Improved Multiple Disease Detection Using Modified ANFIS and K-Medoid Clustering

• Published in: 2025 Global Conference in Emerging Technology (GINOTECH) pp. 1 - 6
• Main Authors: Chandanan, Amit Kumar, Kandepu, Sunitha, Giri, Neeraj, Somasundaram, B., Ravi, C. N., Lathigara, Amit
• Format: Conference Proceeding
• Language: English
• Published: IEEE 09.05.2025
• Subjects: Accuracy; ADKD; ANFIS; Biomedical imaging; CFCM; CFI; Deep learning; Global Positioning System; Insulin; IVP-SVM; LSE; M-ANFIS; Medical devices; Medical services; Metabolism; NDKD; Performance evaluation; Systematic literature review
• DOI: 10.1109/GINOTECH63460.2025.11076895

The present study focuses on the use of ML and DL methods to forecast the occurrence of common disorders in the area, including diabetes, allergies. Diabetic retinopathy (ADKD) and diabetic nephropathy (NDKD) are two major consequences of diabetes that researchers are also trying to quantify in their study subjects. The previously processed information is queried for variables like illness name, indicators, medicine name, country, year, sex, and so on. Then, the Enclosed Frequent Item-set (CFI) count is determined. The CFI count's diversity is subsequently calculated. The disorders that are common in society can be recognized, at last, by using the M-ANFIS method. Clustered the CFI volatility of medical data is done using the M-ANFIS (Modified Adaptive Neuro-Fuzzy Inference System) technique using the k-Medoid clustered technique. The degree of accuracy achieved by the suggested strategy is 96.342%.