Chi-square automatic interaction detector decision tree analysis model: Predicting cefmetazole response in intra-abdominal infection.
Cefmetazole
Decision tree analysis
Intra-abdominal infections
Prediction model
Journal
Journal of infection and chemotherapy : official journal of the Japan Society of Chemotherapy
ISSN: 1437-7780
Titre abrégé: J Infect Chemother
Pays: Netherlands
ID NLM: 9608375
Informations de publication
Date de publication:
Jan 2023
Jan 2023
Historique:
received:
30
05
2022
revised:
27
07
2022
accepted:
03
09
2022
pubmed:
12
9
2022
medline:
19
11
2022
entrez:
11
9
2022
Statut:
ppublish
Résumé
Cefmetazole is used as the first-line treatment for intra-abdominal infections. However, only a few studies have investigated the risk factors for cefmetazole treatment failure. This study aimed to develop a decision tree-based predictive model to assess the effectiveness of cefmetazole in initial intra-abdominal infection treatment to improve the clinical treatment strategies. This retrospective cohort study included adult patients who were unexpectedly hospitalized due to intra-abdominal infections between 2003 and 2020 and initially treated with cefmetazole. The primary outcome was clinical intra-abdominal infection improvement. The chi-square automatic interaction detector decision tree analysis was used to create a predictive model for clinical improvement after cefmetazole treatment. Among 2,194 patients, 1,807 (82.4%) showed clinical improvement post-treatment; their mean age was 48.7 (standard deviation: 18.8) years, and 1,213 (55.3%) patients were men. The intra-abdomせinal infections were appendicitis (n = 1,186, 54.1%), diverticulitis (n = 334, 15.2%), and pancreatitis (n = 285, 13.0%). The chi-square automatic interaction detector decision tree analysis identified the intra-abdominal infection type, C-reactive protein level, heart rate, and body temperature as predictive factors by categorizing patients into seven groups. The area under the receiver operating characteristic curve was 0.71 (95% confidence interval: 0.68-0.73). This predictive model is easily understandable visually and may be applied in clinical practice.
Sections du résumé
BACKGROUND
BACKGROUND
Cefmetazole is used as the first-line treatment for intra-abdominal infections. However, only a few studies have investigated the risk factors for cefmetazole treatment failure.
AIMS
OBJECTIVE
This study aimed to develop a decision tree-based predictive model to assess the effectiveness of cefmetazole in initial intra-abdominal infection treatment to improve the clinical treatment strategies.
METHODS
METHODS
This retrospective cohort study included adult patients who were unexpectedly hospitalized due to intra-abdominal infections between 2003 and 2020 and initially treated with cefmetazole. The primary outcome was clinical intra-abdominal infection improvement. The chi-square automatic interaction detector decision tree analysis was used to create a predictive model for clinical improvement after cefmetazole treatment.
RESULTS
RESULTS
Among 2,194 patients, 1,807 (82.4%) showed clinical improvement post-treatment; their mean age was 48.7 (standard deviation: 18.8) years, and 1,213 (55.3%) patients were men. The intra-abdomせinal infections were appendicitis (n = 1,186, 54.1%), diverticulitis (n = 334, 15.2%), and pancreatitis (n = 285, 13.0%). The chi-square automatic interaction detector decision tree analysis identified the intra-abdominal infection type, C-reactive protein level, heart rate, and body temperature as predictive factors by categorizing patients into seven groups. The area under the receiver operating characteristic curve was 0.71 (95% confidence interval: 0.68-0.73).
CONCLUSION
CONCLUSIONS
This predictive model is easily understandable visually and may be applied in clinical practice.
Identifiants
pubmed: 36089256
pii: S1341-321X(22)00255-0
doi: 10.1016/j.jiac.2022.09.002
pii:
doi:
Substances chimiques
Cefmetazole
3J962UJT8H
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
7-14Informations de copyright
Copyright © 2022 Japanese Society of Chemotherapy and The Japanese Association for Infectious Diseases. Published by Elsevier Ltd. All rights reserved.
Déclaration de conflit d'intérêts
Declaration of competing interest The authors have no relevant financial or non-financial interests to disclose.