Healthcare Analytics for Thyroid Disorder Classification Using AI
International Journal of Scientific Research in Engineering and Management · 13.03.2026 · 10 (03) · 1-9
DOI: 10.55041/ijsrem57619 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Scientific Research in Engineering and Management, online erschienen am 13.03.2026. Verfasst von Surya Krishna.M. und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Thyroid disorders are among the most widespread endocrine diseases affecting millions of individuals globally. The thyroid gland plays a crucial role in regulating metabolism, energy production, heart rate, and overall hormonal balance within the human body. Any imbalance in thyroid hormone production can lead to severe medical conditions such as hypothyroidism and hyperthyroidism. Early detection of thyroid disease is essential because delayed diagnosis can result in serious complications including cardiovascular problems, infertility, metabolic disorders, and psychological issues. Traditional thyroid disease diagnosis relies heavily on laboratory blood tests and medical consultation, which often involve long waiting times, high healthcare costs, and limited accessibility in rural regions. Patients frequently experience anxiety and uncertainty while waiting for test results and medical interpretation. These challenges highlight the need for an intelligent system capable of providing quick preliminary diagnosis using available medical data. This research proposes a machine learning–based thyroid disease prediction and assessment system designed as a web-based application. The system collects essential patient information such as age, gender, medical history, medication details, pregnancy status, and thyroid hormone levels including TSH, T3, TT4, T4U, FTI, and TBG. The collected data undergoes preprocessing steps such as data cleaning, normalization, and feature selection before being analyzed using advanced machine learning algorithms including Random Forest and Logistic Regression. The trained model predicts the likelihood of thyroid disease and generates a percentage-based risk score along with AI-driven medical recommendations. The system is developed using modern web technologies such as HTML, CSS, Bootstrap, JavaScript, Python, and Flask framework. The proposed system improves early detection, reduces patient stress, supports healthcare professionals, and enhances healthcare accessibility. In addition to prediction, the system also performs intelligent risk assessment by calculating probability scores based on patient input data. The integration of machine learning enables the system to identify complex relationships between medical parameters that may not be easily detectable through manual analysis. By providing real-time prediction results and personalized health recommendations, the system acts as a preliminary diagnostic support tool. This reduces dependency on repeated laboratory visits and improves patient awareness about thyroid health. The proposed solution demonstrates how artificial intelligence can be effectively integrated into healthcare systems to enhance early detection, improve treatment outcomes, and reduce overall medical costs. KEYWORDS Machine Learning, Thyroid Prediction, Healthcare Analytics, Random Forest, Medical Decision Support System, Artificial Intelligence.
Zitieren
APA
Krishna.M., S., & Ahamed, J. N. (2026). Healthcare Analytics for Thyroid Disorder Classification Using AI. International Journal of Scientific Research in Engineering and Management, 10(03), 1-9. https://doi.org/10.55041/ijsrem57619
Vancouver
Krishna.M. S, Ahamed JN. Healthcare Analytics for Thyroid Disorder Classification Using AI. International Journal of Scientific Research in Engineering and Management. 2026;10(03):1-9. doi:10.55041/ijsrem57619
BibTeX
@article{KrishnaM2026,
author = {Krishna.M., Surya and Ahamed, J. Noor},
title = {Healthcare Analytics for Thyroid Disorder Classification Using AI},
journal = {International Journal of Scientific Research in Engineering and Management},
year = {2026},
volume = {10},
number = {03},
pages = {1--9},
doi = {10.55041/ijsrem57619}
}
EUVIMED