ITDS | SPMS

HEART DISEASE PREDICTION USING HYBRID 1D CONVOLUTIONAL NEURAL NETWORK AND BIDIRECTIONAL LONG SHORT-TERM MEMORY

Project Description
Supervisor

As one aspect of human life is the health, heart disease is one the disturbing health concerns which damages both vessels of heart and blood. Targeted early detection methods for cardiovascular diseases are also instrumental in identifying high-risk candidates and then intervening accordingly to decrease their risk. This study seeks to identify a heart condition where in its early stage in order to save lives. This project introduces the study of the architectural design for a hybrid model deploying Deep learning techniques, 1D Convolutional Neural Networks (1D CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) for predicting heart disease and generate critical diagnostic strategies This is achieved by using Heart Disease Cleveland UCI data from Kaggle and StandardScaler is applied to the dataset to scale all features and put them on a same scale and this helps the model converge more quickly during training. The performance of the approach is demonstrated by the results of experiments on the Heart Disease Cleveland UCI dataset obtained from Kaggle. Evaluation metrics like accuracy, precision, recall and F1-score help in evaluation of the diagnostic model. When tested on 1,191 data samples we achieve an accuracy of 93.70% vs traditional machine learning which achieved with the best technique 86.5%.

Machine Learning: Machine Learning (ML) research in Computer Science and Information Technology focuses on the development of algorithms and models that enable computers to learn from data and improve their performance over time without being explicitly programmed. It is a subset of Artificial Intelligence that uses statistical techniques to give machines the ability to learn patterns, make decisions, and predict outcomes based on data. Supervised learning, a key area of ML research, involves training models on labeled data, where the input-output relationships are predefined. This method is widely used for tasks such as classification (e.g., spam detection) and regression (e.g., predicting house prices). Unsupervised learning, on the other hand, involves finding hidden patterns in data without predefined labels, with clustering and association being typical applications in areas such as customer segmentation and anomaly detection. Reinforcement learning is another area of ML that focuses on teaching agents to make decisions by interacting with their environment and receiving feedback in the form of rewards or penalties. It is often applied in robotics, game playing, and autonomous systems, where continuous learning and adaptation are required.

Develop an automated system for heart disease prediction using hybrid 1D Convolutional Neural Networks (CNNs) and Bidirectional Long Short-Term Memory (Bi-LSTM)

2023/2024

Oct 31, 2024

NSOH PETER, BATSA RUTH MAMILE, TAMAKLOE HOPELAND, TANNOR JUSTICE BOAFO, AMANKONA MAXWELL

BSc Information Technology