Cardio Vascular Disease Prediction based on ANN Algorithm

• Published in: 2023 Second International Conference on Electronics and Renewable Systems (ICEARS) pp. 919 - 925
• Main Authors: K, Anitha, M, Arunprasath, K, Dinesh Kumar, P, Gokul, N, Gowtham
• Format: Conference Proceeding
• Language: English
• Published: IEEE 02.03.2023
• Subjects: Artificial neural networks; cardiovascular disease prediction; Classification algorithms; Data mining; Data models; Deep learning; machine learning; multi-layer perceptron; Prediction algorithms; System performance
• DOI: 10.1109/ICEARS56392.2023.10085084

Cardiovascular disease is a leading cause of mortality and disability in the United States. However, there aren't many efficient methods available to find hidden trends and linkages in e-health data. Medical diagnosis is a difficult process that has to be carried out precisely and effectively if people are to be saved. To lower the cost of performing clinical tests, an appropriate and accurate computer-based automated decision support system is required. The use of ML in health analytics has been proposed to anticipate precise patient data analysis. The data generated by the healthcare sector is not mined. Datasets containing patient risk factors can be utilised to create intelligent models in the medical industry by utilising data mining techniques. The growth of methods and tools for using data has surprised knowledge discovery in database. This study sheds light on machine learning and deep learning approaches used in disease detection. There are several data mining classifiers that have been developed recently for accurate and efficient illness diagnosis. The heart attack prediction system proposed in this research uses deep learning techniques, more especially Multi-Layer Perceptron (MLP), to forecast the patient's likelihood of developing heart-related disorders. The Deep Learning technique in Artificial Neural Networks is used by MLP, a particularly potent classification system. To provide reliable results with a minimal amount of error, the suggested model combines deep learning with data mining.