Fusion of Graph and Tabular Deep Learning Models for Predicting Chronic Kidney Disease

Patike Kiran Rao; Subarna Chatterjee; K Nagaraju; Surbhi B Khan; Ahlam Almusharraf; Abdullah I Alharbi

doi:10.3390/diagnostics13121981

Fusion of Graph and Tabular Deep Learning Models for Predicting Chronic Kidney Disease

Diagnostics (Basel). 2023 Jun 6;13(12):1981. doi: 10.3390/diagnostics13121981.

Authors

Patike Kiran Rao¹, Subarna Chatterjee¹, K Nagaraju², Surbhi B Khan³, Ahlam Almusharraf⁴, Abdullah I Alharbi⁵

Affiliations

¹ Department of Computer Science and Engineering, Faculty of Engineering, MS Ramaiah University of Applied Sciences, Bengaluru 560054, Karnataka, India.
² Department of Computer Science and Engineering, Indian Institute of Information Technology Design and Manufacturing, Kurnool 518008, Andhra Pradesh, India.
³ Department of Data Science, School of Science, Engineering and Environment, University of Salford, Manchester M5 4WT, UK.
⁴ Department of Business Administration, College of Business and Administration, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia.
⁵ Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Rabigh 21911, Saudi Arabia.

Abstract

Chronic Kidney Disease (CKD) represents a considerable global health challenge, emphasizing the need for precise and prompt prediction of disease progression to enable early intervention and enhance patient outcomes. As per this study, we introduce an innovative fusion deep learning model that combines a Graph Neural Network (GNN) and a tabular data model for predicting CKD progression by capitalizing on the strengths of both graph-structured and tabular data representations. The GNN model processes graph-structured data, uncovering intricate relationships between patients and their medical conditions, while the tabular data model adeptly manages patient-specific features within a conventional data format. An extensive comparison of the fusion model, GNN model, tabular data model, and a baseline model was conducted utilizing various evaluation metrics, encompassing accuracy, precision, recall, and F1-score. The fusion model exhibited outstanding performance across all metrics, underlining its augmented capacity for predicting CKD progression. The GNN model's performance closely trailed the fusion model, accentuating the advantages of integrating graph-structured data into the prediction process. Hyperparameter optimization was performed using grid search, ensuring a fair comparison among the models. The fusion model displayed consistent performance across diverse data splits, demonstrating its adaptability to dataset variations and resilience against noise and outliers. In conclusion, the proposed fusion deep learning model, which amalgamates the capabilities of both the GNN model and the tabular data model, substantially surpasses the individual models and the baseline model in predicting CKD progression. This pioneering approach provides a more precise and dependable method for early detection and management of CKD, highlighting its potential to advance the domain of precision medicine and elevate patient care.

Keywords: CKD; GNN; chronic kidney disease; deep learning; graph neural network model; healthcare; prediction; tabular data model.

Grants and funding

This research is supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number (PNURSP2023R432), Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.