The Role of cfDNA Biomarkers and Patient Data in the Early Prediction of Preeclampsia: Artificial Intelligence Model

Asma Khalil, Department of Obstetrics and Gynaecology, St. George's University Hospital, University of London, London, England, UK. Electronic address: akhalil@sgul.ac.uk.
Giovanni Bellesia, Natera Inc., Austin, TX, USA.
Mary E. Norton, Department of Obstetrics, Gynecology and Reproductive Sciences, University of California, San Francisco, San Francisco, CA, USA.
Bo Jacobsson, Department of Obstetrics and Gynecology, Institute of Clinical Sciences, Sahlgrenska Academy at the University of Gothenburg, Gothenburg Sweden; Department of Obstetrics and Gynecology, Sahlgrenska University Hospital, Gothenburg Sweden.
Sina Haeri, Austin Maternal-Fetal Medicine, Austin, TX, USA.
Melissa Egbert, Natera Inc., Austin, TX, USA.
Fergal D. Malone, Department of Obstetrics and Gynecology, Rotunda Hospital, Royal College of Surgeons in Ireland, Dublin, Ireland.
Ronald J. Wapner, Department of Obstetrics and Gynecology, Columbia University Irving Medical Center, New York, NY, USA.
Ashley Roman, Department of Obstetrics and Gynecology, New York University Grossman School of Medicine, New York, NY, USA.
Revital Faro, Department of Obstetrics and Gynecology, Saint Peter's University Hospital, New Brunswick, NJ.
Rajeevi Madankumar, Department of Obstetrics and Gynecology, Long Island Jewish Medical Center, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, New Hyde Park, NY, USA.
Noel Strong, Department of Obstetrics and Gynecology, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Robert M. Silver, Department of Obstetrics and Gynecology, University of Utah, Salt Lake City, UT, USA.
Nidhi Vohra, Department of Obstetrics and Gynecology, North Shore University Hospital, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Manhasset, NY, USA.
Jon Hyett, Department of Obstetrics and Gynecology, Royal Prince Alfred Hospital, Western Sydney University, Camperdown, NSW, Australia.
Cora Macpherson, The Biostatistics Center, George Washington University, Rockville, MD, USA.
Brittany Prigmore, Natera Inc., Austin, TX, USA.
Ebad Ahmed, Natera Inc., Austin, TX, USA.
Zach Demko, Natera Inc., Austin, TX, USA.
J Bryce Ortiz, Natera Inc., Austin, TX, USA.
Vivienne Souter, Natera Inc., Austin, TX, USA.
Pe'er Dar, Department of Obstetrics and Gynecology and Women's Health, Montefiore Medical Center, Albert Einstein College of Medicine, The Bronx, NY, USA.

Document Type

Journal Article

Publication Date

3-1-2024

Journal

American journal of obstetrics and gynecology

DOI

10.1016/j.ajog.2024.02.299

Keywords

cell-free DNA; early-onset preeclampsia; fetal fraction; linear neural network; non-invasive prenatal screening; non-linear neural network; pregnancy; preterm preeclampsia; term preeclampsia

Abstract

OBJECTIVE: Accurate individualized assessment of preeclampsia risk enables the identification of patients most likely to benefit from initiation of low-dose aspirin at 12-16 weeks' gestation when there is evidence for its effectiveness, as well as guiding appropriate pregnancy care pathways and surveillance. The primary objective of this study was to evaluate the performance of artificial neural network models for the prediction of preterm preeclampsia (<37 weeks' gestation) using patient characteristics available at the first antenatal visit and data from prenatal cell-free DNA (cfDNA) screening. Secondary outcomes were prediction of early onset preeclampsia (<34 weeks' gestation) and term preeclampsia (≥37 weeks' gestation). METHODS: This secondary analysis of a prospective, multicenter, observational prenatal cfDNA screening study (SMART) included singleton pregnancies with known pregnancy outcomes. Thirteen patient characteristics that are routinely collected at the first prenatal visit and two characteristics of cfDNA, total cfDNA and fetal fraction (FF), were used to develop predictive models for early-onset (<34 weeks), preterm (<37 weeks), and term (≥37 weeks) preeclampsia. For the models, the 'reference' classifier was a shallow logistic regression (LR) model. We also explored several feedforward (non-linear) neural network (NN) architectures with one or more hidden layers and compared their performance with the LR model. We selected a simple NN model built with one hidden layer and made up of 15 units. RESULTS: Of 17,520 participants included in the final analysis, 72 (0.4%) developed early onset, 251 (1.4%) preterm, and 420 (2.4%) term preeclampsia. Median gestational age at cfDNA measurement was 12.6 weeks and 2,155 (12.3%) had their cfDNA measurement at 16 weeks' gestation or greater. Preeclampsia was associated with higher total cfDNA (median 362.3 versus 339.0 copies/ml cfDNA; p<0.001) and lower FF (median 7.5% versus 9.4%; p<0.001). The expected, cross-validated area under the curve (AUC) scores for early onset, preterm, and term preeclampsia were 0.782, 0.801, and 0.712, respectively for the LR model, and 0.797, 0.800, and 0.713, respectively for the NN model. At a screen-positive rate of 15%, sensitivity for preterm preeclampsia was 58.4% (95% CI 0.569, 0.599) for the LR model and 59.3% (95% CI 0.578, 0.608) for the NN model.The contribution of both total cfDNA and FF to the prediction of term and preterm preeclampsia was negligible. For early-onset preeclampsia, removal of the total cfDNA and FF features from the NN model was associated with a 6.9% decrease in sensitivity at a 15% screen positive rate, from 54.9% (95% CI 52.9-56.9) to 48.0% (95% CI 45.0-51.0). CONCLUSION: Routinely available patient characteristics and cfDNA markers can be used to predict preeclampsia with performance comparable to other patient characteristic models for the prediction of preterm preeclampsia. Both LR and NN models showed similar performance.

Department

Epidemiology

Link to Full Text

Share

COinS