Chronic Kidney Disease Risk Prediction Using Machine Learning Techniques
نویسندگان
1 School of Computing and Information Technology, REVA University, Bangalore (North), Karnataka, India.
2 Computer Science and Engineering, Panimalar Engineering College, Chennai, Tamil Nadu, India.
3 School of Computing Science and Engineering, Galgotias University, Greater Noida, Uttar Pradesh, India.
4 Computer Science and Engineering, Vasavi College of Engineering, Hyderabad, Telangana, India.
5 Computing Science and Engineering, Institute of Aeronautical Engineering, Hyderabad, Telangana, India.
6 Computer Science and Engineering MLR Institute of Technology, Dundigal, Hyderabad, Telangana, India.
7 School of Computing Science and Artificial Intelligence, SR University, Warangal-506371, Telangana, India.
doi
10.22059/jitm.2024.96378چکیده
In healthcare, a diagnosis is reached after a thorough physical assessment and analysis of the patient's medicinal history, as well as the utilization of appropriate diagnostic tests and procedures. 1.7 million People worldwide lose their lives every year due to complications from chronic kidney disease (CKD). Despite the availability of other diagnostic approaches, this investigation relies on machine learning because of its superior accuracy. Patients with chronic kidney disease (CKD) who experience health complications like high blood pressure, anemia, mineral-bone disorder, poor nutrition, acid abnormalities, and neurological-complications may benefit from timely and exact recognition of the disease's levels so that they can begin treatment with the most effective medications as soon as possible. Several works have been investigated on the early recognition of CKD utilizing machine-learning (ML) strategies. The accuracy of stage anticipations was not their primary concern. Both binary and multiclass classification methods have been used for stage anticipation in this investigation. Random-Forest (RF), Support-Vector-Machine (SVM), and Decision-Tree (DT) are the prediction models employed. Feature-selection has been carried out through scrutiny of variation and recursive feature elimination utilizing cross-validation (CV). 10-flod CV was utilized to assess the models. Experiments showed that RF utilizing recursive feature removal with CV outperformed SVM and DT.
