Статья
Методы машинного обучения в оценке предтестовой вероятности обструктивных и необструктивных поражений коронарного русла
В обзоре представлен анализ научной литературы по результатам использования методов машинного обучения (МО) для оценки предтестовой вероятности (ПТВ) обструктивных (ОПКА) и необструктивных (НПКА) поражений коронарных артерий (КА) у больных с различными клиническими вариантами ишемической болезни сердца. Приведены данные о высокой распространенности НПКА среди лиц, направляемых на инвазивную коронарографию (КАГ), что послужило поводом для разработки моделей и алгоритмов на основе методов МО для использования в качестве дополнительных инструментов ПТВ, позволяющих прогнозировать анатомический статус КА до проведения КАГ Применение современных технологий моделирования обладает большим потенциалом в верификации НПКА и ОПКА. Подчеркивается, что совершенствование прогностических моделей и их внедрение в клиническую практику является важным элементом поддержки принятия врачебных решений и должно осуществляться на основе междисциплинарной научной кооперации клиницистов и специалистов в области информационных технологий.
1. The World Health Organization the top ten causes of death fact sheet. Available at: http://www.who.int/mediacentre/factsheets/fs310/en/ (28 May 2018).
2. Бойцов С. А., Шальнова С. А., Деев А. Д. Эпидемиологическая ситуация как фактор, определяющий стратегию действий по снижению смертности в Российской Федерации. Терапевтический архив. 2020;92(1):4-9. doi:10.26442/00403660.2020.01.000510.
3. Sumin AN. The assessment of pretest probability in obstructive coronary lesion diagnostics: unresolved issues. Russ J Cardiol. 2017;(11):68-76. (In Russ.). Сумин А. Н. Оценка предтестовой вероятности в диагностики обструктивных поражений коронарных артерий: нерешенные вопросы. Российский кардиологический журнал. 2017;(11):68-76. doi:10.15829/1560-4071-2017-11-68-76.
4. Wang ZJ, Zhang LL, Elmariah S, et al. Prevalence and Prognosis of Nonobstructive Coronary Artery Disease in Patients Undergoing Coronary Angiography or Coronary Computed Tomography Angiography: A Meta-Analysis. Mayo Clin Proc. 2017;92(3):329-46. doi:10.1016/j.mayocp.2016.11.016.
5. Scalone G, Niccoli G, Crea F. Editor's Choice — Pathophysiology, diagnosis and management of MINOCA: an update. Eur Heart J Acute Cardiovasc Care. 2019;8(1):54-62. doi:10.1177/2048872618782414.
6. Planer D, Mehran R, Ohman EM, et al. Prognosis of patients with non-ST-segment-elevation myocardial infarction and nonobstructive coronary artery disease: propensitymatched analysis from the Acute Catheterization and Urgent Intervention Triage Strategy Trial. Circ Cardiovasc Interv. 2014;7:285-93. doi:10.1161/circinterventions.113.000606.
7. Agewall S, Beltrame JF, Reynolds HR, et al. ESC working group position paper on myocardial infarction with non-obstructive coronary arteries. Eur Heart J. 2017;38(3):143-53. doi:10.1093/eurheartj/ehw149.
8. Fihn SD, Blankenship JC, Alexander KP, et al. 2014 ACC/AHA/AATS/PCNA/SCAI/STS focused update of the guideline for the diagnosis and management of patients with stable ischemic heart disease. Journal of the American College of Cardiology. 2014;64(18):1929-49. doi:10.1016/j.jacc.2014.07.017.
9. Knuuti J, Wijns W, Saraste A, et al. 2019 ESC Guidelines on the diagnosis and management of chronic coronary syndromes: The Task Force for diagnosis and management of chroni coronary syndromes of the European Society of Cardiology (ESC). Eur Heart J. 2020;41:407-77. doi:101093/eurheartj/ehz425.
10. Smeeth L, Skinner JS, Ashcroft J, et al. Chest Pain Guideline Development Group. NICE clinical guideline: chest pain of recent onset. Br J Gen Pract. 2010;60(577) :607-10. doi:10.3399/bjgp10X515124.
11. Alizadehsani R, Hosseini MJ, Khosravi A, et al. Non-invasive detection of coronary artery disease in high-risk patients based on the stenosis prediction of separate coronary arteries. Computer Methods and Programs in Biomedicine. 2018;162:119-27. doi:10.1016/j.cmpb.2018.05.009.
