MACHINE AND DEEP LEARNING TECHNIQUES FOR CARDIOVASCULAR DISEASE DETECTION
DOI:
https://doi.org/10.56536/jicet.v4i2.131Keywords:
Machine Learning, Deep Learning, HealthcareAbstract
CVDs have been cutting short millions of lives every year and remain one of the significant threats to global health. Machine learning approaches have a great potential for improvement in diagnostic accuracy, which already forms the backbone for early diagnosis and treatment to improve outcomes. In this paper, some ML algorithms for the identification of CVDs will be investigated using patient demographics and health indicator datasets. Some of the new techniques pointed out in the literature study include diagnosing atherosclerotic heart diseases using hybrid genetic algorithms and heart failure prediction using random search algorithms. presences in the Efficacy of ML models like decision trees, Naïve Bayes, and random forests in categorizing cardiac diseases have also been studied. In this paper, we introduce and evaluate a new neural network design for the prediction of cardiovascular disease. Results from a comprehensive model assessment including measures like accurateness, exactness, recollection, and F1 score provide light on the competencies and possible uses of ML in cardiovascular health care. Results are impressive; created prediction models specifically show promise to help doctors intervene quickly and improve patients' outcomes with an accuracy of 74% classification.
Keywords: Heart disease, Machine learning, Feature selection, Cardiovascular diseases, Quality of life, Disease prevention, CVD.