New Technology Could Help Spot Adverse Reactions

Published Online: Monday, April 18, 2011
Follow Pharmacy_Times:

Certain protocols and precautions, such as knowing an individual patient’s hypersensitivity or disease state, can help pharmacists reduce the likelihood that an adverse drug reaction (ADR) will occur. But predicting them with any certainty or consistency is nearly impossible.

A team of researchers at the University of Medicine and Dentistry of New Jersey set out to tackle that barrier using a mathematical model that mimics the human biological neural network. They “trained” the model by feeding it data on known pharmaceuticals and associated ADRs collected through the FDA’s adverse event reporting system.

In an article on the trial, published in the March 2011 issue of the International Journal of Medical Engineering and Informatics, the scientists reported that their model, called an artificial neural network, was 99.87% accurate in predicting ADRs overall and 100% accurate in predicting nonserious ADRs in 10,000 observations.

The authors said the technology’s ability to quickly predict adverse drug reactions before they occur has potential to save both lives and health care dollars. They are currently training the neural network with a larger data set of 10,000 drug molecules and associated ADRs in order to refine its predictions.



Related Articles
Treating patients with status epilepticus is a challenging balance of minimizing the risk of medication adverse events while managing the serious dangers of status epilepticus itself.
Antiepileptic medications are a broad category of drugs with many potential adverse events. In this session, Eugen Trinka, MD, MSc, reviews the most common adverse events associated with these therapies.
A lack of training on pharmacovigilance likely leads pharmacists to underreport adverse drug reactions (ADRs).
Involving pharmacists in the intensive care unit reduces adverse events and costs for patients who receive continuous veno-venous hemofiltration.
Latest Issues
$auto_registration$