Künstliche Intelligenz in der Medizin – Holzweg oder Heilversprechen?

Artificial intelligence in medicine—the wrong track or promise of cure?

Zusammenfassung

Künstliche Intelligenz (KI) hat in den letzten Jahren eine neue Reifephase erreicht und entwickelt sich zum Treiber der Digitalisierung in allen Lebensbereichen. Die KI ist eine Querschnittstechnologie, die für alle Bereiche der Medizin mit Bilddaten, Textdaten und Biodaten von großer Bedeutung ist. Es gibt keinen medizinischen Bereich, der nicht von KI beeinflusst werden wird. Dabei spielt die klinische Entscheidungsunterstützung eine wichtige Rolle. Gerade beim medizinischen Workflow-Management und bei der Vorhersage des Behandlungserfolgs bzw. Behandlungsergebnisses etablieren sich KI‑Methoden. In der Bilddiagnose und im Patientenmanagement können KI‑Systeme bereits unterstützen, aber sie können keine kritischen Entscheidungen vorschlagen. Die jeweiligen Präventions- oder Therapiemaßnahmen können mit KI‑Unterstützung sinnvoller bewertet werden, allerdings ist die Abdeckung der Krankheiten noch viel zu gering, um robuste Systeme für den klinischen Alltag zu erstellen. Der flächendeckende Einsatz setzt Fortbildungsmaßnahmen für Ärzte voraus, um die Entscheidung treffen zu können, wann auf automatische Entscheidungsunterstützung vertraut werden kann.

Abstract

Artificial intelligence (AI) has attained a new level of maturity in recent years and is developing into the driver of digitalization in all areas of life. AI is a cross-sectional technology with great importance for all branches of medicine employing imaging as well as text and biodata. There is no field of medicine that remains unaffected by AI, with AI-assisted clinical decision-making assuming a particularly important role. AI methods are becoming established in medial workflow management and for prediction of therapeutic success or treatment outcome. AI systems are already able to lend support to imaging-based diagnosis and patient management, but cannot suggest critical decisions. The corresponding preventive or therapeutic measures can be more rationally assessed with the help of AI, although the number of diseases covered is currently far too low for the creation of robust systems for clinical routine. Prerequisite for the comprehensive use of AI systems is appropriate training to enable physicians to decide when computer-assisted decision-making can be relied upon.

This is a preview of subscription content, log in to check access.

Abb. 1

Notes

  1. 1.

    https://fb-ki.gi.de

  2. 2.

    https://www.ki-strategie-deutschland.de/home.html

  3. 3.

    http://iml.dfki.de

  4. 4.

    https://www.bmbf.de/de/deutsches-konsortium-fuer-translationale-krebsforschung-395.html

  5. 5.

    http://medicalcps.dfki.de/www/wp-content/uploads/BIRADS-30-seconds.mp4

  6. 6.

    http://medicalcps.dfki.de/www/wp-content/uploads/KDI_V2_Pro_v04_2.mp4

  7. 7.

    http://www.gesundheitsforschung-bmbf.de/_media/Medizininformatik_englisch_barrierefrei.pdf

  8. 8.

    http://www.transformproject.eu/

  9. 9.

    Es gibt aber auch Ansätze, die Diagnostik vorwiegend auf das Finden ähnlicher Patientenfälle zu beschränken [4].

  10. 10.

    International Skin Imaging Collaboration, https://isic-archive.com/ Letzter Download am 5. Februar 2019. Dank an Fabrizio Nunnari.

  11. 11.

    https://camelyon17.grand-challenge.org

Literatur

  1. 1.

    Alpaydin E (2018) Classifying multimodal data. In: The handbook of multimodal-multisensor interfaces, signal processing, architectures, and detection of emotion and cognition, Bd. 2. Morgan & Claypool Publishers, San Rafael

    Google Scholar 

  2. 2.

    Bahl M, Barzilay R, Yedidia A, Locascio N, Yu L, Lehman C (2018) High-risk breast lesions: a machine learning model to predict pathologic upgrade and reduce unnecessary surgical excision. Radiology 286:810–818

    Article  Google Scholar 

  3. 3.

    Baltrusaitis T, Ahuja C, Morency L‑P (2018) Multimodal machine learning. In: The handbook of multimodal-multisensor interfaces: signal processing, architectures, and detection of emotion and cognition, Bd. 2. Morgan & Claypool Publishers, San Rafael

    Google Scholar 

  4. 4.

