Dermatologist-like explainable AI enhances melanoma diagnosis accuracy: eye-tracking study
Tirtha Chanda, Sarah Haggenmueller, Tabea-Clara Bucher, Tim Holland‐Letz, Harald Kittler, Philipp Tschandl, Markus V. Heppt, Carola Berking, Jochen Utikal, Bastian Schilling, Claudia Buerger, Cristián Navarrete‐Dechent, Matthias Goebeler, Jakob Nikolas Kather, Carolin V. Schneider, Benjamin Durani, Hendrike Durani, Martin Jansen, Juliane Wacker, Joerg Wacker, Nina Booken, Verena Ahlgrimm-Siess, Julia Welzel, Oana-Diana Persa, Florentia Dimitriou, Stephan Alexander Braun, Lara Valeska Maul, Antonia Reimer-Taschenbrecker, Sandra Schuh, Falk G. Bechara, Laurence Feldmeyer, Beda Mühleisen, Elisabeth Gössinger, Stephan Alexander Braun, Van Anh Nguyen, Julia-Tatjana Maul, Friederike Hoffmann, Claudia Pföhler, Janis Thamm, Wiebke Ludwig-Peitsch, Daniela Hartmann, Laura Garzona-Navas, Martyna Sławińska, Panagiota Theofilogiannakou, Ana Sanader Vucemilovic, Juan José Lluch-Galcerá, Aude Beyens, Dilara Ilhan Erdil, Rym Afiouni, Vanda Bondare-Ansberga, Martha Alejandra Morales-Sánchez, Arzu Ferhatosmanoğlu, Roque Rafael Oliveira Neto, Lidija Petrovska, Amalia Tsakiri, Hülya Cenk, Sharon Hudson, Miroslav Dragolov, Zorica Zafirovik, Ivana Jocic, Alise Balcere, Zsuzsanna Lengyel, Alexander Salava, Isabelle Hoorens, Sonia Rodriguez Saa, Emõke Rácz, Gabriel Salerni, Karen Manuelyan, Amr Mohammad Ammar, Michael Erdmann, Nicola Wagner, Jannik Sambale, Stephan Kemenes, Moritz Ronicke, Lukas Sollfrank, Caroline Bosch-Voskens, Ioannis Sagonas, Thomas Breakell, Christopher Uebel, Lisa Zieringer, Michael Hoener, Leonie Rabe, Tim Sackmann, Julia Baumert, Marthe Lisa Schaarschmidt, Nadia Ninosu, Kaan Yilmaz, Danai Dionysia, Franca Christ, Sarah Fahimi, Sabina Loos, Ani Sachweizer, Janika Gosmann, Tobias Weberschock, Ufuk Erdogdu, Amelie Buchinger, Jasmin Lunderstedt, Timo Funk, Hess Klifo, Sebastian Kiefer
Abstract
Artificial intelligence (AI) systems substantially improve dermatologists' diagnostic accuracy for melanoma, with explainable AI (XAI) systems further enhancing their confidence and trust in AI-driven decisions. Despite these advancements, there remains a critical need for objective evaluation of how dermatologists engage with both AI and XAI tools. In this study, 76 dermatologists participate in a reader study, diagnosing 16 dermoscopic images of melanomas and nevi using an XAI system that provides detailed, domain-specific explanations, while eye-tracking technology assesses their interactions. Diagnostic performance is compared with that of a standard AI system lacking explanatory features. Here we show that XAI significantly improves dermatologists' diagnostic balanced accuracy by 2.8 percentage points compared to standard AI. Moreover, diagnostic disagreements with AI/XAI systems and complex lesions are associated with elevated cognitive load, as evidenced by increased ocular fixations. These insights have significant implications for the design of AI/XAI tools for visual tasks in dermatology and the broader development of XAI in medical diagnostics.