ABSTRACT
Objetivo: Investigar a prevalência e os riscos para tuberculose (TB) em pacientes com psoríase em uso de imunobiológicos tratados em centro de referência na Paraíba. Métodos: Trata-se de um estudo transversal, com psoriásicos registrados no Centro de Referência de Psoríase de um Hospital Universitário em parceria com o Centro Especializado de Dispensação de Medicamentos Excepcionais, com idade ≥ 18 anos, tratados com imunobiológicos de setembro/2021 a agosto/2022. Resultados: A amostra de 185 pacientes, foram 94 (50.8%) mulheres, com média de idade de 51,8 ± 16,0 anos,147 (79.4%) eram da capital da Paraíba. A forma de psoríase mais prevalente foi do tipo Vulgar em placas, com 181 (45.9%) pacientes. Todos os pacientes estavam usando imunobiológicos, sendo o inibidor do fator de necrose tumoral o mais utilizado. Observou-se Teste de Mantoux reativo em 12 (6.5%) pacientes e fortemente reativo em 5 (2.7%), e alteração na radiografia de tórax em 6 pacientes. Os 17 pacientes com TB- latente foram tratados com isoniazida por 9 meses, e nenhum desenvolveu a TB-doença. Conclusão: Este estudo foi imperioso para conhecer o perfil epidemiológico dos pacientes com psoríase em uso de imunobiológicos e que estão expostos a um risco maior em desenvolver a TB-doença.
Objective: To investigate the prevalence and risks of tuberculosis (TB) in patients with psoriasis using immunobiologics treated at a referral center in Paraíba. Methods: This is a cross-sectional study with psoriatic individuals registered at the Psoriasis Reference Center at the University Hospita in partnership with the Specialized Center for the Dispensation of Exceptional Medicines, aged ≥ 18 years, treated with immunobiologics from September/2021 to August/2022. Results: The sample of 185 patients who met the criteria were 94 (50.8%) women, with a mean age of 51.8 ± 16.0 years,147 (79.4%) were from the capital of Paraíba. The most prevalent form of psoriasis was the vulgar plaque type, with 181 (45.9%) patients. All patients were using immunobiologicals, and the tumor necrosis factor inhibitor was the most widely used. Reactive Mantoux test was observed in 12 (6.5%) patients and strongly reactive in 5 (2.7%), and chest X-ray changes were observed in 6 patients. The 17 patients with latent TB were treated with isoniazid for 9 months, and none developed TB-disease. Conclusion: This study was imperative to know the epidemiological profile of patients with psoriasis using immunobiologics and who are exposed to a higher risk of developing TB-disease.
Objetivo: Investigar la prevalencia y los riesgos de tuberculosis (TB) en pacientes con psoriasis utilizando inmunobiológicos tratados en un centro de referencia en Paraíba. Métodos: Estudio transversal con individuos psoriásicos registrados en el Centro de Referencia de Psoriasis del Hospital en asociación con el Centro Especializado para la Dispensación de Medicamentos Excepcionales, con edad ≥ 18 años, tratados con productos inmunobiológicos desde septiembre/2021 hasta agosto/2022. Resultados: La muestra de 185 pacientes que cumplieron con los criterios fueron 94 (50,8%) mujeres, con edad promedio de 51,8 ± 16,0 años, 147 (79,4%) eran de la capital de Paraíba. La forma más prevalente de psoriasis fue el tipo de placa vulgar, con 181 (45,9%) pacientes. Todos los pacientes usaban productos inmunobiológicos, y el inhibidor del factor de necrosis tumoral fue el más utilizado. Se observó teste de Mantoux reactiva en 12 (6,5%) pacientes y fuertemente reactiva en 5 (2,7%), y se observaron cambios en la radiografía de tórax en 6 pacientes. Los 17 pacientes con TB latente fueron tratados con isoniazida durante 9 meses, y ninguno desarrolló enfermedad de TB. Conclusión: Este estudio fue imprescindible para conocer el perfil epidemiológico de los pacientes con psoriasis que utilizan productos inmunológicos y que están expuestos a un mayor riesgo de desarrollar la enfermedad de TB.
ABSTRACT
OBJECTIVE: To analyze the performance of 10 different machine learning (ML) classifiers for discrimination between dysphonic and non-dysphonic voices, using a variance threshold as a method for the selection and reduction of acoustic measurements used in the classifier. METHOD: We analyzed 435 samples of individuals (337 female and 98 male), with a mean age of 41.07 ± 13.73 years, of which 384 were dysphonic and 51 were non-dysphonic. From the sustained /ε/ vowel sample, 34 acoustic measurements were extracted, including traditional perturbation and noise measurements, cepstral/spectral measurements, and measurements based on nonlinear models. The variance method was used to select the best set of acoustic measurements. We tested the performance of the best-selected set with 10 ML classifiers using precision, sensitivity, specificity, accuracy, and F1-Score measurements. The kappa coefficient was used to verify the reproducibility between the two datasets (training and testing). RESULTS: The naive Bayes (NB) and stochastic gradient descent classifier (SGDC) models performed best in terms of accuracy, AUC, sensitivity, and specificity for a reduced dataset of 15 acoustic measures compared to the full dataset of 34 acoustic measures. SGDC and NB obtained the best performance results, with an accuracy of 0.91 and 0.76, respectively. These two classifiers presented moderate agreement, with a Kappa of 0.57 (SGDC) and 0.45 (NB). CONCLUSION: Among the tested models, the NB and SGDC models performed better in discriminating between dysphonic and non-dysphonic voices from a set of 15 acoustic measures.
