KJSET Volume. 1, Issue 1 (2022)

Contributor(s)

Ubochi Chibueze Nwamouh, Ukagwu Kelechi John, Nakajubi Safina
 

Keywords

Machine Learning Cardiovascular Disease Artificial Intelligence Artificial Neural Network
 

Download Full-text (PDF)

... Download File [ 0.53 MB ]
 
Go Back

Design and Implementation of a Cardiovascular Disease Detection System Using Artificial Neural Network

Abstract: Cardiovascular diseases are a major cause of death globally. The early detection of these diseases and continuous supervision by health personnel can significantly reduce the mortality rate. However, accurate detection of cardiovascular diseases in all cases and supervision of a patient round-the-clock by a doctor is not feasible since it requires more sapience, time and expertise. Therefore, the aim of this work is to design and implement a cardiovascular disease detection system using artificial neural network. For the accurate detection of cardiovascular diseases, an efficient artificial neural network technique known as Multilayer Perception (MLP) neural network was used to build the predictive model. The system requires patients’ heart-related medical records to detect the presence or absence of any cardiovascular disease and it will serve as an aid for medical personnel to diagnose the disease in a more efficient way. In the project’s prototype implementation, system logic implementation was achieved using Java while user interfaces were built using the JavaFX framework. The development of the system followed the waterfall model which helped in breaking down the development process into smaller sub-processes that were followed sequentially to achieve a fairly efficient cardiovascular disease detection system. The system is a stand-alone desktop application and tested using WEKA and a laptop. In order to ascertain the accuracy, validation and performance measure of the developed system, a comparative analysis of the developed system against existing cardiovascular disease detection system was done, and the developed system yielded an accurate result of about 91.10%