Künstliche Intelligenz in der Kardiologie

Relevanz, aktuelle Anwendungen und nächste Schritte

Artificial intelligence in cardiology

Relevance, current applications, and future developments

Zusammenfassung

Big Data und Anwendungen der künstlichen Intelligenz (KI), wie maschinelles Lernen oder Deep Learning, werden die Gesundheitsversorgung zukünftig bereichern und an Bedeutung gewinnen. Sie haben u. a. das Potenzial, unnötige Untersuchungen sowie Diagnose- und Therapiefehler zu vermeiden und eine verbesserte, frühzeitige und beschleunigte Entscheidungsfindung zu ermöglichen. Die Autoren geben in dem Artikel einen Überblick über aktuelle KI-basierte Anwendungen in der Kardiologie. Die Beispiele beschreiben innovative Lösungen zur Risikobewertung, Diagnosestellung und Therapieunterstützung bis hin zum Selbstmanagement der Patienten. Big Data und KI dienen dabei als Basis für eine effiziente, prädiktive, präventive und personalisierte Medizin. Allerdings zeigen die Beispiele auch, dass es weiterer Forschungen bedarf, um die Lösungen im Sinne der Patienten und Ärzteschaft weiter zu entwickeln, die Effektivität und den Nutzen in der Gesundheitsversorgung zu zeigen sowie rechtliche und ethische Standards zu etablieren.

Abstract

Big data and applications of artificial intelligence (AI), such as machine learning or deep learning, will enrich healthcare in the future and become increasingly important. Among other things, they have the potential to avoid unnecessary examinations as well as diagnostic and therapeutic errors. They could enable improved, early and accelerated decision-making. In the article, the authors provide an overview of current AI-based applications in cardiology. The examples describe innovative solutions for risk assessment, diagnosis and therapy support up to patient self-management. Big data and AI serve as a basis for efficient, predictive, preventive and personalised medicine. However, the examples also show that research is needed to further develop the solutions for the benefit of the patient and the medical profession, to demonstrate the effectiveness and benefits in health care and to establish legal and ethical standards.

This is a preview of subscription content, access via your institution.

Abb. 1

Notes

  1. 1.

    Aus Gründen der besseren Lesbarkeit wird auf die gleichzeitige Verwendung männlicher und weiblicher Sprachformen verzichtet. Sämtliche Personenbezeichnungen gelten gleichermaßen für Frauen, Männer und andere Geschlechter.

Literatur

  1. 1.

    Adedinsewo D, Carter RE, Attia Z, Johnson P, Kashou AH, Dugan JL, Albus M, Sheele JM, Bellolio F, Friedman PA, Lopez-Jimenez F, Noseworthy PA (2020) Artificial Intelligence-Enabled ECG Algorithm to Identify Patients With Left Ventricular Systolic Dysfunction Presenting to the Emergency Department With Dyspnea. Circ Arrhythmia Electrophysiol 13(8):e8437

    CAS  Google Scholar 

  2. 2.

    Andersen RS, Peimankar A, Puthusserypady S (2019) A deep learning approach for real-time detection of atrial fibrillation. Expert Syst Appl 115:465–473

    Google Scholar 

  3. 3.

    Attia ZI, Kapa S, Lopez-Jimenez F, McKie PM, Ladewig DJ, Satam G, Pellikka PA, Enriquez-Sarano M, Noseworthy PA, Munger TM, Asirvatham SJ, Scott CG, Carter RE, Friedman PA (2019) Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram. Nat Med 25(1):70–74

    CAS  PubMed  Google Scholar 

  4. 4.

    Braunwald E (2019) Diabetes, heart failure, and renal dysfunction: The vicious circles. Prog Cardiovasc Dis 62(4):298–302

    PubMed  Google Scholar 

  5. 5.

    Brunner-La Rocca H‑P, Fleischhacker L, Golubnitschaja O, Heemskerk F, Helms T, Hoedemakers T, Allianses SH, Jaarsma T, Kinkorova J, Ramaekers J, Ruff P, Schnur I, Vanoli E, Verdu J, Zippel-Schultz B (2016) Challenges in personalised management of chronic diseases-heart failure as prominent example to advance the care process. EPMA J 7(1):2–2

    PubMed  PubMed Central  Google Scholar 

  6. 6.

    Brynjolfsson E, McAfee A (2017) The Business of Artificial Intelligence: what it can and cannot do for your organization. Harv Bus Rev Digit Articles 7(21):1–20

    Google Scholar 

  7. 7.

