A Review on Diabetic Detection Using Machine Learning
Shirin S. Pinjari , Nilesh Vani
DOI : 10.46335/IJIES.2023.8.8.6
Abstract – Healthcare data typically consists of a variety of variable types, missing values, and is quite large, complex, and heterogeneous. These days, having access to such knowledge is required. By building models from healthcare data sets, such as those pertinent to patient data sets for diabetes, data mining can be utilized to extract knowledge. In order to predict the prevalence of diabetes using 18 risk factors, three data mining algorithms—Self-Organizing Map (SOM), C4.5, and Random Forest—are used to adult population data from the Ministry of National Guard Health Affairs (MNGHA), Saudi Arabia. Random Forest performed better than other data mining classifiers in comparison.
