TY - JOUR
T1 - Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma
AU - Chanda, Tirtha
AU - Hauser, Katja
AU - Hobelsberger, Sarah
AU - Bucher, Tabea-Clara
AU - Garcia, Carina Nogueira
AU - Wies, Christoph
AU - Kittler, Harald
AU - Tschandl, Philipp
AU - Navarrete-Dechent, Cristian
AU - Podlipnik, Sebastian
AU - Chousakos, Emmanouil
AU - Crnaric, Iva
AU - Majstorovic, Jovana
AU - Alhajwan, Linda
AU - Foreman, Tanya
AU - Peternel, Sandra
AU - Sarap, Sergei
AU - Özdemir, İrem
AU - Barnhill, Raymond L
AU - Llamas-Velasco, Mar
AU - Poch, Gabriela
AU - Korsing, Sören
AU - Sondermann, Wiebke
AU - Gellrich, Frank Friedrich
AU - Heppt, Markus V
AU - Erdmann, Michael
AU - Haferkamp, Sebastian
AU - Drexler, Konstantin
AU - Goebeler, Matthias
AU - Schilling, Bastian
AU - Utikal, Jochen S
AU - Ghoreschi, Kamran
AU - Fröhling, Stefan
AU - Krieghoff-Henning, Eva
AU - Brinker, Titus J
AU - Reader Study Consortium
A2 - Salava, Alexander
A2 - Thiem, Alexander
A2 - Dimitrios, Alexandris
A2 - Ammar, Amr Mohammad
A2 - Vučemilović, Ana Sanader
A2 - Kaļva, Artūrs
A2 - Bondare-Ansberga , Vanda
A2 - Balcere, Alise
N1 - Publisher Copyright:
© 2024, The Author(s).
PY - 2024/12
Y1 - 2024/12
N2 - 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.
AB - 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.
KW - Humans
KW - Trust
KW - Artificial Intelligence
KW - Dermatologists
KW - Melanoma/diagnosis
KW - Diagnosis, Differential
UR - http://www.scopus.com/inward/record.url?scp=85182489709&partnerID=8YFLogxK
U2 - 10.1038/s41467-023-43095-4
DO - 10.1038/s41467-023-43095-4
M3 - Article
C2 - 38225244
SN - 2041-1723
VL - 15
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 524
ER -