Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort
Main Author: | |
---|---|
Publication Date: | 2024 |
Other Authors: | , , , , , |
Format: | preprint |
Language: | eng |
Source: | SciELO Preprints |
Download full: | https://preprints.scielo.org/index.php/scielo/preprint/view/7882 |
Summary: | Problem: Preterm birth is the leading cause of death and can result in significant long-term loss of physical and psychological capacity among survivors.Background: An estimated 15 million babies are born preterm every year. Prediction models based on machine learning methods have reported promising results.Aims: To identify risk factors associated with preterm birth and to develop and validate a prediction model for this outcome in a Brazilian birth cohort.Methods: Cross-sectional study of all births that occurred in Ribeirão Preto-SP and of one in three births that occurred in São Luís-MA, Brazil, in 2010. Questionnaires were applied to obtain pregnancy-related data. Multivariate adaptive regression splines were used to determine the independent variables. Preterm birth, defined as birth before 37 weeks gestational age, was the dependent variable. A random forest model was developed and its performance was evaluated by ROC analysis.Findings: The preterm birth rates were 12.7% (RP) and 14.1% (SL). The prediction and validation accuracies of the RF-based model were 91.3% and 85.5% respectively. The model can be applied starting in the third month of gestation and is more effective in identifying preterm infants with GA<31 weeks and 6 days (AUC=0.98).Discussion: It was possible to build a prediction model based on easily accessible low-cost data, without the need for complementary tests, providing results similar to those of other studies.Conclusions: Previous preterm birth and prenatal care were determinants. The use of an application for individualized patient monitoring an early stage can have positive effects on the quality of life of mother and child. |
id |
SCI-1_8cf617c1954d42d3d37562354a474ada |
---|---|
oai_identifier_str |
oai:ops.preprints.scielo.org:preprint/7882 |
network_acronym_str |
SCI-1 |
network_name_str |
SciELO Preprints |
repository_id_str |
|
spelling |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohortPreterm birthperinatal healthhealth policiesprediction modelsmachine learningProblem: Preterm birth is the leading cause of death and can result in significant long-term loss of physical and psychological capacity among survivors.Background: An estimated 15 million babies are born preterm every year. Prediction models based on machine learning methods have reported promising results.Aims: To identify risk factors associated with preterm birth and to develop and validate a prediction model for this outcome in a Brazilian birth cohort.Methods: Cross-sectional study of all births that occurred in Ribeirão Preto-SP and of one in three births that occurred in São Luís-MA, Brazil, in 2010. Questionnaires were applied to obtain pregnancy-related data. Multivariate adaptive regression splines were used to determine the independent variables. Preterm birth, defined as birth before 37 weeks gestational age, was the dependent variable. A random forest model was developed and its performance was evaluated by ROC analysis.Findings: The preterm birth rates were 12.7% (RP) and 14.1% (SL). The prediction and validation accuracies of the RF-based model were 91.3% and 85.5% respectively. The model can be applied starting in the third month of gestation and is more effective in identifying preterm infants with GA<31 weeks and 6 days (AUC=0.98).Discussion: It was possible to build a prediction model based on easily accessible low-cost data, without the need for complementary tests, providing results similar to those of other studies.Conclusions: Previous preterm birth and prenatal care were determinants. The use of an application for individualized patient monitoring an early stage can have positive effects on the quality of life of mother and child.SciELO PreprintsSciELO PreprintsSciELO Preprints2024-01-15info:eu-repo/semantics/preprintinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://preprints.scielo.org/index.php/scielo/preprint/view/788210.1590/SciELOPreprints.7882enghttps://preprints.scielo.org/index.php/scielo/article/view/7882/14757Copyright (c) 2024 Gabriel Bazo, Ricardo Zorzetto N. Vêncio, Paulo Ricardo H. Rocha, Ricardo Cavalli, Alexandre Ferraro, Heloisa Bettiol, Marco Antonio Barbierihttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessBazo, GabrielVêncio, Ricardo Zorzetto N.Rocha, Paulo Ricardo H.Cavalli, RicardoFerraro, AlexandreBettiol, HeloisaBarbieri, Marco Antonioreponame:SciELO Preprintsinstname:Scientific Electronic Library Online (SCIELO)instacron:SCI2024-01-11T17:55:21Zoai:ops.preprints.scielo.org:preprint/7882Servidor de preprintshttps://preprints.scielo.org/index.php/scieloONGhttps://preprints.scielo.org/index.php/scielo/oaiscielo.submission@scielo.orgopendoar:2024-01-11T17:55:21SciELO Preprints - Scientific Electronic Library Online (SCIELO)false |
