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 S. Utikal
- Bastian Schilling
- Claudia Buerger
- Cristian 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
- 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
2025-05-21
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.