Machine learning and artificial intelligence in the prediction, diagnosis and treatment of thoracic aortic diseases (literature review). Part 1

Despite their relatively low prevalence compared to cardiac valve lesions and coronary heart disease, thoracic aortic aneurysm and dissection are potentially fatal and represent serious public health problems. The indications for surgical treatment in most thoracic aortic diseases are predominantly based on the maximum aortic diameter in a particular area. Congenital connective tissue disorder, thoracic aortic anomalies (e.g., coarctation), family history of aneurysms, aortic dissections, and sudden deaths are considered as additional risk factors of aortic-related complications influencing the “stricter” indications and lowering the “threshold” aortic diameter. At the same time, a certain proportion of patients with aortic diseases develop aortic dissection and rupture in normal or near-normal thoracic aortic diameter in certain section. Many factors influence the development of aortic diseases and complications, and assessing the contribution to the aetiology and pathogenesis of each factor is difficult. Machine learning and mathematical modeling using artificial intelligence is an actively developing area of computer science, which also finds application in medicine, in particular in the study, diagnosis, and treatment of thoracic aortic aneurysms and dissections. This article discusses modern methods of data analysis, prediction of thoracic aortic aneurysms and dissections, treatment planning in thoracic aortic diseases, and prediction of complications using machine learning and artificial intelligence.

1. Olsson C, Thelin S, Stahle E, et al. Thoracic aortic aneurysm and dissection: increasing prevalence and improved outcomes reported in a nationwide population-based study of more than 14,000 cases from 1987 to 2002. Circulation. 2006;114(24):2611–8.

2. Elefteriades JA, Farkas EA. Thoracic aortic aneurysm clinically pertinent controversies and uncertainties. Journal of the American College of Cardiology. 2010;55(9):841–57.

3. Kuzmik GA, Sang AX, Elefteriades JA. Natural history of thoracic aortic aneurysms. Journal of vascular surgery. 2012;56(2):565–71.

4. Mussa FF, Horton JD, Moridzadeh R, et al. Acute aortic dissection and intramural hematoma: a systematic review. Jama. 2016;316(7):754–63.

5. Evangelista A, Isselbacher EM, Bossone E, et al. Insights from the International Registry of Acute Aortic Dissection: a 20-year experience of collaborative clinical research. Circulation. 2018;137(17):1846–60.

6. Ziganshin BA, Elefteriades JA. Treatment of thoracic aortic aneurysm: role of earlier intervention. Seminars in thoracic and cardiovascular surgery. 2015;27(2):135–43.

7. Elefteriades JA. Natural history of thoracic aortic aneurysms: indications for surgery, and surgical versus nonsurgical risks. The Annals of thoracic surgery. 2002;74(5):S1877–80; discussion S92–8.

8. Folkersen L, Wagsater D, Paloschi V, et al. Unraveling divergent gene expression profiles in bicuspid and tricuspid aortic valve patients with thoracic aortic dilatation: the ASAP study. Molecular medicine (Cambridge, Mass). 2011;17(11–12):1365–73.

9. Kim S, Park JS, Yoo SM, et al. Traumatic aortic regurgitation combined with descending aortic pseudoaneurysm secondary to blunt chest trauma. Cardiovascular journal of Africa. 2014;25(5):e5–8.

10. Coady MA, Rizzo JA, Goldstein LJ, Elefteriades JA. Natural history, pathogenesis, and etiology of thoracic aortic aneurysms and dissections. Cardiology clinics. 1999;17(4):615–35; vii.

11. Roberts WC, Moore AJ, Roberts CS. Syphilitic aortitis: still a current common cause of aneurysm of the tubular portion of ascending aorta. Cardiovascular pathology : the official journal of the Society for Cardiovascular Pathology. 2019;46:107175.

12. Agnese V, Pasta S, Michelena HI, et al. Patterns of ascending aortic dilatation and predictors of surgical replacement of the aorta: A comparison of bicuspid and tricuspid aortic valve patients over eight years of followup. J Mol Cell Cardiol. 2019;135:31–9.

