Empirical Method for Thyroid Disease Prediction Using a Deep Learning Techniques

Thyroid issues are quite general, effecting millions of people across the globe. The thyroid gland is susceptible to a wide range of illnesses, including hypothyroidism, hyperthyroidism, and malignancy. The symptoms of hypothyroidism are often very unpleasant. Timely identification of thyroid disorders is greatly aided by accurate categorization and machine learning. Treatment times for patients will be impacted by this rapid categorization. If we want to save time and have fewer mistakes made by radiologists, automatic and exact thyroid nodule recognition in ultrasound images is essential. The use of medical imaging has increased dramatically as a trustworthy and significant data source for the growth of machine learning (ML) strategies. In this study, we apply numerous diverse ML strategies to the dataset and accomplish a comparative examination of their efficiency so that we can more perfectly anticipate the disease utilizing the factors recognized by the dataset. In addition, the dataset has been tweaked to improve classification prediction accuracy. Both the sampled and non-sampled datasets were classified so that the two could be contrasted more precisely. With some data tweaking, we were able to boost the random forest algorithm's accuracy to 99 percent, with 97 percent specificity.