Dataset Information

An Integrative Data Science Pipeline to Identify Novel Drug Interactions that Prolong the QT Interval.

ABSTRACT:

Introduction

Drug-induced prolongation of the QT interval on the electrocardiogram (long QT syndrome, LQTS) can lead to a potentially fatal ventricular arrhythmia known as torsades de pointes (TdP). Over 40 drugs with both cardiac and non-cardiac indications are associated with increased risk of TdP, but drug-drug interactions contributing to LQTS (QT-DDIs) remain poorly characterized. Traditional methods for mining observational healthcare data are poorly equipped to detect QT-DDI signals due to low reporting numbers and lack of direct evidence for LQTS.

Objective

We hypothesized that LQTS could be identified latently using an adverse event (AE) fingerprint of more commonly reported AEs. We aimed to generate an integrated data science pipeline that addresses current limitations by identifying latent signals for QT-DDIs in the US FDA's Adverse Event Reporting System (FAERS) and retrospectively validating these predictions using electrocardiogram data in electronic health records (EHRs).

Methods

We trained a model to identify an AE fingerprint for risk of TdP for single drugs and applied this model to drug pair data to predict novel DDIs. In the EHR at Columbia University Medical Center, we compared the QTc intervals of patients prescribed the flagged drug pairs with patients prescribed either drug individually.

Results

We created an AE fingerprint consisting of 13 latently detected side effects. This model significantly outperformed a direct evidence control model in the detection of established interactions (p = 1.62E-3) and significantly enriched for validated QT-DDIs in the EHR (p = 0.01). Of 889 pairs flagged in FAERS, eight novel QT-DDIs were significantly associated with prolonged QTc intervals in the EHR and were not due to co-prescribed medications.

Conclusions

Latent signal detection in FAERS validated using the EHR presents an automated and data-driven approach for systematically identifying novel QT-DDIs. The high-confidence hypotheses flagged using this method warrant further investigation.

SUBMITTER: Lorberbaum T

PROVIDER: S-EPMC4835515 | biostudies-literature | 2016 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An Integrative Data Science Pipeline to Identify Novel Drug Interactions that Prolong the QT Interval.

Lorberbaum Tal T Sampson Kevin J KJ Woosley Raymond L RL Kass Robert S RS Tatonetti Nicholas P NP

Drug safety 20160501 5

<h4>Introduction</h4>Drug-induced prolongation of the QT interval on the electrocardiogram (long QT syndrome, LQTS) can lead to a potentially fatal ventricular arrhythmia known as torsades de pointes (TdP). Over 40 drugs with both cardiac and non-cardiac indications are associated with increased risk of TdP, but drug-drug interactions contributing to LQTS (QT-DDIs) remain poorly characterized. Traditional methods for mining observational healthcare data are poorly equipped to detect QT-DDI signa ...[more]

PMID: 26860921

Similar Datasets

Project description:BackgroundDabigatran etexilate is a pro-drug of the oral reversible direct thrombin inhibitor dabigatran that interacts with the active site in the catalytic domain of the thrombin molecule.ObjectiveTo assess the electrophysiological effects of therapeutic and supratherapeutic doses of dabigatran etexilate in healthy subjects, a thorough QT study was performed.MethodsIn this single-centre, blinded, placebo- and active-controlled, four-period, crossover study, 40 healthy Caucasian subjects (20 women and 20 men) received single oral doses of dabigatran etexilate (150 mg and 600 mg), moxifloxacin 400 mg (positive control) or placebo, in a randomized order. Electrocardiogram (ECG) profiles were recorded at baseline and during the randomized study treatment in each period. The individually heart-rate-corrected QT interval (QTcI) was the primary parameter. The primary endpoint was the mean of these QTcI values obtained at 1.5, 2 and 3 h following study drug administration minus the mean of the time-matched QTcI values obtained at baseline day -1. The hypothesis tested was that the difference between each of the two doses of dabigatran etexilate (150 mg and 600 mg) and placebo, for the mean time-matched change from baseline (CfB) of QTcI between 1.5 and 3 h (the primary endpoint), was greater than or equal to 10 ms. Secondary endpoints were the time-matched CfB of QTcI between 0.5 and 24 h post-dose.ResultsAll subjects completed the study without premature discontinuation and all treatments were well tolerated. Following dabigatran etexilate administration, the mean values of the placebo-adjusted time-matched CfB of QTcI between 1.5 and 3 h post-dose were close to 0; the upper bound of the two-sided 90 % confidence interval (CI) was 1.4 ms for dabigatran etexilate 150 mg and 1.3 ms for dabigatran etexilate 600 mg. The placebo-adjusted time-matched CfB of QTcI remained close to 0 at all time points, and all 90 % CIs were between -5 ms and 5 ms, well below the pre-defined non-inferiority margin of 10 ms.ConclusionThis thorough QT study demonstrated that therapeutic and fourfold supratherapeutic doses of dabigatran etexilate do not prolong QT intervals.

Dataset Information

An Integrative Data Science Pipeline to Identify Novel Drug Interactions that Prolong the QT Interval.

Introduction

Objective

Methods

Results

Conclusions

Publications

An Integrative Data Science Pipeline to Identify Novel Drug Interactions that Prolong the QT Interval.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets