Transparency and Representation in Clinical Research Utilizing Artificial Intelligence in Oncology: A Scoping Review
Transparenz und Repräsentation in der klinischen Forschung mit Künstlicher Intelligenz in der Onkologie: Scoping Review
Cancer Medicine · 2025-03 · 14 (5)
DOI: 10.1002/cam4.70728 ↗Auf einen Blick
Die Review untersuchte die Transparenz der Demografie-Berichte und die Vielfalt der Teilnehmenden in klinischen Studien mit KI in der Onkologie. Nur wenige Studien berichteten Rasse/ethnische Daten.
Fragestellung
Wie transparent berichten klinische Studien mit KI in der Onkologie demografische Daten, und wie vielfältig sind die eingeschlossenen Teilnehmenden?
Methode
Scoping Review von peer-reviewten Originalarbeiten aus PubMed (2016–2021); klinische Studien und Originalforschung, keine Reviews/Metaanalysen; deskriptive Statistik.
Ergebnisse
220 Studien gescreent, 118 eingeschlossen. 47 (40%) hatten mindestens einen öffentlich verfügbaren Datensatz für Training/Validierung. Alter: 69 (58%), Geschlecht: 60 (51%), Rasse: 6 (5%).
Schlussfolgerung der Autor:innen
Die Autor:innen fanden, dass nur eine Minderheit der Studien (5%) rassische und ethnische demografische Daten berichtete. Zudem waren in diesen Studien wenige nicht-weiße Patient:innen vertreten.
Kernaussagen
- 47 von 118 Studien hatten öffentlich verfügbare Trainings- oder Validierungsdatensätze.
- Rasse wurde nur in 6 Studien (5%) berichtet.
- In den Berichten mit Rassedaten lag der Weißanteil bei 70,7 % bis 93,4 %.
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Scoping Review in der Zeitschrift Cancer Medicine, online erschienen am 09.03.2025. Verfasst von Anjali J D'Amiano und 5 weiteren Autor:innen. Beteiligte Einrichtung: Johns Hopkins University School of Medicine, Baltimore, Maryland, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Medical Oncology, Biomedical Research, Neoplasms. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 141 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Artificial intelligence (AI) has significant potential to improve health outcomes in oncology. However, as AI utility increases, it is imperative to ensure that these models do not systematize racial and ethnic bias and further perpetuate disparities in health. This scoping review evaluates the transparency of demographic data reporting and diversity of participants included in published clinical studies utilizing AI in oncology.
Methods
We utilized PubMed to search for peer‐reviewed research articles published between 2016 and 2021 with the query type “(“deep learning” or “machine learning” or “neural network” or “artificial intelligence”) and (“neoplas$” or “cancer$” or “tumor$” or “tumour$”).” We included clinical trials and original research studies and excluded reviews and meta‐analyses. Oncology‐related studies that described data sets used in training or validation of the AI models were eligible. Data regarding public reporting of patient demographics were collected, including age, sex at birth, and race. We used descriptive statistics to analyze these data across studies.
Results
Out of 220 total studies, 118 were eligible and 47 (40%) had at least one described training or validation data set publicly available. 69 studies (58%) reported age data for patients included in training or validation sets, 60 studies (51%) reported sex, and six studies (5%) reported race. Of the studies that reported race, a range of 70.7%–93.4% of individuals were White. Only three studies reported racial demographic data with greater than two categories (i.e. “White” vs. “non‐White” or “White” vs. “Black”).
Conclusions
We found that a minority of studies (5%) analyzed reported racial and ethnic demographic data. Furthermore, studies that did report racial demographic data had few non‐White patients. Increased transparency regarding reporting of demographics and greater representation in data sets is essential to ensure fair and unbiased clinical integration of AI in oncology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
- Brigham and Women's Hospital/Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts, USA.
- The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
ORCID-Profile: Anjali J D'Amiano
Zitieren
APA
D'Amiano, A. J., Cheunkarndee, T., Azoba, C., Chen, K. Y., Mak, R. H., & Perni, S. (2025). Transparency and Representation in Clinical Research Utilizing Artificial Intelligence in Oncology: A Scoping Review. Cancer Medicine, 14(5). https://doi.org/10.1002/cam4.70728
Vancouver
D'Amiano AJ, Cheunkarndee T, Azoba C, Chen KY, Mak RH, Perni S. Transparency and Representation in Clinical Research Utilizing Artificial Intelligence in Oncology: A Scoping Review. Cancer Medicine. 2025;14(5). doi:10.1002/cam4.70728
BibTeX
@article{DAmiano2025,
author = {D'Amiano, Anjali J and Cheunkarndee, Tia and Azoba, Chinenye and Chen, Krista Y and Mak, Raymond H and Perni, Subha},
title = {Transparency and Representation in Clinical Research Utilizing Artificial Intelligence in Oncology: A Scoping Review},
journal = {Cancer Medicine},
year = {2025},
volume = {14},
number = {5},
doi = {10.1002/cam4.70728}
}
EUVIMED