Hallucinations in medical devices
Artificial Intelligence in the Life Sciences · 2025-12 · 8 · 100145
DOI: 10.1016/j.ailsci.2025.100145 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Intelligence in the Life Sciences, 2025-12. Verfasst von Jason Granstedt und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 148 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Computer methods in medical devices are frequently imperfect and are known to produce errors in clinical or diagnostic tasks. However, when deep learning and data-based approaches yield output that exhibit errors, the devices are frequently said to hallucinate. Drawing from theoretical developments and empirical studies in multiple medical device areas, we introduce a practical and universal definition that denotes hallucinations as a type of error that is plausible and can be either impactful or benign to the task at hand. The definition aims at facilitating the evaluation of medical devices that suffer from hallucinations across product areas. Using examples from imaging and non-imaging applications, we explore how the proposed definition relates to evaluation methodologies and discuss existing approaches for minimizing the prevalence of hallucinations.
Zitieren
APA
Granstedt, J., Kc, P., Deshpande, R., Garcia, V., & Badano, A. (2025). Hallucinations in medical devices. Artificial Intelligence in the Life Sciences, 8, 100145. https://doi.org/10.1016/j.ailsci.2025.100145
Vancouver
Granstedt J, Kc P, Deshpande R, Garcia V, Badano A. Hallucinations in medical devices. Artificial Intelligence in the Life Sciences. 2025;8:100145. doi:10.1016/j.ailsci.2025.100145
BibTeX
@article{Granstedt2025,
author = {Granstedt, Jason and Kc, Prabhat and Deshpande, Rucha and Garcia, Victor and Badano, Aldo},
title = {Hallucinations in medical devices},
journal = {Artificial Intelligence in the Life Sciences},
year = {2025},
volume = {8},
pages = {100145},
doi = {10.1016/j.ailsci.2025.100145}
}
EUVIMED