Automated classification of hidradenitis suppurativa disease severity by convolutional neural network analyses using calibrated clinical images.

BACKGROUND: The assessment of hidradenitis suppurativa (HS) severity requires detailed, and error-prone lesion counts. This proof-of-concept study aimed to automatically classify HS disease severity using machine learning of clinical smartphone images. METHODS: 777 ambient-light and size-controlled images were used to build a class-balanced synthetic dataset (n = 7675). Convolutional neural networks (CNN) were used for automated severity classification (scale 0-3), and to assess disease-dynamics. International Hidradenitis Suppurativa Severity Score System (IHS4) served as reference. A U-NET algorithm was implemented for automated localization of diseased skin. RESULTS: CNNs were able to distinguish no/mild from moderate/severe disease with an overall prediction accuracy of 78% [receiver operating curve (AUC) 0.85]. Correct IHS4 classification was achieved with an overall accuracy of 72% (AUC 0.84-0.89). In addition, disease dynamics using IHS4 numerical values aligned with CNN outputs (NRMSE 0.262). The UNET algorithm localized lesions with a pixel accuracy of 88.1% and test loss of 0.42. LIMITATIONS: Limitations in assessing tattooed and hairy skin. Limited number of patients with dark skin colour and Hurley I. CONCLUSION: CNNs were able to distinguish no/mild from moderate/severe disease, classify disease severity over time, and automatically identify diseased skin areas and the skin phototype. This study breaks new grounds for fast, reliable, reproducible and easy-to-use HS severity assessments using clinical images.

Outcomes after stereotactic radiosurgery of brain metastases in patients with malignant melanoma and validation of the melanoma molGPA.

INTRODUCTION: Malignant melanoma is the third most common primary in the diagnosis of brain metastases. Stereotactic radiosurgery (SRS) is a well-established treatment option in limited brain disease. We analyzed outcomes of SRS with a particular focus on the graded prognostic assessment (GPA, melanoma molGPA), prognostic factors, and toxicity. METHODS: We evaluated 173 brain metastases in 83 patients with malignant melanoma. All were treated with SRS median dose of 20 Gy prescribed to the 80 or 100% isodose line between 2002 and 2019. All patients were followed-up regularly, including contrast-enhanced brain imaging as well as clinical examination, initially 6 weeks after treatment, then in quarterly follow-up. RESULTS: The median age was 61 years (range 27-80); 36 female and 47 male patients were treated. After a median follow-up of 5.7 months, median OS (overall survival) was 9.7 months 95%-KI 4.7-14.7). LC (local control) at 6 months, 12, 24 months was 89%, 86%, and 72%, respectively (median was not reached). Median DBC (distant brain control) was 8.2 months (95%-KI 4.7-11.7). For OS, a KPS ≥ 80%, a positive BRAF mutation status, a small PTV (planning target volume), the absence of extracranial metastases, as well as a GPA and melanoma molGPA > 2 were prognostic factors. In the MVA, a small PTV and a melanoma molGPA > 2 remained significant. CONCLUSION: The present survival outcomes support the use of the disease-specific melanoma molGPA as reliable prognostic score. Favorable outcomes for SRS compared to other studies were observed. In the treatment of brain metastases of malignant melanoma patients, a multidisciplinary approach consisting of surgery, SRS, chemotherapy, and immunotherapy should be considered.

Anti-BP180 autoantibody levels at diagnosis correlate with 1-year mortality rates in patients with bullous pemphigoid.

BACKGROUND: Bullous pemphigoid (BP) is the most frequent autoimmune blistering disease mainly affecting elderly patients. Among several published risk factors, a recent post hoc analysis linked anti-BP180 autoantibodies (AABs) to fatal outcomes in BP. To date, this finding has not been confirmed independently. OBJECTIVE: To investigate the potential of anti-BP180-AAB levels as a marker of prognosis and to identify a cut-off level indicative of an increased risk for early death. Secondly, to characterize parameters associated with mortality. METHODS: Retrospective, single-centre study of BP patients diagnosed between 2001 and 2012. Analyses included epidemiological and patient- and disease-specific characteristics as well as immunological parameters at diagnosis and during follow-up. Standardized mortality ratios as well as uni- and multivariate regression analyses were calculated. RESULTS: One hundred patients (56 women, 44 men) with a median age of 81 years (interquartile range 74-86) were followed up for a median of 775 days (interquartile range 162-1617). One-year mortality rates were 25.0% implying a 2.4-fold increased risk of death compared with the general population. High anti-BP180 autoantibody levels at diagnosis (CI95 1.30-2.89; P = 0.001), dementia (CI95 1.13-6.72; P =0.03), length of hospitalization (CI95 1.16-2.41; P = 0.01) and age (CI95 1.23-4.19; P = 0.009) correlated significantly with 1-year mortality. BP180-AAB concentrations of ≥61 U/mL characterized a subgroup of patients with a particular higher risk for early death compared with the general population (CI95 1.81-3.81; P < 0.0001). CONCLUSION: In bullous pemphigoid, serum concentrations of BP180 autoantibodies at diagnosis could help to identify patients at risk for death within the first year after diagnosis (cut-off value 61 U/mL).

