Data Mining HeData Mining Helps Detect Adverse Drug Reactions

Researchers at the New Jersey Institute of Technology (NJIT; Newark, USA) examined 12 years of EMR data from Vanderbilt University Medical Center (VUMC; Nashville, TN, USA; www.mc.vanderbilt.edu) and reviewed retrospective medication orders and inpatient laboratory results documented in the EMR to identify ADRs. The researchers then assessed the relative merits of six pharmacovigilance measures used in spontaneous reporting systems: proportional reporting ratio (PRR), reporting OR (ROR), Yule's Q (YULE), the CHI-squared test, Bayesian confidence propagation neural networks (BCPNN), and a gamma Poisson shrinker (GPS).

The researchers then systematically evaluated the six methods on two independently constructed reference standard datasets of drug-event pairs. The first was the Yoon et al dataset, containing 470 drug-event pairs (10 drugs and 47 laboratory abnormalities). The second dataset was created using the VUMC EMRs, containing 378 drug-event pairs (9 drugs and 42 laboratory abnormalities). After evaluation, CHI, ROR, PRR, and YULE all had the same F score (62%). When the reference standard of Yoon et al was used, ROR had the best F score of 68%, with 77% precision and 61% recall. The study was published in the May 2013 issue of the Journal of American Medical Informatics Association.

“Medication safety requires that each drug be monitored throughout its market life as early detection of adverse drug reactions can lead to alerts that prevent patient harm,” said lead author computer scientist Mei Liu, PhD. “EMRs have created an unprecedented resource for observational studies since they contain not only detailed patient information, but also large amounts of longitudinal clinical data.”

Pharmacovigilance is the pharmacological science relating to the collection, detection, assessment, monitoring, and prevention of ADRs, which are defined as any response to a drug, which is noxious and unintended, including lack of efficacy, which occurs at doses normally used for the prophylaxis, diagnosis, or therapy of disease, or for the modification of physiological function. ADRs are one of the major causes for failure in drug development, and severe ADRs that go undetected until the postmarketing phase of a drug often lead to patient morbidity, as exemplified by numerous drug withdrawals.

Related Links:
New Jersey Institute of Technology