Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma

Tirtha Chanda, Katja Hauser, Sarah Hobelsberger, Tabea-Clara Bucher, Carina Nogueira Garcia, Christoph Wies, Harald Kittler, Philipp Tschandl, Cristian Navarrete-Dechent, Sebastian Podlipnik, Emmanouil Chousakos, Iva Crnaric, Jovana Majstorovic, Linda Alhajwan, Tanya Foreman, Sandra Peternel, Sergei Sarap, İrem Özdemir, Raymond L. Barnhill, Mar Llamas-Velasco, Gabriela Poch, Sören Korsing, Wiebke Sondermann, Frank Friedrich Gellrich, Markus V. Heppt, Michael Erdmann, Sebastian Haferkamp, Konstantin Drexler, Matthias Goebeler, Bastian Schilling, Jochen S. Utikal, Kamran Ghoreschi, Stefan Fröhling, Eva Krieghoff-Henning and Titus J. Brinker ()
Additional contact information
Tirtha Chanda: German Cancer Research Center (DKFZ)
Katja Hauser: German Cancer Research Center (DKFZ)
Sarah Hobelsberger: University Hospital, Technical University Dresden
Tabea-Clara Bucher: German Cancer Research Center (DKFZ)
Carina Nogueira Garcia: German Cancer Research Center (DKFZ)
Christoph Wies: German Cancer Research Center (DKFZ)
Harald Kittler: Medical University of Vienna
Philipp Tschandl: Medical University of Vienna
Cristian Navarrete-Dechent: Pontificia Universidad Católica de Chile
Sebastian Podlipnik: University of Barcelona, IDIBAPS
Emmanouil Chousakos: National & Kapodistrian University of Athens
Iva Crnaric: Sestre milosrdnice University Hospital Center
Jovana Majstorovic: Derma Style, Dermatovenerology clinic
Linda Alhajwan: Dubai London Clinic
Tanya Foreman: West Dermatology, Newport Beach
Sandra Peternel: Clinical Hospital Center Rijeka, Faculty of Medicine, University of Rijeka
Sergei Sarap: LaserMed
İrem Özdemir: Faculty of Medicine, Gazi University
Raymond L. Barnhill: Unit of Formation and Research of Medicine University of Paris
Mar Llamas-Velasco: Universidad Autónoma de Madrid
Gabriela Poch: Venereology and Allergology
Sören Korsing: University Hospital Essen, University Duisburg-Essen
Wiebke Sondermann: Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg
Frank Friedrich Gellrich: University Hospital, Technical University Dresden
Markus V. Heppt: Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg
Michael Erdmann: Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg
Sebastian Haferkamp: University Hospital Regensburg
Konstantin Drexler: University Hospital Regensburg
Matthias Goebeler: Venereology and Allergology, University Hospital Würzburg
Bastian Schilling: Venereology and Allergology, University Hospital Würzburg
Jochen S. Utikal: Venereology and Allergology, University Medical Center Mannheim, Ruprecht-Karl University of Heidelberg
Kamran Ghoreschi: Venereology and Allergology
Stefan Fröhling: National Center for Tumor Diseases (NCT) Heidelberg and German Cancer Research Center (DKFZ)
Eva Krieghoff-Henning: German Cancer Research Center (DKFZ)
Titus J. Brinker: German Cancer Research Center (DKFZ)

Nature Communications, 2024, vol. 15, issue 1, 1-17

Abstract: Abstract Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists’ decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists’ diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists’ confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists’ willingness to adopt such XAI systems, promoting future use in the clinic.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-023-43095-4 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-023-43095-4

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-43095-4

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().