Predictive Modeling of Thyroid Disease Using Machine Learning Algorithms
Abstract
Thyroid disease is a prevalent endocrine disorder affecting millions of people worldwide. Timely diagnosis and accurate prediction of thyroid disease are crucial for effective patient care. In this research paper, we investigate the performance of two popular machine learning algorithms, Multilayer Perceptron (MLP) and Support Vector Machine (SVM), in predicting thyroid disease based on a comprehensive dataset containing 30 attributes and 3772 instances with two class labels: Negative and Sick. Our results indicate that MLP achieved superior predictive accuracy, precision, and recall compared to SVM, with an accuracy rate of 96.76%, precision of 96.7%, and recall of 96.8%. These findings suggest that MLP may be a valuable tool for improving thyroid disease diagnosis and patient outcomes. This paper discusses the implications of these results for clinical practice and future research directions.
Keywords
Download Options
Introduction
The thyroid organ secretes synthetics which controls a lot of things in the human body system like use the food, use energy, and rest plans, temperature tendencies, body weight balance and fundamentally more. In this assessment work to approach thyroid ailment examination were performed by using AI procedures that is Backing Vector Machine (SVM) and Complex Perceptron (MLP). Factors that impact the thyroid ability are: stress, tainting, injury, harms, low-calorie diet, certain medication, etc. It is imperative to prevent such ailments rather than fix them, in light of the fact that the vast majority of treatments contain in long stretch remedy or in chirurgical intervention. The stream focus on suggests thyroid sickness request in two of the most notable thyroid dysfunctions (hyperthyroidism and hypothyroidism) among the general population.
Nowadays, thyroid issues decimation the standard working of the thyroid organ which causes weird making of synthetic substances inciting hyperthyroidism [1]. The occasion of hypothyroidism in the made world is surveyed to associate with 4- 5%. Hypothyroidism could cause raised cholesterol levels, a development in beat, cardiovascular intricacies, reduced readiness, and despairing while potentially not fittingly treated. Thyroid is a butterfly-shaped organ, which is arranged at the lower part of the throat at risk for making two powerful thyroid synthetic compounds, levothyroxine (T4) and triiodothyronine (T3) that impact a couple of components of the body, for instance, settling interior intensity level, circulatory strain, controlling the beat, etc. Switch T3 (RT3) is produced using thyroxine (T4), and its responsibility is to block the movement of T3.
The development and information in clinical sciences, the computer programming specialists are prepared for giving expert advance notice system. To decide different kinds of ailments to have high precision. The clinical specialists are made to use these structures as a result of a couple of made bungles during general assurance process [5]. Disorder examination exercises using EAS are acted considering sets of disease incidental effects. These structures rely upon man-made intelligence methodology which helps the specialist with restricting the costs and time in fruitful examinations. A peculiar capacity of the thyroid derives the occasion of hyperthyroidism and hypothyroidism, two of the ordinary thyroid warm signals. Hypothyroidism (underactive thyroid or low thyroid) suggests that the thyroid organ doesn't make enough of explicit huge synthetics. Without an adequate therapy, hypothyroidism can cause different clinical issues, for instance, strength, joint desolation, fruitlessness and coronary disease. Hyperthyroidism (overactive thyroid) implies a condition where the thyroid organ conveys a ton of the synthetic thyroxin.
Conclusion
Our study demonstrates the potential of machine learning algorithms, particularly MLP, in predicting thyroid disease with high accuracy, precision, and recall. These results hold promise for improving the diagnosis and management of thyroid disease, ultimately benefiting patient care and public health. Future research should focus on refining and validating these models for real-world clinical applications. While MLP has shown excellent performance in this study, further research is needed to explore the generalizability of these results on larger and more diverse datasets. Additionally, the interpretability of MLP models should be investigated to ensure their clinical adoption.