Variable selection constitutes an essential step to reduce dimensionality and improve performance of fault detection and diagnosis in large scale industrial processes. For this reason, in this paper, variable selection approaches based on causality are proposed and compared, in terms of model adjustment of available data and fault detection performance, with several other filter-based, wrapper-based, and embedded-based variable selection methods. These approaches are applied in a simulated benchmark case and an actual oil and gas industrial case considering four different learning models. The experimental results show that obtained models presented better performance during the fault detection stage when variable selection procedures based on causality were used for purpose of model building.
Objetivo: Relatar caso de uma paciente imunossuprimida, internada em enfermaria, evoluindo com coinfecção por fusariose e criptococose devido a aplasia após quimioterapia para tratamento de leucemia mielóide aguda (LMA) refratáriaDetalhamento de caso: Mulher de 24 anos, previamente hígida, teve diagnóstico de LMA em abril de 2018, foi submetida a quimioterapia em duas ocasiões, a primeira com citarabina e idarrubicina com resposta parcial e remissão incompleta, sendo sucedido do protocolo com as mesmas drogas em altas doses, apresentando remissão completa eventual. Em novembro de 2018, foi diagnosticada recidiva da doença, apresentando lesões nodulares eritemato-violáceas, sendo confirmada fusariose com estudo anatomopatológico e hemocultura para fungos positiva para Cryptococcus laurentii. Realizado tratamento com voriconazol e anfotericina B desoxicolato, obteve pouca resposta. Com a falha terapêutica, foi instituído protocolo de cuidados paliativos, evoluindo com óbito no décimo quinto dia de internação. Considerações finais: A aplasia após infusão da quimioterapia é esperada por volta do décimo dia, sendo que a queda dos glóbulos brancos é um fenômeno preocupante, podendo ser fatal. O estado de neutropenia severa pode deixar o paciente susceptível a infecções, impondo um estado de alerta constante à equipe de saúde assistente.
Goal: Contribute to the knowledge of medical society by identifying the disease and understanding its importance, especially from the point of view of clinical and laboratory diagnosis, with emphasis on clinical manifestations. Methods: The proposed study is a case report, observational and descriptive, developed at Hospital Pronto Socorro da Criança Zona Sul, started in February 2021. The instruments used to collect information were anamnesis and physical examination. during the period in which the patient remained hospitalized in the referred hospital unit -by means of a medical record review. The observation and discussion of the case in the service's multidisciplinary meetings were also part of the data acquisition. The completion of the collection of information took place through the acquisition of secondary data with continuous review of the medical record and photographic record of the diagnostic methods to which the patient was submitted and literature review (until October 18, 2022 in the databases of the PubMed/MedLine with the keywords of this work). All records and information obtained were duly explained and requested from the patient's legal guardian, who by mutual agreement and non-profit signed a free and informed consent form (ICF). Experience report: To reinforce, through a case report, the importance of the clinical manifestations and complementary tests of MIS-C in a child from the Western Amazon and to describe the treatment instituted and the recommended clinical follow-up. Conclusion: Pediatric multisystem inflammatory syndrome was reported in Brazil during the second wave of the COVID-19 pandemic and the importance of such a serious disease requires studies and publications of similar cases in order to identify the factors involved in the etiology of the disease and create a database for correlations of cases and treatments instituted.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.