FELIPE YU MATSUSHITA

(Fonte: Lattes)
Índice h a partir de 2011
5
Lattes
ORCID
Projetos de Pesquisa
Unidades Organizacionais
Instituto da Criança, Hospital das Clínicas, Faculdade de Medicina - Médico
Instituto do Coração, Hospital das Clínicas, Faculdade de Medicina - Médico
LIM/36 - Laboratório de Pediatria Clínica, Hospital das Clínicas, Faculdade de Medicina

Filtros

Limpar filtros

Configurações

Revista / Livro: Clinics ×

Resultados de Busca

Agora exibindo 1 - 2 de 2
  • article 1 Citação(ões) na Scopus
    Association between ventilatory settings and pneumothorax in extremely preterm neonates
    (2021) MATSUSHITA, Felipe Y.; KREBS, Vera L. J.; CARVALHO, Werther B. de
    OBJECTIVES: Pneumothorax is a catastrophic event associated with high morbidity and mortality, and it is relatively common in neonates. This study aimed to investigate the association between ventilatory parameters and the risk of developing pneumothorax in extremely low birth weight neonates. METHODS: This single-center retrospective cohort study analyzed 257 extremely low birth weight neonates admitted to a neonatal intensive care unit between January 2012 and December 2017. A comparison was carried out to evaluate the highest value of positive end-expiratory pressure (PEEP), peak inspiratory pressure (PIP), and driving pressure (DP) in the first 7 days of life between neonates who developed pneumothorax and those who did not. The primary outcome was pneumothorax with chest drainage necessity in the first 7 days of life. A matched control group was created in order to adjust for cofounders associated with pneumothorax (CRIB II score, birth weight, and gestational age). RESULTS: There was no statistically significant difference in PEEP, PIP, and DP values in the first 7 days of life between extremely low birth weight neonates who had pneumothorax with chest drainage necessity and those who did not have pneumothorax, even after adjusting for potential cofounders. CONCLUSIONS: Pressure-related ventilatory settings in mechanically ventilated extremely low birth weight neonates are not associated with a higher risk of pneumothorax in the first 7 days of life.
  • article 1 Citação(ões) na Scopus
    Complete blood count and C-reactive protein to predict positive blood culture among neonates using machine learning algorithms
    (2023) MATSUSHITA, Felipe Yu; KREBS, Vera Lucia Jornada; CARVALHO, Werther Brunow de
    Purpose: The authors aimed to develop a Machine-Learning (ML) algorithm that can predict positive blood culture in the neonatal intensive care unit, using complete blood count and C-reactive protein values.Methods: The study was based on patients' electronic health records at a tertiary neonatal intensive care unit in Sao Paulo, Brazil. All blood cultures that had paired complete blood count and C-reactive protein measurements taken at the same time were included. To evaluate the machine learning model's performance, the authors used accuracy, Area Under the Receiver Operating Characteristics (AUROC), recall, precision, and F1-score.Results: The dataset included 1181 blood cultures with paired complete blood count plus c-reactive protein and 1911 blood cultures with paired complete blood count only. The f1-score ranged from 0.14 to 0.43, recall ranged from 0.08 to 0.59, precision ranged from 0.29 to 1.00, and accuracy ranged from 0.688 to 0.864.Conclusion: Complete blood count parameters and C-reactive protein levels cannot be used in ML models to pre-dict bacteremia in newborns.