Federated Learning for Decentralized Artificial Intelligence in Melanoma Diagnostics.

Importance: The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals. Objective: To investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics. Design, Setting, and Participants: This multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023. Exposures: All whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care. Main Outcomes and Measures: The area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity. Results: The study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479). Conclusions and Relevance: The findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond.

Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma.

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.

Interleukin 17 signaling supports clinical benefit of dual CTLA-4 and PD-1 checkpoint inhibition in melanoma.

Recent studies suggest that BRAFV600-mutated melanomas in particular respond to dual anti-programmed cell death protein 1 (PD-1) and anti-cytotoxic T lymphocyte-associated protein 4 (CTLA-4) immune checkpoint inhibition (ICI). Here we identified an over-representation of interleukin (IL)-17-type 17 helper T (TH17) gene expression signatures (GES) in BRAFV600-mutated tumors. Moreover, high baseline IL-17 GES consistently predicted clinical responses in dual-ICI-treated patient cohorts but not in mono anti-CTLA-4 or anti-PD-1 ICI cohorts. High IL-17 GES corresponded to tumor infiltration with T cells and neutrophils. Accordingly, high neutrophil infiltration correlated with clinical response specifically to dual ICI, and tumor-associated neutrophils also showed strong IL-17-TH17 pathway activity and T cell activation capacity. Both the blockade of IL-17A and the depletion of neutrophils impaired dual-ICI response and decreased T cell activation. Finally, high IL-17A levels in the blood of patients with melanoma indicated a higher global TH17 cytokine profile preceding clinical response to dual ICI but not to anti-PD-1 monotherapy, suggesting a future role as a biomarker for patient stratification.

COVID-19 vaccination in psoriasis patients receiving systemic treatment: A prospective single-center study.

Background: The rate of seroconversion after COVID-19 vaccination in patients with moderate to severe psoriasis requiring systemic treatment is poorly understood. Objectives: The aim of this prospective single-center cohort study performed between May 2020 and October 2021 was to determine the rate of seroconversion after COVID-19 vaccination in patients under active systemic treatment for moderate to severe psoriasis. Methods: Inclusion criteria were systemic treatment for moderate to severe psoriasis, known COVID-19 vaccination status, and repetitive anti-SARS-CoV-2-S IgG serum quantification. The primary outcome was the rate of anti-SARS-CoV-2-S IgG seroconversion after complete COVID-19 vaccination. Results: 77 patients with a median age of 55.9 years undergoing systemic treatment for moderate to severe psoriasis were included. The majority of patients received interleukin- (n=50, 64.9%) or tumor necrosis factor (TNF)-α inhibitors (n=16, 20.8%) as systemic treatment for psoriasis; nine patients (11.7%) were treated with methotrexate (MTX) monotherapy, and one patient each received dimethyl fumarate (1.3%), respectively apremilast (1.3%). All included patients completed COVID-19 vaccination with two doses over the course of the study. Serum testing revealed that 74 patients (96.1%) showed an anti-SARS-CoV-2-S IgG seroconversion. While all patients on IL-17A, -12 or -12/23 inhibitors (n=50) achieved seroconversion, three of 16 patients (18.8%) receiving MTX and/or a TNF-α inhibitor as main anti-psoriatic treatment did not. At follow-up, none of the patients had developed symptomatic COVID-19 or died from COVID-19. Conclusions: Anti-SARS-CoV-2-S IgG seroconversion rates following COVID-19 vaccination in psoriasis patients under systemic treatment were high. An impaired serological response, however, was observed in patients receiving MTX and/or TNF-α inhibitors, in particular infliximab.

COVID-19 vaccination in advanced skin cancer patients receiving systemic anticancer treatment: A prospective singlecenter study investigating seroconversion rates.

