Abstract—When researchers examine a broad range of thyroid-related conditions with respect to patient outcomes and treatment effectiveness. Modifications to our lifestyle can significantly reduce our risk of developing certain thyroid disorders. Regrettably, the number of fatalities caused by various thyroid conditions has been rising. Our thyroid is examined by endocrinologists, thyroid specialists, or computed ultrasound. Most people, however, cannot afford these tests. Nowadays, the primary means of prolonging the life of a thyroid patient is medication. However, the goal of this study is to use machine learning to forecast a person’s risk of developing thyroid disease before they experience any symptoms or issues. Preventing an issue from arising in the first place is the same as preventing it rather than treating it. Basic patient data, including age, gender, blood pressure, hyperthyroidism, and hypothyroidism, are used in this prediction process. Machine learning is used by endocrinologists to assist them in selecting the most appropriate treatment plan for each patient. It has been demonstrated that machine learning algorithms can reliably generate accurate results based on input data. This study compares three distinct methods to ascertain which one yields the best results and efficacy levels: Random Forest, Decision Tree Algorithm, and Logistic Regression. The results demonstrate the importance of algorithm selection and lay the groundwork for further studies to improve predictive models for better thyroid disease prevention and treatment. The authors found that, with an accuracy of 94.04%, Logistic Regression performed better than both of their methods in this investigation. Accurate outputs based on input data have been established.
 
Keywords—logistic regression, decision tree, random forest, supervised learning, thyroid disease


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).