Evaluation of an artificial intelligence-based decision support for the detection of cutaneous melanoma in primary care: a prospective real-life clinical trial.

BACKGROUND: Use of artificial intelligence (AI), or machine learning, to assess dermoscopic images of skin lesions to detect melanoma has, in several retrospective studies, shown high levels of diagnostic accuracy on par with - or even outperforming - experienced dermatologists. However, the enthusiasm around these algorithms has not yet been matched by prospective clinical trials performed in authentic clinical settings. In several European countries, including Sweden, the initial clinical assessment of suspected skin cancer is principally conducted in the primary healthcare setting by primary care physicians, with or without access to teledermoscopic support from dermatology clinics. OBJECTIVES: To determine the diagnostic performance of an AI-based clinical decision support tool for cutaneous melanoma detection, operated by a smartphone application (app), when used prospectively by primary care physicians to assess skin lesions of concern due to some degree of melanoma suspicion. METHODS: This prospective multicentre clinical trial was conducted at 36 primary care centres in Sweden. Physicians used the smartphone app on skin lesions of concern by photographing them dermoscopically, which resulted in a dichotomous decision support text regarding evidence for melanoma. Regardless of the app outcome, all lesions underwent standard diagnostic procedures (surgical excision or referral to a dermatologist). After investigations were complete, lesion diagnoses were collected from the patients' medical records and compared with the app's outcome and other lesion data. RESULTS: In total, 253 lesions of concern in 228 patients were included, of which 21 proved to be melanomas, with 11 thin invasive melanomas and 10 melanomas in situ. The app's accuracy in identifying melanomas was reflected in an area under the receiver operating characteristic (AUROC) curve of 0.960 [95% confidence interval (CI) 0.928-0.980], corresponding to a maximum sensitivity and specificity of 95.2% and 84.5%, respectively. For invasive melanomas alone, the AUROC was 0.988 (95% CI 0.965-0.997), corresponding to a maximum sensitivity and specificity of 100% and 92.6%, respectively. CONCLUSIONS: The clinical decision support tool evaluated in this investigation showed high diagnostic accuracy when used prospectively in primary care patients, which could add significant clinical value for primary care physicians assessing skin lesions for melanoma.

Use of methotrexate and risk of skin cancer: a nationwide case-control study.

BACKGROUND: Methotrexate (MTX) use has been suspected of increasing the risk of skin cancer. The aim of this investigation was to examine the association between the use of MTX and the risk of basal cell carcinoma (BCC), cutaneous squamous cell carcinoma (cSCC) and cutaneous malignant melanoma (CMM). METHODS: In a nationwide Danish case-control study, we identified incident, histologically verified cases of BCC (n = 131,447), cSCC (n = 18,661) or CMM (26,068) from 2004 to 2018. We matched 10 controls to each case on sex and birth year using risk-set sampling and computed crude and adjusted odds ratios (ORs) using conditional logistic regression for the use of MTX (≥2.5 g) compared with never-use. RESULTS: Use of MTX was associated with increased risk of BCC, cSCC and CMM with adjusted ORs of (95% confidence interval) 1.29 (1.20-1.38), 1.61 (1.37-1.89) and 1.35 (1.13-1.61), respectively. For BCC and cSCC, ORs increased with higher cumulative doses. When restricting the study population to patients with psoriasis, the ORs were 1.43 (1.23-1.67), 1.18 (0.80-1.74) and 1.15 (0.77-1.72), respectively. CONCLUSIONS: We observed an increased risk of BCC and cSCC associated with the use of MTX with evidence of a dose-response pattern; however, the association was not consistent when restricting the study population to patients with psoriasis.

Incidence and Prevalence of 73 Different Genodermatoses: A Nationwide Study in Sweden.

