persmedРоссийский журнал персонализированной медициныRussian Journal for Personalized Medicine2782-38062782-3814ФОНД АЛМАЗОВА10.18705/2782-3806-2022-2-6-16-22persmed-98Research ArticleИСКУССТВЕННЫЙ ИНТЕЛЛЕКТARTIFICIAL INTELLIGENCEИскусственный интеллект в кардиологии: сработал ли он?Artificial intelligence in cardiology: did it take off?ЙеоК. К.YeoK. K.

Профессор Йео Кхунг Кеонг, FAHA, FESC, FACC, FAPSC, FAMS, FAPSIC, отделение кардиологии

5 Больничный проезд, Сингапур, 169609

Prof. Yeo Khung Keong, FAHA, FESC, FACC, FAPSC, FAMS, FAPSIC, Department of Cardiology

5 Hospital Drive, Singapore, 169609

Национальный кардиологический центр СингапураСингапурNational Heart Centre SingaporeSingapore202221012023261622Copyright © Йео К.К., 20232023Йео К.К.Yeo K.K.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://persmed.elpub.ru/jour/article/view/98

Искусственный интеллект (ИИ) позиционируется как технология, меняющая парадигму и «правила игры» в медицине. Существует ли он в кардиологии? В этой статье мы обсудим некоторые области кардиологии, в которых достигнут определенный прогресс во внедрении технологий искусственного интеллекта. Несмотря на перспективы искусственного интеллекта, сохраняются проблемы, включая кибербезопасность, трудности с внедрением и управлением изменениями. В этой статье обсуждается использование ИИ, встроенного в качестве технологии «черного ящика» в существующие диагностические и интервенционные инструменты, ИИ в качестве дополнения к диагностическим инструментам, таким как ЭХО, компьютерная томография или МРТ, ИИ в коммерчески доступных мобильных устройствах и ИИ в чат-ботах и других технологиях взаимодействия с пациентами. При этом, несмотря на определенный прогресс, правовая, нормативная, финансовая и этическая базы по-прежнему находятся в процессе эволюции на национальном и международном уровнях.

Artificial intelligence (AI) has been touted as a paradigm shifting, game-changing development in medicine. Did AI in cardiology take off? In this paper, we discuss some areas within cardiology in which there has some been progress in the implementation of AI technologies. Despite the promise of AI, challenges remain including cybersecurity, implementation and change management difficulties. This paper discusses the use of AI embedded as a ‘black box’ technology in existing diagnostic and interventional tools, AI as an adjunct to diagnostic tools such as echo or CT or MRI scans, AI in commercially available wearables, and AI in chatbots and other patient-fronting technologies. Lastly, while there has been some progress, the legal, regulatory, financial and ethical framework remains a work in evolution at national and international levels.