Apremilast in psoriasis - a prospective real-world study.

BACKGROUND: Apremilast is a novel oral phosphodiesterase-4 inhibitor approved for psoriasis treatment. Randomized trials have documented its efficacy and safety, but data on real-world patients are scarce. OBJECTIVES: We aim to characterize psoriasis patients treated with apremilast in a real-world setting and calculate drug survival as an important measure of efficacy and compliance. METHODS: All patients with psoriasis who received apremilast between 1 April 2015 and 19 January 2017 were evaluated every 4 weeks, and we documented: age, weight, height, smoking status, family history of psoriasis, joint involvement, previous treatments, psoriasis area severity index (PASI) scores, and the onset and duration of adverse events (AE). Efficacy was analysed by PASI50, PASI75 and PASI90, reflecting the improvement of skin lesions compared to the PASI-baseline. Kaplan-Meier statistics were used for drug survival estimates. RESULTS: Forty-eight patients were included. The median apremilast drug survival was 12.5 weeks (range 1-87). Three patients (6.3%) reached PASI90, nine (18.8%) PASI75 and eight patients (16.7%) PASI50. Patient weight inversely correlated with a PASI50 response (P < 0.05, n = 37), and none of the obese patients (BMI > 30.0, n = 6) reached PASI75, compared to 32% of the non-obese patients (BMI < 30.0, n = 31). Thirty-one patients (64.6%) reported at least one AE, most frequently diarrhoea (n = 21, 43.8%), headache (n = 7, 14.6%) and joint pain (n = 5, 10.4%). CONCLUSIONS: Despite differences between real-world and trial patients, apremilast is safe and effective for the treatment of skin psoriasis in the daily practice. Up to 40% of patients will reach PASI50 or higher, but only few patients will reach PASI90. Bodyweight might affect drug efficacy.

[Bullous Sweet's syndrome with pulmonary involvement]. / Bullöses Sweet-Syndrom mit pulmonaler Beteiligung.

Acute febrile neutrophilic dermatosis (Sweet's syndrome) is a rare dermatosis characterized by painful papules and plaques accompanied by cutaneous infiltration with neutrophilic granulocytes. Bullous changes are observed in some cases. We report about a patient with osteomyelofibrosis who developed fever accompanied by painful plaques and confluent papules on both arms and thighs. The course of the disease was complicated by blistering and pulmonary infiltrates. After the diagnosis of bullous Sweet's syndrome was established, systemic therapy with glucocorticoids was successful in treating skin lesions and dyspnea.

Pyoderma gangrenosum during pregnancy - treatment options revisited.

BACKGROUND: Pyoderma gangrenosum (PG) is a rare, ulcerating neutrophilic dermatosis of unknown aetiology; PG during pregnancy is particularly rare. The disease is frequently associated with immune-mediated, inflammatory diseases. OBJECTIVE: Diagnosis of PG can be challenging and relies upon exclusion of other causes such as traumas, infections, vascular diseases or neoplasms. Treatment options during pregnancy are limited. METHODS: To evaluate current treatment options for PG during pregnancy, we present a case of multilocular PG during the patient's first trimester. In conjunction with a comprehensive review of previously published cases of PG during gravidity, we discuss available treatment modalities including immunosuppressants and TNFα inhibitors. RESULTS: Our patient highlights the importance of including PG as a potential differential diagnosis of cutaneous ulcers during gravidity. Treatment with systemic glucocorticoids is effective and safe for the health of the mother and the unborn. CONCLUSION: In pregnant females, it is particularly important to diagnose PG and control disease activity due to the risk of pathergy and wound healing deficiencies during delivery and post-partum. A limited number of treatment options are available to date, which require a precise risk-benefit evaluation.