Researchers from New York City-based Columbia University Vagelos College of Physicians and Surgeons developed an algorithm that automatically searches a patient's EHR to look for signs of kidney disease, an April 13 study published in npj Digital Medicine found.
One of every eight Americans is believed to have chronic kidney disease, but only only 10 percent of those people in the early stages are aware of it. Of those with serious kidney disease, only 40 percent of people are aware of it. Many patients in early stages of the disease have no symptoms so it can go unnoticed, according to an April 27 news release.
The algorithm overcomes these obstacles by automatically scanning different types of EHRs for medical test results, staging the patient's disease and alerting a physician of the results.
In trials, the tool correctly diagnosed chronic kidney disease in 95 percent of the patients and correctly ruled out the disease in 97 percent of the patients.
The study's leader, Krzysztof Kiryluk, MD, associate professor of medicine at Columbia University said: "Identifying kidney disease early is of paramount importance because we have treatments that can slow disease progression before the damage becomes irreversible. Chronic kidney disease can cause multiple serious problems, including heart disease, anemia, or bone disease, and can lead to an early death, but its early stages are frequently under-recognized and undertreated."