болезни сердечно-сосудистой системыискусственный интеллекткардиологиякибербезопасностьновые диагностические возможностипациент-ориентированный интерфейссмарт-технологииartificial intelligencecardiologycardiovascular diseasecybersecuritynew diagnostic capabilitiespatient-oriented interfacesmart-technologieReferenceshttps://www.forbes.com/sites/forbestechcouncil/2021/06/07/increased-cyberattackson-healthcare-institutions-shows-the-need-for-greatercybersecurity/?sh=58c657145650 (accessed 31 Dec 2021).https://www.forbes.com/sites/forbestechcouncil/2021/06/07/increased-cyberattackson-healthcare-institutions-shows-the-need-for-greatercybersecurity/?sh=58c657145650 (accessed 31 Dec 2021).https://www.cisecurity.org/blog/cyber-attacksin-the-healthcare-sector/ (accessed 31 Dec 2021).https://www.cisecurity.org/blog/cyber-attacksin-the-healthcare-sector/ (accessed 31 Dec 2021).https://www.weforum.org/agenda/2021/11/healthcare-cybersecurity/ (accessed 31 Dec 2021).https://www.weforum.org/agenda/2021/11/healthcare-cybersecurity/ (accessed 31 Dec 2021).Kramer DB, Fu K. Cybersecurity Concerns and Medical Devices: Lessons From a Pacemaker Advisory. JAMA 2017;318(21):2077–2078. DOI: 10.1001/jama.2017.15692.Kramer DB, Fu K. Cybersecurity Concerns and Medical Devices: Lessons From a Pacemaker Advisory. JAMA 2017;318(21):2077–2078. DOI: 10.1001/jama.2017.15692.Baranchuk A, Refaat MM, Patton KK, et al. Cybersecurity for Cardiac Implantable Electronic Devices: What Should You Know? J Am Coll Cardiol 2018;71(11):1284–1288. DOI: 10.1016/j.jacc.2018.01.023.Baranchuk A, Refaat MM, Patton KK, et al. Cybersecurity for Cardiac Implantable Electronic Devices: What Should You Know? J Am Coll Cardiol 2018;71(11):1284–1288. DOI: 10.1016/j.jacc.2018.01.023.Stern AD, Gordon WJ, Landman AB, Kramer DB. Cybersecurity features of digital medical devices: an analysis of FDA product summaries. BMJ Open 2019;9(6):e025374. DOI: 10.1136/bmjopen-2018-025374.Stern AD, Gordon WJ, Landman AB, Kramer DB. Cybersecurity features of digital medical devices: an analysis of FDA product summaries. BMJ Open 2019;9(6):e025374. DOI: 10.1136/bmjopen-2018-025374.Das S, Siroky GP, Lee S, Mehta D, Suri R. Cybersecurity: The need for data and patient safety with cardiac implantable electronic devices. Heart Rhythm 2021;18(3):473–481. DOI: 10.1016/j.hrthm.2020.10.009.Das S, Siroky GP, Lee S, Mehta D, Suri R. Cybersecurity: The need for data and patient safety with cardiac implantable electronic devices. Heart Rhythm 2021;18(3):473–481. DOI: 10.1016/j.hrthm.2020.10.009.https://www.forbes.com/sites/forbestechcouncil/2020/10/14/why-do-most-aiprojects-fail/?sh=1dad757a8aa3 (accessed 29 Dec 2021).https://www.forbes.com/sites/forbestechcouncil/2020/10/14/why-do-most-aiprojects-fail/?sh=1dad757a8aa3 (accessed 29 Dec 2021).Tromp J, Seekings PJ, Hung CL, et al. Automated interpretation of systolic and diastolic function on the echocardiogram: a multicohort study. Lancet Digit Health 2022;4(1):e46–e54. DOI: 10.1016/S2589-7500(21)00235-1.Tromp J, Seekings PJ, Hung CL, et al. Automated interpretation of systolic and diastolic function on the echocardiogram: a multicohort study. Lancet Digit Health 2022;4(1):e46–e54. DOI: 10.1016/S2589-7500(21)00235-1.Chu M, Jia H, Gutierrez-Chico JL, et al. Artificial intelligence and optical coherence tomography for the automatic characterisation of human atherosclerotic plaques. EuroIntervention 2021;17(1):41–50. DOI: 10.4244/EIJ-D-20-01355.Chu M, Jia H, Gutierrez-Chico JL, et al. Artificial intelligence and optical coherence tomography for the automatic characterisation of human atherosclerotic plaques. EuroIntervention 2021;17(1):41–50. DOI: 10.4244/EIJ-D-20-01355.Dey D, Slomka PJ, Leeson P, et al. Artificial Intelligence in Cardiovascular Imaging: JACC State-ofthe-Art Review. J Am Coll Cardiol 2019;73(11):1317–1335. DOI: 10.1016/j.jacc.2018.12.054.Dey D, Slomka PJ, Leeson P, et al. Artificial Intelligence in Cardiovascular Imaging: JACC State-ofthe-Art Review. J Am Coll Cardiol 2019;73(11):1317–1335. DOI: 10.1016/j.jacc.2018.12.054.Hampe N, Wolterink JM, van Velzen SGM, Leiner T, Isgum I. Machine Learning for Assessment of Coronary Artery Disease in