A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus
Abstract 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 predictio...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-10-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12874-023-02070-9 |
| _version_ | 1797558909153574912 |
|---|---|
| author | Yue Lin Jia Shen Chen Ni Zhong Ao Zhang Haiyan Pan |
| author_facet | Yue Lin Jia Shen Chen Ni Zhong Ao Zhang Haiyan Pan |
| author_sort | Yue Lin |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-03-10T17:37:02Z |
| format | Article |
| id | doaj.art-f067b0945d2e403fb1ce2f54edeb12c4 |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-03-10T17:37:02Z |
| publishDate | 2023-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-f067b0945d2e403fb1ce2f54edeb12c42023-11-20T09:49:36ZengBMCBMC Medical Research Methodology1471-22882023-10-0123111210.1186/s12874-023-02070-9A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitusYue Lin0Jia Shen Chen1Ni Zhong2Ao Zhang3Haiyan Pan4School of Public Health, Guangdong Medical UniversitySchool of Public Health, Guangdong Medical UniversitySchool of Public Health, Guangdong Medical UniversitySchool of Public Health, Guangdong Medical UniversitySchool of Public Health, Guangdong Medical UniversityAbstract 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.https://doi.org/10.1186/s12874-023-02070-9Bayesian networksNeonatal pneumoniaNaive Bayes networkTree Augmented Naive Bayes modelK-Dependence Bayesian Classifier |
| spellingShingle | Yue Lin Jia Shen Chen Ni Zhong Ao Zhang Haiyan Pan A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus BMC Medical Research Methodology Bayesian networks Neonatal pneumonia Naive Bayes network Tree Augmented Naive Bayes model K-Dependence Bayesian Classifier |
| title | A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus |
| title_full | A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus |
| title_fullStr | A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus |
| title_full_unstemmed | A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus |
| title_short | A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus |
| title_sort | bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus |
| topic | Bayesian networks Neonatal pneumonia Naive Bayes network Tree Augmented Naive Bayes model K-Dependence Bayesian Classifier |
| url | https://doi.org/10.1186/s12874-023-02070-9 |
| work_keys_str_mv | AT yuelin abayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT jiashenchen abayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT nizhong abayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT aozhang abayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT haiyanpan abayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT yuelin bayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT jiashenchen bayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT nizhong bayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT aozhang bayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus AT haiyanpan bayesiannetworkperspectiveonneonatalpneumoniainpregnantwomenwithdiabetesmellitus |