A novel signal detection algorithm for identifying hidden drug-drug interactions in adverse event reports

Abstract

Objective: Adverse drug events (ADEs) are common and account for 770 000 injuries and deaths each year and drug interactions account for as much as 30% of these ADEs. Spontaneous reporting systems routinely collect ADEs from patients on complex combinations of medications and provide an opportunity to discover unexpected drug interactions. Unfortunately, current algorithms for such "signal detection" are limited by underreporting of interactions that are not expected. We present a novel method to identify latent drug interaction signals in the case of underreporting.

Materials and methods: We identified eight clinically significant adverse events. We used the FDA's Adverse Event Reporting System to build profiles for these adverse events based on the side effects of drugs known to produce them. We then looked for pairs of drugs that match these single-drug profiles in order to predict potential interactions. We evaluated these interactions in two independent data sets and also through a retrospective analysis of the Stanford Hospital electronic medical records.

Results: We identified 171 novel drug interactions (for eight adverse event categories) that are significantly enriched for known drug interactions (p=0.0009) and used the electronic medical record for independently testing drug interaction hypotheses using multivariate statistical models with covariates.

Conclusion: Our method provides an option for detecting hidden interactions in spontaneous reporting systems by using side effect profiles to infer the presence of unreported adverse events.

Figure 1

Methodological overview. (A) Each drug is assigned a label according to their adverse event class, so that each element of the matrix indicates drug i's membership in class j. The fields of this matrix are filled by the user and each column is used as the response variables to train a supervised machine learning algorithm. In this paper we built eight such algorithms for renal impairment, cholesterol, suicide, depression, liver dysfunction, hypertension, hepatotoxicity, and diabetes. (B) Given a particular drug class from (A) (ie, a column), we construct an N by M adverse event frequency matrix, where N is the number of drugs and M is the number of adverse events. Each element of the matrix represents the proportion of reports for drug i which list adverse event j. (C) Since M >> N overfitting the logistic regression model to the training data is a concern. We use feature selection to identify the L most informative adverse events to be used in fitting the logistic regression model. (D) A second adverse event frequency matrix is constructed. The key difference here is that each row represents a drug-pair as opposed to a single drug, as in (B). Note that no data is (continued)shared between these two matrices to ensure they are independent. Therefore each element of this matrix is the proportion of reports for both drugs i and j that list adverse event l. This matrix takes on the same form as the matrix used for fitting the model. This allows us to apply the model and make drug-drug interaction predictions.

Figure 2

Receiver Operating Characteristic curves for the eight logistic regression models on two independent validation data sets. The KE data set was paired drug data from AERS, not used in training, where at least one of the drugs of the pair is known to be associated with the adverse event (according to FDA drug labels). The second validation data set (VA) was a list of critical and significant DDIs from the Veterans Affairs Hospital in Arizona provided by Olvey, et al CHOL, Cholesterol; DEPR, Depression; DIAB, Diabetes; HEPTOX, Hepatotoxicity; HTN, Hypertension; LIVDYS, Liver Dysfunction; RENIMP, renal impairment; SUIC, Suicide.

Figure 3

Putative drug-drug interactions. We predicted drug-drug interactions for eight adverse event classes: renal impairment (RI), cholesterol (CHOL), suicide (SUI), hypertension (HTN), liver dysfunction (LD), diabetes (DM), depression (DEP), and hepatotoxicity (HEP). This plot shows the breakdown of these interactions into three groups: (1) pairs of drugs where the effect can be explained by known single drug effects (filled), (2) pairs of drugs already known to be involved in a clinically significant interactions (shaded), and (3) completely novel interactions (unfilled).

Figure 4

Novel putative drug interaction prediction between paroxetine and pravastatin. Paroxetine and Pravastatin in combination are associated with elevated blood glucose. Mean non-fasting blood glucose levels in eight patients before and after starting combination treatment with paroxetine and pravastatin. The mean increase in blood glucose was 22 mg/dl (p=0.001). We observed no significant change in patients on paroxetine and not pravastatin and vice versa.