This retrospective registry-based cohort study aimed to estimate the incidence and prevalence of genodermatoses in the Swedish population and to analyse associated healthcare usage. Patients diagnosed with genodermatoses were identified from the patient registry of Sahlgrenska University Hospital (Gothenburg, Sweden) between 2016 and 2020. Clinical data from medical records were used to verify diagnoses recorded in the National Patient Registry (NPR). The NPR was then searched for International Classification of Diseases, Tenth Revision (ICD-10) codes Q80-82 and Q84 from 2001 to 2020. The local cohort included 298 patients with 36 unique genodermatosis diagnoses. Verification of these diagnoses in the NPR showed positive predictive values of over 90%. The NPR search yielded 13,318 patients with 73 unique diagnoses, including ichthyoses (n = 3,341; 25%), porokeratosis (n = 2,277; 17%), palmoplantar keratodermas (n = 1,754; 13%), the epidermolysis bullosa group (n = 1011; 7%); Darier disease (n = 770; 6%), Hailey-Hailey disease (n = 477; 4%) and Gorlin syndrome (n = 402; 3%). The incidence and prevalence of each diagnosis were calculated based on the nationwide cohort and are reported. A total of 149,538 outpatient visits were registered, a mean of 4.6 visits per patient. This study provides a valuable resource for the epidemiology of genodermatoses by reporting on the incidence and prevalence of 73 different genodermatoses.

Porokeratosis is one of the most common genodermatoses and is associated with an increased risk of keratinocyte cancer and melanoma.

BACKGROUND: Porokeratosis is a clinically heterogeneous group of keratinization disorders with a genetic background mainly affecting the mevalonate pathway, which is involved in the synthesis of cholesterol, an essential component for the formation of the extracellular lipid lamellae in the stratum corneum. Porokeratosis is reportedly associated with an increased risk of keratinocyte cancer, but to date, no large epidemiological studies have been conducted to further address this association. OBJECTIVES: The first objective was to characterize a cohort of patients diagnosed with porokeratosis at the Department of Dermatology and Venereology, Sahlgrenska University Hospital (SU), Gothenburg, Sweden. The second objective was to conduct a nationwide registry-based cohort study to investigate the association, if any, between porokeratosis and the cutaneous malignancies squamous cell carcinoma (SCC), basal cell carcinoma (BCC) and melanoma. METHODS: For the SU cohort, the hospital registry was searched for patients with a diagnosis of porokeratosis recorded between 2016 and 2020. Clinical data were extracted from the records of the identified patients. For the nationwide cohort, national registries were searched to identify patients with a diagnosis of porokeratosis between 2001 and 2020. A tenfold control cohort was formed by Statistics Sweden. The data was cross-referenced with the Swedish Cancer Register to study the associations between porokeratosis and SCC, BCC and melanoma. RESULTS: Disseminated superficial actinic porokeratosis was the most common clinical type among the 108 patients in the SU cohort. In the nationwide search, 2277 patients with porokeratosis were identified (prevalence 1/4132). Porokeratosis was associated with an increased risk for SCC, BCC and melanoma with hazard ratios (95% CI) of 4.3 (3.4-5.4), 2.42 (1.97-2.98) and 1.83 (1.18-2.82), respectively, in the patient cohort, compared to the matched control group. CONCLUSION: Porokeratosis is a common genodermatosis, and it is associated with an enhanced risk of skin cancer.

Ability to Predict Melanoma Within 5 Years Using Registry Data and a Convolutional Neural Network: A Proof of Concept Study.

Research relating to machine learning algorithms, including convolutional neural networks, has increased during the past 5 years. The aim of this pilot study was to investigate how accurately a convolutional neural network, trained on Swedish registry data, could perform in predicting cutaneous invasive and in situ melanoma (CMM) within 5 years. A cohort of 1,208,393 individuals was used. Registry data ranged from 4 July 2005 to 31 December 2011, predicting CMM between 1 January 2012 and 31 December 2016. A convolutional neural network with one-dimensional convolutions with respect to time was trained using healthcare databases and registers. The algorithm was trained on 23,886 individuals. Validation was performed on a holdout validation set including 6,000 individuals. After training and validation, the convolutional neural network was evaluated on a test set (1,000 individuals with an CMM occurring within 5 years and 5,000 without). The area under the receiver-operating characteristic curve was 0.59 (95% confidence interval (95% CI) 0.57-0.61). The point on the receiver-operating characteristic curve where sensitivity equalled specificity had a value of 56% (sensitivity 95% CI 53-60% and specificity 95% CI 55-58%). Albeit at an early stage, this pilot investigation demonstrates potential usefulness for machine learning algorithms in predicting melanoma risk.

Evaluation of Melanoma Thickness with Clinical Close-up and Dermoscopic Images Using a Convolutional Neural Network.

