The final, formatted version of the article will be published soon.
PERSPECTIVE article
Front. Med.
Sec. Precision Medicine
Volume 11 - 2024 |
doi: 10.3389/fmed.2024.1451649
This article is part of the Research Topic Digital Health Innovations for Patient-Centered Care View all articles
Considerations on the basis of medical reasoning for use in AI applications
Provisionally accepted- 1 University Hospital of Cologne, Cologne, Germany
- 2 Berlin Institute of Health, Charité Medical University of Berlin, Berlin, Baden-Württemberg, Germany
We discuss the integration of Artificial Intelligence and Machine Learning in medical reasoning and decision-making, with a focus to the challenges and opportunities associated with the massive consumption of data required for training AI systems and contrast this with the limited data typically available to medical practitioners. We argue for a balanced approach that includes small data and emphasize the importance of maintaining the art of clinical reasoning amidst technological advancements. Finally, we provide, related to the complexities of medical reasoning, the potential of multidisciplinary research, and the necessity for careful abstraction and conceptual modeling in AI applications.
Keywords: Medical Reasoning, artificial intelligence, machine learning, conceptual modeling, abduction, duck test, abstraction, Rare Diseases
Received: 19 Jun 2024; Accepted: 27 Aug 2024.
Copyright: © 2024 Koumpis and Graefe. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Adamantios Koumpis, University Hospital of Cologne, Cologne, Germany
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.