Статья
Машинное обучение в прогнозировании ближайших и отдаленных результатов реваскуляризации миокарда: систематический обзор
Методы машинного обучения (МО) относятся к основным инструментам искусственного интеллекта и все шире используются в популяционной и клинической кардиологии для стратификации рисков развития сердечно-сосудистых заболеваний и их осложнений. В систематическом обзоре представлен анализ научной литературы по результатам использования различных методов МО (искусственных нейронных сетей, случайного леса, стохастического градиентного бустинга, машины опорных векторов и др.) для разработки прогностических моделей, определяющих риск развития неблагоприятных событий в ближайшем и отдаленном периодах после коронарного шунтирования и чрескожных коронарных вмешательств. Большинство исследований по данной проблеме сосредоточено на создании новых прогностических моделей c более высокой предсказательной ценностью, что является базовым условием для их внедрения в клиническую практику. Подчеркивается, что совершенствование технологий моделирования и разработка на этой основе практико-ориентированных инструментов поддержки принятия врачебных решений относится к одному из наиболее перспективных направлений цифровизации здравоохранения, востребованных в повседневной профессиональной деятельности.
1. The World Health Organization the top ten causes of death fact sheet. https://www.who.int/health-topics/cardiovascular-diseases#tab=tab_1 (1 May 2021).
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. Emelia JB, Paul M, Alonso A, et al. Heart Disease and Stroke Statistics — 2019 Update: A Report From the American Heart Association. Circulation. 2019;139:e56-e528. doi:10.1161/CIR.0000000000000659.
4. Neumann FJ, Sousa-Uva M, Ahlsson A, et al. 2018 ESC/EACTS Guidelines on myocardial revascularization. European Heart Journal. 2019;40(2):87-165. doi:10.1093/eurheartj/ehy394.
5. Chou YY, Hwang JJ, Tung YC. Optimal surgeon and hospital volume thresholds to reduce mortality and length of stay for CABG. PLoS One. 2021;16(4):e0249750. doi:10.1371/journal.pone.0249750.
6. Inohara T, Kohsaka S, Yamaji K, et al. Risk stratification model for in-hospital death in patients undergoing percutaneous coronary intervention: a nationwide retrospective cohort study in Japan. BMJ Open. 2019;9(5):e026683. doi:10.1136/bmjopen-2018-026683.
7. Гельцер Б.И., Циванюк М.М., Шахгельдян К.И. и др. Методы машинного обучения как инструмент диагностических и прогностических исследований при ишемической болезни сердца. Российский кардиологический журнал. 2020;25(12):3999. doi:10.15829/1560-4071-2020-3999.
8. McCarthy PM. Outcomes after coronary artery bypass: getting better all the time. J. Am. Coll. Cardiol. 2019;73:1887-9. doi:10.1016/j.jacc.2019.01.060.
9. Nashef SA, Roques F, Sharples LD, et al. EuroSCORE II. European Journal of CardioThoracic Surgery, 2012;41(4):734-45. doi:10.1093/ejcts/ezs043.
10. Shahian MD, Jeffrey P, Vinay B, et al. STS 2018 ADULT CARDIAC RISK MODELS PART 1. Ann Thorac Surg. 2018;105:1411-8. doi:10.1016/j.athoracsur.2018.03.002.
11. Stone GW, Kappetein AP, Sabik JF, et al. Five-Year Outcomes after PCI or CABG for Left Main Coronary Disease. N Engl J Med. 2019;381:1820-30. doi:10.1056/NEJMoa1909406.
12. Lamy A, Eikelboom J, Sheth T, et al. Rivaroxaban, Aspirin, or Both to Prevent Early Coronary Bypass Graft Occlusion: The COMPASS-CABG Study. J Am Coll Cardiol. 2019;73(2):121-30. doi:10.1016/j.jacc.2018.10.048.
13. Holm NR, Mäkikallio T, Lindsay MM, et al. Percutaneous coronary angioplasty versus coronary artery bypass grafting in the treatment of unprotected left main stenosis: updated 5-year outcomes from the randomised, non-inferiority NOBLE trial. Lancet. 2020;395(10219):191-9. doi:10.1016/S0140-6736(19)32972-1.