Convolutional neural networks (CNNs) have shown promise in discriminating between invasive and in situ melanomas. The aim of this study was to analyse how a CNN model, integrating both clinical close-up and dermoscopic images, performed compared with 6 independent dermatologists. The secondary aim was to address which clinical and dermoscopic features dermatologists found to be suggestive of invasive and in situ melanomas, respectively. A retrospective investigation was conducted including 1,578 cases of paired images of invasive (n = 728, 46.1%) and in situ melanomas (n = 850, 53.9%). All images were obtained from the Department of Dermatology and Venereology at Sahlgrenska University Hospital and were randomized to a training set (n = 1,078), a validation set (n = 200) and a test set (n = 300). The area under the receiver operating characteristics curve (AUC) among the dermatologists ranged from 0.75 (95% confidence interval 0.70-0.81) to 0.80 (95% confidence interval 0.75-0.85). The combined dermatologists' AUC was 0.80 (95% confidence interval 0.77-0.86), which was significantly higher than the CNN model (0.73, 95% confidence interval 0.67-0.78, p = 0.001). Three of the dermatologists significantly outperformed the CNN. Shiny white lines, atypical blue-white structures and polymorphous vessels displayed a moderate interobserver agreement, and these features also correlated with invasive melanoma. Prospective trials are needed to address the clinical usefulness of CNN models in this setting.

Hyperspectral Imaging for Non-invasive Diagnostics of Melanocytic Lesions.

Malignant melanoma poses a clinical diagnostic problem, since a large number of benign lesions are excised to find a single melanoma. This study assessed the accuracy of a novel non-invasive diagnostic technology, hyperspectral imaging, for melanoma detection. Lesions were imaged prior to excision and histopathological analysis. A deep neural network algorithm was trained twice to distinguish between histopathologically verified malignant and benign melanocytic lesions and to classify the separate subgroups. Furthermore, 2 different approaches were used: a majority vote classification and a pixel-wise classification. The study included 325 lesions from 285 patients. Of these, 74 were invasive melanoma, 88 melanoma in situ, 115 dysplastic naevi, and 48 non-dysplastic naevi. The study included a training set of 358,800 pixels and a validation set of 7,313 pixels, which was then tested with a training set of 24,375 pixels. The majority vote classification achieved high overall sensitivity of 95% and a specificity of 92% (95% confidence interval (95% CI) 0.024-0.029) in differentiating malignant from benign lesions. In the pixel-wise classification, the overall sensitivity and specificity were both 82% (95% CI 0.005-0.005). When divided into 4 subgroups, the diagnostic accuracy was lower. Hyperspectral imaging provides high sensitivity and specificity in distinguishing between naevi and melanoma. This novel method still needs further validation.

Frequency of Publication of Dermoscopic Images in Inter-observer Studies: A Systematic Review.

Research interest in dermoscopy is increasing, but the complete dermoscopic image sets used in inter-observer studies of skin tumours are not often shared in research publications. The aim of this systematic review was to analyse what proportion of images depicting skin tumours are published in studies investigating inter-observer variations in the assessment of dermoscopic features and/or patterns. Embase, MEDLINE and Scopus databases were screened for eligible studies published from inception to 2 July 2020. For included studies the proportion of lesion images presented in the papers and/or supplements was extracted. A total of 61 studies (53 original studies and 8 shorter reports (i.e. research letters or concise reports)). published in the period 1997 to 2020 were included. These studies combined included 14,124 skin tumours, of which 373 (3%) images were published. This systematic review highlights that the vast majority of images included in dermoscopy research are not published. Data sharing should be a requirement for future studies, and must be enabled and standardized by the dermatology research community and editorial offices.

Impact of Etanercept on Vitamin D Status and Vitamin D-binding Protein in Bio-naïve Patients with Psoriasis.

High levels of serum vitamin D-binding protein have been shown previously in patients with psoriasis compared with healthy controls; a possible role in inflammation is implied. The primary objective of this study was to investigate the impact of 24-week etanercept treatment on vitamin D status and vitamin D-binding protein in patients with psoriasis. The secondary aim was to explore whether pre-treatment vitamin D levels could predict the treatment effect. A prospective observational study was performed, including 20 patients with psoriasis and 15 controls. Serum samples were analyzed for, among others, vitamin D metabolites, vitamin D-binding protein and highly sensitive C-reactive protein. Baseline levels of vitamin D-binding protein were higher in patients with self-reported arthropathy than in those without. After 24 weeks' treatment, an improvement in psoriasis was noted, as was a decrease in highly sensitive C-reactive protein. Vitamin D-binding protein decreased in those with self-reported arthropathy. Higher baseline levels of vitamin D were associated with faster and greater improvement in psoriasis. Vitamin D-binding protein may have an inflammatory biomarker role.