Cardiac CT: A Survey. Front Cardiovasc Med 2019;6:172. DOI: 10.3389/fcvm.2019.00172.Hampe N, Wolterink JM, van Velzen SGM, Leiner T, Isgum I. Machine Learning for Assessment of Coronary Artery Disease in Cardiac CT: A Survey. Front Cardiovasc Med 2019;6:172. DOI: 10.3389/fcvm.2019.00172.Muscogiuri G, Van Assen M, Tesche C, et al. Artificial Intelligence in Coronary Computed Tomography Angiography: From Anatomy to Prognosis. Biomed Res Int 2020;2020:6649410. DOI: 10.1155/2020/6649410.Muscogiuri G, Van Assen M, Tesche C, et al. Artificial Intelligence in Coronary Computed Tomography Angiography: From Anatomy to Prognosis. Biomed Res Int 2020;2020:6649410. DOI: 10.1155/2020/6649410.Bai W, Sinclair M, Tarroni G, et al. Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J Cardiovasc Magn Reson 2018;20(1):65. DOI: 10.1186/s12968-018-0471-x.Bai W, Sinclair M, Tarroni G, et al. Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J Cardiovasc Magn Reson 2018;20(1):65. DOI: 10.1186/s12968-018-0471-x.Tan LK, McLaughlin RA, Lim E, Abdul Aziz YF, Liew YM. Fully automated segmentation of the left ventricle in cine cardiac MRI using neural network regression. J Magn Reson Imaging 2018;48(1):140–152. DOI: 10.1002/jmri.25932.Tan LK, McLaughlin RA, Lim E, Abdul Aziz YF, Liew YM. Fully automated segmentation of the left ventricle in cine cardiac MRI using neural network regression. J Magn Reson Imaging 2018;48(1):140–152. DOI: 10.1002/jmri.25932.Chen C, Qin C, Qiu H, et al. Deep Learning for Cardiac Image Segmentation: A Review. Front Cardiovasc Med 2020;7:25. DOI: 10.3389/fcvm.2020.00025.Chen C, Qin C, Qiu H, et al. Deep Learning for Cardiac Image Segmentation: A Review. Front Cardiovasc Med 2020;7:25. DOI: 10.3389/fcvm.2020.00025.Upendra RR, Dangi S, Linte CA. Automated Segmentation of Cardiac Chambers from Cine Cardiac MRI Using an Adversarial Network Architecture. Proc SPIE Int Soc Opt Eng 2020;11315. DOI: 10.1117/12.2550656.Upendra RR, Dangi S, Linte CA. Automated Segmentation of Cardiac Chambers from Cine Cardiac MRI Using an Adversarial Network Architecture. Proc SPIE Int Soc Opt Eng 2020;11315. DOI: 10.1117/12.2550656.https://www.philips.com.sg/healthcare/resources/landing/ct-precise-suite (Accessed 29 Dec 2021).https://www.philips.com.sg/healthcare/resources/landing/ct-precise-suite (Accessed 29 Dec 2021).https://www.gehealthcare.com/article/ai-atthe-point-of-care-x-ray-and-ct (accessed 29 Dec 2021).https://www.gehealthcare.com/article/ai-atthe-point-of-care-x-ray-and-ct (accessed 29 Dec 2021).https://new.siemens.com/global/en/company/stories/research-technologies/artificial-intelligence/artificial-intelligence-imaging-techniques.html (accessed 29 Dec 2021).https://new.siemens.com/global/en/company/stories/research-technologies/artificial-intelligence/artificial-intelligence-imaging-techniques.html (accessed 29 Dec 2021).Quer G, Arnaout R, Henne M, Arnaout R. Machine Learning and the Future of Cardiovascular Care: JACC State-of-the-Art Review. J Am Coll Cardiol 2021;77(3):300–313. DOI: 10.1016/j.jacc.2020.11.030.Quer G, Arnaout R, Henne M, Arnaout R. Machine Learning and the Future of Cardiovascular Care: JACC State-of-the-Art Review. J Am Coll Cardiol 2021;77(3):300–313. DOI: 10.1016/j.jacc.2020.11.030.Bai Y, Tompkins C, Gell N, Dione D, Zhang T, Byun W. Comprehensive comparison of Apple Watch and Fitbit monitors in a free-living setting. PLoS One 2021;16(5):e0251975. DOI: 10.1371/journal. pone.0251975.Bai Y, Tompkins C, Gell N, Dione D, Zhang T, Byun W. Comprehensive comparison of Apple Watch and Fitbit monitors in a free-living setting. PLoS One 2021;16(5):e0251975. DOI: 10.1371/journal. pone.0251975.Perez MV, Mahaffey KW, Hedlin H, et al. LargeScale Assessment of a Smartwatch to Identify Atrial Fibrillation. N Engl J Med 2019;381(20):1909–1917. DOI: 10.1056/NEJMoa1901183.Perez MV, Mahaffey KW, Hedlin H, et al. LargeScale Assessment of a Smartwatch to Identify Atrial Fibrillation. N Engl J Med 2019;381(20):1909–1917. DOI: 10.1056/NEJMoa1901183.https://medicalfuturist.com/top-12-healthchatbots/ (accessed 29 Dec 2021).https://medicalfuturist.com/top-12-healthchatbots/ (accessed 29 Dec 