclass node classification problem. A new patient requiring admission to ED is a node of the graph without a label, and the learned model is used to derive the correct label.
• Figure 3: The Architecture of the System.
• Figure 4: The Figure represents the experiments we performed to test the approach. The input dataset is converted into a network using cosine similarity, Euclidean, Manhattan, and Minkowski Distances. For each measure, we generated a set of networks using different thresholds. Then each single network is used to learn a classifier and finally results are evaluated.
• Figure 5: Figure reports the Preprocessing workflow.