Detection of coronary artery disease using deep learning algorithms
AbstractAim of the study was to analyze the possibility of using neural network analysis to predict the severity of coronary bed lesion.
Material and methods. The study included 120 patients, who underwent elective or emergency coronary catherization and met the inclusion and exclusion criteria.
Inclusion criteria: patients older 18 years, performed coronary catherization, recorded electrocardiography one day before/or less before the operation.
Exclusion criteria: ECG identification of arrhythmias as the atrial fibrillation, atrioventricular nodal reentrant tachycardia, ventricular tachycardia while recording, previous coronary stenting and/or coronary artery bypass grafting. The method of neural network analysis was used to predict the coronary bed lesion. The machine learning included clinical, laboratory, instrumental (ECG-images) parameters (23 parameters in total). The neural network was used to solve the classification problems, receiving input as the structured data and images and providing output as a multifactorial classification of the main coronary arteries. The ratio for training and testing was 100/20. Supervised learning was used on the available data, where the outcomes were known, and neural network parameters were adjusted to minimize the error by backpropagation.
Results. On a test sample including 20 patients, the AUC score was 0.74, where the accuracy was 80%, sensitivity was 63%, and the specificity was 88%.
Conclusion. Neural network analysis of the available clinical, laboratory and instrumentation data allow to configure the network parameters for further prediction of coronary artery disease. The results obtained in the form of an AUC score allow to consider this method to be effective in the coronary artery disease diagnosis.
Keywords:coronary arteries, neural networks, deep learning, percutaneous coronary intervention, cardiovascular disease risk
Funding. The study had no sponsor support.
Conflict of interests. The authors declare no conflict of interests.
For citation: Abdualimov T.P., Obrezan A.G. Detection of coronary artery disease using deep learning algorithms. Kardiologiya: novosti, mneniya, obuchenie [Cardiology: News, Opinions, Training]. 2021; 9 (2): 9-13. DOI: https://doi.org/10.33029/2309-1908-2021-9-2-9-13 (in Russian)
REFERENCES
1. Boytsov S.A., Demkina A.E., Oshchepkova E.V., Dolgusheva Yu.A. Progress and Problems of Practical Cardiology in Russia at the Present Stage. Kardiologiia [Cardiology]. 2019; 59 (3): 53–9. DOI: https://doi.org/10.18087/cardio.2019.3.10242 (in Russian)
2. Al’Aref S.J., Singh G, van Rosendael A.R., Kolli K.K., Ma X., Maliakal G., Pandey M., Lee B.C., Wang J., Xu Z., Zhang Y., Min J.K., Wong S.C., Minutello R.M. Determinants of In‐Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning. Journal of the American Heart Association. 2019; 8: e011160. DOI: https://www.doi.org/10.1161/JAHA.118.011160
3. Kakadiaris I.A., Vrigkas M., Yen A.A., Kuznetsova T., Budoff M., Naghavi M. Machine Learning Outperforms ACC/AHA CVD Risk Calculator in MESA. Journal of the American Heart Association. 2018; 7: e009476. DOI: https://www.doi.org/10.1161/JAHA.118.009476
4. Alaa A.M., Bolton T., Di Angelantonio E., Rudd J.H.F., van der Schaar M. Cardiovascular disease risk prediction using automated machine learning: A prospective study of 423,604 UK Biobank participants. PLoS One. 2019; 14 (5): e0213653. DOI: https://www.doi.org/10.1371/journal.pone.0213653
5. Ambale-Venkatesh B., Yang X., Wu C.O., Liu K., Hundley W.G., McClelland R., Gomes A.S., Folsom A.R., Shea S., Guallar E., Bluemke D.A., Lima J.A.C. Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis. Circ Res. 2017; 121 (9): 1092–101. DOI: https://www.doi.org/10.1161/CIRCRESAHA.117.311312