Chronic Kidney Disease: A Machine Learning Based Improved Analytical Forecasting

Abstract

Chronic kidney disease (CKD) refers to a variety of conditions that cause harm to the kidneys or a decrease in the Glomerular Filtration Rate (GFR). Due to recent advancements in medicine, doctors have been able to treat this issue utilising a number of various ways. A rising number of people are interested in applying artificial intelligence and machine learning, especially in the field of health, to enhance medical research and treatment. Because kidney condition can be deadly, machine learning must be used to forecast when it will first manifest. A number of machine learning approaches, applications, and algorithms may be utilised to forecast how "Chronic Disease" might progress. As a consequence, any doctor may be able to see the beginning of this condition as soon as the dialysis report is obtained. This approach may also be utilised to identify the disease component that, according to the report research, is the main contributor to the condition. To get the best results in this system, advanced and dynamic algorithms like Random Forest, Nave Bayes, Decision Tree, K-Nearest Neighbor (KNN), XGBoost, AdaBoost.