EUVIMEDEUVIMED entdecken
Open Access

Machine Learning Models for Prediction of Maternal Hemorrhage and Transfusion: Model Development Study

Homa Khorrami Ahmadzia iD, Alexa C Dzienny iD, Mike Bopf iD, Jaclyn M Phillips iD, Jerome Jeffrey Federspiel iD, Richard Amdur iD, Madeline Murguia Rice iD, Laritza Rodriguez iD

JMIR Bioinformatics and Biotechnology · 05.02.2024 · 5 · e52059

DOI: 10.2196/52059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Bioinformatics and Biotechnology, online erschienen am 05.02.2024. Verfasst von Homa Khorrami Ahmadzia und 7 weiteren Autor:innen. Beteiligte Einrichtung: Division of Maternal-Fetal Medicine, Department of Obstetrics and Gynecology, George Washington University, Washington, DC, United States. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Current postpartum hemorrhage (PPH) risk stratification is based on traditional statistical models or expert opinion. Machine learning could optimize PPH prediction by allowing for more complex modeling.

Objective

We sought to improve PPH prediction and compare machine learning and traditional statistical methods.

Methods

We developed models using the Consortium for Safe Labor data set (2002-2008) from 12 US hospitals. The primary outcome was a transfusion of blood products or PPH (estimated blood loss of ≥1000 mL). The secondary outcome was a transfusion of any blood product. Fifty antepartum and intrapartum characteristics and hospital characteristics were included. Logistic regression, support vector machines, multilayer perceptron, random forest, and gradient boosting (GB) were used to generate prediction models. The area under the receiver operating characteristic curve (ROC-AUC) and area under the precision/recall curve (PR-AUC) were used to compare performance.

Results

Among 228,438 births, 5760 (3.1%) women had a postpartum hemorrhage, 5170 (2.8%) had a transfusion, and 10,344 (5.6%) met the criteria for the transfusion-PPH composite. Models predicting the transfusion-PPH composite using antepartum and intrapartum features had the best positive predictive values, with the GB machine learning model performing best overall (ROC-AUC=0.833, 95% CI 0.828-0.838; PR-AUC=0.210, 95% CI 0.201-0.220). The most predictive features in the GB model predicting the transfusion-PPH composite were the mode of delivery, oxytocin incremental dose for labor (mU/minute), intrapartum tocolytic use, presence of anesthesia nurse, and hospital type.

Conclusions

Machine learning offers higher discriminability than logistic regression in predicting PPH. The Consortium for Safe Labor data set may not be optimal for analyzing risk due to strong subgroup effects, which decreases accuracy and limits generalizability.

Schlagwörter

Stichwörter der Autor:innen

antepartumbirthbleedingbloodgynecologicalgynecologyhemorrhagehemorrhagingmachine learningmaternalobstetricobstetricspostnatalpostpartum hemorrhagepredict

Autor:innen und Institutionen

  • Division of Maternal-Fetal Medicine, Department of Obstetrics and Gynecology, George Washington University, Washington, DC, United States.
  • Division of Maternal-Fetal Medicine, Department of Obstetrics and Gynecology, Inova Health System, Falls Church, VA, United States.
  • The George Washington University School of Medicine and Health Sciences,, Washington DC, DC, United States.
  • Lister Hill National Center for Biomedical Communications, U.S. National Library of Medicine, Bethesda, MD, United States.
  • Division of Maternal-Fetal Medicine, Department of Obstetrics and Gynecology, Duke University, Durham, NC, United States.
  • Medical Faculty Associates, The George Washington University School of Medicine and Health Sciences, Washington, DC, United States.

ORCID-Profile: Homa Khorrami Ahmadzia, Alexa C Dzienny, Mike Bopf, Jaclyn M Phillips, Jerome Jeffrey Federspiel, Richard Amdur, Madeline Murguia Rice, Laritza Rodriguez

Zitieren

APA

Ahmadzia, H. K., Dzienny, A. C., Bopf, M., Phillips, J. M., Federspiel, J. J., Amdur, R., Rice, M. M., & Rodriguez, L. (2024). Machine Learning Models for Prediction of Maternal Hemorrhage and Transfusion: Model Development Study. JMIR Bioinformatics and Biotechnology, 5, e52059. https://doi.org/10.2196/52059

Vancouver

Ahmadzia HK, Dzienny AC, Bopf M, Phillips JM, Federspiel JJ, Amdur R, et al. Machine Learning Models for Prediction of Maternal Hemorrhage and Transfusion: Model Development Study. JMIR Bioinformatics and Biotechnology. 2024;5:e52059. doi:10.2196/52059

BibTeX
@article{Ahmadzia2024,
  author = {Ahmadzia, Homa Khorrami and Dzienny, Alexa C and Bopf, Mike and Phillips, Jaclyn M and Federspiel, Jerome Jeffrey and Amdur, Richard and Rice, Madeline Murguia and Rodriguez, Laritza},
  title = {Machine Learning Models for Prediction of Maternal Hemorrhage and Transfusion: Model Development Study},
  journal = {JMIR Bioinformatics and Biotechnology},
  year = {2024},
  volume = {5},
  pages = {e52059},
  doi = {10.2196/52059}
}
Kostenlos starten →