Open AccessComparison of Neural Network and Machine Learning Approaches in Prediction of Chronic Kidney Disease
Author(s) -
Shreya Nag,
Nimitha Jammula
Publication year - 2021
Publication title -
journal of student research
Language(s) - English
Resource type - Journals
ISSN - 2167-1907
DOI - 10.47611/jsrhs.v10i3.1570
Subject(s) - machine learning , flexibility (engineering) , artificial intelligence , computer science , artificial neural network , decision tree , kidney disease , supervised learning , random forest , health care , clinical decision support system , set (abstract data type) , decision support system , medicine , statistics , mathematics , economics , programming language , economic growth
The diagnosis of a disease to determine a specific condition is crucial in caring for patients and furthering medical research. The timely and accurate diagnosis can have important implications for both patients and healthcare providers. An earlier diagnosis allows doctors to consider more methods of treatment, allowing them to have a greater flexibility of tailoring their decisions, and ultimately improving the patient’s health. Additionally, a timely detection allows patients to have a greater control over their health and their decisions, allowing them to plan ahead. As advancements in computer science and technology continue to improve, these two factors can play a major role in aiding healthcare providers with medical issues. The emergence of artificial intelligence and machine learning can aid in addressing the challenge of completing timely and accurate diagnosis. The goal of this research work is to design a system that utilizes machine learning and neural network techniques to diagnose chronic kidney disease with more than 90% accuracy based on a clinical data set, and to do a comparative study of the performance of the neural network versus supervised machine learning approaches. Based on the results, all the algorithms performed well in prediction of chronic kidney disease (CKD) with more that 90% accuracy. The neural network system provided the best performance (accuracy = 100%) in prediction of chronic kidney disease in comparison with the supervised Random Forest algorithm (accuracy = 99%) and the supervised Decision Tree algorithm (accuracy = 97%).