Early diagnosis of end-stage renal disease risk in type 2 diabetes mellitus using advanced analysis of clinical laboratory data

Authors: Raafat M. Munshi ^{1, 2,} *, Othman Y. Alyahyawy ², Lammar R. Munshi ³, Shashi Kant Gupta ^{1, 4}

Affiliations:

¹Department of Computer Science and Engineering, Lincoln University College, Petaling Jaya, Malaysia
²Department of Medical Laboratory Technology (MLT), Faculty of Applied Medical Sciences, King Abdulaziz University, Jeddah, Saudi Arabia
³Faculty of Medicine, King Abdulaziz University, Jeddah, Saudi Arabia
⁴Center for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab 140401, India

Abstract

End-stage renal disease (ESRD) is a serious complication of Type 2 Diabetes Mellitus (T2DM) and has a significant negative effect on patient health. Early and accurate detection is essential but difficult to achieve in clinical settings. This study introduces an Optimized Grey Wolf Convolutional Decision Tree (OGW-ConvDT) classifier to predict the risk of ESRD by combining advanced machine learning techniques with clinical laboratory data. The model uses Z-score standardization for data normalization, Principal Component Analysis (PCA) to reduce data dimensions, and the SelectKBest method for selecting the most important features. A Convolutional Neural Network (CNN) is used to extract spatial features, and a Decision Tree (DT), optimized using the Grey Wolf (GW) algorithm, performs the final classification. The proposed method was tested on a publicly available dataset from Kaggle and achieved strong performance: precision (0.996), F1-score (0.996), recall (0.997), accuracy (0.997), AUC (0.999), specificity (0.959), log loss (0.009), and AUC-PRC (0.824). These results show that the OGW-ConvDT model performs better than traditional methods and provides an effective and reliable tool for early ESRD risk detection in T2DM patients.

Keywords

End-stage renal disease, Type 2 diabetes, Risk prediction, Machine learning, Decision tree

Download

📄 Full PDF

DOI

https://doi.org/10.21833/ijaas.2026.01.002

Citation (APA)

Munshi, R. M., Alyahyawy, O. Y., Munshi, L. R., & Gupta, S. K. (2026). Early diagnosis of end-stage renal disease risk in type 2 diabetes mellitus using advanced analysis of clinical laboratory data. International Journal of Advanced and Applied Sciences, 13(1), 13–26. https://doi.org/10.21833/ijaas.2026.01.002