This paper is being written to provide a source of reference for the research scholars who want to work in the area of prediction of thyroid disease. From the different machine learning techniques, compared widely used three algorithms namely logistic regression, decision trees and k-nearest neighbor (kNN) algorithms to predict and evaluate their performance in terms of accuracy. This study has represented the intuition of how to predict the thyroid disease and highlighted how to apply the logistic regression, decision trees and kNN as a tool for the classification. For this, thyroid data set of machine learning repository has used from UC Irvin knowledge discovery in databases archive.

本文旨在为希望在甲状腺疾病预测领域工作的研究学者提供参考。从不同的机器学习技术中，比较了广泛使用的三种算法，即逻辑回归，决策树和k最近邻（k NN）算法，以预测和评估其性能。这项研究代表了如何预测甲状腺疾病的直觉，并强调了如何将逻辑回归，决策树和k NN作为分类工具。为此，已从UC Irvin知识发现数据库数据库中使用了机器学习存储库的甲状腺数据集。