Common pitfalls and recommendations for grand challenges in medical artificial intelligence

With the impact of artificial intelligence (AI) algorithms on medical research on the rise, the importance of competitions for comparative validation of algorithms, so-called challenges, has been steadily increasing, to a point at which challenges can be considered major drivers of research, particu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Reinke, Annika (VerfasserIn) , Tizabi, Minu (VerfasserIn) , Eisenmann, Matthias (VerfasserIn) , Maier-Hein, Lena (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 11 June 2021
In: European urology focus
Year: 2021, Jahrgang: 7, Heft: 4, Pages: 710-712
ISSN:2405-4569
DOI:10.1016/j.euf.2021.05.008
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.euf.2021.05.008
Verlag, lizenzpflichtig, Volltext: https://www.sciencedirect.com/science/article/pii/S2405456921001607
Volltext
Verfasserangaben:Annika Reinke, Minu D. Tizabi, Matthias Eisenmann, Lena Maier-Hein
Beschreibung
Zusammenfassung:With the impact of artificial intelligence (AI) algorithms on medical research on the rise, the importance of competitions for comparative validation of algorithms, so-called challenges, has been steadily increasing, to a point at which challenges can be considered major drivers of research, particularly in the biomedical image analysis domain. Given their importance, high quality, transparency, and interpretability of challenges is essential for good scientific practice and meaningful validation of AI algorithms, for instance towards clinical translation. This mini-review presents several issues related to the design, execution, and interpretation of challenges in the biomedical domain and provides best-practice recommendations. - Patient summary - This paper presents recommendations on how to reliably compare the usefulness of new artificial intelligence methods for analysis of medical images.
Beschreibung:Gesehen am 25.10.2021
Beschreibung:Online Resource
ISSN:2405-4569
DOI:10.1016/j.euf.2021.05.008