New research from the FH Foundation’s FIND (FLAG, IDENTIFY, NETWORK, DELIVER) FH® initiative demonstrating that a machine learning algorithm could effectively guide the identification of probable familial hypercholesterolemia (FH) individuals within a healthcare system was published online today in npj Digital Medicine.
| PASADENA, Calif., April 11, 2019 /PRNewswire/ -- New research from the FH Foundation’s FIND (FLAG, IDENTIFY, NETWORK, DELIVER) FH® initiative demonstrating that a machine learning algorithm could effectively guide the identification of probable familial hypercholesterolemia (FH) individuals within a healthcare system was published online today in npj Digital Medicine. FH is the most common genetic cause of high cholesterol, affecting 1 in 250 people, and leads to early onset heart disease when untreated. FIND FH is critical as today less than 10% of all FH cases are diagnosed. i
FIND FH leverages machine learning and big data to identify individuals who should be evaluated by clinicians for diagnosis. Conducted in collaboration with the Stanford University School of Medicine, the study demonstrates for the first time that the screening algorithm correctly identified, 84 percent of the time, individuals with the highest probability of having FH. Thus, by applying the FIND FH algorithm to electronic health records (EHR), the screening algorithm significantly reduces the number needed to find eight people with FH from thousands to 10. “Familial hypercholesterolemia is a common life-threatening genetic disorder that is vastly underdiagnosed across the U.S. healthcare system,” said Katherine Wilemon, founder and CEO of the FH Foundation and co-author. “FIND FH is a precision screening tool that addresses this gap in care, by leveraging the latest cutting-edge technology to identify adults and children born with FH, who have historically fallen through the cracks. The FH Foundation is committed to working with health systems to accelerate the diagnosis and life-saving care of over 1 million people in the United States.” In addition to validation within Stanford Health Care, the EHR algorithm was independently validated with EHR data from a second health system. Today’s publication validates the EHR algorithm, and the algorithm designed to analyze national healthcare encounter databases and EHR records is being validated in multiple sites across the United States. “It’s imperative we change the paradigm for how we identify individuals with FH within healthcare systems because they are at high risk for cardiovascular disease,” said Daniel J. Rader, MD, chair of the department of Genetics in the Perelman School of Medicine at the University of Pennsylvania, Chief Scientific Advisor of The FH Foundation and co-author. “Applying advanced technology such as this novel FIND FH algorithm is particularly relevant for FH, because once flagged and diagnosed, individuals can immediately benefit from treatment with readily-available therapies.” About Familial Hypercholesterolemia (FH) About the FH Foundation
i Knowles J, et al. Reducing the burden of disease and death from familial hypercholesterolemia: A call to action. Am Heart J.2014;168:807-811. ii Hopkins P, Toth P. Familial hypercholesterolemia: prevalence, genetics, diagnosis and screening recommendations from the National Lipid Association Expert Panel on Familial Hypercholesterolemia. J Clin Lipidol. 2011 June;5(3 Suppl):S9–17.
SOURCE The FH Foundation |
View original content to download multimedia:
