Using information mining of the medical literature to improve drug safety
- Correspondence to Siddhartha Dalal, RAND Corporation, 1776 Main St, Santa Monica, CA 90401, USA;
Contributors Both Drs Dalal and Shetty had full access to all of the data in the study and take responsibility for the integrity of the data and the accuracy of the data analysis. All significant contributors have been acknowledged.
- Received 26 July 2011
- Accepted 2 March 2011
- Published Online First 5 May 2011
Objective Prescription drugs can be associated with adverse effects (AEs) that are unrecognized despite evidence in the medical literature, as shown by rofecoxib's late recall in 2004. We assessed whether applying information mining to PubMed could reveal major drug–AE associations if articles testing whether drugs cause AEs are over-represented in the literature.
Design MEDLINE citations published between 1949 and September 2009 were retrieved if they mentioned one of 38 drugs and one of 55 AEs. A statistical document classifier (using MeSH index terms) was constructed to remove irrelevant articles unlikely to test whether a drug caused an AE. The remaining relevant articles were analyzed using a disproportionality analysis that identified drug–AE associations (signals of disproportionate reporting) using step-up procedures developed to control the familywise type I error rate.
Measurements Sensitivity and positive predictive value (PPV) for empirical drug–AE associations as judged against drug–AE associations subject to FDA warnings.
Results In testing, the statistical document classifier identified relevant articles with 81% sensitivity and 87% PPV. Using data filtered by the statistical document classifier, base-case models showed 64.9% sensitivity and 42.4% PPV for detecting FDA warnings. Base-case models discovered 54% of all detected FDA warnings using literature published before warnings. For example, the rofecoxib–heart disease association was evident using literature published before 2002. Analyses incorporating literature mentioning AEs common to the drug class of interest yielded 71.4% sensitivity and 40.7% PPV.
Conclusions Results from large-scale literature retrieval and analysis (literature mining) compared favorably with and could complement current drug safety methods.
- Data mining
- drug safety
- machine learning
- statistical algorithm
- biomedical literature
- literature mining
Funding The RAND Corporation funded this work through an internal grant to Dr Dalal, and had no role in the study.
Competing interests None.
Provenance and peer review Not commissioned; internally peer reviewed.