Related Experiment Videos
Predicting coronary artery disease using different artificial neural network models
M Cengiz Colak1, Cemil Colak, Hasan Kocatürk
1Department of Cardiovascular Surgery, Faculty of Medicine University of Firat, Elaziğ, Turkey. cemilcolak@yahoo.com
Insights
Artificial neural network (ANN) models show high accuracy in predicting coronary artery disease (CAD). These models offer a promising, non-invasive approach for clinical decision-making in CAD prediction.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Informatics
Background:
- Coronary artery disease (CAD) diagnosis often relies on invasive procedures.
- Developing accurate non-invasive prediction models for CAD is crucial for early detection and management.
- Artificial neural networks (ANNs) offer potential for complex pattern recognition in medical data.
Purpose of the Study:
- To evaluate the efficacy of eight different learning algorithms in creating artificial neural network (ANN) models for coronary artery disease (CAD) prediction.
- To compare the performance of various ANN models in identifying CAD.
- To assess the potential of ANN models as a non-invasive tool for CAD risk stratification.
Main Methods:
- A retrospective case-control study involving 124 patients diagnosed with CAD and 113 controls with normal coronary arteries.
- Application of multi-layered perceptrons ANN architecture.
- Training and testing of ANN models on 237 records (171 training, 66 testing) using eight distinct learning algorithms.
- Performance evaluation based on sensitivity, specificity, and accuracy.
Main Results:
- ANN models trained with eight different learning algorithms demonstrated promising predictive performance for CAD.
- High sensitivity, specificity, and accuracy values were achieved, exceeding 71% for testing data.
- For training data, accuracy ranged from 83.63%-100%, sensitivity from 86.46%-100%, and specificity from 74.67%-100%.
Conclusions:
- ANN models trained with various learning algorithms show significant potential for predicting CAD.
- Further improvements in prediction performance may be achieved by exploring algorithms beyond backpropagation and increasing sample sizes.
- These ANN models represent a promising non-invasive approach for CAD prediction, aiding clinical decision-making.
Objective:
Eight different learning algorithms used for creating artificial neural network (ANN) models and the different ANN models in the prediction of coronary artery disease (CAD) are introduced.
Methods:
This work was carried out as a retrospective case-control study. Overall, 124 consecutive patients who had been diagnosed with CAD by coronary angiography (at least 1 coronary stenosis > 50% in major epicardial arteries) were enrolled in the work. Angiographically, the 113 people (group 2) with normal coronary arteries were taken as control subjects. Multi-layered perceptrons ANN architecture were applied. The ANN models trained with different learning algorithms were performed in 237 records, divided into training (n=171) and testing (n=66) data sets. The performance of prediction was evaluated by sensitivity, specificity and accuracy values based on standard definitions.
Results:
The results have demonstrated that ANN models trained with eight different learning algorithms are promising because of high (greater than 71%) sensitivity, specificity and accuracy values in the prediction of CAD. Accuracy, sensitivity and specificity values varied between 83.63%-100%, 86.46%-100% and 74.67%-100% for training, respectively. For testing, the values were more than 71% for sensitivity, 76% for specificity and 81% for accuracy.
Conclusions:
It may be proposed that the use of different learning algorithms other than backpropagation and larger sample sizes can improve the performance of prediction. The proposed ANN models trained with these learning algorithms could be used a promising approach for predicting CAD without the need for invasive diagnostic methods and could help in the prognostic clinical decision.