13. Erbel R, Aboyans V, Boileau C, et al. 2014 ESC Guidelines on the diagnosis and treatment of aortic diseases: Document covering acute and chronic aortic diseases of the thoracic and abdominal aorta of the adult. The Task Force for the Diagnosis and Treatment of Aortic Diseases of the European Society of Cardiology (ESC). European heart journal. 2014;35(41):2873–926.

14. Isselbacher EM, Preventza O, Hamilton Black J,

15. rd, et al. 2022 ACC/AHA Guideline for the Diagnosis and

16. Management of Aortic Disease: A Report of the American Heart Association/American College of Cardiology Joint Committee on Clinical Practice Guidelines. Circulation. 2022;146(24):e334–e482.

17. Elefteriades JA. Thoracic aortic aneurysm: reading the enemy’s playbook. The Yale journal of biology and medicine. 2008;81(4):175–86.

18. Davies RR, Gallo A, Coady MA, et al. Novel measurement of relative aortic size predicts rupture of thoracic aortic aneurysms. The Annals of thoracic surgery. 2006;81(1):169–77.

19. Borger MA, Fedak PWM, Stephens EH, et al. The American Association for Thoracic Surgery consensus guidelines on bicuspid aortic valve-related aortopathy: full online-only version. The Journal of thoracic and cardiovascular surgery. 2018;156(2):e41–e74.

20. Kerneis C, Pasi N, Arangalage D, et al. Ascending aorta dilatation rates in patients with tricuspid and bicuspid aortic stenosis: the COFRASA/GENERAC study. European heart journal cardiovascular Imaging. 2018;19(7):792–9.

21. Oladokun D, Patterson BO, Sobocinski J, et al. Systematic review of the growth rates and influencing factors in thoracic aortic aneurysms. European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery. 2016;51(5):674–81.

22. Pape LA, Tsai TT, Isselbacher EM, et al. Aortic diameter >or = 5.5 cm is not a good predictor of type A aortic dissection: observations from the International Registry of Acute Aortic Dissection (IRAD). Circulation. 2007;116(10):1120–7.

23. Juraszek A, Czerny M, Rylski B. Update in aortic dissection. Trends in cardiovascular medicine. 2022;32(7):456–61.

24.

25. Sievers HH, Rylski B, Czerny M, et al. Aortic dissection reconsidered: type, entry site, malperfusion classification adding clarity and enabling outcome prediction. Interactive cardiovascular and thoracic surgery. 2020;30(3):451–7.

26. Rylski B, Schilling O, Czerny M. Acute aortic dissection: evidence, uncertainties, and future therapies. European heart journal. 2022.

27. Simon MV, Dong CC, Jacobs MJ, Mess WH. Neuromonitoring during descending aorta procedures. Handbook of clinical neurology. 2022;186:407–31.

28. Volynsky MA, Mamontov OV, Osipchuk AV, et al. Study of cerebrovascular reactivity to hypercapnia by imaging photoplethysmography to develop a method for intraoperative assessment of the brain functional reserve. Biomedical optics express. 2022;13(1):184–96.

29. Herrmann MD, Clunie DA, Fedorov A, et al. Implementing the DICOM standard for digital pathology. Journal of pathology informatics. 2018;9:37.

30. Wang KC, Kohli M, Carrino JA. Technology standards in imaging: a practical overview. Journal of the American College of Radiology : JACR. 2014;11(12 Pt B):1251–9.

31. DICOM reference guide. Health devices. 2001;30(1–2):5–30.

32. Lenchik L, Heacock L, Weaver AA, et al. Automated segmentation of tissues using CT and MRI: a systematic review. Academic radiology. 2019;26(12):1695–706.