Background: COVID-19 vaccination reduces risk of SARS-CoV-2 infection, COVID-19 severity and death. However, the rate of seroconversion after COVID-19 vaccination in cancer patients requiring systemic anticancer treatment is poorly investigated. The aim of the present study was to determine the rate of seroconversion after COVID-19 vaccination in advanced skin cancer patients under active systemic anticancer treatment. Methods: This prospective single-center study of a consecutive sample of advanced skin cancer patients was performed from May 2020 until October 2021. Inclusion criteria were systemic treatment for advanced skin cancer, known COVID-19 vaccination status, repetitive anti-SARS-CoV-2-S IgG serum quantification and first and second COVID-19 vaccination. Primary outcome was the rate of anti-SARS-CoV-2-S IgG seroconversion after complete COVID-19 vaccination. Results: Of 60 patients with advanced skin cancers, 52 patients (86.7%) received immune checkpoint inhibition (ICI), seven (11.7%) targeted agents (TT), one (1.7%) chemotherapy. Median follow-up time was 12.7 months. During study progress ten patients had died from skin cancer prior to vaccination completion, six patients were lost to follow-up and three patients had refused vaccination. 41 patients completed COVID-19 vaccination with two doses and known serological status. Of those, serum testing revealed n=3 patients (7.3%) as anti-SARS-CoV-2-S IgG positive prior to vaccination, n=32 patients (78.0%) showed a seroconversion, n=6 patients (14.6%) did not achieve a seroconversion. Patients failing serological response were immunocompromised due to concomitant hematological malignancy, previous chemotherapy or autoimmune disease requiring immunosuppressive comedications. Immunosuppressive comedication due to severe adverse events of ICI therapy did not impair seroconversion following COVID-19 vaccination. Of 41 completely vaccinated patients, 35 (85.4%) were under treatment with ICI, five (12.2%) with TT, and one (2.4%) with chemotherapy. 27 patients (65.9%) were treated non adjuvantly. Of these patients, 13 patients had achieved objective response (complete/partial response) as best tumor response (48.2%). Conclusion and relevance: Rate of anti-SARS-CoV-2-S IgG seroconversion in advanced skin cancer patients under systemic anticancer treatment after complete COVID-19 vaccination is comparable to other cancer entities. An impaired serological response was observed in patients who were immunocompromised due to concomitant diseases or previous chemotherapies. Immunosuppressive comedication due to severe adverse events of ICI did not impair the serological response to COVID-19 vaccination.

Model soups improve performance of dermoscopic skin cancer classifiers.

BACKGROUND: Image-based cancer classifiers suffer from a variety of problems which negatively affect their performance. For example, variation in image brightness or different cameras can already suffice to diminish performance. Ensemble solutions, where multiple model predictions are combined into one, can improve these problems. However, ensembles are computationally intensive and less transparent to practitioners than single model solutions. Constructing model soups, by averaging the weights of multiple models into a single model, could circumvent these limitations while still improving performance. OBJECTIVE: To investigate the performance of model soups for a dermoscopic melanoma-nevus skin cancer classification task with respect to (1) generalisation to images from other clinics, (2) robustness against small image changes and (3) calibration such that the confidences correspond closely to the actual predictive uncertainties. METHODS: We construct model soups by fine-tuning pre-trained models on seven different image resolutions and subsequently averaging their weights. Performance is evaluated on a multi-source dataset including holdout and external components. RESULTS: We find that model soups improve generalisation and calibration on the external component while maintaining performance on the holdout component. For robustness, we observe performance improvements for pertubated test images, while the performance on corrupted test images remains on par. CONCLUSIONS: Overall, souping for skin cancer classifiers has a positive effect on generalisation, robustness and calibration. It is easy for practitioners to implement and by combining multiple models into a single model, complexity is reduced. This could be an important factor in achieving clinical applicability, as less complexity generally means more transparency.

High Tolerability, Favorable Safety, and Subjects' Preference for a Single 200 mg/2 mL Tildrakizumab Injection: A Phase I, Open-Label, Randomized Crossover Trial in Healthy Volunteers.

INTRODUCTION: Tildrakizumab 200 mg/2 mL pre-filled syringe is a new preparation of tildrakizumab that is developed to facilitate patients' compliance. This phase I clinical trial compares the local tolerability, safety, and subjects' preferred method of administration of tildrakizumab when administered as a new single 200 mg/2 mL subcutaneous injection or as two 100 mg/1 mL subcutaneous injections in healthy subjects. METHODS: Visual analogue scores were used to self-assess injection site pain immediately (< 1 min) after each administration and at 1 h and 48 h after each administration. Treatment injection site reactions were assessed at 1 h and 48 h after each administration. Treatment safety was monitored throughout the study period. Subjects' preferred method of administration was assessed 4 weeks after the last administration (day 56). RESULTS: No statistically significant difference in visual analogue scores and injection site reactions was detected between the two treatments. Treatment-emergent adverse events were mild, and there were no deaths or serious adverse events. Most subjects (61.5%) preferred the treatment when administered as a single 200 mg/2 mL subcutaneous injection rather than as two 100 mg/mL subcutaneous injections. CONCLUSIONS: Administration of 200 mg tildrakizumab as a single 2 mL subcutaneous injection was safe, well tolerated, and preferred over two separate 100 mg/1 mL subcutaneous injections by healthy subjects. Eudract No. 2020-000183-37.

