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.

Non-biologic immunosuppressive drugs for inflammatory and autoimmune skin diseases.

Non-biologic immunosuppressive drugs, such as azathioprine, dapsone or methotrexate are fundamental treatment options for a wide range of autoimmune and chronic inflammatory skin diseases. Some of these drugs were initially used for malignancies (e.g., azathioprine or methotrexate) or infectious diseases (e.g., hydroxychloroquine or dapsone) but are nowadays mostly used for their immunosuppressive/immunomodulating action. Although dermatologists have years of clinical experience with these drugs, some of the mechanisms of action are not fully understood and are the subject of research. Although these drugs are commonly used, lack of experience or knowledge regarding their safety profiles and management leads to skepticism among physicians. Here, we summarize the mechanism of action and detailed management of adverse effects of the most commonly used immunosuppressive drugs for skin diseases. Furthermore, we discuss the management of these drugs during pregnancy and breastfeeding, as well as their interaction and handling during vaccination.

Acidosis-mediated increase in IFN-γ-induced PD-L1 expression on cancer cells as an immune escape mechanism in solid tumors.

Immune checkpoint inhibitors have revolutionized cancer therapy, yet the efficacy of these treatments is often limited by the heterogeneous and hypoxic tumor microenvironment (TME) of solid tumors. In the TME, programmed death-ligand 1 (PD-L1) expression on cancer cells is mainly regulated by Interferon-gamma (IFN-γ), which induces T cell exhaustion and enables tumor immune evasion. In this study, we demonstrate that acidosis, a common characteristic of solid tumors, significantly increases IFN-γ-induced PD-L1 expression on aggressive cancer cells, thus promoting immune escape. Using preclinical models, we found that acidosis enhances the genomic expression and phosphorylation of signal transducer and activator of transcription 1 (STAT1), and the translation of STAT1 mRNA by eukaryotic initiation factor 4F (elF4F), resulting in an increased PD-L1 expression. We observed this effect in murine and human anti-PD-L1-responsive tumor cell lines, but not in anti-PD-L1-nonresponsive tumor cell lines. In vivo studies fully validated our in vitro findings and revealed that neutralizing the acidic extracellular tumor pH by sodium bicarbonate treatment suppresses IFN-γ-induced PD-L1 expression and promotes immune cell infiltration in responsive tumors and thus reduces tumor growth. However, this effect was not observed in anti-PD-L1-nonresponsive tumors. In vivo experiments in tumor-bearing IFN-γ-/- mice validated the dependency on immune cell-derived IFN-γ for acidosis-mediated cancer cell PD-L1 induction and tumor immune escape. Thus, acidosis and IFN-γ-induced elevation of PD-L1 expression on cancer cells represent a previously unknown immune escape mechanism that may serve as a novel biomarker for anti-PD-L1/PD-1 treatment response. These findings have important implications for the development of new strategies to enhance the efficacy of immunotherapy in cancer patients.

Neutrophilic granulocyte-derived B-cell activating factor supports B cells in skin lesions in hidradenitis suppurativa.

