Thyroid Disease Prediction with Features Selection and Meta- Classifiers

Abstract

Thyroid prediction is a complicated assumption within medical investigation. To manage the vast volume of healthcare records, (ML)Machine learning algorithms are growing increasingly prevalent,powerful and compact. The approaches in machinelearning allow for the usage of various forms of data values for prediction. Data cleaning strategies serve to amplify the dataset anddeliver more accurate results.Data pre-processing.There are methods to deal with noisy and missing values. Adaboost and Bagging algorithms are utilised in this research for thyroid classification. The approaches are tested, and the findings are compared to establish which method is most successful for thyroid prediction.