EUVIMEDEUVIMED entdecken
Scoping Review

Ethical considerations for artificial intelligence in dermatology: a scoping review

Ethische Aspekte künstlicher Intelligenz in der Dermatologie: Scoping Review

Emily R Gordon, Megan H Trager, Despina Kontos, Chunhua Weng iD, Larisa J Geskin, Lydia S Dugdale, Faramarz H Samie iD

British Journal of Dermatology · 17.05.2024 · 190 (6) · 789-797

DOI: 10.1093/bjd/ljae040 ↗

Auf einen Blick

Das Scoping Review beschreibt Anwendungen von KI in der Dermatologie und die dazu diskutierten ethischen Fragen. Genannt werden u. a. Fehlklassifikation, Datenschutz, Unterrepräsentation von Hautfarben und ungenaue Antworten von Large Language Models.

Fragestellung

Welche KI-Anwendungen in der Dermatologie gibt es und welche ethischen Implikationen werden dazu beschrieben?

Methode

Scoping Review nach PRISMA Extension for Scoping Reviews; Suche in PubMed, MEDLINE, Cochrane Library und Google Scholar.

Ergebnisse

202 Paper identifiziert, 68 Studien eingeschlossen. 32 zu klinischer Bildanalyse, 17 zu begrenzter Repräsentation von Hautfarben, 9 zu Teledermatologie, 7 zu Large Language Models und 7 zu Einstellungen/Vertrauen in KI.

Schlussfolgerung der Autor:innen

Die Autor:innen betonen, dass Schutzmaßnahmen erforderlich sind, damit KI in der Dermatologie ethisch angewendet wird.

Kernaussagen

  • 32 Studien zu klinischer Bildanalyse mit ethischen Bedenken
  • 17 Studien zu unzureichender Repräsentation von Hautfarben
  • 7 Studien zu ungenauen Antworten von Large Language Models

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 British Journal of Dermatology, online erschienen am 08.02.2024. Verfasst von Emily R Gordon und 6 weiteren Autor:innen. Beteiligte Einrichtung: Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Dermatology. Die Arbeit wurde bisher 94-mal zitiert (Crossref) und nennt 81 Literaturangaben.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The field of dermatology is experiencing the rapid deployment of artificial intelligence (AI), from mobile applications (apps) for skin cancer detection to large language models like ChatGPT that can answer generalist or specialist questions about skin diagnoses. With these new applications, ethical concerns have emerged. In this scoping review, we aimed to identify the applications of AI to the field of dermatology and to understand their ethical implications. We used a multifaceted search approach, searching PubMed, MEDLINE, Cochrane Library and Google Scholar for primary literature, following the PRISMA Extension for Scoping Reviews guidance. Our advanced query included terms related to dermatology, AI and ethical considerations. Our search yielded 202 papers. After initial screening, 68 studies were included. Thirty-two were related to clinical image analysis and raised ethical concerns for misdiagnosis, data security, privacy violations and replacement of dermatologist jobs. Seventeen discussed limited skin of colour representation in datasets leading to potential misdiagnosis in the general population. Nine articles about teledermatology raised ethical concerns, including the exacerbation of health disparities, lack of standardized regulations, informed consent for AI use and privacy challenges. Seven addressed inaccuracies in the responses of large language models. Seven examined attitudes toward and trust in AI, with most patients requesting supplemental assessment by a physician to ensure reliability and accountability. Benefits of AI integration into clinical practice include increased patient access, improved clinical decision-making, efficiency and many others. However, safeguards must be put in place to ensure the ethical application of AI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceDermatologyHumansTelemedicineInformed ConsentConfidentialityDiagnostic ErrorsComputer SecuritySkin DiseasesMobile Applications

Autor:innen und Institutionen

  • Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA.
  • Columbia University Irving Medical Center, Departments of Dermatology.
  • University of Pennsylvania, Perelman School of Medicine, Department of Radiology, Philadelphia, PA, USA.
  • Radiology.
  • Biomedical Informatics, New York, NY, USA.
  • Columbia University Vagelos College of Physicians and Surgeons, Department of Medicine, Center for Clinical Medical Ethics, New York, NY, USA.

ORCID-Profile: Chunhua Weng, Faramarz H Samie

Zitieren

APA

Gordon, E. R., Trager, M. H., Kontos, D., Weng, C., Geskin, L. J., Dugdale, L. S., & Samie, F. H. (2024). Ethical considerations for artificial intelligence in dermatology: a scoping review. British Journal of Dermatology, 190(6), 789-797. https://doi.org/10.1093/bjd/ljae040

Vancouver

Gordon ER, Trager MH, Kontos D, Weng C, Geskin LJ, Dugdale LS, et al. Ethical considerations for artificial intelligence in dermatology: a scoping review. British Journal of Dermatology. 2024;190(6):789-797. doi:10.1093/bjd/ljae040

BibTeX
@article{Gordon2024,
  author = {Gordon, Emily R and Trager, Megan H and Kontos, Despina and Weng, Chunhua and Geskin, Larisa J and Dugdale, Lydia S and Samie, Faramarz H},
  title = {Ethical considerations for artificial intelligence in dermatology: a scoping review},
  journal = {British Journal of Dermatology},
  year = {2024},
  volume = {190},
  number = {6},
  pages = {789--797},
  doi = {10.1093/bjd/ljae040}
}
Kostenlos starten →