BACKGROUND: Hidradenitis suppurativa (HS) is a chronic inflammatory disease characterized by painful inflamed nodules, abscesses, and pus-draining tunnels appearing in axillary, inguinal, and perianal skin areas. HS lesions contain various types of immigrated immune cells. OBJECTIVE: This study aimed to characterize mediators that support lesional B/plasma cell persistence in HS. METHODS: Skin samples from several cohorts of HS patients and control cohorts were assessed by mRNA sequencing, quantitative PCR on reverse-transcribed RNA, flow cytometry, and immunohistofluorescence. Blood plasma and cultured skin biopsy samples, keratinocytes, dermal fibroblasts, neutrophilic granulocytes (neutrophils), monocytes, and B cells were analyzed. Complex systems biology approaches were used to evaluate bulk and single-cell RNA sequencing data. RESULTS: Proportions of B/plasma cells, neutrophils, CD8+ T cells, and M0 and M1 macrophages were elevated in HS lesions compared to skin of healthy and perilesional intertriginous areas. There was an association between B/plasma cells, neutrophils, and B-cell activating factor (BAFF, aka TNFSF13B). BAFF was abundant in HS lesions, particularly in nodules and abscesses. Among the cell types present in HS lesions, myeloid cells were the main BAFF producers. Mechanistically, granulocyte colony-stimulating factor in the presence of bacterial products was the major stimulus for neutrophils' BAFF secretion. Lesional upregulation of BAFF receptors was attributed to B cells (TNFRSF13C/BAFFR and TNFRSF13B/TACI) and plasma cells (TNFRSF17/BCMA). Characterization of the lesional BAFF pathway revealed molecules involved in migration/adhesion (eg, CXCR4, CD37, CD53, SELL), proliferation/survival (eg, BST2), activation (eg, KLF2, PRKCB), and reactive oxygen species production (eg, NCF1, CYBC1) of B/plasma cells. CONCLUSION: Neutrophil-derived BAFF supports B/plasma cell persistence and function in HS lesions.

Treatment of the Candida subspecies Candida albicans and Candida parapsilosis with two far-UVC sources to minimise mycoses in clinical practice.

Fungal infections have increased considerably over the last decades, becoming progressively resistant to common drugs. UVC light has shown microbiological eradication effects, whereby the wavelength of 254 nm is strongly carcino- and mutagenic. Therefore, 222 and 233 nm, which do not significantly harm skin cells, were tested for their antifungal effects. Microbicidal doses were reached at 40 mJ/cm2 for both wavelengths, resulting in only minor superficial skin damage (<20 µm). UVC irradiation with far-UVC <240 nm represents a new opportunity to effectively eradicate even larger pathogens on tissue causing no or strongly reduced DNA and tissue damage.

Sex-disaggregated population analysis in patients with hidradenitis suppurativa.

Background: Hidradenitis suppurativa (HS) is a common chronic inflammatory skin disease, which affects both sexes. Objectives: Identification of sex-specific risk factors, comorbidity, clinical manifestations, and treatments in HS patients. Methods: A non-interventional, cross-sectional, mono-centric study with 500 HS patients. All patients were examined by dermatologists. Prospectively collected demographic, anamnestic, clinical data, and blood parameters were evaluated. Results: There were no significant differences in age at HS onset and in disease duration between female and male patients. Furthermore, no differences regarding the family history for HS were found between sexes. Regarding further risk factors for HS, central obesity was more frequent in women while extensive cigarette smoking and acne vulgaris were more commonly found among male patients. Regarding comorbidity, lower HDL-levels were significantly more frequent in men. Female patients were found to suffer significantly more often from back pain, especially in the neck/shoulder region and lower back. Analyzing the clinical manifestation of HS, the groin was more frequently involved in women and the axillae in men. Women showed a higher number of skin sites with inflammatory nodules, whereas fistulas were observed more frequently in men. Nevertheless, there was no difference in HS treatment applied to female vs. male patients. Limitations: Data were obtained from a mono-centric study. Conclusion: Significant differences in HS risk factors, comorbidity, and clinical manifestation exist between female and male patients. Thus, sex-specific differences should be taken into account in the prevention as well as medical and surgical treatment of HS patients.

Detection of rare autoreactive T cell subsets in patients with pemphigus vulgaris.

