Novel HealthCare Framework for Cardiac Arrest With the Application of AI Using ANN
Nasmin Jiwani, Ketan Gupta, Pawan Whig
Abstract
Cardiovascular illnesses are the leading cause of mortality worldwide, killing an estimated 27.9 million people each year, accounting for 31% of fatalities worldwide. Cardiovascular disorders are a common cause of heart failure. It is distinguished by the heart's inability to provide an appropriate amount of blood to the body. All main bodily processes are affected when there is insufficient blood flow. Heart failure is a disease or set of symptoms that cause the heart to weaken. The Main Findings of the research study lies on the three major factors; first, the timing of the patient's follow-up appointment for the condition is critical since early detection of a cardiovascular problem and treatment decreases the likelihood of death. It has an inverse relationship. The second most significant aspect is the ejection fraction. It is to be anticipated, given that it is essentially the efficiency of the heart. At last, the patient's age is the third most linked characteristic. Clearly, as one ages, the heart's function deteriorates. The Data is Modeled Using Machine learning with ANN, and an accuracy of about 80% obtained shows the Framework is fairly useful for the Detection of Cardiac Arrest. Further, the accuracy can be increased to 90-95% by using deep learning models