Efficient Thyroid Disease Prediction using Features Selection and Meta-Classifiers

IEEE BASE PAPER ABSTRACT:

Prediction of Thyroid is a complex axiom in medical research. Machine learning methods are more powerful and compact for the healthcare industry to handle the massive amount of healthcare records. The methods in machine learning provides the facility to use different kind of data values which are used for prediction. Data cleaning techniques are used for enhancing the dataset to provide accurate results. The noisy and missing values are handled using data pre-processing methods. In this work, Adaboost and Bagging techniques are used for thyroid classification. The methods are executed, and the results are compared to show the effective method for thyroid prediction.

OUR PROPOSED ABSTRACT:

One of the most prevalent medical conditions, thyroid disease can cause a number of different health issues. According to recent studies, 42 million Indians suffer from thyroid dysfunction or disorders. Thyroid disorders, which can include hypothyroidism or hyperthyroidism, are brought on by the thyroid hormone.

TSH (Thyroid Stimulating Hormone), T3 (Triiodothyronine, T3-RIA), T4 (Thyroxine), and FTI (Free Thyroxine Index, FTI, T7) are important thyroid test components used to determine how thyroid hormone behaves. To diagnose and predict the disease, manual analysis of these parameters on massive databases is laborious.

In the suggested system, a Decision Tree Classifier-based machine learning technique has been used to create a predictive model. The decision tree appears to produce better outcomes, with the greatest training accuracy of 100% and validation accuracy of 97%, according to the performance evaluation. Additionally, this work may help researchers find a good model for detecting and classifying hypothyroidism.

According to our research, thyroid measures play a significant influence in predicting the clinical course of depression. To identify which patients most urgently require early or intensive therapies to stop continuing dysfunction, thyroid hormone assessment should be expanded to routine clinical settings.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

Decision Tree Classifier.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB

SOFTWARE REQUIREMENTS:

Operating System : Windows 10 / 11.
Coding Language : Python 3.8.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

D.Priyadharsini1, Dr.S.Sasikala, “Efficient Thyroid Disease Prediction using Features Selection and Meta-Classifiers”, Proceedings of the Sixth International Conference on Computing Methodologies and Communication (ICCMC 2022) IEEE Xplore, IEEE CONFERENCE, 2022.

Python IEEE Projects

Efficient Thyroid Disease Prediction using Features Selection and Meta-Classifiers