Predicting Cardiovascular Disease in Patients with Machine Learning and Feature Engineering Techniques

• Published in: 2022 5th International Conference on Signal Processing and Information Security (ICSPIS) pp. 107 - 112
• Main Authors: Tyagi, Sapna, Sirohi, Preeti, Maheshwari, Piyush
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07-12-2022
• Subjects: forecasting; healthcare; Heart; Machine learning; Medical services; prediction; Prediction algorithms; Predictive models; regression; Signal processing; Signal processing algorithms
• ISSN: 2831-3844
• DOI: 10.1109/ICSPIS57063.2022.10002692

Cardiac disease prediction and detection are among the most difficult and important jobs encountered by medical practitioners. Heart disease can be caused by a range of factors, including a sedentary lifestyle, stress, alcohol, cigarette intake, and so on. The current prediction algorithms focus on forecasting the illness label though the likelihood of getting the condition is still unknown. This study is conducted to forecast the heart disease progression well in advance so that essential action can be taken before the condition becomes severe. As a result, the research proposes a model for predicting the likelihood of heart disease incidence using logistic regression capabilities.