DEEP LEARNING IN HEALTHCARE: HEART DISEASE DETECTION

Abstract

Many people die every year from heart disease, which is one of the most common and deadly diseases in the world. To preserve lives, this disease needs to be discovered early. One of the easiest, quickest, and least expensive ways to detect disease is using machine learning (ML), an artificial intelligence technique. Researchers are concentrating on developing intelligent systems that employ machine learning and deep learning algorithms for accurately identifying cardiac defects based on electronic health data because these disorders can be fatal. The paper demonstrates distinguished machine learning techniques to facilitate the prediction of heart disease using patient data on vital health indicators. Identifying the patient who is more prone to develop a heart problem based on a number of medical traits is the primary goal of this study effort. By utilizing the patient's medical background, we created an algorithm to predict the chance of a heart disease diagnosis. Various machine learning techniques, such as KNN and logistic regression, were employed to anticipate and classify the heart disease sufferer. A very helpful method was employed to control the model's ability to increase any person's heart attack prediction accuracy.The suggested model demonstrated a satisfactory level of strength and demonstrated acceptable accuracy in predicting the presence of heart disease in a given individual through the use of KNN and Logistic Regression.