Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

APC-GNN++: An Adaptive Patient-Centric GNN with Context-Aware Attention and Mini-Graph Explainability for Diabetes Classification

Khaled Berkani

TL;DR

APC-GNN++ introduces an adaptive, patient-centric GNN for diabetes classification that combines context-aware edge attention, confidence-guided feature blending, and neighborhood consistency regularization to exploit inter-patient relationships. It adds mini-graph explainability for unseen patients, enabling real-time, localized predictions without retraining the global model, and is deployed through a Tkinter GUI for clinicians. On a real-world Algeria dataset (N=540), it surpasses MLP, RF, XGBoost, and vanilla GCN in accuracy and macro F1, with strong per-class AUC, while providing interpretable insights via node-level confidence scores. The work highlights practical clinical impact by balancing graph-derived evidence with self-features and offering interpretable, patient-specific decision support.

Abstract

We propose APC-GNN++, an adaptive patient-centric Graph Neural Network for diabetes classification. Our model integrates context-aware edge attention, confidence-guided blending of node features and graph representations, and neighborhood consistency regularization to better capture clinically meaningful relationships between patients. To handle unseen patients, we introduce a mini-graph approach that leverages the nearest neighbors of the new patient, enabling real-time explainable predictions without retraining the global model. We evaluate APC-GNN++ on a real-world diabetes dataset collected from a regional hospital in Algeria and show that it outperforms traditional machine learning models (MLP, Random Forest, XGBoost) and a vanilla GCN, achieving higher test accuracy and macro F1- score. The analysis of node-level confidence scores further reveals how the model balances self-information and graph-based evidence across different patient groups, providing interpretable patient-centric insights. The system is also embedded in a Tkinter-based graphical user interface (GUI) for interactive use by healthcare professionals .

APC-GNN++: An Adaptive Patient-Centric GNN with Context-Aware Attention and Mini-Graph Explainability for Diabetes Classification

TL;DR

APC-GNN++ introduces an adaptive, patient-centric GNN for diabetes classification that combines context-aware edge attention, confidence-guided feature blending, and neighborhood consistency regularization to exploit inter-patient relationships. It adds mini-graph explainability for unseen patients, enabling real-time, localized predictions without retraining the global model, and is deployed through a Tkinter GUI for clinicians. On a real-world Algeria dataset (N=540), it surpasses MLP, RF, XGBoost, and vanilla GCN in accuracy and macro F1, with strong per-class AUC, while providing interpretable insights via node-level confidence scores. The work highlights practical clinical impact by balancing graph-derived evidence with self-features and offering interpretable, patient-specific decision support.

Abstract

We propose APC-GNN++, an adaptive patient-centric Graph Neural Network for diabetes classification. Our model integrates context-aware edge attention, confidence-guided blending of node features and graph representations, and neighborhood consistency regularization to better capture clinically meaningful relationships between patients. To handle unseen patients, we introduce a mini-graph approach that leverages the nearest neighbors of the new patient, enabling real-time explainable predictions without retraining the global model. We evaluate APC-GNN++ on a real-world diabetes dataset collected from a regional hospital in Algeria and show that it outperforms traditional machine learning models (MLP, Random Forest, XGBoost) and a vanilla GCN, achieving higher test accuracy and macro F1- score. The analysis of node-level confidence scores further reveals how the model balances self-information and graph-based evidence across different patient groups, providing interpretable patient-centric insights. The system is also embedded in a Tkinter-based graphical user interface (GUI) for interactive use by healthcare professionals .

Paper Structure

This paper contains 21 sections, 9 equations, 2 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Context-Aware Edge Convolution
  5. Confidence-Guided Feature Blending
  6. Interpretation of the confidence score.
  7. Adaptive k-NN Graph Construction
  8. Neighborhood Consistency Regularization
  9. Mini-Graph Construction for New Patients
  10. Implementation Details
  11. Experiments and Evaluation
  12. Dataset and Preprocessing
  13. Baselines
  14. Evaluation Metrics
  15. Implementation Details
  16. ...and 6 more sections

Figures (2)

  • Figure 1: Confusion matrix for APC-GNN++ on the test set (classes ordered as Type 1, Type 2, Gestational).
  • Figure 2: One-vs-rest ROC curves for APC-GNN++ across the three diabetes types