ExplainabilityTransparencyTrustworthinesscs.AI
Improving Chronic Kidney Disease Detection Efficiency: Fine Tuned CatBoost and Nature-Inspired Algorithms with Explainable AI
Md. Ehsanul Haque, S. M. Jahidul Islam, Jeba Maliha, Md. Shakhauat Hossan Sumon, Rumana Sharmin, Sakib Rokoni
April 5, 2025
International Conference on Communication Systems and Network Technologies
23 citations
3 influential
Key Takeaways
-
High accuracy AI can support early CKD detection in resource-limited settings: The study achieved 98.75% accuracy using a fine-tuned CatBoost model, suggesting machine learning could help identify kidney disease earlier in areas where traditional diagnostic methods are unavailable or expensive.
-
Explainability is essential for clinical trust: The researchers used SHAP (a transparency technique) to identify which clinical factors the AI model relied on—specifically gravity, serum creatinine, albumin, hemoglobin, and diabetes status—demonstrating that responsible AI in healthcare requires showing why a model makes predictions, not just that it works.
-
Multiple optimization techniques improve reliability: The model combined nature-inspired algorithms (Simulated Annealing, Cuckoo Search) with traditional methods to select important features and handle data quality issues, illustrating that responsible AI development requires careful engineering to ensure models are robust and trustworthy.
-
AI should complement, not replace, clinical judgment: By identifying the specific clinical features the model prioritizes, this approach enables doctors to understand and verify the AI's reasoning, supporting human-centered decision-making rather than blind automation in medical diagnosis.
Abstract
Chronic Kidney Disease (CKD) is a major global health issue which is affecting million people around the world and with increasing rate of mortality. Mitigation of progression of CKD and better patient outcomes requires early detection. Nevertheless, limitations lie in traditional diagnostic methods, especially in resource constrained settings. This study proposes an advanced machine learning approach to enhance CKD detection by evaluating four models: Random Forest (RF), Multi-Layer Perceptron (MLP), Logistic Regression (LR), and a fine-tuned CatBoost algorithm. Specifically, among these, the fine-tuned CatBoost model demonstrated the best overall performance having an accuracy of 98.75%, an AUC of 0.9993 and a Kappa score of 97.35% of the studies. The proposed CatBoost model has used a nature inspired algorithm such as Simulated Annealing to select the most important features, Cuckoo Search to adjust outliers and grid search to fine tune its settings in such a way to achieve improved prediction accuracy. Features significance is explained by SHAP-a well-known XAI technique-for gaining transparency in the decision-making process of proposed model and bring up trust in diagnostic systems. Using SHAP, the significant clinical features were identified as specific gravity, serum creatinine, albumin, hemoglobin, and diabetes mellitus. The potential of advanced machine learning techniques in CKD detection is shown in this research, particularly for low income and middle-income healthcare settings where prompt and correct diagnoses are vital. This study seeks to provide a highly accurate, interpretable, and efficient diagnostic tool to add to efforts for early intervention and improved healthcare outcomes for all CKD patients.