Comparing Multiple Machine Learning Techniques for Forecasting Chronic Periodontitis

Artificial intelligence contain ML, ML Algorithm the stage a substantial part in forecasting infections in order to yield the most excellent forecast accuracy. The crucial aim of the work is to forecast periodontal illness and associate the novel models with the previous algorithms to examine its routine to predict periodontal infection at a very initial stages. The ML algorithm can be used to mechanize the classification of periodontal infection. Several learning algorithms for diabetic illness organization are associated in this study. Naïve Bayes algorithms and neural network and Support Vector Machine are among the ones that are advised and evaluated for this categorization use. These methods tested with a custom periodontal disease dataset. Matlab simulation has been used to compare the algorithms' results regarding of precision, recall, F-measure sensitivity, specificity, accuracy and Dasiys Correlation Coefficient. Finally, it includes the most appropriate model for long-term periodontal disease.