    Bates DW, Saria S, Ohno-Machado L, Shah A, Escobar G (2014) Big data in health care: using analytics to identify and manage high-risk and high-cost patients. Health Aff (Millwood) 33(7):1123–1131

    Article  Google Scholar 

  5. 5.

    Bengio S, Deng L, Morency L‑P, Schuller B (2018) Multidisciplinary challenge topic: perspectives on predictive power of multimodal deep learning: surprises and future directions. In: The handbook of multimodal-multisensor interfaces: signal processing, architectures, and detection of emotion and cognition, Bd. 2. Morgan & Claypool Publishers, San Rafael

    Google Scholar 

  6. 6.

    Boden MA (2008) Mind as machine: a history of cognitive science. Clarendon Press, Oxford, England. (https://books.google.de/books?id=yRyETy43AdQC.)

    Google Scholar 

  7. 7.

    Boden MA, Bryson J, Caldwell DG, Dautenhahn K, Edwards L, Kember S, Newman P, Parry V, Pegman G, Rodden T, Sorrell T, Wallis M, Whitby B, Winfield AFT (2017) Principles of robotics: regulating robots in the real world. Connect Sci 29(2):124–129. https://doi.org/10.1080/09540091.2016.1271400

    Article  Google Scholar 

  8. 8.

    Burdick J, Marques O, Weinthal J, Furht B (2018) Rethinking skin lesion segmentation in a convolutional classifier. J Digit Imaging 31(4):435–440. https://doi.org/10.1007/s10278-017-0026-y

    Article  PubMed  Google Scholar 

  9. 9.

    Choi J‑H, Kang BJ, Baek JE, Lee HS, Kim SH (2018) Application of computer-aided diagnosis in breast ultrasound interpretation: improvements in diagnostic performance according to reader experience. Ultrasonography 37(3):217–225. https://doi.org/10.14366/usg.17046

    Article  PubMed  Google Scholar 

  10. 10.

    Codella NCF, Gutman D, Celebi ME, Helba B, Marchetti MA, Dusza SW, Kalloo A, Liopyris K, Mishra N, Kittler H, Halpern A (2018) Skin lesion analysis toward melanoma detection: a challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In: 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018). IEEE, Washington, DC https://doi.org/10.1109/ISBI.2018.8363547

    Google Scholar 

  11. 11.

    Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun SJ (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115. https://doi.org/10.1038/nature21056

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  12. 12.

    Fujisawa Y, Otomo Y, Ogata Y, Nakamura Y, Fujita R, Ishitsuka Y, Watanabe R, Okiyama N, Ohara K, Fujimoto M (2018) Deep-learning-based, computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumour diagnosis. Br J Dermatol 1111. https://doi.org/10.1111/bjd.16924

    Article  PubMed  Google Scholar 

  13. 13.

    Gelissen J, Sonntag D (2015a) Special issue on health and wellbeing. KI Künstliche Intell 29(2):111–113. https://doi.org/10.1007/s13218-015-0360-5

    Article  Google Scholar 

  14. 14.

    Gelissen J, Sonntag D (2015b) Special issue on health and wellbeing. KI Künstliche Intell 29(2):111–113. https://doi.org/10.1007/s13218-015-0360-5

    Article  Google Scholar 

  15. 15.

    Gibson E, Li W, Sudre C, Fidon L, Shakir DI, Wang G, Eaton-Rosen Z, Gray R, Doel T, Hu Y, Whyntie T, Nachev P, Modat M, Barratt DC, Ourselin S, Cardoso MJ, Vercauteren T (2018) Niftynet: a deep-learning platform for medical imaging. Comput Methods Programs Biomed 158:113–122. https://doi.org/10.1016/j.cmpb.2018.01.025

    Article  PubMed  PubMed Central  Google Scholar 

  16. 16.

    Handels H (2015) Medizinische Bildverarbeitung. Springer, Heidelberg, Berlin

    Google Scholar 

  17. 17.

    Keren G, Mousa AE-D, Pietquin O, Zafeiriou S, Schuller B (2018) Deep learning for multisensorial and multimodal interaction. In: The handbook of multimodal-multisensor interfaces: signal processing, architectures, and detection of emotion and cognition, Bd. 2. Morgan & Claypool Publishers, San Rafael

    Google Scholar 

  18. 18.

