Abstract:
One of the significant motives of death globally is a heart-attack. Heart-attack detection
early on can save lives. In this exploration, we mention a predictive machine learning
algorithm of heart attack. The algorithm is trained on a dataset of worldwide patients which
is taken from Kaggle. The dataset includes features such as gender, machine learning status, age,
cholesterol level, systolic pressure, and familial heart-disease history. Heart-attack
prediction is a difficult problem due to the complex nature of the data and the lack of
understanding of the underlying causes of the disease. However, predictive models that can
be used to identify people at high risk can be created using the machine learning algorithm.
This study employed a machine learning system to forecast cardiac attacks in a sizable
population. A set of clinical and demographic variables served as the training ground for
the algorithm. In the test dataset, the results demonstrated that the algorithm was capable
of accurately predicting heart attacks. Cardiovascular failure is the main source of death
around the world. Heart attack detection early can save lives. The algorithm can be used to
predict heart attack in future patients. Heart attack prediction is a challenging problem in
the machine learning field. This report's objective is to develop a machine learning system
algorithm that is able to accurately forecast the occurrence of heart attacks. The dataset
used for this purpose contains information on various risk factors such as age, gender,
smoking habits, medical history, etc. The machine learning algorithm is trained on this
dataset and is able to accurately predict the occurrence of heart attacks. The Decision Tree
algorithm is able to achieve an accuracy of 99.70% in predicting heart attack. In future, we
will do more research about heart attack & will make an android app so that people can
easily detect their disease. It will help everyone to predict their disease.
