• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.17.2020.tde-08022021-150617
Document
Author
Full name
Lorena Aparecida de Brito Rodrigues
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
Ribeirão Preto, 2020
Supervisor
Committee
Basile Filho, Anibal (President)
Moreira, Marcos Mello
Saia, Rafael Simone
Title in Portuguese
O uso do modelo de floresta aleatória para quantificar preditores de risco para requisitos de traqueostomia em pacientes sépticos. Um estudo de coorte retrospectivo
Keywords in Portuguese
Desfecho
SAPS 3
Sepse
SOFA
Traqueostomia
UTI
Abstract in Portuguese
A busca de fatores de risco clínicos precoces no contexto dos cuidados intensivos pode melhorar a sobrevida de pacientes criticamente enfermos. Os objetivos deste estudo retrospectivo é comparar os pacientes com sepse internados na UTI, identificando precocemente os preditores para os pacientes que teriam a necessidade de se submeter à traqueostomia e os quantificando. Métodos: Todos os dados de diagnóstico de chegada na UTI, bem como as variáveis clínicas e fisiológicas foram registradas. As curvas de calibração para o SAPS3 e o SOFA foram construídas para melhorar os seus desempenhos, sendo utilizado o teste de Hosmer-Lemeshow que se baseia na comparação entre as probabilidades preditas e os resultados observados. As comparações de dados demográficos e clínicos dos quinhentos e quarenta e quatro pacientes sépticos que foram divididos em dois grupos: não-traqueostomizados (NT) (n = 484) e traqueostomizados (T) (n = 60), consistituindo em 241 (49,8%) para o grupo não traqueostomizados e 27 (45%) para o grupo traqueostomizados, foram realizados o teste para duas amostras independentes (rank-sum) de Mann-Whitney para as variáveis quantitativas e o teste exato de Fisher para as variáveis qualitativas. Resultados: A mediana e a diferença interquartil para a idade de NT grupo era de 72 anos [59-82] e T de 75 [55,0-83,5] (P = 0,4687). O SAPS 3 para o grupo NTxT foi de 70 [55-85] e 85,5 [77-91] (P = 0,0001), o sofá de 9 [6-13] e 12 [10-14] (P = 0,0002). A comparação da análise de regressão logística para preditores de grupos não-traqueostomia e de traqueostomia mostrou um odds ratio ajustado (OR) para o SAPS 3 entre 74 e 87 de 18,14 (95%IC = 3,36- 97,84) e entre 88-116 de 27,77 (95%IC = 4,43-174,24) (P <0,05). Para o SOFA o OR ajustado entre 10-13 foi 12,23 (95%IC = 2,46-60,81) e entre 14 e 20 foi de 8,45 (95%IC = 1,58-45,29) (P <0,05). A necessidade de transfusões de sangue e diálise apresentaram um OR de 2,74 (95%IC = 1,23-6,08) e 3,33 (95%IC = 1,43-7,73) (P <0,05), respectivamente. Conclusão: Os nossos dados mostram que SAPS 3 ≥ 74, SOFA ≥ 11, transfusões de sangue e necessidade de diálise foram fatores independentemente associados e podem ser considerados preditores para requisitos de traqueostomia em pacientes sépticos.
Title in English
The use of the random forest model to quantify risk predictors for tracheostomy requirements in septic patients. A retrospective cohort study
Keywords in English
ICU setting
Outcome
SAPS 3
Sepsis
SOFA
Tracheostomy
Abstract in English
The search for early clinical risk factors in the context of intensive care may improve outcomes for critically ill patients. The aim of this retrospective study is to compare patients with sepsis outcomes admitted to the ICU, early identifying predictors for patients requiring tracheostomy and quantifying them. Methods: All data on the diagnosis of arrival at the ICU, as well as the clinical and physiological variables were recorded. The SAPS3 and SOFA calibration was built to improve the performance of the scores, using the Hosmer-Lemeshow test based on the comparison between the predicted probabilities and the observed results. Comparisons of demographic and clinical data of the five hundred and forty-four septic patients who were divided into two groups: non-tracheostomized (NT) (n = 484) and tracheostomized (T) (n = 60), consisting of 241 (49.8%) for the non-tracheostomized group and 27 (45%) for the tracheostomized group, were performed using the Mann-Whitney test for two independent samples for quantitative variables and Fisher's exact test for variables qualitative. Results: The median and interquartile age range difference of NT group was 72 years [59-82] and T of 75 [55.0-83.5] (P = 0.4687). The SAPS 3 for the NTxT group was 70 [55-85] and 85.5 [77-91] (P = 0.0001), the SOFA 9 [6-13] and 12 [10-14] (P = 0.0002). Comparison of logistic regression analysis for predictors of non-tracheostomy and tracheostomy groups showed an adjusted odds ratio (OR) for SAPS 3 range between 74 and 87 of 18.14 (95%CI = 3.36-97.84) and between 88-116 of 27.77 (95%CI = 4.43-174.24) (P <0.05). For SOFA OR adjusted between 10 and 13 was 12.23 (95%CI = 2.46-60.81) and between 14 and 20 was 8.45 (95%CI = 1.58- 45.29) (P <0.05). The need for blood transfusions and dialysis presented an OR of 2.74 (95% CI = 1.23-6.08) and 3.33 (95%CI = 1.43-7.73) (P < 0.05), respectively. Conclusion: Our data showed that SAPS 3 ≥ 74, SOFA ≥ 11, blood transfusions, and the need for dialysis were independently associated and can be considered major predictors for tracheostomy requirements in septic patients.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2021-03-26
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.