Evaluating the Performance of Traditional Pharmacoepidemiologic and Machine Learning Models to Predict Pregnancies at Risk of Major Congenital Malformations
Birth Defects Research · 2026
DOI: 10.1002/bdr2.70117 ↗Kurz gefasst
Fachartikel in der Zeitschrift Birth Defects Research, 2026. Verfasst von Gabra Nohmie und 7 weiteren Autor:innen. Beteiligte Einrichtung: Medications and Pregnancy Unit, CHU Sainte-Justine Azrieli Research Center, Montréal, Quebec, Canada. Hauptthemen laut MEDLINE: Pharmacoepidemiology, Machine Learning, Congenital Abnormalities. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Background
With approximately 50% of pregnancies being unplanned, there is an unintended exposure to potential feto‐toxic drugs that may cause major congenital malformations (MCM). This study aims to compare the predictive performance between traditional pharmacoepidemiologic (PE) and machine learning (ML) models.
Methods
We conducted a cohort study within the Quebec Pregnancy Cohort, including all pregnancies covered by Quebec's prescription drug insurance program and their children from 01/1998 to 12/2015. Medication exposures, comorbidities, and women's characteristics 12 months before pregnancy and during the first trimester were considered. Robust Poisson models were used to obtain adjusted risk ratios (aRR) and 95% confidence intervals (CI) of predictors. Logistic regression, robust Poisson, K‐Nearest Neighbors, Random Forest, XGBoost, Naïve bayes, Multilayer Perceptron, and Support Vector Machine were developed to predict pregnancies at risk of MCM. Sensitivity, specificity, PPV, NPV, accuracy, ROC‐AUCs, PR‐AUCs, and F1‐score were used to evaluate the performance of predictive models.
Results
We analyzed 213,744 pregnancies, finding a 9.7% prevalence of MCM. Logistic regression had the highest discriminative power across models at predicting MCM, with a ROC‐AUC of 53.3% and the highest sensitivity (41.5%) and F1‐score (46.6%). KNN had the highest specificity (97.9%) but the lowest sensitivity (2.3%). Robust Poisson performed similarly to logistic regression, with the highest accuracy (52.3%). Robust Poisson performed slightly better than logistic regression at classifying organ‐specific malformations. All models showed poor overall predictive performance. Results were robust across sensitivity analyses.
Conclusion
There is insufficient evidence for the superiority of ML over traditional pharmacoepidemiologic modeling in predicting MCM.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Medications and Pregnancy Unit, CHU Sainte-Justine Azrieli Research Center, Montréal, Quebec, Canada.
- Faculty of Pharmacy, University of Montréal, Montréal, Quebec, Canada.
- Faculty of Arts and Sciences, University of Montréal, Montréal, Quebec, Canada.
- Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montréal, Quebec, Canada.
- Canada CIFAR AI Chair, Mila Québec AI Institute, Montréal, Quebec, Canada.
- Laval University, Quebec, Quebec, Canada.
ORCID-Profile: Gabra Nohmie, Marc Lanovaz, Odile Sheehy, Cristina Longo, Robert Platt, Audrey Durand, Christine Damase-Michel, Anick Bérard
Zitieren
APA
Nohmie, G., Lanovaz, M., Sheehy, O., Longo, C., Platt, R., Durand, A., Damase-Michel, C., & Bérard, A. (2026). Evaluating the Performance of Traditional Pharmacoepidemiologic and Machine Learning Models to Predict Pregnancies at Risk of Major Congenital Malformations. Birth Defects Research. https://doi.org/10.1002/bdr2.70117
Vancouver
Nohmie G, Lanovaz M, Sheehy O, Longo C, Platt R, Durand A, et al. Evaluating the Performance of Traditional Pharmacoepidemiologic and Machine Learning Models to Predict Pregnancies at Risk of Major Congenital Malformations. Birth Defects Research. 2026. doi:10.1002/bdr2.70117
BibTeX
@article{Nohmie2026,
author = {Nohmie, Gabra and Lanovaz, Marc and Sheehy, Odile and Longo, Cristina and Platt, Robert and Durand, Audrey and Damase-Michel, Christine and Bérard, Anick},
title = {Evaluating the Performance of Traditional Pharmacoepidemiologic and Machine Learning Models to Predict Pregnancies at Risk of Major Congenital Malformations},
journal = {Birth Defects Research},
year = {2026},
doi = {10.1002/bdr2.70117}
}
EUVIMED