Methotrexate Use for Patients with Psoriasis and Risk of Cutaneous Squamous Cell Carcinoma: A Nested Case-control Study.

An association between methotrexate use and risk of cutaneous squamous cell carcinoma has been reported in patients with rheumatoid and psoriatic arthritis. A nested case-control study was performed to investigate if methotrexate use among patients with psoriasis was associated with increased risk of cutaneous squamous cell carcinoma. Data were obtained from Swedish registers and included 623 patients with psoriasis and a first cutaneous squamous cell carcinoma from 2010 to 2016. Ten randomly selected patients with psoriasis were matched on age and sex to each case. Among cases, 160 (26%) were ever-users of metho-trexate. The corresponding number among the controls was 1,370 (22%), yielding an unadjusted odds ratio (OR) of 1.23 (95% confidence interval (95% CI) 1.02-1.49); p = 0.034. After adjusting for use of other immunosuppressive drugs the association was close to unity (OR 1.09; 95% CI 0.89-1.34); p = 0.39. The slightly increased risk of cutaneous squamous cell carcinoma associated with methotrexate-exposure in patients with psoriasis does not seem to be associated with metho-trexate, but rather with disease severity, other anti-psoriatic treatments, and ultraviolet exposure.

Interobserver Agreement on Dermoscopic Features and their Associations with In Situ and Invasive Cutaneous Melanomas.

Several melanoma-specific dermoscopic features have been described, some of which have been reported as indicative of in situ or invasive melanomas. To assess the usefulness of these features to differentiate between these 2 categories, a retrospective, single-centre investigation was conducted. Dermoscopic images of melanomas were reviewed by 7 independent dermatologists. Fleiss' kappa (κ) was used to analyse interobserver agreement of predefined features. Logistic regression and odds ratios were used to assess whether specific features correlated with melanoma in situ or invasive melanoma. Overall, 182 melanomas (101 melanoma in situ and 81 invasive melanomas) were included. The interobserver agreement for melanoma-specific features ranged from slight to substantial. Atypical blue-white structures (κ=0.62, 95% confidence interval 0.59-0.65) and shiny white lines (κ=0.61, 95% confidence interval 0.58-0.64) had a substantial interobserver agreement. These 2 features were also indicative of invasive melanomas >1.0 mm in Breslow thickness. Furthermore, regression/peppering correlated with thin invasive melanomas. The overall agreement for classification of the lesions as invasive or melanoma in situ was moderate (κ=0.52, 95% confidence interval 0.49-0.56).

Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis.

Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the consumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application (Skin Image Search™) for recognition of skin diseases. Clinical images including tumours, infective and inflammatory skin diseases were collected at the Department of Dermatology at the Sahlgrenska University Hospital and uploaded for classification by the online application. The AI algorithm classified the images giving 5 differential diagnoses, which were then compared to the diagnoses made clinically by the dermatologists and/or histologically. We included 521 images portraying 26 diagnoses. The diagnostic accuracy was 56.4% for the top 5 suggested diagnoses and 22.8% when only considering the most probable diagnosis. The level of diagnostic accuracy varied considerably for diagnostic groups. The online application demonstrated low diagnostic accuracy compared to a dermatologist evaluation and needs further development.

Methotrexate Exposure and Risk of Cutaneous Malignant Melanoma: No Evidence of a Dose-response Relationship.

Methotrexate treatment has been linked with an increased risk of melanoma. However, a possible dose-response relationship with respect to methotrexate exposure and melanoma has not been addressed. The aim of the present study was to investigate whether higher accumulated doses of methotrexate correlate with an increased risk of melanoma, which would further support a possible association. A nationwide retrospective cohort study was conducted. All Swedish patients over 18 years of age who were dispensed methotrexate in the period 2005 to 2014 were registered (n = 101,966) and matched to the cancer registry. A Cox proportional hazards model, testing risk of melanoma vs. total accumulated methotrexate dose, controlled for sex, age group, and time from first to last dispensed prescription of methotrexate, yielded no significant risk dependence on dose, and a hazard ratio of 1.02 (95% CI 0.97-1.08). Overall, no conclusive dose-response relationship was observed between methotrexate exposure and risk of melanoma.