Safety of Common Medications for Treating Dermatology Disorders in Pregnant Women

Machine learning on drug-specific data to predict small molecule teratogenicity

Pregnant women are an especially vulnerable population, given the sensitivity of a developing fetus to chemical exposures. However, prescribing behavior for the gravid patient is guided on limited human data and conflicting cases of adverse outcomes due to the exclusion of pregnant populations from randomized, controlled trials. These factors increase risk for adverse drug outcomes and reduce quality of care for pregnant populations. Herein, we propose the application of artificial intelligence to systematically predict the teratogenicity of a prescriptible small molecule from information inherent to the drug. Using unsupervised and supervised machine learning, our model probes all small molecules with known structure and teratogenicity data published in research-amenable formats to identify patterns among structural, meta-structural, and in vitro bioactivity data for each drug and its teratogenicity score. With this workflow, we discovered three chemical functionalities that predispose a drug towards increased teratogenicity and two moieties with potentially protective effects. Our models predict three clinically-relevant classes of teratogenicity with AUC = 0.8 and nearly double the predictive accuracy of a blind control for the same task, suggesting successful modeling. We also present extensive barriers to translational research that restrict data-driven studies in pregnancy and therapeutically "orphan" pregnant populations. Collectively, this work represents a first-in-kind platform for the application of computing to study and predict teratogenicity.

Utilisation of teratogenic medicines before and during pregnancy in Australian women

BACKGROUND

Given the potential hazards of teratogenic medicines, to a fetus exposed in utero, monitoring their use around pregnancy is imperative.

AIM

To measure utilisation of teratogenic medicines (Therapeutic Goods Administration's category D or X) in women who gave birth in New South Wales, Australia, during pregnancy and the 24 months prior.

MATERIALS AND METHODS

We used linked population-based datasets including dispensing and perinatal data for all deliveries in NSW between 2005 and 2012. We included pregnancies among concessional beneficiaries only, with complete ascertainment of dispensing claims. Pre-pregnancy and during-pregnancy periods were based on birth dates and gestational age. We determined prevalence of exposure using percent of pregnancies in which women had at least one dispensed teratogenic medicine in three-month time periods.

RESULTS

The study included 191 588 pregnancies (145 419 women). Prevalence of exposure to D/X medicines anytime during pregnancy was 2.0% (<20 pregnancies category X), decreasing from pre-pregnancy (3.8-6.0%) to first trimester (1.5%), further decreasing in second and third trimesters (0.8% and 0.6% respectively). We observed large reductions in antibiotic prevalence but only modest reductions for psychotropics and antilipidemic agents (all category D). Our results suggest higher use of potentially teratogenic medicines (category D) than those strictly contraindicated for use (category X), during pregnancy. Overall, use was higher in the first trimester than the rest of pregnancy. The high prevalence of potentially contraindicated psychotropics in all three trimesters may suggest a higher benefit-to-risk ratio and warrants future research focusing on the reasons for their prescribing to pregnant women.