A comparative study on machine learning approaches for diagnosis of thyroid disease

Machine learning’s ability to be used in disease identification and management makes it inevitable that technology will play a part in the healthcare sector. When machine learning techniques are used for disease detection, false positive rates can be decreased and decision-making speed increased. The thyroid gland controls the body’s metabolism, making it one of the most significant glands. Releasing particular hormones into the blood regulates how the body functions. The conditions related to hormones are known as hyperthyroidism and hypothyroidism. The thyroid gland produces a specific hormone in the bloodstream that controls the body’s metabolism when particular problems arise. Inflammation, autoimmune diseases, and iodine shortage can exacerbate thyroid problems. A blood test is used to diagnose the condition. However, noise and disruption are common. Analytical procedures that display the patient’s risk of thyroid disease can be carried out relatively easily using data-cleansing techniques. Based on data collected from a dataset retrieved from the machine learning repository at UCI, this study analyses and classifies models used in thyroid illness. An essential component of thyroid illness identification is machine learning.