14. Kosmidou I, Chen S, Kappetein AP, et al. New-Onset Atrial Fibrillation After PCI or CABG for Left Main Disease: The EXCEL Trial. J Am Coll Cardiol. 2018;71(7):739-48. doi:10.1016/j.jacc.2017.12.012.
15. Ganyukov V, Kochergin N, Shilov A, et al. Randomized Clinical Trial of Surgical vs. Percutaneous vs. Hybrid Revascularization in Multivessel Coronary Artery Disease: Residual Myocardial Ischemia and Clinical Outcomes at One Year-Hybrid coronary REvascularization Versus Stenting or Surgery (HREVS). J Interv Cardiol. 2020;2020:5458064. doi:10.1155/2020/5458064.
16. Moher D, Liberati A, Tetzlaff J, et al. The PRISMA Group. Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement. PLoS Medicine. 2009;6(7):e1000097. doi:10.1371/journal.pmed.1000097.
17. Ter Woorst JF, van Straten AHM, Houterman S, et al. Sex Difference in Coronary Artery Bypass Grafting: Preoperative Profile and Early Outcome. J Cardiothorac Vasc Anesth. 2019;33(10):2679-84. doi:10.1053/j.jvca.2019.02.040.
18. Vidotti E, Vidotti LFK, Arruda Tavares CAG, et al. Predicting postoperative atrial fibrillation after myocardial revascularization without cardiopulmonary bypass: A retrospective cohort study. J Card Surg. 2019;34(7):577-82. doi:10.1111/jocs.14088.
19. AlWaqfi N, Khader Y, Ibrahim K. Coronary artery bypass: predictors of 30-day operative mortality in Jordanians. Asian Cardiovasc Thorac Ann. 2012;20(3):245-51. doi:10.1177/0218492311434647.
20. Manyam RB, Zhang Y, Keeling W, et al. Deep Learning Approach for Predicting 30 Day Readmissions after Coronary Artery Bypass Graft Surgery. NeurlIPS (ML4H). 2018;222 ArXiv:abs/1812.00596.
21. Andersson B, She L, Tan RS, et al. The association between blood pressure and longterm outcomes of patients with ischaemic cardiomyopathy with and without surgical revascularization: an analysis of the STICH trial. Eur Heart J. 2018;39(37):3464-71. doi:10.1093/eurheartj/ehy438.
22. Moore PT, Janssen C, Murphy A, et al. Coronary Angiography and Revascularization Following Coronary Artery Bypass Grafting in British Columbia: Incidence, Predictors and Longer-term Outcomes. Can J Cardiol. 2018;34(8):983-91. doi:10.1016/j.cjca.2018.04.030.
23. Wang Y, Simon MA, Bonde P, et al. Decision tree for adjuvant right ventricular support in patients receiving a left ventricular assist device. J Heart Lung Transplant. 2012;31(2):140-9. doi:10.1016/j.healun.2011.11.003.
24. Goto S, Kimura M, Katsumata Y, et al. Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients. PLoS One. 2019;14(1):e0210103. doi:10.1371/journal.pone.0210103.
25. Wise ES, Stonko DP, Glaser ZA, et al. Prediction of Prolonged Ventilation after Coronary Artery Bypass Grafting: Data from an Artificial Neural Network. Heart Surg Forum. 2017;20(1):E007-E014. doi:10.1532/hsf.1566.
26. Lee HC, Yoon HK, Nam K, et al. Derivation and Validation of Machine Learning Approaches to Predict Acute Kidney Injury after Cardiac Surgery. J Clin Med. 2018;7(10):322. doi:10.3390/jcm7100322.
27. Allyn J, Allou N, Augustin P, et al. A Comparison of a Machine Learning Model with EuroSCORE II in Predicting Mortality after Elective Cardiac Surgery: A Decision Curve Analysis. PLoS One. 2017;12(1):e0169772. doi:10.1371/journal.pone.0169772.
