Machine learning screens patients for life-threatening genetic disease
Using large healthcare encounter datasets, a machine learning algorithm is able to identify patients with a common genetic disorder that carries a high risk for early heart attacks and strokes.
Using large healthcare encounter datasets, a machine learning algorithm is able to identify patients with a common genetic disorder that carries a high risk for early heart attacks and strokes.
While individuals with familial hypercholesterolaemia (FH) have 20 times the risk of developing cardiovascular disease than the general population, fewer than 10 percent of the 1.3 million Americans born with the genetic disease are diagnosed.
“People born with familial hypercholesterolemia develop cardiovascular damage by puberty, often culminating in early heart attacks or the need for surgery as young or middle-aged adults," says Katherine Wilemon, founder and CEO of the FH Foundation, a non-profit research and advocacy organization. “Since diagnosis of this deadly but treatable condition has stalled in the American medical system, the FH Foundation harnessed artificial intelligence and big data to accelerate identification of those most likely to have FH.”
In a new study, a machine learning model created by the FH Foundation successfully leveraged healthcare encounter databases to identify individuals with the genetic disorder.
Specifically, the FIND (Flag, Identify, Network, Deliver) FH model utilized a database that has been developed over the past six years by the FH Foundation and includes national healthcare encounter data on more 272 million individuals in the U.S. being treated or evaluated for cardiovascular disease.
In addition, the study used electronic health record data from the Oregon Health & Science University healthcare system that included diagnoses, procedures, laboratory tests, as well as medications.
According to the results, the FIND FH model correctly identified individuals with probable FH 87 percent of the time in the national database and 77 percent of the time in the Oregon Health & Science University EHR.
“FIND FH identified a large number of individuals with probable familial hypercholesterolaemia who had not been previously diagnosed,” states the study published online this week in The Lancet Digital Health journal. “This new tool carries the promise of finding new individuals with familial hypercholesterolaemia at scale and leading to more effective preventive therapy for them and newly identified family members.”
“Precision screening for FH is now a reality in any healthcare system with electronic health records," concludes study co-author Daniel Rader, MD, chair of the Department of Genetics in the Perelman School of Medicine at the University of Pennsylvania and chief scientific advisor of the FH Foundation. “We no longer need to screen everyone to find individuals who are at genetic risk for heart attacks and strokes. After further clinical evaluation, if an FH diagnosis is made, it will trigger screening of relatives as well. While FH is manageable, the greatest benefit is from treatment earlier in life."
While individuals with familial hypercholesterolaemia (FH) have 20 times the risk of developing cardiovascular disease than the general population, fewer than 10 percent of the 1.3 million Americans born with the genetic disease are diagnosed.
“People born with familial hypercholesterolemia develop cardiovascular damage by puberty, often culminating in early heart attacks or the need for surgery as young or middle-aged adults," says Katherine Wilemon, founder and CEO of the FH Foundation, a non-profit research and advocacy organization. “Since diagnosis of this deadly but treatable condition has stalled in the American medical system, the FH Foundation harnessed artificial intelligence and big data to accelerate identification of those most likely to have FH.”
In a new study, a machine learning model created by the FH Foundation successfully leveraged healthcare encounter databases to identify individuals with the genetic disorder.
Specifically, the FIND (Flag, Identify, Network, Deliver) FH model utilized a database that has been developed over the past six years by the FH Foundation and includes national healthcare encounter data on more 272 million individuals in the U.S. being treated or evaluated for cardiovascular disease.
In addition, the study used electronic health record data from the Oregon Health & Science University healthcare system that included diagnoses, procedures, laboratory tests, as well as medications.
According to the results, the FIND FH model correctly identified individuals with probable FH 87 percent of the time in the national database and 77 percent of the time in the Oregon Health & Science University EHR.
“FIND FH identified a large number of individuals with probable familial hypercholesterolaemia who had not been previously diagnosed,” states the study published online this week in The Lancet Digital Health journal. “This new tool carries the promise of finding new individuals with familial hypercholesterolaemia at scale and leading to more effective preventive therapy for them and newly identified family members.”
“Precision screening for FH is now a reality in any healthcare system with electronic health records," concludes study co-author Daniel Rader, MD, chair of the Department of Genetics in the Perelman School of Medicine at the University of Pennsylvania and chief scientific advisor of the FH Foundation. “We no longer need to screen everyone to find individuals who are at genetic risk for heart attacks and strokes. After further clinical evaluation, if an FH diagnosis is made, it will trigger screening of relatives as well. While FH is manageable, the greatest benefit is from treatment earlier in life."
More for you
Loading data for hdm_tax_topic #better-outcomes...