Factor analysis and risk prediction of postpartum hemorrhage in pregnant women.
Postpartum hemorrhage (PPH) remains the leading cause of maternal mortality and a common obstetric complication. Rapid onset and severity can lead to hemorrhagic shock and fatal outcomes if not promptly managed. Major causes include uterine atony, placental abnormalities, birth canal trauma, and coa...
| Publicado en: | African Journal of Reproductive Health Vol. 30; no. 1; pp. 29 - 37 |
|---|---|
| Autores principales: | , , |
| Formato: | equations & formulas research tables/charts Journal Article |
| Publicado: |
Women's Health & Action Research Centre
Jan2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=190875925&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 190875925 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 11184841 G7W jtl: African Journal of Reproductive Health issn: 11184841 maglogo: N pubinfo: dt: Jan2026 vid: 30 iid: 1 pid: 12182 pub: Women's Health & Action Research Centre place: Benin City Edostate 234, <Blank> artinfo: ui: 190875925 190875925 190875925 10.29063/ajrh2026/v30i1.4 190875925 ppf: 29 ppct: 8 formats: tig: atl: Factor analysis and risk prediction of postpartum hemorrhage in pregnant women. aug: au: Kang, Xiaodi Zhang, Yawei Li, Li affil: Department of Obstetrics, Beijing Ditan Hospital Affiliated to Capital Medical University, 100015, Beijing; China sug: subj: Postpartum Hemorrhage Risk Factors Expectant Mothers Psychosocial Factors Prediction Models Deep Learning Neural Networks (Computer) Electronic Health Records Risk Assessment China Human Female Adult Pregnancy Models, Theoretical Sensitivity and Specificity Logistic Regression Early Diagnosis Algorithms Factor Analysis Postpartum Hemorrhage Diagnosis Postpartum Hemorrhage Epidemiology Postpartum Hemorrhage Etiology Academic Medical Centers Descriptive Statistics Retrospective Design Record Review Prospective Studies Adult: 19-44 years Female ab: Postpartum hemorrhage (PPH) remains the leading cause of maternal mortality and a common obstetric complication. Rapid onset and severity can lead to hemorrhagic shock and fatal outcomes if not promptly managed. Major causes include uterine atony, placental abnormalities, birth canal trauma, and coagulation disorders. This study proposes a risk prediction model for PPH based on a Deep Belief Network (DBN), using relevant risk factors as input features. To address limitations from random initialization in the DBN, an improved Particle Swarm Optimization (IPSO) algorithm--featuring adaptive inertia weight and learning factors-- was introduced to optimize network parameters. The optimized model, referred to as IDBN, was applied to predict PPH risk levels more accurately and efficiently. The results demonstrate the superior performance of the IDBN method, which achieved the highest accuracy and F1 score among all models evaluated. This approach offers a novel, data-driven method for early PPH risk identification and clinical intervention. L'hémorragie du post-partum (HPP) demeure la principale cause de mortalité maternelle ainsi qu'une complication obstétricale fréquente. Son apparition rapide et sa gravité peuvent entraîner un choc hémorragique et des issues fatales si elle n'est pas prise en charge rapidement. Les causes majeures incluent l'atonie utérine, les anomalies placentaires, les traumatismes du canal génital et les troubles de la coagulation. Cette étude propose un modèle de prédiction du risque de HPP basé sur un Réseau de Croyance Profond (Deep Belief Network, DBN), utilisant des facteurs de risque pertinents comme variables d'entrée. Afin de pallier les limitations dues à l'initialisation aléatoire dans le DBN, un algorithme amélioré d'optimisation par essaim particulaire (IPSO) -- intégrant un poids d'inertie adaptatif et des facteurs d'apprentissage modulables -- a été introduit pour optimiser les paramètres du réseau. Le modèle optimisé, nommé IDBN, a été appliqué pour prédire les niveaux de risque de HPP de manière plus précise et efficace. Les résultats démontrent les performances supérieures de la méthode IDBN, qui a obtenu les meilleurs scores en termes de précision et de F1 parmi tous les modèles évalués. Cette approche offre une méthode innovante et fondée sur les données pour l'identification précoce du risque de HPP et pour guider les interventions cliniques. pubtype: Academic Journal doctype: equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|