JIITA, Vol.10 no.2 pp.1337-1350(2026), DOI: 10.22664/ISITA.2026.10.2.1337
K.Balasree
Abstract. Data mining is crucial in healthcare for early diagnosis and preventive
treatment, particularly for long-term conditions. This study focuses on classifying
hypothyroidism and hyperthyroidism using machine learning models to improve
prediction accuracy.
Utilizing data from the UCI Machine Learning repository and the RapidMiner tool, the
research evaluates four algorithms: Support Vector Machine (SVM), Random Forest,
Naive Bayes, and Decision Trees. By analyzing classification and recall, the proposed
model successfully identifies thyroid ailments with a 94% accuracy rate, demonstrating
the effectiveness of these automated tools in clinical decision-making.
Keywords; Thyroid disease diagnosis, Decision Tree, Support Vector Machine, Naïve Bayes, Random Forest.