Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma
-
Published:2024-01-15
Issue:1
Volume:15
Page:
-
ISSN:2041-1723
-
Container-title:Nature Communications
-
language:en
-
Short-container-title:Nat Commun
Author:
Chanda TirthaORCID, Hauser KatjaORCID, Hobelsberger Sarah, Bucher Tabea-ClaraORCID, Garcia Carina NogueiraORCID, Wies ChristophORCID, Kittler HaraldORCID, Tschandl PhilippORCID, Navarrete-Dechent Cristian, Podlipnik SebastianORCID, Chousakos EmmanouilORCID, Crnaric Iva, Majstorovic JovanaORCID, Alhajwan Linda, Foreman Tanya, Peternel SandraORCID, Sarap Sergei, Özdemir İremORCID, Barnhill Raymond L., Llamas-Velasco Mar, Poch Gabriela, Korsing Sören, Sondermann WiebkeORCID, Gellrich Frank FriedrichORCID, Heppt Markus V., Erdmann MichaelORCID, Haferkamp Sebastian, Drexler Konstantin, Goebeler MatthiasORCID, Schilling BastianORCID, Utikal Jochen S.ORCID, Ghoreschi KamranORCID, Fröhling StefanORCID, Krieghoff-Henning Eva, Salava Alexander, Thiem Alexander, Dimitrios Alexandris, Ammar Amr Mohammad, Vučemilović Ana Sanader, Yoshimura Andrea Miyuki, Ilieva Andzelka, Gesierich Anja, Reimer-Taschenbrecker Antonia, Kolios Antonios G. A., Kalva Arturs, Ferhatosmanoğlu Arzu, Beyens Aude, Pföhler Claudia, Erdil Dilara Ilhan, Jovanovic Dobrila, Racz Emoke, Bechara Falk G., Vaccaro Federico, Dimitriou Florentia, Rasulova Gunel, Cenk Hulya, Yanatma Irem, Kolm Isabel, Hoorens Isabelle, Sheshova Iskra Petrovska, Jocic Ivana, Knuever Jana, Fleißner Janik, Thamm Janis Raphael, Dahlberg Johan, Lluch-Galcerá Juan José, Figueroa Juan Sebastián Andreani, Holzgruber Julia, Welzel Julia, Damevska Katerina, Mayer Kristine Elisabeth, Maul Lara Valeska, Garzona-Navas Laura, Bley Laura Isabell, Schmitt Laurenz, Reipen Lena, Shafik Lidia, Petrovska Lidija, Golle Linda, Jopen Luise, Gogilidze Magda, Burg Maria Rosa, Morales-Sánchez Martha Alejandra, Sławińska Martyna, Mengoni Miriam, Dragolov Miroslav, Iglesias-Pena Nicolás, Booken Nina, Enechukwu Nkechi Anne, Persa Oana-Diana, Oninla Olumayowa Abimbola, Theofilogiannakou Panagiota, Kage Paula, Neto Roque Rafael Oliveira, Peralta Rosario, Afiouni Rym, Schuh Sandra, Schnabl-Scheu Saskia, Vural Seçil, Hudson Sharon, Saa Sonia Rodriguez, Hartmann Sören, Damevska Stefana, Finck Stefanie, Braun Stephan Alexander, Hartmann Tim, Welponer Tobias, Sotirovski Tomica, Bondare-Ansberga Vanda, Ahlgrimm-Siess Verena, Frings Verena Gerlinde, Simeonovski Viktor, Zafirovik Zorica, Maul Julia-Tatjana, Lehr Saskia, Wobser Marion, Debus Dirk, Riad Hassan, Pereira Manuel P., Lengyel Zsuzsanna, Balcere Alise, Tsakiri Amalia, Braun Ralph P., Brinker Titus J.ORCID,
Abstract
AbstractArtificial 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.
Publisher
Springer Science and Business Media LLC
Subject
General Physics and Astronomy,General Biochemistry, Genetics and Molecular Biology,General Chemistry,Multidisciplinary
Reference63 articles.
1. Maron, R. C. et al. Artificial Intelligence and its effect on dermatologists’ accuracy in dermoscopic melanoma image classification: web-based survey study. J. Med. Internet Res. 22, e18091 (2020). 2. Tschandl, P. et al. Human–computer collaboration for skin cancer recognition. Nat. Med. 26, 1229–1234 (2020). 3. Yu, K.-H., Beam, A. L. & Kohane, I. S. Artificial intelligence in healthcare. Nat. Biomed. Eng. 2, 719–731 (2018). 4. Goodman, B. & Flaxman, S. European Union Regulations on Algorithmic Decision-Making and a “Right to Explanation”. AI Mag. 38, 50–57 (2017). 5. Tonekaboni, S., Joshi, S., McCradden, M. D. & Goldenberg, A. What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use. In Proceedings of the 4th Machine Learning for Healthcare Conference 359–380 (PMLR, 2019).
|
|