28. Kilic A, Goyal A, Miller JK, et al. Predictive Utility of a Machine Learning Algorithm in Estimating Mortality Risk in Cardiac Surgery. Ann Thorac Surg. 2020;109(6):1811-9. doi:10.1016/j.athoracsur.2019.09.049.
29. Гельцер Б.И., Грицив Р.С., Рублев В.Ю., Шахгельдян К.И. Сравнительная оценка методов машинного обучения в прогнозировании отдаленных результатов аортокоронарного шунтирования. Семнадцатая Национальная конференция по искусственному интеллекту с международным участием. КИИ-2019 Сборник научных трудов: в 2-х томах. 2019. сс. 28-39.
30. Bertsimas D, Orfanoudaki A, Weiner RB. Personalized Treatment for Coronary Artery Disease Patients: A Machine Learning Approach. Circulation. 2020;23(4):482-506. doi:10.1007/s10729-020-09522-4.
31. Al’Aref SJ, Singh G, Rosendael AR, et al. Determinants of In-Hospital Mortality After Percutaneous Coronary Intervention: A Machine Learning Approach. J Am Heart Assoc. 2019;8(5):e011160. doi:10.1161/JAHA.118.011160.
32. Hu D, Huang Z, Chan TM, et al. Utilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome. Int J Environ Res Public Health. 2016;13(9):912. doi:10.3390/ijerph13090912.
33. Berikol GB, Yildiz O, Özcan IT. Diagnosis of Acute Coronary Syndrome with a Support Vector Machine. J Med Syst. 2016;40(4):84. doi:10.1007/s10916-016-0432-6.
34. Sladojevic M, Sladojevic S, Culibrk D, et al. Echocardiographic parameters as predictors of in-hospital mortality in patients with acute coronary syndrome undergoing percutaneous coronary intervention. Scientific World Journal. 2014;2014:818365. doi:10.1155/2014/818365.
35. Peterson ED, Dai D, DeLong ER, et al. Contemporary mortality risk prediction for percutaneous coronary intervention: results from 588,398 procedures in the National Cardiovascular Data Registry. J Am Coll Cardiol. 2010;55(18):1923-32. doi:10.1016/j.jacc.2010.02.005.
36. Hsieh MH, Lin SY, Lin CL, et al. A fitting machine learning prediction model for short-term mortality following percutaneous catheterization intervention: a nationwide population-based study. Ann Transl Med. 2019;7(23):732. doi:10.21037/atm.2019.12.21.
37. Швец Д.А., Карасёв А.Ю., Смоляков М.В. и др. Нейросетевой анализ предикторов летального риска у больных после перенесенного острого коронарного синдрома. Российский кардиологический журнал. 2020;25(3):3645. doi:10.15829/1560-4071-2020-3-3645.
38. Duffy BK, Gurm HS, Rajagopal V, et al. Usefulness of an elevated neutrophil to lymphocyte ratio in predicting long-term mortality after percutaneous coronary intervention. Am J Cardiol. 2006;97(7):993-6. doi:10.1016/j.amjcard.2005.10.034.
39. Pieszko K, Hiczkiewicz J, Budzianowski P, et al. Machine-learned models using hematological inflammation markers in the prediction of short-term acute coronary syndrome outcomes. J Transl Med. 2018;16(1):334. doi:10.1186/s12967-018-1702-5.
40. Berchialla P, Foltran F, Bigi R, et al. Integrating stress-related ventricular functional and angiographic data in preventive cardiology: a unified approach implementing a Bayesian network. J Eval Clin Pract. 2012;18(3):637-43. doi:10.1111/j.1365-2753.2011.01651.x.
41. Kwon JM, Jeon KH, Kim HM, et al. Deep-learning-based risk stratification for mortality of patients with acute myocardial infarction. PLoS One. 2019;14(10):e0224502. doi:10.1371/journal.pone.0224502.
42. Kim YJ, Saqlian M, Lee JY. Deep learning-based prediction model of occurrences of major adverse cardiac events during 1-year follow-up after hospital discharge in patients with AMI using knowledge mining. Personal and Ubiquitous Computing. 2019;23(4):485-94. doi:10.1007/s00779-019-01248-7.
