Journal of Ilam University of Medical Sciences

fa From Data to Treatment: Early Detection of Heart Disease Using Machine Learning Techniques From Data to Treatment: Early Detection of Heart Disease Using Machine Learning Techniques آمار stats پژوهشي Research <div style="text-align: left;">Introduction: Early detection of cardiovascular diseases (CVDs) is a significant challenge in the medical field. As one of the leading causes of mortality worldwide, CVDs require timely and accurate diagnosis for effective prevention. Delayed diagnoses often result from limitations in traditional methods and the insufficient identification of risk factors. This study aimed to enhance the accuracy of heart disease prediction using machine learning techniques. Materials & Methods: This research assessed the detection rate and accuracy of cardiovascular disease prediction using machine learning algorithms, including logistic regression, the C5.0 decision tree, neural networks, and mixed models. Data from the Cleveland Clinic dataset, comprising 303 samples and 13 clinical features, were analyzed. Performance metrics such as accuracy, sensitivity, and specificity were used to evaluate the models. Data analysis was conducted using SPSS Modeler 18 software. Results:  The evaluated models demonstrated varying accuracies ranging from 85% to 93%. The hybrid model achieved the best performance with an accuracy of 93.44%. Additionally, ST slope, chest pain type, and fasting blood sugar were identified as the most significant risk factors for cardiovascular diseases. Conclusion:  Machine learning algorithms offer significant potential for the early detection of cardiovascular diseases, thereby reducing mortality rates. These techniques enable precise analysis of clinical data, improve medical decision-making, and enhance treatment outcomes.</div> <div style="text-align: left;"></div> <div style="text-align: justify;">Introduction: Early detection of cardiovascular diseases (CVDs) is a significant challenge in the medical field. As one of the leading causes of mortality worldwide, CVDs require timely and accurate diagnosis for effective prevention. Delayed diagnoses often result from limitations in traditional methods and the insufficient identification of risk factors. This study aimed to enhance the accuracy of heart disease prediction using machine learning techniques. Materials & Methods: This research assessed the detection rate and accuracy of cardiovascular disease prediction using machine learning algorithms, including logistic regression, the C5.0 decision tree, neural networks, and mixed models. Data from the Cleveland Clinic dataset, comprising 303 samples and 13 clinical features, were analyzed. Performance metrics such as accuracy, sensitivity, and specificity were used to evaluate the models. Data analysis was conducted using SPSS Modeler 18 software. Results:  The evaluated models demonstrated varying accuracies ranging from 85% to 93%. The hybrid model achieved the best performance with an accuracy of 93.44%. Additionally, ST slope, chest pain type, and fasting blood sugar were identified as the most significant risk factors for cardiovascular diseases. Conclusion:  Machine learning algorithms offer significant potential for the early detection of cardiovascular diseases, thereby reducing mortality rates. These techniques enable precise analysis of clinical data, improve medical decision-making, and enhance treatment outcomes. </div> Cardiovascular Diseases, Early Diagnosis, Machine Learning, Risk Factors, Predictive Analytics Cardiovascular Diseases, Early Diagnosis, Machine Learning, Risk Factors, Predictive Analytics 72 89 http://sjimu.medilam.ac.ir/browse.php?a_code=A-10-8361-1&slc_lang=fa&sid=1 Mostafa Yousofi Tezerjan Mostafa Yousofi Tezerjan yousofi@uast.ac.ir 9600319475328460050507 9600319475328460050507 No Dept of Industry, University of Applied Science and Technology, Tehran, Iran Dept of Industry, University of Applied Science and Technology, Tehran, Iran Maryam Mollabagher Maryam Mollabagher mollabagher@uast.ac.ir 9600319475328460050508 9600319475328460050508 Yes Dept of Management and Social Services, University of Applied Science and Technology, Tehran, Iran Dept of Management and Social Services, University of Applied Science and Technology, Tehran, Iran