14 October 2022 in Applied Immunohistochemistry & Molecular Morphology
MRMaría D. Sánchez-Aguilar Y. Rojas
María D. Sánchez-Aguilar Y. Rojas
JSJosé M. Suárez-Peñaranda
Melanoma is the cutaneous neoplasm responsible for more patient deaths in all countries. BRAF mutations are the most common driver mutation and with the development of molecular targeted therapy, the precise knowledge of BRAF status has become increasingly important. Evaluation of BRAF mutation status has routinely been performed by polymerase chain reaction, a time consuming and expensive technique. Immunohistochemistry has been suggested as a cheaper alternative, but it has not gained general acceptance. A retrospective observational study in a cohort of 106 patients with invasive melanoma was conducted in order to develop and evaluate a machine learning approach to predict BRAF status using clinical and histologic variables. We compared the performance of different common machine learning algorithms and use SHapley Additive exPlanations (SHAP) to explain individual predictions and extract medical insights to define a heuristic model to estimate BRAF mutation probability. The Extreme Gradient Boosting algorithms obtained the best performance. Interpretability of models shows that the most important variables to estimate BRAF mutation probability are: age, Breslow thickness, and Breslow density. Based in this interpretation and medical knowledge, a simplify heuristic model is proposed to predict BRAF status using only 7 variables and obtain a performance of 0.878 of area under the curve. We propose a heuristic model that could be used by clinicians to obtain a good estimator of BRAF mutation probability.
8 December 2022 in Anais Brasileiros de Dermatologia
The COVID-19 lockdown possibly meant a delay in the diagnosis and treatment of melanoma and therefore, worsening its prognosis. This unique situation of diagnosis deferral is an exceptional opportunity to investigate melanoma biology. To evaluate the immediate and mid-term impact of diagnosis delay on melanoma. A retrospective observational study of melanoma diagnosed between March 14th 2019 and March 13th 2021. We compared the characteristics of melanomas diagnosed during the first 6-month period after the lockdown instauration and a second period after recovery of normal activity with the same periods of the previous year, respectively. A total of 119 melanomas were diagnosed. There were no differences in age, sex, incidence, location, presence of ulceration or mitoses, and in situ/invasive melanoma rate (p > 0.05). After the recovery of the normal activity, Breslow thickness increased in comparison with the previous year (2.4 vs 1.9 mm, p < 0.05) resulting in a significant upstaging according to the AJCC 8th ed. (p < 0.05). The main limitation is that this is a single-center study. The COVID-19 lockdown implied a diagnosis delay leading to a mid-term increase in Breslow thickness and an upstaging of invasive melanomas. However, the detection deferral did not result in a higher progression of in situ to invasive melanoma, in our sample.
1 January 2017 in Dermatology Online Journal
MEMartina Espasandín-Arias
VFVirginia Fernández-Redondo
Virginia Fernández-Redondo
Bazex syndrome (BS) is a rare paraneoplastic syndrome most frequently associated with squamous cell carcinomas of the upper aerodigestive tractand other tumours. Characteristically, cutaneous lesions precede the diagnosis of malignancy. We report a 72-year-old patient with 1-year history of acral dermatitis. The diagnosis of BS was based on the presence of psoriasiform acral dermatitis and the evidence of two simultaneous tumors (prostate adenocarcinoma and undifferentiated carcinoma ofthe submandibular gland). It is important to have this syndrome in mind since cutaneous features usually precede an underlying neoplasm.
30 April 2024 in Clinical and Experimental Dermatology
Background: Current staging systems have limitations in stratifying high-risk cutaneous squamous cell carcinoma (cSCC). Tumour budding (TB) has emerged as a potential prognostic factor in various cancers. Objectives: To evaluate the prognostic significance of TB in predicting lymph node metastases (NM) in cSCC. Methods: A comprehensive search of the PubMed, Web of Science, Embase and Cochrane databases was conducted. Studies investigating the association of TB using a 5-bud cutoff and NM in cSCC were included. A meta-analysis was performed using odds ratios (OR) to evaluate the association between TB and NM. Results: Six retrospective studies comprising 793 patients with cSCC were included. The random-effects analysis showed a significant association between high TB (≥ 5 buds) and NM (OR = 13.29, 95% confidence interval 5.55–31.86). Discussion: TB is a promising histopathological feature for predicting NM in cSCC. The results show a strong association between high TB and NM, supporting its utility as a risk factor for NM in cSCC. Its inclusion in clinical practice and cSCC staging might be helpful in the stratification of patients with high-risk cases and to guide optimal management strategies for each patient. However, further investigation is needed to determine standardized reporting guidelines for TB in cSCC.
1 June 2022 in Journal of the American Academy of Dermatology
JSJose Manuel Suárez-Peñaranda
Jose Manuel Suárez-Peñaranda
MRMaria Dolores Sánchez-Aguilar Rojas
Maria Dolores Sánchez-Aguilar Rojas
4 November 2022 in Journal of the European Academy of Dermatology and Venereology
IBIsabel Rodríguez Blanco
+2