The cholesterol-raising, heart-threatening disease familial hypercholesterolemia (FH) is a tough one to catch. One of the telling symptoms of FH is elevated lipid levels, making it easy for the disease to masquerade as high cholesterol, and nothing more.
So how to tell the difference?
Joshua Knowles, MD, PhD, assistant professor of cardiovascular medicine at Stanford, and Nigam Shah, MBBS, PhD, associate professor of medicine and of biomedical data science, are devising a solution based in artificial intelligence and a lot of de-identified electronic health records. Specifically, the researchers used data from Stanford's FH Clinic to "teach" the algorithm what FH looks like in the form of a patient record.
The code essentially sorts out those with the highest likelihood of having FH, based on myriad factors that come from patient electronic health records, such as family history, current prescriptions, lipid levels, and much more.
From our release:
In test runs of the algorithm, it correctly identified 88 percent of the cases it screened. Theoretically, if the algorithm were used in a clinic, any patient it flagged as having FH could undergo further genetic testing to verify the algorithm's calculation.
A paper describing the work published online in npj Digital Medicine. Shah and Knowles, who is the director of the FH clinic at Stanford Health Care's Center for Inherited Cardiovascular Disease, share senior authorship. Juan Banda, PhD, a former research scientist at Stanford, is the lead author.
According to Knowles, only about 10 percent of those with FH actually know that they have it. That, he said, is a big problem. Patients with FH are about three times as likely to suffer heart problems than those without FH, but with high cholesterol.
Using the new FH algorithm, patients with high cholesterol levels are ranked: Those who are at the top of the list are most likely to have the disease, while those at the bottom are most probably FH-free.
"Theoretically, when someone comes into the clinic with high cholesterol or heart disease, we would run this algorithm," Shah said. "If they're flagged, it means there's an 80 percent chance that they have FH. Those few individuals could then get sequenced to confirm the diagnosis and could start an LDL-lowering treatment right away."
Now, the team is working toward approval so that they can use the algorithm in the clinic.
Photo by paulbr75