The Utilization of Machine Learning Algorithms in the Diagnosis of Heart Disease

• Published in: 2023 International Conference on IoT, Communication and Automation Technology (ICICAT) pp. 1 - 6
• Main Authors: Dutt, Ankit, Sharma, Swati
• Format: Conference Proceeding
• Language: English
• Published: IEEE 23.06.2023
• Subjects: Codes; Feature selection; Heart; Heart Disease; Libraries; Machine Learning; Machine learning algorithms; Naive Bayes methods; Prediction Model; Stochastic processes; Support vector machine; Support vector machines
• DOI: 10.1109/ICICAT57735.2023.10263723

According to data compiled by the World Health Organisation, heart disease and stroke account for 17.9 million annual deaths worldwide. Conditions including cardiac arrhythmias, stroke, and Cardiovascular rheumatism all belong to the larger category of heart and circulatory system illnesses. Stroke causes more than 80% of all fatalities from CVD, and it's the leading cause of mortality for those under 70 years old. In this study, we train and evaluate the k-nearest neighbour approach, the naive Bayes classifier, the stochastic gradient classifier, and the support vector machine using the Kaggle dataset of around 4238 individuals-to predict cardiovascular disease. Accuracy, Precision, recall, and f-score were only few of the criteria used to evaluate the various model's performance. Consequently, the stochastic gradient classifier model obtained a maximum accuracy of 93% in the heart condition dataset. The Jupyter notebook is the ideal tool for implementing Python code since it comes with a plethora of libraries and standard header files that guarantee flawless results.