Artificial Intelligence and Its Effect on Dermatologists' Accuracy in Dermoscopic Melanoma Image Classification: Web-Based Survey Study

• Main Authors: Maron, Roman C (Author), Utikal, Jochen S (Author), Hekler, Achim (Author), Hauschild, Axel (Author), Sattler, Elke (Author), Sondermann, Wiebke (Author), Haferkamp, Sebastian (Author), Schilling, Bastian (Author), Heppt, Markus V (Author), Jansen, Philipp (Author), Reinholz, Markus (Author), Franklin, Cindy (Author), Schmitt, Laurenz (Author), Hartmann, Daniela (Author), Krieghoff-Henning, Eva (Author), Schmitt, Max (Author), Weichenthal, Michael (Author), von Kalle, Christof (Author), Fröhling, Stefan (Author), Brinker, Titus J (Author)
• Formato: Livro
• Publicado em: JMIR Publications, 2020-09-01T00:00:00Z.
• Assuntos: article
• Acesso em linha: Connect to this object online.
• Notes: 1438-8871; 10.2196/18091
• Keywords: Computer applications to medicine. Medical informatics; R858-859.7; Public aspects of medicine; RA1-1270
• Source: Journal of Medical Internet Research, Vol 22, Iss 9, p e18091 (2020)

BackgroundEarly detection of melanoma can be lifesaving but this remains a challenge. Recent diagnostic studies have revealed the superiority of artificial intelligence (AI) in classifying dermoscopic images of melanoma and nevi, concluding that these algorithms should assist a dermatologist's diagnoses. ObjectiveThe aim of this study was to investigate whether AI support improves the accuracy and overall diagnostic performance of dermatologists in the dichotomous image-based discrimination between melanoma and nevus. MethodsTwelve board-certified dermatologists were presented disjoint sets of 100 unique dermoscopic images of melanomas and nevi (total of 1200 unique images), and they had to classify the images based on personal experience alone (part I) and with the support of a trained convolutional neural network (CNN, part II). Additionally, dermatologists were asked to rate their confidence in their final decision for each image. ResultsWhile the mean specificity of the dermatologists based on personal experience alone remained almost unchanged (70.6% vs 72.4%; P=.54) with AI support, the mean sensitivity and mean accuracy increased significantly (59.4% vs 74.6%; P=.003 and 65.0% vs 73.6%; P=.002, respectively) with AI support. Out of the 10% (10/94; 95% CI 8.4%-11.8%) of cases where dermatologists were correct and AI was incorrect, dermatologists on average changed to the incorrect answer for 39% (4/10; 95% CI 23.2%-55.6%) of cases. When dermatologists were incorrect and AI was correct (25/94, 27%; 95% CI 24.0%-30.1%), dermatologists changed their answers to the correct answer for 46% (11/25; 95% CI 33.1%-58.4%) of cases. Additionally, the dermatologists' average confidence in their decisions increased when the CNN confirmed their decision and decreased when the CNN disagreed, even when the dermatologists were correct. Reported values are based on the mean of all participants. Whenever absolute values are shown, the denominator and numerator are approximations as every dermatologist ended up rating a varying number of images due to a quality control step. ConclusionsThe findings of our study show that AI support can improve the overall accuracy of the dermatologists in the dichotomous image-based discrimination between melanoma and nevus. This supports the argument for AI-based tools to aid clinicians in skin lesion classification and provides a rationale for studies of such classifiers in real-life settings, wherein clinicians can integrate additional information such as patient age and medical history into their decisions.