Please use this identifier to cite or link to this item: 10.1038/s41467-023-43095-4
Title: Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma
Authors: Chanda, Tirtha
Hauser, Katja
Hobelsberger, Sarah
Brinker, Titus J
Reader Study Consortium
Kaļva, Artūrs
Bondare-Ansberga , Vanda
Balcere, Alise
Department of Public Health and Epidemiology
Department of Dermatology and Venereology
Keywords: Humans;Trust;Artificial Intelligence;Dermatologists;Melanoma/diagnosis;Diagnosis, Differential;3.2 Clinical medicine;1.1. Scientific article indexed in Web of Science and/or Scopus database
Issue Date: Dec-2024
Citation: Chanda , T , Hauser , K , Hobelsberger , S , Brinker , T J , Reader Study Consortium , Kaļva , A , Bondare-Ansberga , V & Balcere , A 2024 , ' Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma ' , Nature Communications , vol. 15 , no. 1 , 524 . https://doi.org/10.1038/s41467-023-43095-4
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.
Description: Publisher Copyright: © 2024, The Author(s).
DOI: 10.1038/s41467-023-43095-4
ISSN: 2041-1723
Appears in Collections:Research outputs from Pure / Zinātniskās darbības rezultāti no ZDIS Pure

Files in This Item:
File SizeFormat 
Dermatologist-like_explainable.pdf3.23 MBAdobe PDFView/Openopen_acces_unlocked


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.