Preterm birth (PTB) is defined as delivery occurring before 37 weeks of gestation. In this paper, Artificial Intelligence (AI)-based predictive models are adapted to accurately estimate the probability of PTB. In doing so, pregnant women' objective results and variables extracted from the screening procedure in combination with demographics, medical history, social history, and other medical data are used. A dataset consisting of 375 pregnant women is used and a number of alternative Machine Learning (ML) algorithms are applied to predict PTB. The ensemble voting model produced the best results across all performance metrics with an area under the curve (ROC-AUC) of approximately 0.84 and a precision-recall curve (PR-AUC) of approximately 0.73. An attempt to provide clinicians with an explanation of the prediction is performed to increase trustworthiness.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.3233/SHTI230207 | DOI Listing |
BMC Pregnancy Childbirth
December 2024
Kumamoto University Regional Centre, The Japan Environment and Children's Study (JECS), 718, Medical Research Building, 1-1-1 Honjo, Chuo-ku, Kumamoto, Kumamoto, 860-8556, Japan.
Background: Antinuclear antibodies (ANA) are important biomarkers for the diagnosis of autoimmune diseases; however, the general population also tests positive at a low frequency, especially in women. Although the effects of various autoimmune diseases on pregnancy outcomes have been studied, the association of ANA with pregnancy outcomes in healthy individuals is unclear. Preterm birth (PTB), a major cause of neonatal death or long-term health problems, is a complex condition with a multifactorial etiology, and the underlying mechanism remains unclear.
View Article and Find Full Text PDFBMC Pediatr
December 2024
Department of Nursing and Midwifery, College of Health, Wellbeing and Life Sciences, Sheffield Hallam University, Sheffield, UK.
Background: Despite progress made towards SDG 3, sub-Saharan Africa lags behind the rest of the world, accounting for over 50% of global neonatal deaths. The increased number of hospital births in the region has not reciprocated the reduction in neonatal mortality rates. Sick newborns face uncertain journeys from peripheral facilities to specialized centres arriving in suboptimal conditions, which impacts their outcomes, due partly to the scarcity of dedicated neonatal transport services.
View Article and Find Full Text PDFBMC Pediatr
December 2024
Department of Nursing, Shenzhen People's Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, Guangdong, China.
Background: Birth asphyxia is a critical condition caused by an insufficient oxygen supply during delivery, and it poses a major threat to the health of newborns. The present meta-analysis aimed to estimate the prevalence of birth asphyxia among neonates and identify its risk factors in China.
Methods: PubMed, EMBASE, Scopus, Web of Science, the China Academic Journals (CNKI), the Chinese Biomedical Literature (CBM), the China Science and Technology Journal Database (VIP), and the WanFang database were searched for related publications.
Eur J Obstet Gynecol Reprod Biol
November 2024
Department of Obstetrics and Gynecology, The Coombe Hospital, Dublin, Ireland.
Objectives: To examine the influence of the season of conception, and the season of birth on the incidence of preterm birth (PTB) and neonatal outcomes.
Study Design: This is a single center, retrospective cohort study of singleton births that took place in The Coombe Hospital in Dublin, Ireland, between January 2013 and December 2022. A comprehensive database was analyzed to determine the incidence of PTB per season of conception and season of birth.
Int J Gynaecol Obstet
December 2024
Department of Obstetrics and Gynecology, Nord Hospital, APHM, Chemin Des Bourrely, Marseille, France.
Objective: This study investigates whether early gestational age (GA) at delivery is associated with an increased risk for severe maternal morbidity (SMM) in women with preterm delivery.
Methods: This retrospective national cohort study based on the Programme de Médicalisation des Systèmes d'Information database included mothers who gave birth between 22 and 37 weeks in metropolitan France in 2019 (in utero deaths and medical terminations of pregnancies were excluded). SMM was defined as a composite criterion consisting of the occurrence of at least one of the following events: death, severe preeclampsia, obstetric surgical complications, severe maternal diseases, and admission to the intensive care unit.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!