dc.title.none.fl_str_mv |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort |
title |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort |
spellingShingle |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort Bazo, Gabriel Preterm birth perinatal health health policies prediction models machine learning |
title_short |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort |
title_full |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort |
title_fullStr |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort |
title_full_unstemmed |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort |
title_sort |
Risk factors associated with preterm birth: identification, prediction and evaluation in the BRISA cohort |
author |
Bazo, Gabriel |
author_facet |
Bazo, Gabriel Vêncio, Ricardo Zorzetto N. Rocha, Paulo Ricardo H. Cavalli, Ricardo Ferraro, Alexandre Bettiol, Heloisa Barbieri, Marco Antonio |
author_role |
author |
author2 |
Vêncio, Ricardo Zorzetto N. Rocha, Paulo Ricardo H. Cavalli, Ricardo Ferraro, Alexandre Bettiol, Heloisa Barbieri, Marco Antonio |
author2_role |
author author author author author author |
dc.contributor.author.fl_str_mv |
Bazo, Gabriel Vêncio, Ricardo Zorzetto N. Rocha, Paulo Ricardo H. Cavalli, Ricardo Ferraro, Alexandre Bettiol, Heloisa Barbieri, Marco Antonio |
dc.subject.por.fl_str_mv |
Preterm birth perinatal health health policies prediction models machine learning |
topic |
Preterm birth perinatal health health policies prediction models machine learning |
description |
Problem: Preterm birth is the leading cause of death and can result in significant long-term loss of physical and psychological capacity among survivors.Background: An estimated 15 million babies are born preterm every year. Prediction models based on machine learning methods have reported promising results.Aims: To identify risk factors associated with preterm birth and to develop and validate a prediction model for this outcome in a Brazilian birth cohort.Methods: Cross-sectional study of all births that occurred in Ribeirão Preto-SP and of one in three births that occurred in São Luís-MA, Brazil, in 2010. Questionnaires were applied to obtain pregnancy-related data. Multivariate adaptive regression splines were used to determine the independent variables. Preterm birth, defined as birth before 37 weeks gestational age, was the dependent variable. A random forest model was developed and its performance was evaluated by ROC analysis.Findings: The preterm birth rates were 12.7% (RP) and 14.1% (SL). The prediction and validation accuracies of the RF-based model were 91.3% and 85.5% respectively. The model can be applied starting in the third month of gestation and is more effective in identifying preterm infants with GA<31 weeks and 6 days (AUC=0.98).Discussion: It was possible to build a prediction model based on easily accessible low-cost data, without the need for complementary tests, providing results similar to those of other studies.Conclusions: Previous preterm birth and prenatal care were determinants. The use of an application for individualized patient monitoring an early stage can have positive effects on the quality of life of mother and child. |
publishDate |
2024 |
dc.date.none.fl_str_mv |
2024-01-15 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/preprint info:eu-repo/semantics/publishedVersion |
format |
preprint |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://preprints.scielo.org/index.php/scielo/preprint/view/7882 10.1590/SciELOPreprints.7882 |
url |
https://preprints.scielo.org/index.php/scielo/preprint/view/7882 |
identifier_str_mv |
10.1590/SciELOPreprints.7882 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://preprints.scielo.org/index.php/scielo/article/view/7882/14757 |
dc.rights.driver.fl_str_mv |
https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
SciELO Preprints SciELO Preprints SciELO Preprints |
publisher.none.fl_str_mv |
SciELO Preprints SciELO Preprints SciELO Preprints |
dc.source.none.fl_str_mv |
reponame:SciELO Preprints instname:Scientific Electronic Library Online (SCIELO) instacron:SCI |
instname_str |
Scientific Electronic Library Online (SCIELO) |
instacron_str |
SCI |
institution |
SCI |
reponame_str |
SciELO Preprints |
collection |
SciELO Preprints |
repository.name.fl_str_mv |
SciELO Preprints - Scientific Electronic Library Online (SCIELO) |
repository.mail.fl_str_mv |
scielo.submission@scielo.org |
_version_ |
1797047814759383040 |