Title: | Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma |
Authors: | Chanda, T. Hauser, K. Hobelsberger, S. Bucher, T.-C. Garcia, C.N. Wies, C. Kittler, H. Tschandl, Philipp Navarrete-Dechent, Cristian Podlipnik, Sebastian Chousakos, Emmanouil Majstorovic, Jovana Foreman, Tanya Balcere, Alise Peternel, Sandra Sarap, Sergei Özdemir, İrem Barnhill, Raymond L. Sondermann, Wiebke Llamas-Velasco, Mar Poch, Gabriela Krieghoff-Henning, Eva Korsing, Sören Ghoreschi, Kamran Maul, Julia-Tatjana Gellrich, Frank Friedrich Heppt, Markus V. Erdmann, Michael Haferkamp, Sebastian Drexler, Konstantin Goebeler, Matthias Schilling, Bastian Zafirovik, Zorica Utikal, Jochen S. Lengyel, Zsuzsanna Salava, Alexander Fröhling, Stefan Thiem, Alexander Dimitrios, Alexandris Ammar, Amr Mohammad Vučemilović, Ana Sanader Yoshimura, Andrea Miyuki Pföhler, Claudia Ilieva, Andzelka Gesierich, Anja Rasulova, Gunel Reimer-Taschenbrecker, Antonia Kolios, Antonios G. A. Ferhatosmanoğlu, Arzu Kalva, Arturs Simeonovski, Viktor Beyens, Aude Pereira, Manuel P. Erdil, Dilara Ilhan Jovanovic, Dobrila Racz, Emoke Cenk, Hulya Bechara, Falk G. Vaccaro, Federico Dimitriou, Florentia Brinker, Titus J. Frings, Verena Gerlinde Thamm, Janis Raphael Yanatma, Irem Kolm, Isabel Hoorens, Isabelle Sheshova, Iskra Petrovska Jocic, Ivana Knuever, Jana Bondare-Ansberga, Vanda Fleißner, Janik Riad, Hassan Ahlgrimm-Siess, Verena Dahlberg, Johan Lluch-Galcerá, Juan José Figueroa, Juan Sebastián Andreani Holzgruber, Julia Welzel, Julia Damevska, Katerina Mayer, Kristine Elisabeth Garzona-Navas, Laura Maul, Lara Valeska Petrovska, Lidija Braun, Ralph P. Bley, Laura Isabell Schmitt, Laurenz Reipen, Lena Shafik, Lidia Debus, Dirk Golle, Linda Sotirovski, Tomica Jopen, Luise Persa, Oana-Diana Gogilidze, Magda Burg, Maria Rosa Morales-Sánchez, Martha Alejandra Sławińska, Martyna Mengoni, Miriam Welponer, Tobias Hartmann, Tim Dragolov, Miroslav Iglesias-Pena, Nicolás Booken, Nina Wobser, Marion Enechukwu, Nkechi Anne Tsakiri, Amalia Oninla, Olumayowa Abimbola Theofilogiannakou, Panagiota Kage, Paula Neto, Roque Rafael Oliveira Braun, Stephan Alexander Peralta, Rosario Afiouni, Rym Schuh, Sandra Alhajwan, Linda Finck, Stefanie Hartmann, Sören Schnabl-Scheu, Saskia Vural, Seçil Damevska, Stefana Hudson, Sharon Lehr, Saskia Saa, Sonia Rodriguez Crnaric, Iva |
Keywords: | accuracy assessment cancer detection method artificial intelligence dermatologist differential diagnosis human melanoma trust Artificial Intelligence Dermatologists Diagnosis, Differential Humans Melanoma Trust |
Publisher: | Nature Research |
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. © 2024, The Author(s). |
URI: | https://doi.org/10.1038/s41467-023-43095-4 https://hdl.handle.net/11499/56723 |
ISSN: | 2041-1723 |
Appears in Collections: | PubMed İndeksli Yayınlar Koleksiyonu / PubMed Indexed Publications Collection Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection Tıp Fakültesi Koleksiyonu WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
|