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.

Figure 1

Multi-Dimensional Scaling (MDS) Component Plots for: Fetal Loss, Congenital Anomaly and Minor Congenital Anomaly. The three subplots on the left hand side of the figure (A,C,E) contain all drugs while on the right hand side of the figure (B,D,F) contain only drugs typically prescribed with legal termination. Red drugs are those shown as category D or X, blue drugs are category A or B while category C drugs are shown as grey. For all subplots, triangles indicate that the drug affected a protein encoded by a known Mendelian gene whereas circles indicate that the drug did not affect a protein encoded by a known Mendelian gene. For congenital anomalies, the proportion with an anomaly for each of the 5 exposure periods (2 pre-conception and 3 trimesters) were included as features. For fetal loss, only the 2 pre-conception periods and the first trimester were included.

Figure 2

Component vs. Proportion with Fetal Loss. There is a clear relationship between the first component and the proportion of individuals experiencing fetal loss following prenatal exposure to the drug during the first trimester. This effect is not entirely due to drugs prescribed for legal termination, which are shown separately in the right most subplots. Red drugs are those shown as category D or X, blue drugs are category A or B while category C drugs are shown as grey. For all subplots, triangles indicate that the drug affected a protein encoded by a known Mendelian gene whereas circles indicate that the drug did not affect a protein encoded by a known Mendelian gene.

Figure 3

Model Probability of Being a Harmful Drug (D or X). The top portion of the graph shows drugs with known FDA pregnancy class. All drugs above the 50% probability threshold were predicted to be harmful and were harmful (three top graphs) across all models including fetal loss, congenital anomaly and minor congenital anomalies alone. In the lower three graphs FDA category C drugs are included (depicted in light grey). These drugs have no FDA recommendation regarding their safety during pregnancy. The majority of these drugs were predicted to be pregnancy safe (less than 50% probability of being harmful). While some drugs were above the 50% threshold and were more similar to known harmful drugs.

Figure 4

Model Probability of Being a Harmful Drug (D or X) in Congenital Anomaly Model vs. Fetal Loss Model for Category C Drugs (i.e., those with no FDA recommendation). The model probabilities for a drug’s harmful status were highly correlated (r = 0.63, p < 0.001) between both congenital anomaly and fetal loss models. NSAIDs like naproxen were predicted harmful by both models. Also live rubella vaccination was harmful in both models. Other drugs were predicted harmful in increasing the risk of either fetal loss only (lower right hand quadrant) or congenital anomalies only (upper left hand quadrant). These may require further investigation to determine the mechanistic rationale for their predicted harm in one fetal outcome over the other.

Figure 5

Model Probability of Being a Harmful Drug (D or X) in the Fetal Loss Model vs. Proportion with Fetal Loss: Investigation of Nervous System Medications that Are Predicted Harmful vs. Predicted Safe and Affect On Risk of Fetal Loss. The overall average proportion of fetal loss for all predicted safe and harmful medications across the different trimester exposure points are presented (upper left-hand plot). Predicted harmful drugs (probability of harmful >=0.50) increased the risk of fetal loss especially following first trimester exposure (upper right-hand plot). The anti-depressant Haloperidol 5 MG, predicted harmful by our model, is compared to the SSRI anti-depressant medication – Citalopram 10 MG, predicted safe by our model, with the former experiencing greater rates of fetal loss following exposure (lower left-hand plot). Haloperidol 5 MG is also compared to the epilepsy medication Levetiracetam 500 MG, predicted safe by our model, with haloperidol again experiencing greater rates of fetal loss following exposure (lower right-hand plot). For drugs predicted as harmful in the fetal loss model, there was an increase in fetal loss rates following exposures when compared to those predicted as safe. Red dashed horizontal lines indicate the CDC reported background rate of 35% fetal loss.

Figure 6

Model Probability of Being a Harmful Drug (D or X) in Congenital Anomaly Model vs. Proportion with Congenital Anomalies: Investigation of NSAIDs that Are Predicted Harmful vs. Predicted Safe and Affect on Anomaly Risk. The overall average proportion of infants with anomalies for all predicted safe and harmful medications across the different trimester exposure points are presented (upper left-hand plot). For NSAIDs, predicted harmful drugs (probability of harmful >=0.50) increased the risk of fetal loss especially following first trimester exposure (upper right-hand plot). Exposure rates changed during pregnancy for all predicted harmful category C medications. The log of the exposure rates prior to conception are shown (middle left-hand plot) and during first trimester (middle right-hand plot). There is a shift in usage patterns for those predicted as harmful. The NSAIDs naproxen 250 MG and 500 MG were both predicted harmful by our model. The NSAIDs Ketorolac Tromethanine 15 MG/ML and 30 MG/ML were both predicted as safe by our model. These two medications are compared to each other with their respective effects on risk of anomaly across the various trimesters (lower left-hand and right-hand plots). First trimester exposure to naproxen 250 MG greatly increased the risk of anomaly vs. ketorolac 15 MG/ML (lower left-hand plot). Red dashed horizontal lines indicate the CDC reported background rate of 15% for all congenital anomalies.