    Budde K et al. (2020) KI in der Medizin und. Pflege : (aus der Perspektive Betroffener. Tagungsbericht zum Runden Tisch mit Patientenvertretungen aus der Plattform Lernender Systeme. München). https://www.plattform-lernende-systeme.de/files/Downloads/Publikationen/AG6_Whitepaper_Medizin_Pflege_Tagungsbericht.pdf

  8. 8.

    Bumgarner JM, Lambert CT, Hussein AA, Cantillon DJ, Baranowski B, Wolski K, Lindsay BD, Wazni OM, Tarakji KG (2018) Smartwatch Algorithm for Automated Detection of Atrial Fibrillation. J Am Coll Cardiol 71(21):2381–2388

    PubMed  Google Scholar 

  9. 9.

    Cano Martín JA, Martínez-Pérez B, de la Torre-Díez I, López-Coronado M (2014) Economic Impact Assessment from the Use of a Mobile App for the Self-management of Heart Diseases by Patients with Heart Failure in a Spanish Region. J Med Syst 38(9):96

    PubMed  Google Scholar 

  10. 10.

    Cantwell CD, Mohamied Y, Tzortzis KN, Garasto S, Houston C, Chowdhury RA, Ng FS, Bharath AA, Peters NS (2019) Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling. Comput Biol Med 104:339–351

    PubMed  PubMed Central  Google Scholar 

  11. 11.

    Capper, D., Jones, D. T. W., Sill, M., Hovestadt, V., Schrimpf, D., Sturm, D., Koelsche, C., Sahm, F., Chavez, L., Reuss, D. E., Kratz, A., Wefers, A. K., Huang, K., Pajtler, K. W., Schweizer, L., Stichel, D., Olar, A., Engel, N. W., Lindenberg, K., …, & Pfister, S. M. 2018. DNA methylation-based classification of central nervous system tumours. Nature, 555(7697): 469–474.

  12. 12.

    Choi BG, Rha SW, Kim SW, Kang JH, Park JY, Noh YK (2019) Machine Learning for the Prediction of New-Onset Diabetes Mellitus during 5‑Year Follow-up in Non-Diabetic Patients with Cardiovascular Risks. Yonsei Med J 60(2):191–199

    CAS  PubMed  PubMed Central  Google Scholar 

  13. 13.

    Cikes M, Sanchez-Martinez S, Claggett B, Duchateau N, Piella G, Butakoff C, Pouleur AC, Knappe D, Biering-Sørensen T, Kutyifa V, Moss A, Stein K, Solomon SD, Bijnens B, Sanchez-Martinez S, Biering-Sørensen T (2019) Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy. Eur J Heart Fail 21(1):74–85

    PubMed  Google Scholar 

  14. 14.

    Clark AM, Wiens KS, Banner D, Kryworuchko J, Thirsk L, McLean L, Currie K (2016) A systematic review of the main mechanisms of heart failure disease management interventions. Heart 102(9):707–711

    CAS  PubMed  Google Scholar 

  15. 15.

    Coudray N, Ocampo PS, Sakellaropoulos T, Narula N, Snuderl M, Fenyö D, Moreira AL, Razavian N, Tsirigos A (2018) Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med 24(10):1559–1567

    CAS  PubMed  Google Scholar 

  16. 16.

    Dengler K, Matthes B (2015) Folgen der Digitalisierung für die Arbeitswelt. Substituierbarkeitspotenziale von Berufen in Deutschland: Institut für Arbeitsmarkt- und Berufsforschung der Bundesagentur für Arbeit. http://doku.iab.de/forschungsbericht/2015/fb1115.pdf

  17. 17.

    Ehteshami Bejnordi B, Veta M, van Diest JP, van Ginneken B, Karssemeijer N, Litjens G, van der Laak J, Hermsen M, Manson QF, Balkenhol M, Geessink O, Stathonikos N, van Dijk MC, Bult P, Beca F, Beck AH, Wang D, Khosla A, Gargeya R, Irshad H, Zhong A, Dou Q, Li Q, Chen H, Lin HJ, Heng PA, Haß C, Bruni E, Wong Q, Halici U, Öner M, Cetin-Atalay R, Berseth M, Khvatkov V, Vylegzhanin A, Kraus O, Shaban M, Rajpoot N, Awan R, Sirinukunwattana K, Qaiser T, Tsang YW, Tellez D, Annuscheit J, Hufnagl P, Valkonen M, Kartasalo K, Latonen L, Ruusuvuori P, Liimatainen K, Albarqouni S, Mungal B, George A, Demirci S, Navab N, Watanabe S, Seno S, Takenaka Y, Matsuda H, Ahmady Phoulady H, Kovalev V, Kalinovsky A, Liauchuk V, Bueno G, Fernandez-Carrobles MM, Serrano I, Deniz O, Racoceanu D, Venâncio R (2017) Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer. JAMA 318(22):2199–2210

    PubMed  PubMed Central  Google Scholar 

  18. 18.

    Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118

    CAS  PubMed  Google Scholar 

  19. 19.

    Feldman DI, Robison TW, Pacor JM, Caddell LC, Feldman EB, Deitz RL, Feldman T, Martin SS, Nasir K, Blaha MJ (2018) Harnessing mHealth technologies to increase physical activity and prevent cardiovascular disease. Clin Cardiol 41(7):985–991

    PubMed  PubMed Central  Google Scholar 

  20. 20.

    Frey CB, Osborne MA (2017) The future of employment: How susceptible are jobs to computerisation? Technol Forecast Soc Change 114:254–280

    Google Scholar 

  21. 21.

    Galperin, R. V. 2020. Organizational Powers: Contested Innovation and Loss of Professional Jurisdiction in the Case of Retail Medicine. Organization Science, 31(2): 508–534.

  22. 22.

    Golubnitschaja O, Kinkorova J, Costigliola V (2014) Predictive, preventive and personalised medicine as the hardcore of ‘Horizon 2020’: EPMA position paper. EPMA J 5(1):6

    PubMed  PubMed Central  Google Scholar 

  23. 23.

    Greenhalgh T, Wherton J, Papoutsi C, Lynch J, Hughes G, A’Court C, Hinder S, Fahy N, Procter R, Shaw S (2017) Beyond Adoption: A New Framework for Theorizing and Evaluating Nonadoption, Abandonment, and Challenges to the Scale-Up, Spread, and Sustainability of Health and Care Technologies. J Med Internet Res 19(11):e367

    PubMed  PubMed Central  Google Scholar 

  24. 24.

    Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Cuadros J, Kim R, Raman R, Nelson PC, Mega JL, Webster DR (2016) Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA 316(22):2402–2410

    PubMed  Google Scholar 

  25. 25.

    Haenssle HA, Fink C, Schneiderbauer R, Toberer F, Buhl T, Blum A, Kalloo A, Hassen ABH, Thomas L, Enk A, Uhlmann L, Alt C, Arenbergerova M, Bakos R, Baltzer A, Bertlich I, Blum A, Bokor-Billmann T, Bowling J, Braghiroli N, Braun R, Buder-Bakhaya K, Buhl T, Cabo H, Cabrijan L, Cevic N, Classen A, Deltgen D, Fink C, Georgieva I, Hakim-Meibodi LE, Hanner S, Hartmann F, Hartmann J, Haus G, Hoxha E, Karls R, Koga H, Kreusch J, Lallas A, Majenka P, Marghoob A, Massone C, Mekokishvili L, Mestel D, Meyer V, Neuberger A, Nielsen K, Oliviero M, Pampena R, Paoli J, Pawlik E, Rao B, Rendon A, Russo T, Sadek A, Samhaber K, Schneiderbauer R, Schweizer A, Toberer F, Trennheuser L, Vlahova L, Wald A, Winkler J, Wölbing P, Zalaudek I (2018) Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol 29(8):1836–1842

    CAS  PubMed  Google Scholar 

  26. 26.

    Helms T, Duong G, Zippel-Schultz B, Tilz R, Kuck K‑H, Karle C (2014) Prediction and personalised treatment of atrial fibrillation—stroke prevention: consolidated position paper of CVD professionals. Epma J 5(1):15

    PubMed  PubMed Central  Google Scholar 

  27. 27.

    Hernandez-Suarez DF, Ranka S, Kim Y, Latib A, Wiley J, Lopez-Candales A, Pinto DS, Gonzalez MC, Ramakrishna H, Sanina C, Nieves-Rodriguez BG, Rodriguez-Maldonado J, Feliu Maldonado R, Rodriguez-Ruiz IJ, da Luz Sant’Ana I, Wiley KA, Cox-Alomar P, Villablanca PA, Roche-Lima A (2020) Machine-learning-based in-hospital mortality prediction for transcatheter mitral valve repair in the. Cardiovascular Revascularization Medicine, United States

    Google Scholar 

  28. 28.

    Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T (2017) Artificial Intelligence in Precision Cardiovascular Medicine. J Am Coll Cardiol 69(21):2657–2664

    PubMed  Google Scholar 

  29. 29.

