A machine learning tool that analyzes information already captured in a child’s electronic health record helped pediatricians more accurately assess asthma risk in standardized clinical case scenarios, according to a pilot randomized clinical trial led by a Regenstrief Institute researcher. The study was published in Scientific Reports.

The study evaluated a machine learning-enabled clinical decision support tool called the Passive Digital Marker, which uses routinely collected EHR data to classify young children as having a high or low risk of developing persistent asthma.

Asthma is one of the most common chronic childhood diseases, but predicting which young children with wheezing or other respiratory symptoms will go on to develop persistent asthma remains difficult. While some children outgrow these symptoms, others require ongoing treatment, making early risk assessment an important but challenging part of pediatric care.