TY - JOUR AU - Swetha, Avulapati AU - Lakshmi, M. Sri AU - Kumar, M. Rudra PY - 2022/10/15 Y2 - 2024/03/28 TI - Chronic Kidney Disease Diagnostic Approaches using Efficient Artificial Intelligence methods JF - International Journal of Intelligent Systems and Applications in Engineering JA - Int J Intell Syst Appl Eng VL - 10 IS - 1s SE - Research Article DO - UR - https://ijisae.org/index.php/IJISAE/article/view/2289 SP - 254 – 261 AB - <p>Many people worldwide are afflicted with kidney illnesses today. Thus, the primary purpose of this research is to employ several computational-based methods to categorize and diagnose Chronic Kidney Disease. Our analysis relied on data on a chronic renal disease made available to the general population. Chronic renal disease was divided into two categories with the help of eight classifiers (patient or not). For this, we employed RapidMiner Studio 9.8, which ran on the operating system Windows 10. Some performance metrics were produced to evaluate the strategies; the confusion matrix gives us the TP, FP, FN, and TN values. The evaluation of the data mining techniques showed that the accuracy rates of 99.09%, 98.04%, and 96.52% were achieved by Random Forest, Deep Learning network, and Neural Network, respectively. It is worth noting, however, that the AUC for the Deep Learning network, Support Vector Machine, and Random Forest are all equalled. Among the most effective data analysis methods is data mining, which has proven particularly valuable in medicine. These categorization strategies help doctors make more accurate diagnoses by revealing hidden patterns in the data.</p> ER -