    Kuck KH, Böcker D, Chun J, Deneke T, Hindricks G, Hoffmann E, Piorkowski C, Willems S (2017) Qualitätskriterien zur Durchführung der Katheterablation von Vorhofflimmern. Kardiologe 11(3):161–182

    Google Scholar 

  30. 30.

    Liu X, Rivera CS, Moher D, Calvert MJ, Denniston AK, Chan A‑W, Darzi A, Holmes C, Yau C, Ashrafian H, Deeks JJ, Ferrante di Ruffano L, Faes L, Keane PA, Vollmer SJ, Lee AY, Jonas A, Esteva A, Beam AL, Chan A‑W, Panico MB, Lee CS, Haug C, Kelly CJ, Yau C, Mulrow C, Espinoza C, Fletcher J, Paltoo D, Manna E, Price G, Collins GS, Harvey H, Matcham J, Monteiro J, ElZarrad MK, Ferrante di Ruffano L, Oakden-Rayner L, McCradden M, Keane PA, Savage R, Golub R, Sarkar R, Rowley S, The S‑A, Group C‑AW, Spirit AI, Group C‑AS, Spirit AI, Group C‑AC (2020) Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat Med 26(9):1364–1374

    CAS  PubMed  PubMed Central  Google Scholar 

  31. 31.

    McKinney SM, Sieniek M, Godbole V, Godwin J, Antropova N, Ashrafian H, Back T, Chesus M, Corrado GS, Darzi A, Etemadi M, Garcia-Vicente F, Gilbert FJ, Halling-Brown M, Hassabis D, Jansen S, Karthikesalingam A, Kelly CJ, King D, Ledsam JR, Melnick D, Mostofi H, Peng L, Reicher JJ, Romera-Paredes B, Sidebottom R, Suleyman M, Tse D, Young KC, De Fauw J, Shetty S (2020) International evaluation of an AI system for breast cancer screening. Nature 577(7788):89–94

    CAS  PubMed  Google Scholar 

  32. 32.

    Meyer A, Zverinski D, Pfahringer B, Kempfert J, Kuehne T, Sündermann SH, Stamm C, Hofmann T, Falk V, Eickhoff C (2018) Machine learning for real-time prediction of complications in critical care: a retrospective study. Lancet Respir Med 6(12):905–914

    PubMed  Google Scholar 

  33. 33.

    Miller T (2019) Explanation in artificial intelligence: Insights from the social sciences. Artif Intell 267:1–38

    Google Scholar 

  34. 34.

    Misra J, Saha I (2010) Artificial neural networks in hardware: A survey of two decades of progress. Neurocomputing 74(1):239–255

    Google Scholar 

  35. 35.

    Quer G, Muse ED, Nikzad N, Topol EJ, Steinhubl SR (2017) Augmenting diagnostic vision with AI. Lancet 390(10091):221

    PubMed  PubMed Central  Google Scholar 

  36. 36.

    Rank N, Pfahringer B, Kempfert J, Stamm C, Kühne T, Schoenrath F, Falk V, Eickhoff C, Meyer A (2020) Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance. Npj Digit Med 3:139

    PubMed  PubMed Central  Google Scholar 

  37. 37.

    Santo K, Redfern J (2019) The Potential of mHealth Applications in Improving Resistant Hypertension Self-Assessment, Treatment and Control. Curr Hypertens Rep 21(10):81

    PubMed  Google Scholar 

  38. 38.

    Schultz C (2009) Collaboration with users of innovative healthcare services—the role of service familiarity. Int J Serv Technol Manag 12(3):338–355

    Google Scholar 

  39. 39.

    Schwartz, W. B. 1970. Medicine and the computer. The promise and problems of change. N Engl J Med, 283(23): 1257–1264.

  40. 40.

    Sternkopf, J., & Schultz, C. 2020. Hospitals’ adoption of medical device registers: Evidence from the German Arthroplasty Register. Health Care Manage Rev, 45(1): 3–11.

  41. 41.

    Sutton RT, Pincock D, Baumgart DC, Sadowski DC, Fedorak RN, Kroeker KI (2020) An overview of clinical decision support systems: benefits, risks, and strategies for success. Npj Digit Med 3(1):17

    PubMed  PubMed Central  Google Scholar 

  42. 42.

    Tesche C, De Cecco CN, Baumann S, Renker M, McLaurin TW, Duguay TM, Bayer RR 2nd, Steinberg DH, Grant KL, Canstein C, Schwemmer C, Schoebinger M, Itu LM, Rapaka S, Sharma P, Schoepf UJ (2018) Coronary CT Angiography-derived Fractional Flow Reserve: Machine Learning Algorithm versus Computational Fluid Dynamics Modeling. Radiology 288(1):64–72

    PubMed  Google Scholar 

  43. 43.

