Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis
Coronary Artery Disease (CAD) occurs when the coronary vessels become hardened and narrowed, limiting blood flow to the heart muscles. It is the most common type of heart disease and has the highest mortality rate. Early diagnosis of CAD can prevent the disease from progressing and can make treatmen...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/6/1081 |
| _version_ | 1797612390907379712 |
|---|---|
| author | Ferdi Özbilgin Çetin Kurnaz Ertan Aydın |
| author_facet | Ferdi Özbilgin Çetin Kurnaz Ertan Aydın |
| author_sort | Ferdi Özbilgin |
| collection | DOAJ |
| description | Coronary Artery Disease (CAD) occurs when the coronary vessels become hardened and narrowed, limiting blood flow to the heart muscles. It is the most common type of heart disease and has the highest mortality rate. Early diagnosis of CAD can prevent the disease from progressing and can make treatment easier. Optimal treatment, in addition to the early detection of CAD, can improve the prognosis for these patients. This study proposes a new method for non-invasive diagnosis of CAD using iris images. In this study, iridology, a method of analyzing the iris to diagnose health conditions, was combined with image processing techniques to detect the disease in a total of 198 volunteers, 94 with CAD and 104 without. The iris was transformed into a rectangular format using the integral differential operator and the rubber sheet methods, and the heart region was cropped according to the iris map. Features were extracted using wavelet transform, first-order statistical analysis, a Gray-Level Co-Occurrence Matrix (GLCM), and a Gray Level Run Length Matrix (GLRLM). The model’s performance was evaluated based on accuracy, sensitivity, specificity, precision, score, mean, and Area Under the Curve (AUC) metrics. The proposed model has a 93% accuracy rate for predicting CAD using the Support Vector Machine (SVM) classifier. With the proposed method, coronary artery disease can be preliminarily diagnosed by iris analysis without needing electrocardiography, echocardiography, and effort tests. Additionally, the proposed method can be easily used to support telediagnosis applications for coronary artery disease in integrated telemedicine systems. |
| first_indexed | 2024-03-11T06:41:31Z |
| format | Article |
| id | doaj.art-1aa6c3ad8fde4325b99c42cc13a59e37 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T06:41:31Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-1aa6c3ad8fde4325b99c42cc13a59e372023-11-17T10:34:04ZengMDPI AGDiagnostics2075-44182023-03-01136108110.3390/diagnostics13061081Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris AnalysisFerdi Özbilgin0Çetin Kurnaz1Ertan Aydın2Department of Electrical and Electronic Engineering, Giresun University, Giresun 28200, TurkeyDepartment of Electrical and Electronic Engineering, Ondokuz Mayıs University, Samsun 55139, TurkeyFaculty of Medicine, Department of Cardiology, Giresun University, Giresun 28200, TurkeyCoronary Artery Disease (CAD) occurs when the coronary vessels become hardened and narrowed, limiting blood flow to the heart muscles. It is the most common type of heart disease and has the highest mortality rate. Early diagnosis of CAD can prevent the disease from progressing and can make treatment easier. Optimal treatment, in addition to the early detection of CAD, can improve the prognosis for these patients. This study proposes a new method for non-invasive diagnosis of CAD using iris images. In this study, iridology, a method of analyzing the iris to diagnose health conditions, was combined with image processing techniques to detect the disease in a total of 198 volunteers, 94 with CAD and 104 without. The iris was transformed into a rectangular format using the integral differential operator and the rubber sheet methods, and the heart region was cropped according to the iris map. Features were extracted using wavelet transform, first-order statistical analysis, a Gray-Level Co-Occurrence Matrix (GLCM), and a Gray Level Run Length Matrix (GLRLM). The model’s performance was evaluated based on accuracy, sensitivity, specificity, precision, score, mean, and Area Under the Curve (AUC) metrics. The proposed model has a 93% accuracy rate for predicting CAD using the Support Vector Machine (SVM) classifier. With the proposed method, coronary artery disease can be preliminarily diagnosed by iris analysis without needing electrocardiography, echocardiography, and effort tests. Additionally, the proposed method can be easily used to support telediagnosis applications for coronary artery disease in integrated telemedicine systems.https://www.mdpi.com/2075-4418/13/6/1081irisiridologycoronary artery diseasediagnosismachine learning |
| spellingShingle | Ferdi Özbilgin Çetin Kurnaz Ertan Aydın Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis Diagnostics iris iridology coronary artery disease diagnosis machine learning |
| title | Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis |
| title_full | Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis |
| title_fullStr | Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis |
| title_full_unstemmed | Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis |
| title_short | Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis |
| title_sort | prediction of coronary artery disease using machine learning techniques with iris analysis |
| topic | iris iridology coronary artery disease diagnosis machine learning |
| url | https://www.mdpi.com/2075-4418/13/6/1081 |
| work_keys_str_mv | AT ferdiozbilgin predictionofcoronaryarterydiseaseusingmachinelearningtechniqueswithirisanalysis AT cetinkurnaz predictionofcoronaryarterydiseaseusingmachinelearningtechniqueswithirisanalysis AT ertanaydın predictionofcoronaryarterydiseaseusingmachinelearningtechniqueswithirisanalysis |