A Novel Feature Selection-based Algorithm for Medical Correlation of High Dimensional Data

• Published in: 2023 IEEE IAS Global Conference on Emerging Technologies (GlobConET) pp. 1 - 7
• Main Authors: Patil, Shital, Bhosale, Surendra
• Format: Conference Proceeding
• Language: English
• Published: IEEE 19.05.2023
• Subjects: Cardiac arrest; Correlation; Heart; Hyperparameter; K-Nearest Neighbor; Medical services; Neural Networks; Organizations; Pulse measurements; Random Forest; Support Vector Machine; Support vector machines
• DOI: 10.1109/GlobConET56651.2023.10150163

According to the World Health Organization, cardiovascular diseases are the number one cause of death globally, with an estimated 17.9 million deaths each year. Predicting heart attacks can help identify individuals at high risk of developing CVDs, allowing for early intervention and preventive measures to be implemented. data science and machine learning techniques can be very useful in predicting heart attacks by analyzing various risk factors such as blood pressure, cholesterol levels, pulse rate, and diabetes. These techniques can help identify patterns and correlations in large datasets that may be difficult for human analysts to identify and use these patterns to make accurate predictions about an individual's risk of experiencing a heart attack. The purpose of this article is to determine the dependence of various factors and cholesterol levels on human heart health. By analyzing these patterns and risk factors, machine learning models can accurately predict an individual's likelihood of experiencing a heart attack, allowing healthcare providers to implement early intervention and preventive measures to reduce the risk of CVDs. Additionally, these models can help healthcare providers personalize treatment plans for patients based on their specific risk factors, improving the overall effectiveness of CVD prevention and management.