Non-invasive detection of coronary artery disease in high-risk patients based on the stenosis prediction of separate coronary arteries. (August 2018)

• Record Type: Journal Article
• Authors: Alizadehsani, Roohallah; Hosseini, Mohammad Javad; Khosravi, Abbas; Khozeimeh, Fahime; Roshanzamir, Mohamad; Sarrafzadegan, Nizal; Nahavandi, Saeid
• Is Part Of: Computer methods and programs in biomedicine. Volume 162(2018)
• Page Start: 119
• Page End: 127
• Publication Date: 2018-08
• Subjects: Coronary artery disease -- Feature selection -- Support vector machine -- Naive Bayes and C4.5 classifiers; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2018.05.009
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We extended Z-Alizadeh Sani dataset from 303 to 500 records. High accuracy and sensitivity were achieved for diagnosis of CAD. For the first time LAD, LCX and RCA stenosis diagnosis are used for CAD detection. This new method obviates the need for angiography. Abstract: Background and objective: Cardiovascular diseases are an extremely widespread sickness and account for 17 million deaths in the world per annum. Coronary artery disease (CAD) is one of such diseases with an annual mortality rate of about 7 million. Thus, early diagnosis of CAD is of vital importance. Angiography is currently the modality of choice for the detection of CAD. However, its complications and costs have prompted researchers to seek alternative methods via machine learning algorithms. Methods: The present study proposes a novel machine learning algorithm. The proposed algorithm uses three classifiers for detection of the stenosis of three coronary arteries, i.e., left anterior descending (LAD), left circumflex (LCX) and right coronary artery (RCA) to get higher accuracy for CAD diagnosis. Results: This method was applied on the extension of Z-Alizadeh Sani dataset which contains demographic, examination, ECG, and laboratory and echo data of 500 patients. This method achieves an accuracy, sensitivity and specificity rates of 96.40%, 100% and 88.1%, respectively for the detection of CAD. To our knowledge, such high rates of accuracy and sensitivity have not been attained elsewhere before. Conclusion: This new algorithm reliably distinguishes those with normal coronary arteries from those with CAD which may obviate the need for angiography in the normal group.