    Ting DSW, Pasquale LR, Peng L, Campbell JP, Lee AY, Raman R, Tan GSW, Schmetterer L, Keane PA, Wong TY (2019) Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol 103(2):167–175

    PubMed  Google Scholar 

  44. 44.

    Topol E (2019) Deep Medicine. How Artificial. Intelligence : (Can Make Healthcare Human Again. New York: Basic Books)

  45. 45.

    Venkatesh V, Morris MG, Davis GB, Davis FD (2003) User Acceptance of Information Technology: Toward a Unified View. MISQ 27(3):425–478

    Google Scholar 

  46. 46.

    von Knebel Doeberitz PL, De Cecco CN, Schoepf UJ, Duguay TM, Albrecht MH, van Assen M, Bauer MJ, Savage RH, Pannell JT, De Santis D, Johnson AA, Varga-Szemes A, Bayer RR, Schönberg SO, Nance JW, Tesche C (2019) Coronary CT angiography–derived plaque quantification with artificial intelligence CT fractional flow reserve for the identification of lesion-specific ischemia. Eur Radiol 29(5):2378–2387

    Google Scholar 

  47. 47.

    Voss R, Cullen P, Schulte H, Assmann G (2002) Prediction of risk of coronary events in middle-aged men in the Prospective Cardiovascular Münster Study (PROCAM) using neural networks. Int J Epidemiol 31(6):1253–1262

    PubMed  Google Scholar 

  48. 48.

    Wang P, Xiao X, Glissen Brown JR, Berzin TM, Tu M, Xiong F, Hu X, Liu P, Song Y, Zhang D, Yang X, Li L, He J, Yi X, Liu J, Liu X (2018) Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nat Biomed Eng 2(10):741–748

    PubMed  Google Scholar 

  49. 49.

    Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N (2017) Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS ONE 12(4):e174944

    PubMed  PubMed Central  Google Scholar 

  50. 50.

    Young, J. B., Abraham, W. T., Smith, A. L., Leon, A. R., Lieberman, R., Wilkoff, B., Canby, R. C., Schroeder, J. S., Liem, L. B., Hall, S., & Wheelan, K. 2003. Combined cardiac resynchronization and implantable cardioversion defibrillation in advanced chronic heart failure: the MIRACLE ICD Trial. Jama, 289(20): 2685–2694.

  51. 51.

    Zeevi D, Korem T, Zmora N, Israeli D, Rothschild D, Weinberger A, Ben-Yacov O, Lador D, Avnit-Sagi T, Lotan-Pompan M, Suez J, Mahdi JA, Matot E, Malka G, Kosower N, Rein M, Zilberman-Schapira G, Dohnalová L, Pevsner-Fischer M, Bikovsky R, Halpern Z, Elinav E, Segal E (2015) Personalized Nutrition by Prediction of Glycemic Responses. Cell 163(5):1079–1094

    CAS  Google Scholar 

  52. 52.

    Zellweger MJ, Tsirkin A, Vasilchenko V, Failer M, Dressel A, Kleber ME, Ruff P, März W (2018) A new non-invasive diagnostic tool in coronary artery disease: artificial intelligence as an essential element of predictive, preventive, and personalized medicine. EPMA J 9(3):235–247

    PubMed  PubMed Central  Google Scholar 

  53. 53.

    Zippel-Schultz B, Schultz C, Helms TM (2017) Aktueller Stand und Zukunft des Telemonitoring. Herzschr Elektrophys 28(3):245–256

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Dr. Thomas M. Helms.

Ethics declarations

Interessenkonflikt

B. Zippel-Schultz, C. Schultz, D. Müller-Wieland, A.B. Remppis, M. Stockburger, C. Perings und T. M. Helms geben an, dass kein Interessenkonflikt besteht.

Für diesen Beitrag wurden von den Autoren keine Studien an Menschen oder Tieren durchgeführt. Für die aufgeführten Studien gelten die jeweils dort angegebenen ethischen Richtlinien.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zippel-Schultz, B., Schultz, C., Müller-Wieland, D. et al. Künstliche Intelligenz in der Kardiologie. Herzschr Elektrophys 32, 89–98 (2021). https://doi.org/10.1007/s00399-020-00735-2

Download citation

Schlüsselwörter

  • Big Data
  • Risikobewertung
  • Entscheidungsunterstützung
  • Selbstmanagement
  • Akzeptanz

Keywords

  • Big data
  • Risk assessment
  • Decision-making support
  • Self-management
  • Acceptance