Explainable artificial intelligence in skin cancer recognition: A systematic review.

BACKGROUND: Due to their ability to solve complex problems, deep neural networks (DNNs) are becoming increasingly popular in medical applications. However, decision-making by such algorithms is essentially a black-box process that renders it difficult for physicians to judge whether the decisions are reliable. The use of explainable artificial intelligence (XAI) is often suggested as a solution to this problem. We investigate how XAI is used for skin cancer detection: how is it used during the development of new DNNs? What kinds of visualisations are commonly used? Are there systematic evaluations of XAI with dermatologists or dermatopathologists? METHODS: Google Scholar, PubMed, IEEE Explore, Science Direct and Scopus were searched for peer-reviewed studies published between January 2017 and October 2021 applying XAI to dermatological images: the search terms histopathological image, whole-slide image, clinical image, dermoscopic image, skin, dermatology, explainable, interpretable and XAI were used in various combinations. Only studies concerned with skin cancer were included. RESULTS: 37 publications fulfilled our inclusion criteria. Most studies (19/37) simply applied existing XAI methods to their classifier to interpret its decision-making. Some studies (4/37) proposed new XAI methods or improved upon existing techniques. 14/37 studies addressed specific questions such as bias detection and impact of XAI on man-machine-interactions. However, only three of them evaluated the performance and confidence of humans using CAD systems with XAI. CONCLUSION: XAI is commonly applied during the development of DNNs for skin cancer detection. However, a systematic and rigorous evaluation of its usefulness in this scenario is lacking.

A benchmark for neural network robustness in skin cancer classification.

BACKGROUND: One prominent application for deep learning-based classifiers is skin cancer classification on dermoscopic images. However, classifier evaluation is often limited to holdout data which can mask common shortcomings such as susceptibility to confounding factors. To increase clinical applicability, it is necessary to thoroughly evaluate such classifiers on out-of-distribution (OOD) data. OBJECTIVE: The objective of the study was to establish a dermoscopic skin cancer benchmark in which classifier robustness to OOD data can be measured. METHODS: Using a proprietary dermoscopic image database and a set of image transformations, we create an OOD robustness benchmark and evaluate the robustness of four different convolutional neural network (CNN) architectures on it. RESULTS: The benchmark contains three data sets-Skin Archive Munich (SAM), SAM-corrupted (SAM-C) and SAM-perturbed (SAM-P)-and is publicly available for download. To maintain the benchmark's OOD status, ground truth labels are not provided and test results should be sent to us for assessment. The SAM data set contains 319 unmodified and biopsy-verified dermoscopic melanoma (n = 194) and nevus (n = 125) images. SAM-C and SAM-P contain images from SAM which were artificially modified to test a classifier against low-quality inputs and to measure its prediction stability over small image changes, respectively. All four CNNs showed susceptibility to corruptions and perturbations. CONCLUSIONS: This benchmark provides three data sets which allow for OOD testing of binary skin cancer classifiers. Our classifier performance confirms the shortcomings of CNNs and provides a frame of reference. Altogether, this benchmark should facilitate a more thorough evaluation process and thereby enable the development of more robust skin cancer classifiers.

Multispectral optoacoustic tomography might be a helpful tool for noninvasive early diagnosis of psoriatic arthritis.

Currently used imaging methods for diagnosis of psoriatic arthritis (PsA) frequently come along with exposure to radiation and can often only show long-term effects of the disease. The aim of the study was to check the feasibility of a new optoacoustic imaging method to identify PsA. 22 psoriasis patients and 19 healthy volunteers underwent examination using multispectral optoacoustic tomography (MSOT). The presence of arthritis was assessed via quantification of optoacoustic signal intensity of the endogenous chromophores oxy- and deoxyhemoglobin. We conducted high-resolution real-time ultrasound images of the finger joints. The semi quantitative analysis of the optoacoustic signals for both hemoglobin species showed a significant higher blood content and oxygenation in PsA patients compared to healthy controls. Our results indicate that MSOT might allow detection of inflammation in an early stage. If the data is further confirmed, this technique might be a suitable tool to avoid delay of diagnosis of PsA.

