Thalassemia disease prediction using deep learning

Project Code :TCMAPY2068

Objective

The project aims to develop a predictive model for Thalassemia disease using both deep learning and machine learning algorithms. The primary objective is to compare the performance of different algorithms, such as DNN, CNN, XGBoost, and Random Forest, in accurately predicting Thalassemia. A user-friendly web application will be created using Flask, allowing users to input their data and receive disease predictions. The models will be evaluated based on key metrics like accuracy, precision, recall, and F1-score to identify the best-performing algorithm. The project also seeks to provide an efficient and accurate solution for the early detection of Thalassemia, minimizing human intervention in the diagnostic process. Data preprocessing techniques, including normalization, handling missing values, and feature selection, will be implemented to ensure high-quality input data. Furthermore, the system will be designed to be simple, scalable, and adaptable, allowing for future extensions to other genetic disorders with similar prediction requirements. A secure and efficient database system will be developed to store user data and predictions while ensuring privacy.

Abstract

This project focuses on developing a predictive model for Thalassemia disease detection using deep learning and machine learning algorithms. The dataset used is based on HPLC screening data, which includes various features that help in identifying the disease. The models used for prediction include Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), XGBoost, and Random Forest. Each algorithm is evaluated for its ability to accurately classify the data into Thalassemia-positive and negative categories. A web application is built using Flask, which enables users to register, log in, and input their data to receive a prediction. The project aims to provide a simple yet effective method for predicting Thalassemia disease with high accuracy. The system is evaluated on several performance metrics including accuracy, precision, recall, and F1-score to determine the most effective algorithm. This project has the potential to assist in the early detection of Thalassemia, reducing manual work and improving the efficiency of diagnosis processes.

Keywords: Thalassemia, prediction, deep learning, DNN, CNN, XGBoost, Random Forest, classification, disease detection, web application.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.