Analysis of T lymphocyte proliferation and activation after antigenic or mitogenic stimulation is a vital parameter used in the diagnosis of various immuno-deficiencies and during the monitoring of treatment responses. Most applied techniques are based on the incorporation of tritiated thymidine (3H-TdR) or ELISPOT analysis, both rely on rather time-consuming/-intensive ex vivo protocols or encompass inherent drawbacks such as the inability to distinguish specific cell populations (3H-TdR, ELISPOT) or focus on a single cytokine (ELISPOT). Here we aimed at characterizing the rapid expression of intracellular CD154 (CD40L) as a marker for rare antigen-specific CD4+ T cells in pemphigus vulgaris (PV). Upon stimulation with human desmoglein (Dsg) 3, the major autoantigen in PV, the expression of CD154 was significantly increased in PV patients compared to healthy controls (HC) and correlated with anti-Dsg3 IgG titers. Patients with active disease showed higher numbers of Dsg3-reactive CD4+ T cells in CXCR5+ T follicular helper cells. In remittent PV and HC, CXCR5+CD4+ T cells remained largely unaffected by Dsg3. IL-17 and IL-21 expression were significantly induced only in CD154+CD4+ T cells from PV patients, lending themselves as potential novel treatment targets. Additionally, stimulation with immunodominant Dsg3-derived epitopes strongly induced a CD4+ T cell response via CD40-CD154 interaction similar to the human Dsg3 protein. We here established a rapid ex vivo assay allowing the detection of Dsg3-reactive CD4+ T cells from activated systemically available PBMCs, which further supports the crucial concept of antigen-specific T cells in the pathogenesis of PV.

Phytotherapeuthics Affecting the IL-1/IL-17/G-CSF Axis: A Complementary Treatment Option for Hidradenitis Suppurativa?

Hidradenitis suppurativa (HS; also designated as acne inversa) is a chronic inflammatory disease characterized by painful skin lesions that occur in the axillary, inguinal, gluteal and perianal areas of the body. These lesions contain recurring deep-seated, inflamed nodules and pus-discharging abscesses and fistulas. Affecting about 1% of the population, this common disease has gained appropriate clinical attention in the last years. Associated with numerous comorbidities including metabolic syndrome, HS is considered a systemic disease that severely impairs the quality of life and shortens life expectancy. Therapeutic options for HS are limited, comprising long-term antibiotic treatment, the surgical removal of affected skin areas, and neutralization of TNF-α, the only approved systemic treatment. Novel treatment options are needed to close the therapeutic gap. HS pathogenesis is increasingly better understood. In fact, neutrophilic granulocytes (neutrophils) seem to be decisive for the development of the purulent destructive skin inflammation in HS. Recent findings suggest a key role of the immune mediators IL-1ß, IL-17A and G-CSF in the migration into and activation of neutrophils in the skin. Although phytomedical drugs display potent immunoregulatory properties and have been suggested as complementary therapy in several chronic disorders, their application in HS has not been considered so far. In this review, we describe the IL-1/IL-17/G-CSF axis and evaluate it as potential target for an integrated phytomedical treatment of HS.

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.

Early identification of axial psoriatic arthritis among patients with psoriasis: a prospective multicentre study.

OBJECTIVES: To evaluate a dermatologist-centred screening tool followed by a structured rheumatological examination including MRI of sacroiliac joints and spine for the recognition of psoriatic arthritis with axial involvement (axPsA). METHODS: This was a prospective multicentre study. Adult patients with a confirmed diagnosis of psoriasis who had chronic back pain (≥3 months), onset <45 years and had not been treated with any biologic or targeted synthetic disease-modifying antirheumatic drug in the 12 weeks before screening were referred to a specialised rheumatology clinic. A rheumatological investigation including clinical, laboratory and genetic assessments as well as imaging with conventional radiography and MRI of sacroiliac joints and spine was performed. The primary outcome of the study was the proportion of patients diagnosed with axPsA among all referred patients with PsO. RESULTS: Rheumatologists examined 100 patients of those who qualified for referral. 14 patients (including 3 with both axial and peripheral involvement) were diagnosed with axPsA and 5 were diagnosed with peripheral PsA solely. All patients diagnosed with axPsA had active inflammatory and/or structural (post)inflammatory changes in the sacroiliac joints and/or spine on imaging. In five patients, MRI changes indicative of axial involvement were found only in the spine. All but one patient with PsA (13/14 with axPsA and 5/5 with pPsA) fulfilled the Classification Criteria for Psoriatic Arthritis criteria for PsA. The Assessment of SpondyloArthritis International Society criteria for axSpA were fulfilled in 9 (64.3%) patients diagnosed with axPsA. CONCLUSIONS: Applying a dermatologist-centred screening tool may be useful for the early detection of axPsA in at-risk patients with psoriasis .