    Langlotz CP (2006) Radlex: a new method for indexing online educational materials. Radiographics 26:1595–1597. https://doi.org/10.1148/rg.266065168

    Article  PubMed  Google Scholar 

  19. 19.

    Luxenburger A, Prange A, Moniri MM, Sonntag D (2016) Medicalvr: towards medical remote collaboration using virtual reality. In: Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct, UbiComp ’16. ACM, New York, S 321–324 https://doi.org/10.1145/2968219.2971392

    Google Scholar 

  20. 20.

    Marchetti MA, Codella NC, Dusza SW, Gutman DA, Helba B, Kalloo A, Mishra N, Carrera C, Celebi ME, DeFazio JL, Jaimes N, Marghoob AA, Quigley E, Scope A, YÃl’lamos O, Halpern AC (2018) Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. J Am Acad Dermatol 78(2):270–277.e1. https://doi.org/10.1016/j.jaad.2017.08.016

    Article  PubMed  Google Scholar 

  21. 21.

    Mejino JL, Rubin DL, Brinkley JF (2008) FMA-RadLex: an application ontology of radiological anatomy derived from the foundational model of anatomy reference ontology. In: Proc. of AMIA symposium, S 465–469

    Google Scholar 

  22. 22.

    Möller M, Sintek M, Biedert R, Ernst P, Dengel A, Sonntag D (2010) Representing the international classification of diseases version 10 in OWL. In: Filipe J, Dietz JLG (Hrsg) KEOD 2010—proceedings of the international conference on knowledge engineering and ontology development Valencia, 25.10.–28.10. SciTePress, Lisbon, S 50–59. ISBN 978-9-898-42529-4

    Google Scholar 

  23. 23.

    Panagakis Y, Rudovic O, Pantic M (2018) Learning for multi-modal and context-sensitive interfaces. In: The handbook of multimodal-multisensor interfaces: signal processing, architectures, and detection of emotion and cognition, Bd. 2. Morgan & Claypool Publishers, San Rafael

    Google Scholar 

  24. 24.

    Prange A, Barz M, Sonntag D (2018) Medical 3d images in multimodal virtual reality. In: Proceedings of the 23rd International Conference on Intelligent User Interfaces Companion, IUI’18. ACM, New York, S 19:1–19:2 https://doi.org/10.1145/3180308.3180327. ISBN 978-1-4503-5571-1

    Google Scholar 

  25. 25.

    Rizzo A, Talbot TJ (2016) Virtual reality standardized patients for clinical training. In: The digital patient. John Wiley & Sons, Hoboken, S 255–272 https://doi.org/10.1002/9781118952788.ch18. ISBN 978-1-118-95278-8

    Google Scholar 

  26. 26.

    Samwald M, Jentzsch A, Bouton C, Kallesøe C, Willighagen EL, Hajagos J, Marshall MS, Prud’hommeaux E, Hassanzadeh O, Pichler E, Stephens S (2011) Linked open drug data for pharmaceutical research and development. J Cheminform 3:19. https://doi.org/10.1186/1758-2946-3-19

    Article  PubMed  PubMed Central  Google Scholar 

  27. 27.

    Siekmann JH (2009) Die entwicklung der disziplin in deutschland. KI, 23(1): 47–52. http://www.kuenstliche-intelligenz.de/fileadmin/template/main/archiv/pdf/ki2009-01_page47-52_web_full.pdf. Zugegriffen: 28.1.2019

  28. 28.

    Sonntag D (2016) Medical cyber-physical systems. In: Cyber-physical system design with sensor networking technologies, control, robotics and sensors. Institution of Engineering and Technology, London, England, S 311–333

    Google Scholar 

  29. 29.

    Sonntag D (2018) AI in germany: well-prepared and eager to do something. KI Kunstliche Intell 32(2–3):97–99. https://doi.org/10.1007/s13218-018-0555-7

    Article  Google Scholar 

  30. 30.

    Sonntag D, Möller M (2010) A multimodal dialogue mashup for medical image semantics. In: Proceedings of the 15th International Conference on Intelligent User Interfaces, IUI ’10. ACM, New York, S 381–384 https://doi.org/10.1145/1719970.1720036. ISBN 978-1-60558-515-4

    Google Scholar 

  31. 31.

