Justin Mower1, Devika Subramanian2, Trevor Cohen3. 1. Baylor College of Medicine, Quantitative and Computational Biosciences, Houston, Texas, USA. 2. Department of Computer Science, Rice University, Houston, Texas, USA. 3. School of Biomedical Informatics, University of Texas Health Science Center Houston, Texas, USA.
Abstract
Objective: The aim of this work is to leverage relational information extracted from biomedical literature using a novel synthesis of unsupervised pretraining, representational composition, and supervised machine learning for drug safety monitoring. Methods: Using ≈80 million concept-relationship-concept triples extracted from the literature using the SemRep Natural Language Processing system, distributed vector representations (embeddings) were generated for concepts as functions of their relationships utilizing two unsupervised representational approaches. Embeddings for drugs and side effects of interest from two widely used reference standards were then composed to generate embeddings of drug/side-effect pairs, which were used as input for supervised machine learning. This methodology was developed and evaluated using cross-validation strategies and compared to contemporary approaches. To qualitatively assess generalization, models trained on the Observational Medical Outcomes Partnership (OMOP) drug/side-effect reference set were evaluated against a list of ≈1100 drugs from an online database. Results: The employed method improved performance over previous approaches. Cross-validation results advance the state of the art (AUC 0.96; F1 0.90 and AUC 0.95; F1 0.84 across the two sets), outperforming methods utilizing literature and/or spontaneous reporting system data. Examination of predictions for unseen drug/side-effect pairs indicates the ability of these methods to generalize, with over tenfold label support enrichment in the top 100 predictions versus the bottom 100 predictions. Discussion and Conclusion: Our methods can assist the pharmacovigilance process using information from the biomedical literature. Unsupervised pretraining generates a rich relationship-based representational foundation for machine learning techniques to classify drugs in the context of a putative side effect, given known examples.
Objective: The aim of this work is to leverage relational information extracted from biomedical literature using a novel synthesis of unsupervised pretraining, representational composition, and supervised machine learning for drug safety monitoring. Methods: Using ≈80 million concept-relationship-concept triples extracted from the literature using the SemRep Natural Language Processing system, distributed vector representations (embeddings) were generated for concepts as functions of their relationships utilizing two unsupervised representational approaches. Embeddings for drugs and side effects of interest from two widely used reference standards were then composed to generate embeddings of drug/side-effect pairs, which were used as input for supervised machine learning. This methodology was developed and evaluated using cross-validation strategies and compared to contemporary approaches. To qualitatively assess generalization, models trained on the Observational Medical Outcomes Partnership (OMOP) drug/side-effect reference set were evaluated against a list of ≈1100 drugs from an online database. Results: The employed method improved performance over previous approaches. Cross-validation results advance the state of the art (AUC 0.96; F1 0.90 and AUC 0.95; F1 0.84 across the two sets), outperforming methods utilizing literature and/or spontaneous reporting system data. Examination of predictions for unseen drug/side-effect pairs indicates the ability of these methods to generalize, with over tenfold label support enrichment in the top 100 predictions versus the bottom 100 predictions. Discussion and Conclusion: Our methods can assist the pharmacovigilance process using information from the biomedical literature. Unsupervised pretraining generates a rich relationship-based representational foundation for machine learning techniques to classify drugs in the context of a putative side effect, given known examples.
Authors: Hesha J Duggirala; Joseph M Tonning; Ella Smith; Roselie A Bright; John D Baker; Robert Ball; Carlos Bell; Susan J Bright-Ponte; Taxiarchis Botsis; Khaled Bouri; Marc Boyer; Keith Burkhart; G Steven Condrey; James J Chen; Stuart Chirtel; Ross W Filice; Henry Francis; Hongying Jiang; Jonathan Levine; David Martin; Taiye Oladipo; Rene O'Neill; Lee Anne M Palmer; Antonio Paredes; George Rochester; Deborah Sholtes; Ana Szarfman; Hui-Lee Wong; Zhiheng Xu; Taha Kass-Hout Journal: J Am Med Inform Assoc Date: 2015-07-23 Impact factor: 4.497
Authors: Nicholas S Downing; Nilay D Shah; Jenerius A Aminawung; Alison M Pease; Jean-David Zeitoun; Harlan M Krumholz; Joseph S Ross Journal: JAMA Date: 2017-05-09 Impact factor: 56.272
Authors: Rave Harpaz; David Odgers; Greg Gaskin; William DuMouchel; Rainer Winnenburg; Olivier Bodenreider; Anna Ripple; Ana Szarfman; Alfred Sorbello; Eric Horvitz; Ryen W White; Nigam H Shah Journal: Sci Data Date: 2014-11-11 Impact factor: 6.444