43. Hae H, Kang SJ, Kim WJ, et al. Machine learning assessment of myocardial ischemia using angiography: Development and retrospective validation. PLoS Med. 2018;15(11):e1002693. doi:10.1371/journal.pmed.1002693.
44. Wallert J, Tomasoni M, Madison G, et al. Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data. BMC Med Inform Decis Mak. 2017;17(1):99. doi:10.1186/s12911-017-0500-y.
45. Syed Z, Moscucci M, Share D, et al. Predicting emergency coronary artery bypass graft following PCI: application of a computational model to refer patients to hospitals with and without onsite surgical backup. Open Heart. 2015;2(1):e000243. doi:10.1136/openhrt-2015-000243.
46. Shameer K, Johnson KW, Yahi A, et al. Predictive modeling of hospital readmission rates using electronic medical record-wide machine learning: a case-study using mount Sinai heart failure cohort. Pac Symp Biocomput. 2016;22:276-87. doi:10.1142/9789813207813_0027.
47. Angraal S, Mortazavi BJ, Gupta A, et al. Machine Learning Prediction of Mortality and Hospitalization in Heart Failure With Preserved Ejection Fraction. JACC Heart Fail. 2020;8(1):12-21. doi:10.1016/j.jchf.2019.06.013.
48. Hill NR, Ayoubkhani D, McEwan P, et al. Predicting atrial fibrillation in primary care using machine learning. PLoS One. 2019;14(11):e0224582. doi:10.1371/journal.pone.0224582.
49. Mortazavi BJ, Bucholz EM, Desai NR, et al. Comparison of machine learning methods with national cardiovascular data registry models for prediction of risk of bleeding after percutaneous coronary intervention. JAMA Netw Open. 2019;2(7):e196835. doi:10.1001/jamanetworkopen.2019.6835.
50. Huang C, Murugiah K, Mahajan S, et al. Enhancing the prediction of acute kidney injury risk after percutaneous coronary intervention using machine learning techniques: A retrospective cohort study. PLoS Med. 2018;15(11):e1002703. doi:10.1371/journal.pmed.1002703.
51. Laskey WK, Jenkins C, Selzer F, et al. Volume-to-creatinine clearance ratio: a pharmacokinetically based risk factor for prediction of early creatinine increase after percutaneous coronary intervention. J Am Coll Cardiol. 2007;50(7):584-90. doi:10.1016/j.jacc.2007.03.058.
52. Анфиногенова Я.Д., Трубачева И.А., Серебрякова В.Н., Попов С.В. Новые тренды и вызовы популяционной кардиологии. Сибирский медицинский журнал. 2019;34(4):24-38. doi:10.29001/2073-8552-2019-34-4-24-38.
53. Alizadehsani R, Abdar M, Roshanzamir M, et al. Machine learning-based coronary artery disease diagnosis: A comprehensive review. Computers in Biology and Medicine. 2019;103346. doi:10.1016/j.compbiomed.2019.103346.
54. 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.
55. Guyon I, Elisseeff A. An Introduction to Variable and Feature Selection. Journal of Machine Learning Research. 2003;3:1157-82.
56. Dudchenko A, Ganzinger M, Kopanitsa G. Machine Learning Algorithms in Cardiology Domain: A Systematic Review. 2020;13:25-40. doi:10.2174/1875036202013010025.
57. Shahian DM, O’Brien SM, Sheng S, et al. Predictors of long-term survival after coronary artery bypass grafting surgery: results from the Society of Thoracic Surgeons Adult Cardiac Surgery Database (the ASCERT study). Circulation. 2012;125(12):1491-500. doi:10.1161/CIRCULATIONAHA.111.066902.
58. Forte JC, Wiering M, Bouma H, et al. Predicting long-term mortality with first week postoperative data after Coronary Artery Bypass Grafting using Machine Learning models. PMLR. 2017;68:39-58. http://proceedings.mlr.press/v68/forte17a/forte17a.pdf.
59. Karim MN, Reid CM, Huq M, et al. Predicting long-term survival after coronary artery bypass graft surgery. Interact Cardiovasc Thorac Surg. 2018;26(2):257-63. doi:10.1093/icvts/ivx330.