    Sonntag D, Profitlich H (2019) An architecture of open-source tools to combine textual information extraction, faceted search and information visualisation. Artif Intell Med 93:13–28. https://doi.org/10.1016/j.artmed.2018.08.003

    Article  PubMed  Google Scholar 

  32. 32.

    Sonntag D, Wennerberg P, Buitelaar P, Zillner S (2009) Pillars of ontology treatment in the medical domain. J Cases Inf Techn 11(4):47–73

    Article  Google Scholar 

  33. 33.

    Sonntag D, Schulz C, Reuschling C, Galarraga L (2012) Radspeech’s mobile dialogue system for radiologists. In: Proceedings of the 2012 ACM International Conference on Intelligent User Interfaces, IUI ’12. ACM, New York, S 317–318 https://doi.org/10.1145/2166966.2167031. ISBN 978-1-4503-1048-2

    Google Scholar 

  34. 34.

    Sonntag D, Weber M, Cavallaro A, Hammon M (2014) Integrating digital pens in breast imaging for instant knowledge acquisition. AI Mag 35(1):26–37

    Article  Google Scholar 

  35. 35.

    Sonntag D, Tresp V, Zillner S, Cavallaro A, Hammon M, Reis A, Fasching PA, Sedlmayr M, Ganslandt T, Prokosch H, Budde K, Schmidt D, Hinrichs C, Wittenberg T, Daumke P, Oppelt PG (2016) The clinical data intelligence project—a smart data initiative. Inform Spektrum 39(4):290–300. https://doi.org/10.1007/s00287-015-0913-x

    Article  Google Scholar 

  36. 36.

    Stone P, Brooks R, Brynjolfsson E, Calo R, Etzioni O, Hager G, Hirschberg J, Kalyanakrishnan S, Kamar E, Kraus S, Leyton-Brown K, Parkes D, Press W, Saxenian A, Shah J, Tambe M, Teller AS (2016) Artificial intelligence and life in 2030. Technical report, one hundred year study on artificial intelligence: report of the 2015–2016 study panel. Stanford University, Stanford

    Google Scholar 

  37. 37.

    Strecker H, Pfitzner K (1988) XRAY – ein prototypisches konfigurierungs-expertensystem für die automatische röntgenprüfung. KI Kunstliche Intell 2(2):4–8

    Google Scholar 

  38. 38.

    Wang I, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM (2017) Chestx-ray8: Hospital-scale chest x‑ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. CoRR, abs/1705.02315

    Google Scholar 

  39. 39.

    Wright A, Hickman T, McEvoy D et al (2016) Analysis of clinical decision support system malfunctions: a case series and survey. J Am Med Inform Assoc 23:1068–1076

    Article  Google Scholar 

  40. 40.

    Yang Y, Tresp V, Wunderle M, Fasching PA (2018) Explaining therapy predictions with layer-wise relevance propagation in neural networks. 2018 IEEE International Conference on Healthcare Informatics (ICHI), S 152–162 https://doi.org/10.1109/ICHI.2018.00025

    Google Scholar 

  41. 41.

    Zhang X, Wang S, Liu J, Tao C (2017) Computer-aided diagnosis of four common cutaneous diseases using deep learning algorithm. In 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, Kansas City, S 1304–1306 https://doi.org/10.1109/BIBM.2017.8217850. ISBN 978-1-5090-3050-7

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Dr. Daniel Sonntag.

Ethics declarations

Interessenkonflikt

D. Sonntag gibt an, dass kein Interessenkonflikt besteht.

Für diesen Beitrag wurden vom Autor 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

Sonntag, D. Künstliche Intelligenz in der Medizin – Holzweg oder Heilversprechen?. HNO 67, 343–349 (2019). https://doi.org/10.1007/s00106-019-0665-z

Download citation

Schlüsselwörter

  • Bildauswertung, computergestützte
  • Medizinische Informatikanwendungen
  • Computergestützte Diagnostik
  • Entscheidungsunterstützung
  • Maschinelles Lernen

Keywords

  • Image interpretation, computer-assisted
  • Medical informatics applications
  • Diagnosis, computer-assisted
  • Decision making, computer-assisted
  • Machine learning