12. Abe M, Morimoto T, Akao M, et al. Relation of Contrast-Induced Nephropathy to LongTerm Mortality After Percutaneous Coronary Intervention. The American Journal of Cardiology. 2014;114(3):362-8. doi:10.1016/j.amjcard.2014.05.009.
13. Корок Е. В., Сумин А. Н. Сложности в диагностике обструктивных поражений коронарных артерий: роль неинвазивных тестов. Комплексные проблемы сердечно-сосудистых заболеваний. 2019;8(1):70-9. doi:10.17802/2306-1278-2019-8-1-70-79.
14. Diamond GA, Forrester JS. Analysis of Probability as an Aid in the Clinical Diagnosis of Coronary-Artery Disease. New England Journal of Medicine. 1979;300(24): 1350-58. doi:10.1056/nejm197906143002402.
15. Genders TS, Steyerberg EW, Alkadhi H, et al. A clinical prediction rule for the diagnosis of coronary artery disease: validation, updating, and extension. Eur Heart J. 2011;32:1316-30. doi:10.1093/eurheartj/ehr014.
16. Genders TS, Steyerberg EW, Hunink MG, et al. Prediction model to estimate presence of coronary artery disease: retrospective pooled analysis of existing cohorts. BMJ. 2012;344:e3485. doi:10.1136/bmj.e3485.
17. Bittencourt MS, Hulten E, Polonsky TS, et al. European Society of Cardiology-recommended coronary artery disease consortium pretest probability scores more accurately predict obstructive coronary disease and cardiovascular events than the Diamond and Forrester Score: The Partners Registry. Circulation. 2016;134:201-11. doi:10.1161/circulationaha.116.023396.
18. Baskaran L, Danad I, Gransar H, et al. A Comparison of the Updated Diamond-Forrester, CAD Consortium, and CONFIRM History-Based Risk Scores for Predicting Obstructive Coronary Artery Disease in Patients With Stable Chest Pain. JACC: Cardiovascular Imaging. 2019;12(7 Pt 2):1392-400. doi:10.1016/j.jcmg.2018.02.020.
19. Juarez-Orozco LE, Saraste A, Capodanno D, et al. Impact of a decreasing pre-test probability on the performance of diagnostic tests for coronary artery disease. Eur Hear J — Cardiovasc Imaging. 2019;20:1198-207. doi:101093/ehjci/jez054.
20. Cheng VY, Berman DS, Rozanski A, et al. Performance of the traditional age, sex, and angina typicality-based approach for estimating pretest probability of angiographically significant coronary artery disease in patients undergoing coronary computed tomographic angiography: results from the multinational coronary CT angiography evaluation for clinical outcomes: an international multicenter registry (CONFIRM). Circulation. 2011;124:2423-32, 1-8. doi:10.1161/circulationaha.111.039255.
21. Foldyna B, Udelson JE, Karady J, et al. Pretest probability for patients with suspected obstructive coronary artery disease: re-evaluating Diamond-Forrester for the contemporary era and clinical implications: insights from the PROMISE trial. Eur Heart J Cardiovasc Imaging. 2019;20:574-81. doi:10.1093/ehjci/jey182.
22. Adamson PD, Newby DE, Hill CL, et al. Comparison of international guidelines for assessment of suspected stable angina: insights from the PROMISE and SCOT-HEART. JACC Cardiovasc Imaging. 2018;11:1301-10. doi:10.1016/j.jcmg.2018.06.021.
23. Reeh J, Therming CB, Heitmann M, et al. Prediction of obstructive coronary artery disease and prognosis in patients with suspected stable angina. Eur Heart J. 2019;40:1426-35. doi:10.1093/eurheartj/ehy806.
24. Neglia D, Rovai D, Caselli C, et al. Detection of significant coronary artery disease by noninvasive anatomical and functional imaging. Circ Cardiovasc Imaging. 2015; 8.pii:e002179. doi:10.1161/circimaging.114.002179.
25. Saraste A, Barbato E, Capodanno D, et al. Imaging in ESC clinical guidelines: chronic coronary syndromes. European Heart Journal — Cardiovascular Imaging. 2019;20(11):1187-97 doi:10.1093/ehjci/jez219.
26. National Institute for Health and Care Excellence. Chest pain of recent onset: assessment and diagnosis of recent onset chest pain or discomfort of suspected cardiac origin (update) Clinical guideline 95. London: National Institute for Health and Care Excellence; 2016 ISBN: 978-1-4731-2182-9.
