Integration von KI-Anwendungen der bildgebenden Diagnostik – Ein Praxisbericht

Zusammenfassung

Trotz des Wachstums an verfügbaren KI-Produkten wird eine Diskrepanz zwischen deren Verfügbarkeit und der täglichen Nutzung in Kliniken festgestellt. Der Artikel beleuchtet die Integration von KI-Anwendungen der bildgebenden Diagnostik in den klinischen Regelbetrieb und beschreibt wie klinische Nutzungspotenziale durch gezieltes Management erschlossen werden können. Der Beitrag legt den Fokus dabei auf konkrete Maßnahmen und Entscheidungsprozesse, die notwendig sind, um KI erfolgreich in die klinische Routine zu integrieren und gibt Einblicke in Beispiele aus der Praxis innerhalb eines Gesundheitskonzerns.

Abstract

Despite the growth in available AI products, there is a discrepancy between their availability and daily use in clinics. This article sheds light on the integration of AI applications in diagnostic imaging into regular clinical operations and describes how clinical utilization potential can be tapped through targeted management. The article focuses on specific measures and decision-making processes that are necessary to successfully integrate AI into clinical routine and provides insights into practical examples within a healthcare group.

Schlüsselwörter

KI-Anwendungen - Bildgebende Diagnostik - Integration - Validierungsprozesse - Klinische Routine

Keywords

AI applications - imaging diagnostics - integration - validation processes - clinical routine

Publication History

Article published online:
28 November 2024

• Literatur

• 1 Creative Destruction Lab. Geoff Hinton: On Radiology. Accessed November 24, 2016 at: https://www.youtube.com/watch?v=2HMPRXstSvQ
• 2 Nensa F, Demircioglu A, Rischpler C. Artificial Intelligence in Nuclear Medicine. Journal of nuclear medicine: official publication, Society of Nuclear Medicine 2019; 60 (Suppl. 02) 29S-37S
• 3 Shah V. siemens-healthineers.com. Automatic landmarking and parsing of human anatomy (ALPHA) for innovative and smart MI applications]. In White Paper [White paper]. 2021 https://marketing.webassets.siemens-healthineers.com/5d57cb13cb102804/7cf4aee23b4e/siemens-healthineers_mi_alpha_white_paper.pdf
• 4 Kim SH, Mir-Bashiri S, Matthies P. et al. Integration der strukturierten Befundung in den radiologischen Routine-Workflow [Integration of structured reporting into the routine radiological workflow]. Der Radiologe 2021; 61: 1005-1013
• 5 Health AI Register. (o. D.). https://healthairegister.com/
• 6 Center for Devices and Radiological Health. Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices. U.S. Food And Drug Administration. Accessed May 13, 2024 at: https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices
• 7 Kelly BS. Radiology artificial intelligence: a systematic review and evaluation of methods (RAISE). European radiology 2022; 32: 7998-8007 https://healthcare-in-europe.com/en/news/ai-radiology-s-next-frontier.html
• 8 Leiner T, Bennink E, Mol CP. et al. Bringing AI to the clinic: blueprint for a vendor-neutral AI deployment infrastructure. Insights into imaging 2021; 12: 11
• 9 Dr. med. KI – Grundlagen für Ärztinnen und Ärzte | AI Campus. (o. D.). AI Campus. https://ki-campus.org/courses/drmedki_grundlagen_cme
• 10 Mert S, Stoerzer P, Brauer J. et al. Diagnostic power of ChatGPT 4 in distal radius fracture detection through wrist radiographs. Archives Of Orthopaedic And Trauma Surgery 2024; 144: 2461-2467
• 11 Akinci D’Antonoli T, Stanzione A, Bluethgen C. et al. Large language models in radiology: fundamentals, applications, ethical considerations, risks, and future directions. Diagnostic and interventional radiology (Ankara, Turkey) 2024; 30: 80-90