Enhancing the Early Detection of Chronic Kidney Disease: A Robust Machine Learning Model

Abstract

Clinical decision-making in chronic disorder prognosis is often hampered by high variance, leading to uncertainty and negative outcomes, especially in cases such as chronic kidney disease (CKD). Machine learning (ML) techniques have emerged as valuable tools for reducing randomness and enhancing clinical decision-making. However, conventional methods for CKD detection often lack accuracy due to their reliance on limited sets of biological attributes. This research proposes a novel ML model for predicting CKD, incorporating various preprocessing steps, feature selection, a hyperparameter optimization technique, and ML algorithms. To address challenges in medical datasets, we employ iterative imputation for missing values and a novel sequential approach for data scaling, combining robust scaling, z-standardization, and min-max scaling. Feature selection is performed using the Boruta algorithm, and the model is developed using ML algorithms. The proposed model was validated on the UCI CKD dataset, achieving outstanding performance with 100% accuracy. Our approach, combining innovative preprocessing steps, the Boruta feature selection, and the k-nearest neighbors algorithm, along with a hyperparameter optimization using grid-search cross-validation (CV), demonstrates its effectiveness in enhancing the early detection of CKD. This research highlights the potential of ML techniques in improving clinical support systems and reducing the impact of uncertainty in chronic disorder prognosis.

ML-CKDP: Machine learning-based chronic kidney disease prediction with smart web application

“…et al (2023) 6 80:20 DL with SVM 99.69 Arif M.S. et al (2023) 10 80:20 KNN 100 Poonia RC et al (2022) 11 80:20 LR 98.75 Pal S. (2022) 12 80:20 DT 97.23 K.M. Almustafa (2021) 13 K-Fold=10 J48 99.75 Ilyas et al (2021) 14 K-Fold=15 J48 85.5% Our study 70:30, 80:20, K-Fold=10, 15 RF, AdaB 100% …”

“…Arif M.S. et al (2023) 10 designed a machine learning model to predict CKD, incorporating advanced preprocessing, feature selection using the Boruta algorithm, and hyperparameter optimization. Their method involved iterative imputation for missing values and a novel sequential data scaling technique that included robust scaling, z-standardization, and min-max scaling.…”

“… Arif M.S. et al (2023) 10 1. Limited classifier variety (Naive Bayes and KNN) restricts performance exploration.…”

Comparative analysis of machine learning models for breast cancer prediction and diagnosis: a dual-dataset approach

“…A data point's class is determined by taking the majority class among its k closest neighbors, which are found using these distance measures [19]- [21].…”

Automated system for classifying uni-bicompartmental knee osteoarthritis by using redefined residual learning with convolutional neural network

“…The recent advances in artificial intelligence (AI) for healthcare have led to significant improvements and discoveries in orthopedics [ 16 ]. The efficiency of AI allows for quick processing of patient image data, which facilitates timely diagnosis and patient management [ 17 ]. Therefore, many researchers use AI to build computer-aided diagnosing tools to help physicians decrease time and effort while examining patients with knee OA symptoms, as many Radiographic and physicians suffer from the increasing workload in radiology and orthopedic departments [ 18 ].…”