Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 3 de 3
Filtrar
Mais filtros

Base de dados
Tipo de documento
Intervalo de ano de publicação
1.
Hell J Nucl Med ; 25(2): 210-212, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35913868

RESUMO

Subacute thyroiditis (SAT) is a thyroid inflammatory disease, whose pathogenesis is still unclear. We report a 52-year-old female with SAT after the third dose of COVID-19 mRNA vaccine BNT162b2 (Pfizer-BioNTech). This case was documented with laboratory tests and ultrasound examination. She needed therapy during the acute phase and subsequently thyroxine supplementation.


Assuntos
COVID-19 , Tireoidite Subaguda , Vacina BNT162 , Vacinas contra COVID-19 , Feminino , Humanos , Pessoa de Meia-Idade , Vacinas Sintéticas , Vacinas de mRNA
2.
World J Gastrointest Oncol ; 10(1): 56-61, 2018 Jan 15.
Artigo em Inglês | MEDLINE | ID: mdl-29375749

RESUMO

Leptomeningeal carcinomatosis is a very rare manifestation in patients diagnosed with esophagogastric junction and gastric cancer. Its prognosis is ominous and therapy outcomes are disappointing. Herein, we present two patients; one initially diagnosed with gastric cancer and leptomeningeal carcinomatosis but no other evidence of metastatic disease and the other one initially diagnosed with esophagogastric junction cancer, who recurred solitary with leptomeningeal seedings several years after the initial diagnosis and treatment. Furthermore, a thorough and short review of the literature is carried out.

3.
Neural Netw ; 24(8): 842-51, 2011 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-21719251

RESUMO

This paper proposes an extension to conventional regression neural networks (NNs) for replacing the point predictions they produce with prediction intervals that satisfy a required level of confidence. Our approach follows a novel machine learning framework, called Conformal Prediction (CP), for assigning reliable confidence measures to predictions without assuming anything more than that the data are independent and identically distributed (i.i.d.). We evaluate the proposed method on four benchmark datasets and on the problem of predicting Total Electron Content (TEC), which is an important parameter in trans-ionospheric links; for the latter we use a dataset of more than 60000 TEC measurements collected over a period of 11 years. Our experimental results show that the prediction intervals produced by our method are both well calibrated and tight enough to be useful in practice.


Assuntos
Previsões/métodos , Redes Neurais de Computação , Algoritmos , Animais , Inteligência Artificial , Benchmarking , Boston , Calibragem , Computadores , Comportamento Cooperativo , Bases de Dados Factuais , Elétrons , Meio Ambiente Extraterreno , Gastrópodes/fisiologia , Habitação/estatística & dados numéricos , Humanos , Análise de Componente Principal , Análise de Regressão , Reprodutibilidade dos Testes , Atividade Solar
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA