PREDICTING THE RISK OF MYOCARDIAL INFARCTION USING DIFFERENT CLASSIFICATION ALGORITHMS
Journal Title: Acta HealthMedica - Year 2017, Vol 2, Issue 1
Abstract
Introduction: According to WHO, cardiovascular diseases (CVDs) are the leading cause of death globally. Although significant progress has been made in the diagnosis of CVDs, more investigation can be helpful. Considering the significant role of data mining techniques in discovering hidden trends in health data, the present study aimed to predict the risk of myocardial infarction (MI) using k-nearest neighbor (KNN), neural network, decision tree (C5), and Bayesian network algorithms. Methods: The present study is an analytical study. Considering CRISP methodology, data-mining analysis was carried out using KNN, neural network, C5, and Bayesian network algorithms by IBM SPSS modeler (Clementine 14.2) software. The applied data were related to 350 patients admitted to the Shahid Rajaei specialized cardiovascular hospital. However, after cleaning the data, only 274 records were entered in final analysis. Results: This study revealed that the highest percentages of correct classifications achieved were 67.42%, 64.04%, 60.67%, and 60.67% for the KNN, C5, neural network, and Bayesian network algorithms, respectively. The results also revealed that smoking was the leading risk factor for MI. Conclusion: In terms of accuracy, KNN was the most effective algorithm in predicting MI, followed by C5, neural network, and Bayesian network.
Authors and Affiliations
Fatemeh Rahimi, Mahdi Nasiri, Reza Safdari, Roxana Sharifian, Goli Arji, Zahra khanom Hashemi
Keywords
Related Articles
- EP ID EP351177
- DOI 10.19082/ah134
- Views 116
- Downloads 0
DECISION SUPPORT ALGORITHMS FOR CLINICAL EVALUATION OF EEG; EXPERIENCE OF ADHD CHILDREN
Introduction: Attention deficit hyperactivity disorder (ADHD), as one of the most common neuro-behavioral disorders, is caused as a result of brain dysfunction and, depending on the age and frequency, can heavily affect...
RECOMMENDATIONS FOR REGISTRATION AND SURVEILLANCE SYSTEM OF OCCUPATIONAL TOXICITIES AND DISEASES
Introduction: Occupational toxicities and diseases must be registered and have a surveillance system so that they could be treated and followed up better and sooner. The objective is the recommendations for a registratio...
A WEB 2.0 FRAMEWORK FOR MEDICINAL HERB AND TRADITIONAL MEDICINE
Introduction: Nowadays traditional medicine has received significant attention due to its many advantages compared with conventional treatments. In Iran, with regards to the long brilliant and ancient experience and cult...
ASSESSMENT OF DETERMINANTS FOR NEONATAL MORTALITY RISK PREDICTION DECISION SUPPORT SYSTEM
Introduction: In recent years, many decision-making systems have been proposed for neonatal intensive care units, were the high-risk neonates are taken care of. Hence, using these tools helped to decrease neonatal mortal...
USABILITY EVALUATION OF ADMISSION INFORMATION SYSTEMS IN MASHHAD UNIVERSITY OF MEDICAL SCIENCES HOSPITALS: A HEURISTIC EVALUATION
Introduction: The admission department is one of the most important hospital departments, where patients contact with the hospital at first and begin assessing hospital services. An admission information system is a part...