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

被引:27
作者
Arif, Muhammad Shoaib [1 ,2 ]
Mukheimer, Aiman [1 ]
Asif, Daniyal [3 ]
机构
[1] Prince Sultan Univ, Coll Humanities & Sci, Dept Math & Sci, Riyadh 11586, Saudi Arabia
[2] Air Univ, Dept Math, PAF Complex E9, Islamabad 44000, Pakistan
[3] COMSATS Univ Islamabad, Dept Math, Pk Rd, Islamabad 45550, Pakistan
关键词
chronic kidney disease; machine learning; artificial intelligence; data science; healthcare; bioinformatics; big data; PREDICTION;
D O I
10.3390/bdcc7030144
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页数:16
相关论文
共 46 条
[11]   Established and Emerging Markers of Kidney Function [J].
Ferguson, Michael A. ;
Waikar, Sushrut S. .
CLINICAL CHEMISTRY, 2012, 58 (04) :680-689
[12]  
Garcia S., 2015, CA Cancer J. Clin, V72, P59
[13]   Diabetes and end-stage renal disease; a review article on new concepts [J].
Ghaderian, Seyed Bahman ;
Hayati, Fatemeh ;
Shayanpour, Shokouh ;
Mousavi, Seyed Seifollah Beladi .
JOURNAL OF RENAL INJURY PREVENTION, 2015, 4 (02) :28-33
[14]   IoT for Smart Cities: Machine Learning Approaches in Smart Healthcare-A Review [J].
Ghazal, Taher M. ;
Hasan, Mohammad Kamrul ;
Alshurideh, Muhammad Turki ;
Alzoubi, Haitham M. ;
Ahmad, Munir ;
Akbar, Syed Shehryar ;
Al Kurdi, Barween ;
Akour, Iman A. .
FUTURE INTERNET, 2021, 13 (08)
[15]   Obesity, hypertension, and chronic kidney disease [J].
Hall, Michael E. ;
do Carmo, Jussara M. ;
da Silva, Alexandre A. ;
Juncos, Luis A. ;
Wang, Zhen ;
Hall, John E. .
INTERNATIONAL JOURNAL OF NEPHROLOGY AND RENOVASCULAR DISEASE, 2014, 7 :75-88
[16]   A Comparative Study, Prediction and Development of Chronic Kidney Disease Using Machine Learning on Patients Clinical Records [J].
Md. Mehedi Hassan ;
Md. Mahedi Hassan ;
Swarnali Mollick ;
Md. Asif Rakib Khan ;
Farhana Yasmin ;
Anupam Kumar Bairagi ;
M. Raihan ;
Shibbir Ahmed Arif ;
Amrina Rahman .
Human-Centric Intelligent Systems, 2023, 3 (2) :92-104
[17]  
Hoque G., 2021, Data Sci
[18]   Global epidemiology and outcomes of acute kidney injury [J].
Hoste, Eric A. J. ;
Kellum, John A. ;
Selby, Nicholas M. ;
Zarbock, Alexander ;
Palevsky, Paul M. ;
Bagshaw, Sean M. ;
Goldstein, Stuart L. ;
Cerda, Jorge ;
Chawla, Lakhmir S. .
NATURE REVIEWS NEPHROLOGY, 2018, 14 (10) :607-625
[19]  
Ibrahim I., 2021, J. Appl. Sci. Technol. Trends, V2, P10, DOI [10.38094/jastt20179, DOI 10.38094/JASTT20179]
[20]  
Islam Md Ariful, 2023, J Pathol Inform, V14, P100189, DOI 10.1016/j.jpi.2023.100189