Drug Pregnancy Safety

This website provides the most up-to-date pregnancy drug safety information
It includes the predictions of an AI-based pregnancy drug safety model
The full details are described in our paper
The objective of this study was to develop a novel interpretable and multimodal machine learning model for classifying pregnancy drug safety

Read Paper

Drug Information

Select data source
All data - model trained on all available data
Cross-expert - the cross-expert evaluation (see our paper)

SHAP Force Plot

SHAP Decision Plot

DrugBank Data

☯ DrugBank ID - can be found at DrugBank.com
♦ Polifka et al. - Polifka, Janine E., et al. "Assessment of developmental risk information on medicines for inclusion on the WHO’s Essential Medicines List." International health 11.6 (2019): 513-519.
♣ Zerifin TIS (Tel Aviv University) - Data collected from the database of Zerifin TIS (Tel Aviv University), as recorded between the years 2002 and 2019; domain experts from Zerifin TIS (Teratology Information Services) used this information to label the safety of the drug found in the system.
☉ Eltonsy, Sherif, et al. "Systematic procedure for the classification of proven and potential teratogens for use in research." Birth Defects Research Part A: Clinical and Molecular Teratology 106.4 (2016): 285-297.
★ FDA category - FDA category, as collected from safefetus.com
♥ Risk score - Citation

Download Data


Guy Shtar, Lior Rokach, Bracha Shapira, Elkana Kohn, Matitiahu Berkovitch, Maya Berlin, Explainable multimodal machine learning model for classifying pregnancy drug safety, Bioinformatics, 2021;, btab769, https://doi.org/10.1093/bioinformatics/btab769


The content of this website is intended for educational and scientific research purposes only.
The website is not a substitute for professional medical advice or diagnosis. Contact a health professional for any issues or questions you may have.


We are a team of AI experts and pharmacologists who have joined forces to provide you with accurate pregnancy drug safety data.
Shtar G, Rokach L, Shapira B, Kohn E, Berkovitch M, and Berlin M.

Web Hits