Histological interpretation of spitzoid tumours: an extensive machine learning-based concordance analysis for improving decision making.

The histopathological classification of melanocytic tumours with spitzoid features remains a challenging task. We confront the complexities involved in the histological classification of these tumours by proposing machine learning (ML) algorithms that objectively categorise the most relevant features in order of importance. The data set comprises 122 tumours (39 benign, 44 atypical and 39 malignant) from four different countries. BRAF and NRAS mutation status was evaluated in 51. Analysis of variance score was performed to rank 22 clinicopathological variables. The Gaussian naive Bayes algorithm achieved in distinguishing Spitz naevus from malignant spitzoid tumours with an accuracy of 0.95 and kappa score of 0.87, utilising the 12 most important variables. For benign versus non-benign Spitz tumours, the test reached a kappa score of 0.88 using the 13 highest-scored features. Furthermore, for the atypical Spitz tumours (AST) versus Spitz melanoma comparison, the logistic regression algorithm achieved a kappa value of 0.66 and an accuracy rate of 0.85. When the three categories were compared most AST were classified as melanoma, because of the similarities on histological features between the two groups. Our results show promise in supporting the histological classification of these tumours in clinical practice, and provide valuable insight into the use of ML to improve the accuracy and objectivity of this process while minimising interobserver variability. These proposed algorithms represent a potential solution to the lack of a clear threshold for the Spitz/spitzoid tumour classification, and its high accuracy supports its usefulness as a helpful tool to improve diagnostic decision-making.

Características del melanoma cutáneo en dos instituciones de Bogotá, Colombia: Análisis 2012-2016 / Characteristic features of cutaneousmelanoma in two institutions of Bogotá, Colombia: Analysis, 2012-2016

Resumen Introducción: El Melanoma es una neoplasia que se origina de los melanocitos. Este tumor, a pesar de representar solo el 5% de las neoplasias cutáneas, es el responsable del 70% de las muertes producidas por cáncer de piel. En Colombia se ha registrado una supervivencia del 79% a 5 años y en el caso particular del melanoma lentiginoso acral, de tan solo 54%. No obstante, los datos nacionales no son claros, por lo cual es necesario caracterizar a los pacientes con dicho diagnóstico para contribuir con futuros estudios. Metodología: Estudio de corte transversal en el cual se incluyeron y analizaron registros clínicos, demográficos e histopatológicos de pacientes con diagnóstico de melanoma cutáneo atendidos en dos instituciones dermatológicas de Bogotá, Colombia, durante los años 2012-2016. Resultados: Se incluyeron un total de 255 pacientes, la mayoría mujeres (61.0%). Se observó un aumento de 22 a 64 casos diagnosticados en los años 2012 y 2016 respectivamente. El subtipo histológico más frecuente fue el lentigo maligno (33.7%) seguido del melanoma lentiginoso acral (16.1%). La principal localización fue la cara (43.1%). El tiempo entre la detección y la confirmación del diagnóstico por biopsia fue de 17 meses. El 20% de los casos correspondió con un índice de Breslow <1 y el 42.4% de los casos un Clark de I. Conclusiones: Se observó un aumento en el número de casos nuevos de melanoma cutáneo entre los años 2012 y 2016, siendo los subtipos más frecuentemente diagnosticados el lentigo maligno y el melanoma lentiginoso acral. Los tiempos promedio de diagnóstico fueron prolongados.

Abstract Introduction: Melanoma is a cutaneous neoplasm originating from melanocytes. This tumor, despite representing only 5% of skin neoplasms, is responsible for 70% of deaths caused by skin cancer. In Colombia, a mortality of 0.5/100,000 inhabitants has been reported with a survival rate of 79% at 5 years, but in the case of acral lentiginous melanoma, survival is only 54%. However, national data are not clear, which highlights the need to characterize patients with this diagnosis to contribute to further epidemiological studies. Methodology: Cross-sectional study of the clinical, demographic, and histopathological records of patients with diagnosis of cutaneous melanoma, who were attended in two dermatological centers of Bogotá, Colombia, during 2012-2016. Results: A total of 255 patients were included, most of them women (61.0%). An increase from 22 to 64 diagnosed cases was observed from 2012 to 2016, respectively. The most frequent histological subtype was lentigo maligna (33.7%), followed by lentiginous acral melanoma (16.1%). The main location was face (43.1%). The time between detection and confirmation of diagnosis by biopsy was 17 months. 20% of the cases had a Breslow index <1 and 42.4% of the cases were Clark's level I. Conclusions: There was an increase in the number of new cases of cutaneous melanoma between 2012 and 2016, the most frequently diagnosed subtypes being lentigo maligna and acral lentiginous melanoma. The average time of diagnosis was prolonged.

Sindrome de hipersensibilidad a anticonvulsionantes secundario a acido valproico / Hypersensitivity syndrome to anticonvulsionant drugs secundary a valpropic acid

Las reacciones medicamentosas presentan múltiples manifestaciones las cuales incluyen: exantemas, prurito, urticaria, fotosensibilidad y, en casos severos, eritema multiforme y necrólisis epidérmica tóxica; otras manifestaciones infrecuentes son: morfea, púrpura, alopecia, vitíligo, porfiria, vasculitis y reacciones liquenoides; virtualmente cualquier sustancia ingerida puede ocasionar una reacción de hipersensibilidad.Presentamos el caso de una mujer que desarrolló un síndrome de hipersensibilidad a anticonvulsivantes secundario al ácido valpróico caracterizado por: fiebre, eritrodermia, linfadenopatía, alteraciones neurológicas, hematológicas y hepáticas con un patrón histológico cutáneo liquenoide.