An Ontology-Based Diabetes Prediction Algorithm Using Naïve Bayes Classifier and Decision Tree

Millions of people have died as a result of uncontrollably rising blood sugar levels throughout the world. This can be a result of a delayed diabetes diagnosis. A lack of a cohesive framework, data imbalance, and inadequate feature selection methods have all contributed to inaccurate information classification. This study proposes a decision-tree- and Naive Bayes-based ontology-based approach for diabetes classification and prediction. Nave Bayes classifiers are used to categorise different types of diabetes. The document query module searches for and displays the documents that the users have requested. This technique will enable better and more accurate diabetes detection and classification.