Machine Learning Algorithms for Chronic Kidney Disease Risk Prediction

Main Article Content

S. Jaya priya, A.Thamaraiselvi, S.Sinduja


In today's world, everyone tries to be health-conscious, but owing to work and a hectic schedule, people only pay attention to their health when signs of sickness appear. Chronic Kidney Condition is a disease that does not have any symptoms or, in some situations, does not have any disease-specific signs. As a result, it is difficult to forecast, identify, and prevent such a sickness manually, which could result in lasting health damage. Machine learning, which excels at prediction and analysis, provides a ray of hope in this dilemma. We studied CKD patient data and presented a system for predicting CKD risk using machine learning algorithms such as Logistic Regression, Random Forest, and K-Nearest Neighbor (K-NN). We used data from 455 patients. Here, an online data set from the UCI Machine Learning Repository and a real-time dataset from Khulna City Medical College are employed. For the development of our system, we used Python as a high-level interpreted programming language. We used a 10-fold CV to train the data using a Hybrid ensemble technique. The hybrid ensemble technique achieves 97.12 % accuracy, whereas ANN achieves 94.5 %. This technology will aid in the early detection of chronic kidney disorders..


Download data is not yet available.


Metrics Loading ...

Article Details

How to Cite
S. Jaya priya, A.Thamaraiselvi, S.Sinduja. (2021). Machine Learning Algorithms for Chronic Kidney Disease Risk Prediction . Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(13), 4385–4393.
Research Articles