27. Roe MT, Harrington RA, Prosper DM, et al. Clinical and Therapeutic Profile of Patients Presenting with Acute Coronary Syndromes Who Do Not Have Significant Coronary Artery Disease. Circulation. 2000;102(10):1101-6. doi:10.1161/01.cir.102.10.1101.
28. Ballesteros-Ortega D, Martlnez-Gonzalez O, Blancas R, et al. Characteristics of patients with myocardial infarction with nonobstructive coronary arteries (MINOCA) from the ARIAM-SEMICYUC registry: development of a score for predicting MINOCA. Vascular Health and Risk Management. 2019;15:57-67. doi:10.2147/vhrm.s185082.
29. Lee HG, Noh KY, Ryu KH. Mining Biosignal Data: Coronary Artery Disease Diagnosis Using Linear and Nonlinear Features of HRV. Lecture Notes in Computer Science. 2007;218-28. doi:10.1007/978-3-540-77018-3_23.
30. Ярославская Е.И., Кузнецов В. А., Горбатенко Е.А., и др. Калькулятор необструктивного коронарного атеросклероза: клинический пример использования у мужчины с подозрением на ишемическую болезнь сердца. Сибирский медицинский журнал. 2018;33(3):93-101. doi:10.29001/2073-8552-2018-33-3-93-101.
31. Zellweger MJ, Brinkert M, Bucher U, et al. A new memetic pattern based algorithm to diagnose/exclude coronary artery disease. International Journal of Cardiology. 2014;174(1):184-6. doi:10.1016/j.ijcard.2014.03.184.
32. Zellweger MJ, Tsirkin A, Vasilchenko V, et al. A new non-invasive diagnostic tool in coronary artery disease: artificial intelligence as an essential element of predictive, preventive, and personalized medicine. EPMA J. 2018;9(3):235-47. doi:10.1007/s13167-018-0142-x.
33. Patidar S, Pachori RB, Acharya UR. Automated diagnosis of coronary artery disease using tunable-Q wavelet transform applied on heart rate signals. Knowledge-Based Systems. 2015; 82:1-10. doi:101016/j.knosys.2015.02.011.
34. Kim JK, Kang S. Neural Network-Based Coronary Heart Disease Risk Prediction Using Feature Correlation Analysis. Journal of Healthcare Engineering. 2017; 1-13. doi:10.1155/2017/2780501.
35. Banerjee R, Ghose A, Sinha A, et al. A multi-modal approach for non-invasive detection of coronary artery disease. Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers — UbiComp/ISWC '19. doi:101145/3341162.3349331.
36. Kurt I, Ture M, Kurum AT. Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease. Expert Systems with Applications. 2008;34(1):366-74. doi:10.1016/j.eswa.2006.09.004.
37. Babaoglu I, Findik O, Bayrak M. Effects of principle component analysis on assessment of coronary artery diseases using support vector machine. Expert Systems with Applications. 2010;37(3):2182-5. doi:10.1016/j.eswa.2009.07.055.
38. Babaoglu I, Findik O, Ulker E. A comparison of feature selection models utilizing binary particle swarm optimization and genetic algorithm in determining coronary artery disease using support vector machine. Expert Systems with Applications. 2010;37(4):3177-83. doi:10.1016/j.eswa.2009.09.064.
39. Das R, Turkoglu I, Sengur A. Effective diagnosis of heart disease through neural networks ensembles. Expert Systems with Applications. 2009;36(4):7675-80. doi:10.1016/j.eswa.2008.09.013.
40. Dogan MV, Grumbach IM, Michaelson JJ, et al. Integrated genetic and epigenetic prediction of coronary heart disease in the Framingham Heart Study. PLOS ONE. 2018;13(1):e0190549. doi:10.1371/journal.pone.0190549.
41. Ordonez C, Omiecinski E, de Braal L, et al. Mining constrained association rules to predict heart disease. Proceedings 2001 IEEE International Conference on Data Mining. doi:10.1109/icdm.2001.989549.
42. Babaoglu I, Baykan OK, Aygul N, et al. Assessment of exercise stress testing with artificial neural network in determining coronary artery disease and predicting lesion localization. Expert Systems with Applications. 2009;36(2):2562-6. doi:10.1016/j.eswa.2007.11.013.
43. Abdar M, Ksi^zek W, Acharya UR, et al. A New Machine Learning Technique for an Accurate Diagnosis of Coronary Artery Disease. Computer Methods and Programs in Biomedicine. 2019;179:104992. doi:10.1016/j.cmpb.2019.104992.