2021).https://finance.yahoo.com/news/ping-gooddoctor-unveils-strategic-090800676.html (accessed 29 Dec 2021).https://finance.yahoo.com/news/ping-gooddoctor-unveils-strategic-090800676.html (accessed 29 Dec 2021).https://finance.yahoo.com/news/halfway-2021ping-good-doctor-062000451.html?guccounter=1&guce_referrer=aHR0cHM6Ly93d3cuZ29vZ2xlLmNvbS8&guce_referrer_sig=AQAAAAhOoR0XlmmwEDb1blzzEH8BU23gTixRPUZP7IRAeLG0fb3Kma4G3cOGF40Vm10CnTYdvK5au0f04gWuprz36l0z0E0Uhiktykh8YmI7dYphMrbsYLe_1r6hOG6QstH4xw9MmiDTGHz7cEZxvuWGbPpnvdfG31zYnParEXtbDAFD (accessed 29 Dec 2021).https://finance.yahoo.com/news/halfway-2021ping-good-doctor-062000451.html?guccounter=1&guce_referrer=aHR0cHM6Ly93d3cuZ29vZ2xlLmNvbS8&guce_referrer_sig=AQAAAAhOoR0XlmmwEDb1blzzEH8BU23gTixRPUZP7IRAeLG0fb3Kma4G3cOGF40Vm10CnTYdvK5au0f04gWuprz36l0z0E0Uhiktykh8YmI7dYphMrbsYLe_1r6hOG6QstH4xw9MmiDTGHz7cEZxvuWGbPpnvdfG31zYnParEXtbDAFD (accessed 29 Dec 2021).https://www.scmp.com/business/article/3050074/ping-good-doctor-chinas-largesthealth-care-platform-reports-jump-users.https://www.scmp.com/business/article/3050074/ping-good-doctor-chinas-largesthealth-care-platform-reports-jump-users.https://group.pingan.com/media/news/News-2020/Ping-An-Unveils-Health-Care-EcosystemStrategy.html.https://group.pingan.com/media/news/News-2020/Ping-An-Unveils-Health-Care-EcosystemStrategy.html.Zhang PI, Hsu CC, Kao Y, et al. Real-time AI prediction for major adverse cardiac events in emergency department patients with chest pain. Scand J Trauma Resusc Emerg Med 2020;28(1):93. DOI: 10.1186/s13049020-00786-x.Zhang PI, Hsu CC, Kao Y, et al. Real-time AI prediction for major adverse cardiac events in emergency department patients with chest pain. Scand J Trauma Resusc Emerg Med 2020;28(1):93. DOI: 10.1186/s13049020-00786-x.Stewart J, Lu J, Goudie A, et al. Applications of machine learning to undifferentiated chest pain in the emergency department: A systematic review. PLoS One 2021;16(8):e0252612. DOI: 10.1371/journal.pone.0252612.Stewart J, Lu J, Goudie A, et al. Applications of machine learning to undifferentiated chest pain in the emergency department: A systematic review. PLoS One 2021;16(8):e0252612. DOI: 10.1371/journal.pone.0252612.https://hbr.org/2018/12/using-ai-to-improveelectronic-health-records (accessed 31 Dec 2021).https://hbr.org/2018/12/using-ai-to-improveelectronic-health-records (accessed 31 Dec 2021).Chi EA, Chi G, Tsui CT, et al. Development and Validation of an Artificial Intelligence System to Optimize Clinician Review of Patient Records. JAMA Netw Open 2021;4(7):e2117391. DOI: 10.1001/jamanetworkopen.2021.17391.Chi EA, Chi G, Tsui CT, et al. Development and Validation of an Artificial Intelligence System to Optimize Clinician Review of Patient Records. JAMA Netw Open 2021;4(7):e2117391. DOI: 10.1001/jamanetworkopen.2021.17391.Krittanawong C, Rogers AJ, Johnson KW, et al. Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management. Nat Rev Cardiol 2021;18(2):75–91. DOI: 10.1038/s41569-020-00445-9.Krittanawong C, Rogers AJ, Johnson KW, et al. Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management. Nat Rev Cardiol 2021;18(2):75–91. DOI: 10.1038/s41569-020-00445-9.https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligenceand-machine-learning-software-medical-device (accessed 31 Dec 2021).https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligenceand-machine-learning-software-medical-device (accessed 31 Dec 2021).https://www.moh.gov.sg/docs/librariesprovider5/eguides/1-0-artificial-in-healthcareguidelines-(aihgle)_publishedoct21.pdf (accessed 31 Dec 2021).https://www.moh.gov.sg/docs/librariesprovider5/eguides/1-0-artificial-in-healthcareguidelines-(aihgle)_publishedoct21.pdf (accessed 31 Dec 2021).https://ec.europa.eu/futurium/en/ai-allianceconsultation.1.html (accessed 31 Dec 2021).https://ec.europa.eu/futurium/en/ai-allianceconsultation.1.html (accessed 31 Dec 2021).https://www.industry.gov.au/data-andpublications/australias-artificial-intelligence-ethicsframework (accessed 31 Dec 2021).https://www.industry.gov.au/data-andpublications/australias-artificial-intelligence-ethicsframework (accessed 31 Dec 2021).

The authors declare that there are no conflicts of interest present.