Development of A Machine Learning Algorithm to Classify Drugs Of Unknown Fetal Effect

Abstract

Many drugs commonly prescribed during pregnancy lack a fetal safety recommendation – called FDA ‘category C’ drugs. This study aims to classify these drugs into harmful and safe categories using knowledge gained from chemoinformatics (i.e., pharmacological similarity with drugs of known fetal effect) and empirical data (i.e., derived from Electronic Health Records). Our fetal loss cohort contains 14,922 affected and 33,043 unaffected pregnancies and our congenital anomalies cohort contains 5,658 affected and 31,240 unaffected infants. We trained a random forest to classify drugs of unknown pregnancy class into harmful or safe categories, focusing on two distinct outcomes: fetal loss and congenital anomalies. Our models achieved an out-of-bag accuracy of 91% for fetal loss and 87% for congenital anomalies outperforming null models. Fifty-seven ‘category C’ medications were classified as harmful for fetal loss and eleven for congenital anomalies. This includes medications with documented harmful effects, including naproxen, ibuprofen and rubella live vaccine. We also identified several novel drugs, e.g., haloperidol, that increased the risk of fetal loss. Our approach provides important information on the harmfulness of ‘category C’ drugs. This is needed, as no FDA recommendation exists for these drugs’ fetal safety.

Exploiting machine learning for end-to-end drug discovery and development

“…In the area of drug safety, a random forest classifier was used to predict the effect of drugs on the fetus. The models successfully identified category C drugs that are likely to be harmful and those likely to be safe for fetal loss or congenital anomalies 79 .…”

Enabling pregnant women and their physicians to make informed medication decisions using artificial intelligence

“…Boland et al developed a method that utilizes machine learning to predict the fetal toxicity of pharmacologics taken during pregnancy, including first through third trimesters of the pregnancy [79]. The ML method employed a technique called 'random forests' whereby information was learned from drugs that were known to be harmful to the fetus by previous outcomes studies (and were already labeled as contraindicated in pregnancy by the United States Food and Drug Administration (FDA)-or category D or X).…”

“…The AI method was able to predict which drugs were more likely to be fetal toxic versus fetal safe for those drugs that were in the middle or unknown fetal toxicity category (i.e., FDA Category C drugs). Boland et al's method also used chemical information on the drugs and whether or not the drug was known to target a vitamin gene or a known Mendelian disease gene to improve the performance of the method [79]. The importance of understanding Mendelian disease genes and pharmacologics that target them (even as unintended targets or 'off-targets') in fetal outcomes was established via an extensive manual review process [80] that helped to inform the design of our later machine learning approach [79].…”

Data‐driven queries between medications and spontaneous preterm birth among 2.5 million pregnancies

“…We employed computational, data‐driven techniques that offer opportunities to perform simultaneous inferences about the use of multiple medications. Such methods have only recently been considered for discovery of unknown drug effects and interactions (Boland, Polubriaginof, & Tatonetti, ; Chiang et al, ; Tatonetti et al, ; Tatonetti, Ye, Daneshjou, & Altman, ). Tatonetti et al successfully used data mining of ADEs to discover several previously unidentified drug‐to‐drug interactions (Chiang et al, ; Tatonetti et al, ).…”