Document Detail


Detection of pharmacovigilance-related adverse events using electronic health records and automated methods.
MedLine Citation:
PMID:  22713699     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Electronic health records (EHRs) are an important source of data for detection of adverse drug reactions (ADRs). However, adverse events are frequently due not to medications but to the patients' underlying conditions. Mining to detect ADRs from EHR data must account for confounders. We developed an automated method using natural-language processing (NLP) and a knowledge source to differentiate cases in which the patient's disease is responsible for the event rather than a drug. Our method was applied to 199,920 hospitalization records, concentrating on two serious ADRs: rhabdomyolysis (n = 687) and agranulocytosis (n = 772). Our method automatically identified 75% of the cases, those with disease etiology. The sensitivity and specificity were 93.8% (confidence interval: 88.9-96.7%) and 91.8% (confidence interval: 84.0-96.2%), respectively. The method resulted in considerable saving of time: for every 1 h spent in development, there was a saving of at least 20 h in manual review. The review of the remaining 25% of the cases therefore became more feasible, allowing us to identify the medications that had caused the ADRs.
Authors:
K Haerian; D Varn; S Vaidya; L Ena; H S Chase; C Friedman
Related Documents :
16776379 - Tethered brainstem repair and near-fatal ventriculoperitoneal shunt insertion. case rep...
16924199 - Ventral thoracic spinal cord herniation: frequently misdiagnosed entity.
6710329 - Spinal epidural hematoma.
3882299 - Chemonucleolysis failures treated by plif.
16961089 - Correlation of anomalous vascular and osseous anatomy in congenital kyphosis type i. ca...
12450289 - Syringomyelia without hindbrain herniation: tight cisterna magna. report of four cases ...
9805539 - Scopulariopsis: an invasive nasal infection.
11897909 - Assisted conception in the azoospermic male.
22782439 - Whole report uncovers correctly identified but incorrectly placed target information un...
Publication Detail:
Type:  Journal Article; Research Support, N.I.H., Extramural     Date:  2012-06-20
Journal Detail:
Title:  Clinical pharmacology and therapeutics     Volume:  92     ISSN:  1532-6535     ISO Abbreviation:  Clin. Pharmacol. Ther.     Publication Date:  2012 Aug 
Date Detail:
Created Date:  2012-07-24     Completed Date:  2012-10-18     Revised Date:  2013-08-13    
Medline Journal Info:
Nlm Unique ID:  0372741     Medline TA:  Clin Pharmacol Ther     Country:  United States    
Other Details:
Languages:  eng     Pagination:  228-34     Citation Subset:  AIM; IM    
Affiliation:
Department of Biomedical Informatics, Columbia University, New York, NY, USA. krh7003@dmi.columbia.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Adverse Drug Reaction Reporting Systems / organization & administration*
Agranulocytosis / chemically induced
Drug Toxicity / chemically induced*
Electronic Health Records*
Humans
New York City
Pharmaceutical Preparations / adverse effects*
Pharmacovigilance*
Rhabdomyolysis / chemically induced
Sensitivity and Specificity
Grant Support
ID/Acronym/Agency:
R01 LM010016/LM/NLM NIH HHS; R01:LM008635/LM/NLM NIH HHS; R01:LM010016/LM/NLM NIH HHS; R01:LM010016-0S1/LM/NLM NIH HHS; R01:LM010016-0S2/LM/NLM NIH HHS; R01:LM06910/LM/NLM NIH HHS; T15 LM007079/LM/NLM NIH HHS; T15:LM007079/LM/NLM NIH HHS
Chemical
Reg. No./Substance:
0/Pharmaceutical Preparations
Comments/Corrections

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Comparison of 3,000 and 5,000 IU aXa/day certoparin in the prevention of deep-vein thrombosis after ...
Next Document:  UGT1A4*3 encodes significantly increased glucuronidation of olanzapine in patients on maintenance tr...