33. Brown M, Browning P, Wahi-Anwar MW, et al. Integration of chest CT CAD into the clinical workflow and impact on radiologist efficiency. Academic radiology. 2019;26(5):626–31.

34. Greener JG, Kandathil SM, Moffat L, Jones DT. A guide to machine learning for biologists. Nature reviews Molecular cell biology. 2022;23(1):40–55.

35. Bruce P, Bruce A. Practical statistics for data scientists. 50 Essential Concepts.: O’Reilly Media, Inc.; 2017.

36. Uddin S, Khan A, Hossain ME, Moni MA. Comparing different supervised machine learning algorithms for disease prediction. BMC medical informatics and decision making. 2019;19(1):281.

37. Burkov A. The hundred-page machine learning book: Andriy Burkov (January 13, 2019); 2019. 160 p.

38. Baştanlar Y, Ozuysal M. Introduction to machine learning. Methods in molecular biology (Clifton, NJ). 2014;1107:105–28.

39. Zhao L, Chen Y, Schaffner DW. Comparison of logistic regression and linear regression in modeling percentage data. Applied and environmental microbiology. 2001;67(5):2129–35.

40. Tripepi G, Jager KJ, Stel VS, et al. How to deal with continuous and dichotomic outcomes in epidemiological research: linear and logistic regression analyses. Nephron Clinical practice. 2011;118(4):c399–406.

41. Henrard S, Speybroeck N, Hermans C. Classification and regression tree analysis vs. multivariable linear and logistic regression methods as statistical tools for studying haemophilia. Haemophilia : the official journal of the World Federation of Hemophilia. 2015;21(6):715–22.

42. Jain AK, Murty MN, Flynn PJ. Data clustering: a review. ACM Computing Surveys. 1999;31(3):264–323.

43. Ali J, Khan R, Ahmad N, Maqsood I. Random forests and decision trees. International Journal of Computer Science Issues(IJCSI). 2012;9(5):272–8.

44. Nguyen JM, Jézéquel P, Gillois P, et al. Random forest of perfect trees: concept, performance, applications, and perspectives. Bioinformatics (Oxford, England). 2021;37(15):2165–74.

45. Chen T, Guestrin C, editors. Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016.

46. Freund Y, Schapire RE, editors. Game theory, online prediction and boosting. Proceedings of the ninth annual conference on Computational learning theory; 1996.

47. Taunk K, De S, Verma S, Swetapadma A. A brief review of nearest neighbor algorithm for learning and classification. 2019 International Conference on Intelligent Computing and Control Systems (ICCS). 2019:1255–60.

48. Yan Y, Wang Y, Lei Y. Micro learning support vector machine for pattern classification: a high-speed algorithm. Computational intelligence and neuroscience. 2022;2022:4707637.

49. Bradley PS, Mangasarian OL. Massive data discrimination via linear support vector machines. Optimization Methods and Software. 2000;13(1):1–10.

50. Joachims T. Making large-scale SVM learning practical. University of Dortmund Fachbereich Informatik; 1998. Contract No.: LS-8 Report 24.

51. McCarthy J, Hayes PJ. Some philosophical problems from the standpoint of artificial intelligence. In: Michie D, editor. Machine Intelligence. 2.1: Elsevier; 1969. p. 463 ff.

52. Hicks SA, Strümke I, Thambawita V, et al. On evaluation metrics for medical applications of artificial intelligence. Scientific reports. 2022;12(1):5979.

53. Golubev YF. Neural network methods in mechatronics. Moscow: Moscow State University Press; 2007. 157 p. In Russian [Голубев ЮФ. Нейросетевые методы в мехатронике: М.: Изд-во Моск. ун-та; 2007. 157 c.].

54. Choi RY, Coyner AS, Kalpathy-Cramer J, et al. Introduction to machine learning, neural networks, and deep learning. Translational vision science & technology. 2020;9(2):14.

55. LeCun Y, Bengio Y, Hinton G. Deep learning.

56. Nature. 2015;521(7553):436–44.