AI-Powered Thyroid Disorder Recurrence Prediction: An Innovative Fusion of XGBoost, Random Forest and Logistic Regression

View at publisher Summarise with VIRAT
Authors: K. Manoj, C. Niranjan, Ruth Shirley Fernandez, J. Mohanapriya
Cited by: 0
References: 10

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Thyroid disorders are very common endocrine problems that affect people all over the world. Conditions like an underactive thyroid (hypothyroidism), an overactive thyroid (hyperthyroidism), and abnormal growths in the thyroid (nodules) disrupt hormonal balance necessary for control body's metabolism. Thyroid issue is a long-term health problem and put a lot of pressure on healthcare systems. Being able to predict when these problems might come back using computer models can help doctors watch patients more closely, choose better treatments, and improve the quality of life for those affected. In this study, a machine learning model was developed to classify and predict the recurrence of thyroid disorders. The model uses information about a patient's age, medical history, and clinical data. In this study, the data included records from 383 patients, without recurrence and 108 with recurrence Three different approaches were applied to predict the best model: Extreme Gradient Boosting (XGBoost), Random Forest and Logistic Regression. Multiple evaluation measures were used to test the models, viz, area under Receiver Operating Characteristic curve (ROC-AUC), PR-AUC, Accuracy, Confusion Matrix results. The collective model methods XGBoost and Random Forest performed far better than the individual simpler model Logistic Regression. XGBoost and Random Forest help in finding groupings of patients at risk for recurrence of thyroid issues. Using such models in real health care allow physicians to personalize treatment plans. These models also allow early detection of problems and management of patient health and help in developing smarter and data driven systems for treating thyroid disorder.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Thyroid Disorders and Treatments Thyroid and Parathyroid Surgery

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
01–08
Publication date
21 January 2026
Language
EN