Computer-Aided Diagnosis of Chronic Kidney Disease in Developing Countries: A Comparative Analysis of Machine Learning Techniques

Abstract

The high incidence and prevalence of chronic kidney disease (CKD), often caused by late diagnoses, is a critical public health problem, especially in developing countries such as Brazil. CKD treatment therapies, such as dialysis and kidney transplantation, increase the morbidity and mortality rates, besides the public health costs. This study analyses the usage of machine learning techniques to assist in the early diagnosis of CKD in developing countries. Qualitative and quantitative comparative analyses are, respectively, conducted using a systematic literature review and an experiment with machine learning techniques, with the k-fold cross-validation method based on the Weka © software and a CKD dataset. These analyses enable a discussion on the suitability of machine learning techniques for screening for CKD risk, focusing on low-income and hard-to-reach settings of developing countries, due to the specific problems faced by them, e.g., inadequate primary health care. The study results show that the J48 decision tree is a suitable machine learning technique for such screening in developing countries, due to the easy interpretation of its classification results, with 95.00% accuracy, reaching a nearly perfect agreement with an experienced nephrologist's opinion. Conversely, random forest, naive Bayes, support vector machine, multilayer perceptron, and k-nearest neighbor techniques, respectively, yield 93.33%, 88.33%, 76.66%, 75.00%, and 71.67% accuracy, presenting at least moderate agreement with the nephrologist, at the cost of a more difficult interpretation of the classification results.