A Comparative Study of Traditional and Ensemble Supervised Machine Learning Algorithms in Thyroid Disorders Diagnosis

Machine learning models are employed widely in the classification, diagnosis, and prediction of various health disorders. This paper does a comparison study of the popular traditional data classification models with ensemble and hybrid classification models developed and applied in diagnosis and prediction of one of the most frequently occurring endocrinal illness, viz Thyroid disorders. According to a survey conducted in India in 2016, disorders of thyroid gland are increased in an exponential rate in Indian subcontinent. Approximately 1 in every 10 adults suffer from thyroid disorders like hypothyroidism, a condition of hormonal imbalance in which the thyroid produces too little hormone for proper functioning of human body. This condition is more common in women of child-bearing age. Some agents that unfavourably affect the thyroid performance are stress, trauma, infection etc. Various machine learning algorithms popularly applied are Regression models, Bayesian classifier, k Nearest Neighbours, Decision Tree induction, Support Vector Machine, and they are employed in Thyroid disorder prediction researches and tools. Nowadays, ensemble models have replaced simple classification techniques in this area. This paper provides an exclusive comparative study of standard traditional classification models with novel Ensemble models used in the classification and prediction of thyroid disorders.