HEART ATTACK PREDICTION USING MACHINE LEARNING

Abstract

Early detection is essential for both the treatment and prevention of heart attacks, which account for the majority of deaths worldwide. A machine learning model for predicting a person's risk of having a heart attack based on various medical factors is the goal of this project. Patients' medical histories, lifestyle, and physical characteristics, such as temperature, humidity, heart rate (in beats per minute), and spo2 (blood oxygen levels) by corresponding sensors. Using machine learning algorithms like the naive Bayes classifier, SVM classifier, and KNN classifier, the data will be cleaned, pre-processed, and analyzed. Using metrics like precision, recall, and the F1-score, the model will be trained and tested on a dataset of patients who are known to be at risk for heart attacks. The final model will be put into use as a web application that lets users enter their medical information to get a customized heart attack risk score. This project aims to provide individuals and healthcare professionals with an easy-to-use, wearable device and accurate tool for identifying heart attack risk factors and taking preventative measures. Key words – Body Temperature, Heart rate, breathing rates, blood oxygen level, smart wearable system