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.

Prevalence of Candida species in Psoriasis.

BACKGROUND: Psoriasis patients are more frequently colonised with Candida species. The correlation between fungal colonisation and clinical severity is unclear, but may exacerbate psoriasis and the impact of antipsoriatic therapies on the prevalence of Candida is unknown. OBJECTIVES: To examine the prevalence of C species in psoriasis patients compared to an age- and sex-matched control population, we investigated the influence of Candida colonisation on disease severity, immune cell activation and the interplay on psoriatic treatments. METHODS: The prevalence of C species was examined in 265 psoriasis patients and 200 control subjects by swabs and stool samples for fungal cultures. Peripheral mononuclear blood cells (PBMCs) were collected from 20 fungal colonised and 24 uncolonised patients and stimulated. The expression of interferon (IFN)-γ, IL-17A, IL-22 and tumour necrosis factor (TNF)-α from stimulated PBMCs was measured by quantitative real-time polymerase chain reaction (qPCR). RESULTS: A significantly higher prevalence for Candida was detected in psoriatic patients (p ≤ .001) compared to the control subjects; most abundant in stool samples, showing Candida albicans. Older participants (≥51 years) were more frequent colonised, and no correlation with gender, disease severity or systemic treatments like IL-17 inhibitors was found. CONCLUSIONS: Although Candida colonisation is significantly more common in patients with psoriasis, it does not influence the psoriatic disease or cytokine response. Our study showed that Candida colonisation is particularly more frequent in patients with psoriasis ≥51 years of age. Therefore, especially this group should be screened for symptoms of candidiasis during treatment with IL-17 inhibitors.

The Effect of TNF-α Inhibitors on Nail Psoriasis and Psoriatic Arthritis-Real-World Data from Dermatology Practice.

Patients with psoriatic arthritis (PsA) often develop joint symptoms years after their initial diagnosis of psoriasis disease; therefore, dermatologists should test for and detect PsA early. In this study, we focused on patients with psoriasis with both nail and joint disease being treated with tumor necrosis factor-α inhibitors by dermatologists. We performed a noninterventional, prospective, multicenter, and open-label study to evaluate the effectiveness of adalimumab, etanercept, or infliximab over 24 months of continuous therapy in patients with moderate to severe plaque-type psoriasis (Pso) and PsA. Disease assessments with the Psoriasis Area and Severity Index, Nail Psoriasis Severity Index (NAPSI), joint assessment, Dermatology Life Quality Index (DLQI), and Health Assessment Questionnaire (HAQ) instruments were performed every 3 months for the first year and twice annually thereafter. The cohort included 100 patients with Pso, nail psoriasis, and PsA. A significant reduction of NAPSI was observed 3 months after therapy initiation compared with the baseline (mean ± SD, 22.9 ± 17.8 vs. 33.8 ± 21.4; p < 0.001). Similarly, the mean ± SD number of both tender and swollen joints decreased significantly within the first 3 months of treatment, from 10.8 ± 11.5 to 6.4 ± 10.3 (p < 0.001) and from 6.4 ± 9.5 to 3.1 ± 7.2 (p < 0.001), respectively. Additionally, the distal interphalangeal joint involvement improved throughout the observation time, and DLQI and HAQ scores decreased. Improvements in control of skin, nail, and joint symptoms were seen, as well as in patients' quality of life and functionality. Dermatologists have an important role not only in PsA diagnosis but also in PsA long-term care.

