A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus

Objective To predict the influencing factors of neonatal pneumonia in pregnant women with diabetes mellitus using a Bayesian network model. By examining the intricate network connections between the numerous variables given by Bayesian networks (BN), this study aims to compare the prediction effect...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	BMC medical research methodology Ročník 23; číslo 1; s. 1 - 12
Hlavní autoři:	Lin, Yue, Chen, Jia Shen, Zhong, Ni, Zhang, Ao, Pan, Haiyan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London BioMed Central 25.10.2023 BioMed Central Ltd Springer Nature B.V BMC
Témata:	Algorithms Amniotic fluid Bacterial pneumonia Bayesian networks Bayesian statistical decision theory Care and treatment Data mining Decision trees Diabetes Diabetes in pregnancy Diabetics Diagnosis Evaluation Gestational diabetes Glucose Health aspects Health Sciences Hypotheses Infants (Newborn) K-Dependence Bayesian Classifier Machine learning Medical research Medicine Medicine & Public Health Naive Bayes network Neonatal pneumonia Newborn babies Pneumonia Pregnancy Pregnant women Probability distribution Random variables Software Statistical Theory and Methods Statistics for Life Sciences Support vector machines Theory of Medicine/Bioethics Tree Augmented Naive Bayes model Womens health China Neonatal pneumonia K-Dependence Bayesian Classifier Naive Bayes network Bayesian networks Tree Augmented Naive Bayes model
ISSN:	1471-2288, 1471-2288
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Objective To predict the influencing factors of neonatal pneumonia in pregnant women with diabetes mellitus using a Bayesian network model. By examining the intricate network connections between the numerous variables given by Bayesian networks (BN), this study aims to compare the prediction effect of the Bayesian network model and to analyze the influencing factors directly associated to neonatal pneumonia. Method Through the structure learning algorithms of BN, Naive Bayesian (NB), Tree Augmented Naive Bayes (TAN), and k-Dependence Bayesian Classifier (KDB), complex networks connecting variables were presented and their predictive abilities were tested. The BN model and three machine learning models computed using the R bnlean package were also compared in the data set. Results In constraint-based algorithms, three algorithms had different presentation DAGs. KDB had a better prediction effect than NB and TAN, and it achieved higher AUC compared with TAN. Among three machine learning modes, Support Vector Machine showed a accuracy rate of 91.04% and 67.88% of precision, which was lower than TAN (92.70%; 72.10%). Conclusion KDB was applicable, and it can detect the dependencies between variables, identify more potential associations and track changes between variables and outcome.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1471-2288 1471-2288
DOI:	10.1186/s12874-023-02070-9