Heart Disease Prediction Using ML

Abstract

Machine Learning and artificial intelligence have found valuable on variety of disciplines during their growth, particularly in the light of massive increase in data in recent years. It has the potential to be more dependable in terms of producing quicker and more accurate illness prediction judgments. Therefore, the use of machine learning algorithms to forecast different diseases is growing. Building a model can also aid in the visualization and analysis of diseases to increase the accuracy and consistency of reporting. This article has looked into using several machine learning algorithms to identify cardiac disease. This article's study has demonstrated a step procedure. In a dataset on heart disease initially prepared in the format needed to run machine learning algorithms. The UCI is the source of patient medical records and other data. The presence are absence of heart disease in patients is then ascertained using the heart disease dataset. Second, this paper presents a number of noteworthy findings. The confusion matrix is used to validate the accuracy rate of machine learning methods, including Gradient Boosting Classifier, Support Vector Machine, and Logistic Regression. According to recent research, the Logistic Regression method outperforms other algorithms in terms of accuracy, yielding a high 95% rate. It also outperforms the other four algorithms in terms of recall, precision, and f1-score correctness. The difficult and future research component of this project will be raising the accuracy rates of the machine learning algorithms to between 97% and 100%.