Charakteristika von Dermatomyositis-Patienten mit und ohne Malignom-Assoziation.

HINTERGRUND: Die Dermatomyositis gehört zur Gruppe der seltenen, idiopathischen, inflammatorischen Myositiden. Für die paraneoplastische Form der Dermatomyositis wurde in der Vergangenheit ein Zusammenhang mit Malignomen erkannt. Faktoren, die für eine Malignom-Assoziation sprechen, werden bis heute untersucht. PATIENTEN UND METHODIK: Es wurden retrospektiv über einen Zeitraum von 15 Jahren die Daten von 63 Patienten mit Dermatomyositis analysiert. ERGEBNISSE: Folgende Faktoren gaben einen Hinweis für eine Dermatomyositis mit Malignom-Assoziation: ein höheres Patientenalter (> 52 Jahre [P = 0,001], > 65 Jahre [P = 0,002], ≥ 75 Jahre [P = 0,002]), eine kürzere Zeit zwischen Erstmanifestation und Erstdiagnose (Malignom-Gruppe: 59 Tage vs. Nicht-Malignom-Gruppe: 137 Tage [P = 0,022]), eine Hautbeteiligung in Form von Gottron-Zeichen (P = 0,045), zentrofazialen Erythemen (P = 0,036) oder typischen Erythemen an den Ober-/Unterarmen (P = 0,019), eine oropharyngeale Beteiligung (P = 0,015) und eine GPT-Erhöhung (P = 0,031). Folgende Faktoren sprachen eher gegen eine Malignom-Assoziation: ein jüngeres Patientenalter (≤ 52 Jahre [P = 0,001], 40-65 Jahre [P = 0,045]) und Juckreiz (P = 0,026). SCHLUSSFOLGERUNGEN: In der Literatur finden sich heterogene Ergebnisse zu den genannten Faktoren hinsichtlich ihrer Eignung als Marker für eine Malignom-Assoziation. Erschwert ist die Faktorenfindung aufgrund kleiner Studienpopulationen, wenigen prospektiven und kontrollierten Studien, die Einordnung von Populationen als Myositis-Patienten ohne Differenzierung und eine inkonsistente Verwendung der Nomenklatur. Mit unserer Studie wollen wir einen wichtigen Beitrag zur Identifizierung von Risikofaktoren bei Dermatomyositis mit Malignom-Assoziation leisten.

Characteristics of dermatomyositis patients with and without associated malignancy.

BACKGROUND: Dermatomyositis belongs to the rare idiopathic, inflammatory myositis group. A previously postulated link between some cases of dermatomyositis and malignancy has been established in recent years. Criteria suggestive of a malignancy association are still being explored. PATIENTS AND METHODS: We retrospectively analyzed data from 63 patients with dermatomyositis over a period of 15 years. RESULTS: The following criteria argue for cancer-associated dermatomyositis: older age (> 52 years [P = 0.001], > 65 years [P = 0.002], ≥ 75 years [P = 0.002]), shorter time between manifestation and diagnosis of dermatomyositis (malignancy group: 59 days vs. non-malignancy group: 137 days [P = 0.022]), typical skin involvement such as Gottron sign (P = 0.045), centrofacial erythema (P = 0.036) and typical erythema on the upper arms and forearms (P = 0.019), oropharyngeal involvement (P = 0.015) and increased ALT (P = 0.031). The following criteria argue for non-cancer-associated dermatomyositis: younger age (≤ 52 years [P = 0.001], 40-65 years [P = 0.045]) and pruritus (P = 0.026). CONCLUSIONS: The aforementioned criteria have been documented in the literature, but reported findings are heterogenous concerning the suitability of their markers for malignancy association. Small study populations, few prospective controlled studies, summarization of different forms of myositis and inconsistent use nomenclature contribute to biased results. Our study aims to make an important contribution toward the identification of risk factors in cancer-associated dermatomyositis.