Smart Diagnosis: Hybrid Ensemble Learning For Early Detection of Chronic Kidney Disease Using Clinical Data
Download| Volume 7 Issue 1, 2026 | |
|---|---|
| Author(s): |
Sana Batool Riphah International University, Faisalabad, sanabatoolofficial7@gmail.com Shahnawaz Sheikh Riphah International University, Faisalabad, sheikhshahnwaz154@gmail.com Muhammad Ovais Akhter* Bahria University Karachi Campus, ovaisakhter.bukc@bahria.edu.pk Shakir Karim Buksh Bahria University Karachi Campus, shakirkarim.bukc@bahria.edu.pk Abdullah Ayub Khan Bahria University Karachi Campus, abdullahayub.bukc@bahria.edu.pk Muhammad Zohaib Khan Shaheed Mohtarma Benazir Bhutto Institute of Trauma, Karachi, zohaib_khan2017@yahoo.com |
| Abstract | Chronic Kidney Disease (CKD) is a progressive and life-threatening condition that affects millions of people worldwide and is often diagnosed at advanced stages due to the absence of noticeable early symptoms. Early and accurate detection is essential to delay disease progression, reduce complications, and improve patient outcomes. This paper proposes a smart hybrid machine learning framework for the early prediction of CKD using clinical data. The proposed approach integrates Agglomerative Hierarchical Clustering (AHC), Synthetic Minority Over-sampling Technique (SMOTE), Stacking Ensemble Classification (SEC), and Logistic Regression (LR) to address class imbalance and enhance prediction performance. Several machine learning classifiers, including K-Nearest Neighbors (K-NN), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Quadratic Discriminant Analysis (QDA), and Decision Tree (DT), are incorporated into the hybrid framework and comparatively evaluated. Experimental results demonstrate that the proposed hybrid models consistently outperform individual classifiers, with the AHC–SEC-LR–K-NN model achieving the highest classification accuracy of 97.59%, followed by AHC–SEC-LR–MLP (96.39%) and AHC–SEC-LR–SVM (95.90%). The findings indicate that the proposed framework provides a reliable and effective decision-support tool for the early diagnosis of CKD and has significant potential for integration into intelligent healthcare and telemedicine systems to support timely clinical decision-making. |
| Keywords | chronic kidney disease prediction, ensemble machine learning, logistic regression, stacking ensemble classifier, agglomerative hierarchical clustering, support vector machine, decision tree. |
| Year | 2026 |
| Volume | 7 |
| Issue | 1 |
| Type | Research paper, manuscript, article |
| Recognized by | Higher Education Commission of Pakistan, HEC | Category | Journal Name | ILMA Journal of Technology & Software Management | Publisher Name | ILMA University | Jel Classification | -- | DOI | - | ISSN no (E, Electronic) | 2790-590X | ISSN no (P, Print) | 2709-2240 | Country | Pakistan | City | Karachi | Institution Type | University | Journal Type | Open Access | Manuscript Processing | Blind Peer Reviewed | Format | Paper Link | https://ijtsm.ilmauniversity.edu.pk/arc/Vol7/i1/pdf2.pdf | Page | 9-24 |