Integrating Patient Data Into Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review.

BACKGROUND: Recent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par with or better than dermatologists with respect to the classification tasks of single images. However, in clinical practice, dermatologists also use other patient data beyond the visual aspects present in a digitized image, further increasing their diagnostic accuracy. Several pilot studies have recently investigated the effects of integrating different subtypes of patient data into CNN-based skin cancer classifiers. OBJECTIVE: This systematic review focuses on the current research investigating the impact of merging information from image features and patient data on the performance of CNN-based skin cancer image classification. This study aims to explore the potential in this field of research by evaluating the types of patient data used, the ways in which the nonimage data are encoded and merged with the image features, and the impact of the integration on the classifier performance. METHODS: Google Scholar, PubMed, MEDLINE, and ScienceDirect were screened for peer-reviewed studies published in English that dealt with the integration of patient data within a CNN-based skin cancer classification. The search terms skin cancer classification, convolutional neural network(s), deep learning, lesions, melanoma, metadata, clinical information, and patient data were combined. RESULTS: A total of 11 publications fulfilled the inclusion criteria. All of them reported an overall improvement in different skin lesion classification tasks with patient data integration. The most commonly used patient data were age, sex, and lesion location. The patient data were mostly one-hot encoded. There were differences in the complexity that the encoded patient data were processed with regarding deep learning methods before and after fusing them with the image features for a combined classifier. CONCLUSIONS: This study indicates the potential benefits of integrating patient data into CNN-based diagnostic algorithms. However, how exactly the individual patient data enhance classification performance, especially in the case of multiclass classification problems, is still unclear. Moreover, a substantial fraction of patient data used by dermatologists remains to be analyzed in the context of CNN-based skin cancer classification. Further exploratory analyses in this promising field may optimize patient data integration into CNN-based skin cancer diagnostics for patients' benefits.

Skin Reactions in Patients With Multiple Sclerosis Receiving Cladribine Treatment.

OBJECTIVE: To report 77 patients with multiple sclerosis (MS) who developed skin-related adverse events (AEs) following treatment with cladribine. METHODS: We evaluated our prospective bicentric cladribine cohort. Cladribine-treated patients with a skin AE were identified. RESULTS: Two hundred thirty-nine cladribine-treated patients with MS were evaluated. Seventy-seven patients (32%) showed at least 1 skin AE at median 1 month after cladribine initiation (range: 1-12). Within first 3 months following last cladribine exposition, hair thinning (n = 28, 12%), skin rash (n = 20; 8%), mucositis (n = 13, 5%), and pruritus (n = 6, 3%) were observed. Furthermore, 35 patients (15%) developed herpes virus infections (time since last cladribine exposition: median 83 [range: 10-305]). In 15 patients, herpes zoster infection was severe (CTCAE grade ≥ 3) and required hospitalization. Delayed skin AEs (≥3 months after a cladribine treatment cycle) involved 1 case of leukocytoclastic vasculitis and 2 cases of alopecia areata. Finally, 2 patients presented with in total 3 isolated precancerous lesions (1 leukoplakia simplex and 2 actinic keratosis) and 1 patient developed a squamous cell carcinoma. CONCLUSION: Skin AEs are common in patients with MS treated with cladribine. Until risk management plans have been adjusted to include these phenomena, clinicians should perform a thorough clinical follow-up and in suspicious cases seek early interdisciplinary support. In light of the observed delayed skin reactions, we further emphasize the necessity of careful clinical surveillance of cladribine-treated patients for yet undescribed secondary autoimmune events. CLASSIFICATION OF EVIDENCE: This study provides Class IV evidence that skin-related AEs are frequent in patients with MS following cladribine in a real-world setting.

Combining CNN-based histologic whole slide image analysis and patient data to improve skin cancer classification.

