Read more

December 30, 2019
1 min read
Save

EHR-based tool could help identify children with glomerular disease for clinical research

You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

An algorithm using data from an electronic health record accurately identified pediatric patients with glomerular disease which, according to published research, may aid in recruitment for observational or prospective studies of the condition.

“Glomerular disorders are the leading acquired causes of [chronic kidney disease] CKD and ESKD in children and young adults,” Michelle R. Denburg, MD, MSCE, of the division of pediatric nephrology at the Children’s Hospital of Philadelphia (CHOP), and colleagues wrote. “ ... Frequently without known causes, cure, or therapies approved by the U.S. Food and Drug Administration, patients with glomerular disease face uncertainty and high rates of health spending, morbidity, and mortality. Clinical advances have been stymied by the rarity of these health conditions, making identification of sufficient number of patients for clinical trials challenging, particularly in the pediatric setting.”

Using EHR data from 231 patients with glomerular disorders treated at CHOP, researchers developed a computerized algorithm for identification of the condition. The algorithm, based primarily on diagnostic and procedure codes, was tested against a national network of eight pediatric academic health systems. The network, known as PEDSnet, included data on more than 6.5 million children who had at least one clinical encounter and at least one coded diagnosis during or after 2009. Researchers considered patients who had three or more nephrology encounters.

Researchers found the algorithm performed with 94% accuracy, 96% sensitivity, 93% specificity, 89% positive predictive value and 97% negative predictive value.

“This novel approach to rapid cohort identification could greatly enhance and accelerate comparative effectiveness, clinical trials and health outcomes research in glomerular disease,” they concluded. – by Melissa J. Webb

Disclosures: Denburg reports receiving grants from Mallinckrodt Pharmaceuticals. Please see the study for all other authors’ relevant financial disclosures.