Identifying risk of stillbirth using machine learning - 25/08/23
, Nina K. Ayala, MD, ScM a, Halit Pinar, MD b, Donald J. Dudley, MD c, George R. Saade, MD d, Robert M. Silver, MD e, Adam K. Lewkowitz, MD, MPHS aAbstract |
Background |
Previous predictive models using logistic regression for stillbirth do not leverage the advanced and nuanced techniques involved in sophisticated machine learning methods, such as modeling nonlinear relationships between outcomes.
Objective |
This study aimed to create and refine machine learning models for predicting stillbirth using data available before viability (22–24 weeks) and throughout pregnancy, as well as demographic, medical, and prenatal visit data, including ultrasound and fetal genetics.
Study Design |
This is a secondary analysis of the Stillbirth Collaborative Research Network, which included data from pregnancies resulting in stillborn and live-born infants delivered at 59 hospitals in 5 diverse regions across the United States from 2006 to 2009. The primary aim was the creation of a model for predicting stillbirth using data available before viability. Secondary aims included refining models with variables available throughout pregnancy and determining variable importance.
Results |
Among 3000 live births and 982 stillbirths, 101 variables of interest were identified. Of the models incorporating data available before viability, the random forests model had 85.1% accuracy (area under the curve) and high sensitivity (88.6%), specificity (85.3%), positive predictive value (85.3%), and negative predictive value (84.8%). A random forests model using data collected throughout pregnancy resulted in accuracy of 85.0%; this model had 92.2% sensitivity, 77.9% specificity, 84.7% positive predictive value, and 88.3% negative predictive value. Important variables in the previability model included previous stillbirth, minority race, gestational age at the earliest prenatal visit and ultrasound, and second-trimester serum screening.
Conclusion |
Applying advanced machine learning techniques to a comprehensive database of stillbirths and live births with unique and clinically relevant variables resulted in an algorithm that could accurately identify 85% of pregnancies that would result in stillbirth, before they reached viability. Once validated in representative databases reflective of the US birthing population and then prospectively, these models may provide effective risk stratification and clinical decision-making support to better identify and monitor those at risk of stillbirth.
Le texte complet de cet article est disponible en PDF.Key words : boosted trees, clinical decision-making, factor analysis, prenatal care, previability, random forests, second-trimester prenatal screen (Down syndrome risk, unconjugated estriol, maternal serum alpha-fetoprotein), structural racism, ultrasound
Plan
| The authors report no conflict of interest. |
|
| This study was supported by funding from the Eunice Kennedy Shriver National Institute of Child Health and Human Development (grant numbers U10-HD045953 [Brown University, Providence, RI], U10-HD045925 [Emory University, Atlanta, GA], U10-HD045952 [University of Texas Medical Branch, Galveston, TX], U10-HDO45955 [University of Texas Health Science Center at San Antonio, San Antonio, TX], U10-HD045944 [University of Utah Health Sciences Center, Salt Lake City, UT], and U01-HD045954 [RTI International, Research Triangle Park, NC]). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. |
|
| This study was presented at the 43rd Annual Pregnancy Meeting of the Society for Maternal-Fetal Medicine, San Francisco, CA, February 6–11, 2023. |
|
| Cite this article as: Cersonsky TEK, Ayala NK, Pinar H, et al. Identifying risk of stillbirth using machine learning. Am J Obstet Gynecol 2023;229:327.e1-16. |
Vol 229 - N° 3
P. 327.e1-327.e16 - septembre 2023 Retour au numéro
Article précédent
- The value of detailed first-trimester ultrasound in the era of noninvasive prenatal testing
- Kristyn M. Esteves, Nicol Tugarinov, Grace Lechmann, Paola Abi Habib, Erkan Cagliyan, Katherine R. Goetzinger, Ozhan M. Turan, Sifa Turan
- Preventing eviction during pregnancy: a cost-effectiveness analysis of a theoretical safety-net program
- Ava Mandelbaum, Sarah Dzubay, Sarina R. Chaiken, Uma Doshi, Isabel Katlaps, Aaron B. Caughey
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?