BACKGROUND: Clinicians and pathologists traditionally use patient data in addition to clinical examination to support their diagnoses. OBJECTIVES: We investigated whether a combination of histologic whole slides image (WSI) analysis based on convolutional neural networks (CNNs) and commonly available patient data (age, sex and anatomical site of the lesion) in a binary melanoma/nevus classification task could increase the performance compared with CNNs alone. METHODS: We used 431 WSIs from two different laboratories and analysed the performance of classifiers that used the image or patient data individually or three common fusion techniques. Furthermore, we tested a naive combination of patient data and an image classifier: for cases interpreted as 'uncertain' (CNN output score <0.7), the decision of the CNN was replaced by the decision of the patient data classifier. RESULTS: The CNN on its own achieved the best performance (mean ± standard deviation of five individual runs) with AUROC of 92.30% ± 0.23% and balanced accuracy of 83.17% ± 0.38%. While the classification performance was not significantly improved in general by any of the tested fusions, naive strategy of replacing the image classifier with the patient data classifier on slides with low output scores improved balanced accuracy to 86.72% ± 0.36%. CONCLUSION: In most cases, the CNN on its own was so accurate that patient data integration did not provide any benefit. However, incorporating patient data for lesions that were classified by the CNN with low 'confidence' improved balanced accuracy.

Robustness of convolutional neural networks in recognition of pigmented skin lesions.

BACKGROUND: A basic requirement for artificial intelligence (AI)-based image analysis systems, which are to be integrated into clinical practice, is a high robustness. Minor changes in how those images are acquired, for example, during routine skin cancer screening, should not change the diagnosis of such assistance systems. OBJECTIVE: To quantify to what extent minor image perturbations affect the convolutional neural network (CNN)-mediated skin lesion classification and to evaluate three possible solutions for this problem (additional data augmentation, test-time augmentation, anti-aliasing). METHODS: We trained three commonly used CNN architectures to differentiate between dermoscopic melanoma and nevus images. Subsequently, their performance and susceptibility to minor changes ('brittleness') was tested on two distinct test sets with multiple images per lesion. For the first set, image changes, such as rotations or zooms, were generated artificially. The second set contained natural changes that stemmed from multiple photographs taken of the same lesions. RESULTS: All architectures exhibited brittleness on the artificial and natural test set. The three reviewed methods were able to decrease brittleness to varying degrees while still maintaining performance. The observed improvement was greater for the artificial than for the natural test set, where enhancements were minor. CONCLUSIONS: Minor image changes, relatively inconspicuous for humans, can have an effect on the robustness of CNNs differentiating skin lesions. By the methods tested here, this effect can be reduced, but not fully eliminated. Thus, further research to sustain the performance of AI classifiers is needed to facilitate the translation of such systems into the clinic.

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

BACKGROUND: Early 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. OBJECTIVE: The 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. METHODS: Twelve 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. RESULTS: While 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. CONCLUSIONS: The 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.

Artificial Intelligence in Skin Cancer Diagnostics: The Patients' Perspective.

Background: Artificial intelligence (AI) has shown promise in numerous experimental studies, particularly in skin cancer diagnostics. Translation of these findings into the clinic is the logical next step. This translation can only be successful if patients' concerns and questions are addressed suitably. We therefore conducted a survey to evaluate the patients' view of artificial intelligence in melanoma diagnostics in Germany, with a particular focus on patients with a history of melanoma. Participants and Methods: A web-based questionnaire was designed using LimeSurvey, sent by e-mail to university hospitals and melanoma support groups and advertised on social media. The anonymous questionnaire evaluated patients' expectations and concerns toward artificial intelligence in general as well as their attitudes toward different application scenarios. Descriptive analysis was performed with expression of categorical variables as percentages and 95% confidence intervals. Statistical tests were performed to investigate associations between sociodemographic data and selected items of the questionnaire. Results: 298 individuals (154 with a melanoma diagnosis, 143 without) responded to the questionnaire. About 94% [95% CI = 0.91-0.97] of respondents supported the use of artificial intelligence in medical approaches. 88% [95% CI = 0.85-0.92] would even make their own health data anonymously available for the further development of AI-based applications in medicine. Only 41% [95% CI = 0.35-0.46] of respondents were amenable to the use of artificial intelligence as stand-alone system, 94% [95% CI = 0.92-0.97] to its use as assistance system for physicians. In sub-group analyses, only minor differences were detectable. Respondents with a previous history of melanoma were more amenable to the use of AI applications for early detection even at home. They would prefer an application scenario where physician and AI classify the lesions independently. With respect to AI-based applications in medicine, patients were concerned about insufficient data protection, impersonality and susceptibility to errors, but expected faster, more precise and unbiased diagnostics, less diagnostic errors and support for physicians. Conclusions: The vast majority of participants exhibited a positive attitude toward the use of artificial intelligence in melanoma diagnostics, especially as an assistance system.