Thyroid Data Disease Prediction Using Feature Encoded Convolutional Network

  • Sruthy B.S., Dr. S. Muruganantham

Abstract

According to the statistics released by China Health Education Center, the thyroid disease has already been the second largest in the field of endocrine, and shows a rapid growth trend in recent years. Currently, more than 200 million patients suffering from thyroid disease, such as hyperthyreosis, hypothyroidism, thyroid nodule, thyroid cancer and so on. In clinical treatments of thyroid disease, doctors first detect thyroid stimulating hormone (TSH), triiodothyronine (T3), tetraiodothyronine (T4) and many other relevant indexes, and then analyze these data relying on their clinical experience to determine the type of thyroid disease of patients, finally they can take appropriate treatments depending on the type of disease.Most tedious and challenging task is to provide disease diagnosis at early stage with higher accuracy in the medical science field. Clinics and hospitals collect a large amount of patient data over the years. These data provides a basis for the analysis of risk factors for many diseases. Predicting thyroid disease is analyzed in this chapter. Thyroid gland will stow thyroid hormones to maintain the body's metabolic rate. There are two most common problems of the thyroid disorder or thyroid disease they are hyperthyroidism and hypothyroidism. Hyperthyroidism releases too much thyroid hormone into the blood due to over active of thyroid. The thyroid prediction techniques will help to reduce the attributes used in classifying thyroid disease.In our proposed work, the attributes are directly applied to deep learning approach is utilized to predict the hypothyroid disorder by collecting the dataset from UCI repository. The performance measure is calculated from the confusion matrix with the accuracy. The existing work is carried out using the LDA algorithm which has the main disadvantage of LDA does not work well if the design is not balanced (i.e. the number of objects in various classes are (highly) different).

Published
2021-11-22
How to Cite
Sruthy B.S., Dr. S. Muruganantham. (2021). Thyroid Data Disease Prediction Using Feature Encoded Convolutional Network. Design Engineering, 14726-14737. Retrieved from http://thedesignengineering.com/index.php/DE/article/view/6597
Section
Articles