Geisinger uses machine learning to speed up diagnosis of potentially fatal internal head bleeding
,
Time to diagnosis of intracranial hemorrhages reduced by 96 percent
DANVILLE, Pa. – Doctors and researchers at Geisinger have trained computers to “read” CT scans of patients’ heads to detect a life-threatening form of internal bleeding known as intracranial hemorrhage.
By using this innovative approach, Geisinger specialists have reduced the time to diagnosis of intracranial hemorrhages by 96 percent.
This form of internal head bleeding affects approximately 50,000 patients per year in the United States, with 47 percent of patients dying within 30 days. Early and accurate diagnosis is critical for these patients.
Machine learning – using computers to detect patterns in data -- has been so successful, it is now being introduced into the regular clinical workflow at Geisinger.
“This is not about replacing doctors with machines,” said Aalpen Patel, M.D., chair, Geisinger System Radiology. “This is about the smart use of machine learning technology to aid medical providers in delivering better and faster care, especially in these areas where time is critical.”
As an early adopter of the electronic health record, Geisinger has been able to combine radiographic and other medical imaging data that allows specialists to train computers to accurately pinpoint the worst cases. This flags the most urgent images for priority review by radiologists, leading to earlier diagnosis and life-saving emergency interventions.
In a recent case, an 88-year-old woman presenting with symptoms thought to be related to her medication was rushed to the emergency department after the machine algorithm flagged her CT scan for urgent attention. As it turns out, she was actually suffering from an intracranial hemorrhage which was safely resolved by medical intervention.
“The use of intelligent computer assistance is imperative in order to sustain and improve medical care,” said Brandon K. Fornwalt, M.D., Ph.D., associate professor and director, Geisinger Department of Imaging Science & Innovation.
“Geisinger is proud to be at the forefront of clinical applications of these technologies,” said Fornwalt, who is applying machine learning in other areas, including patients with congenital heart disease.
By using this innovative approach, Geisinger specialists have reduced the time to diagnosis of intracranial hemorrhages by 96 percent.
This form of internal head bleeding affects approximately 50,000 patients per year in the United States, with 47 percent of patients dying within 30 days. Early and accurate diagnosis is critical for these patients.
Machine learning – using computers to detect patterns in data -- has been so successful, it is now being introduced into the regular clinical workflow at Geisinger.
“This is not about replacing doctors with machines,” said Aalpen Patel, M.D., chair, Geisinger System Radiology. “This is about the smart use of machine learning technology to aid medical providers in delivering better and faster care, especially in these areas where time is critical.”
As an early adopter of the electronic health record, Geisinger has been able to combine radiographic and other medical imaging data that allows specialists to train computers to accurately pinpoint the worst cases. This flags the most urgent images for priority review by radiologists, leading to earlier diagnosis and life-saving emergency interventions.
In a recent case, an 88-year-old woman presenting with symptoms thought to be related to her medication was rushed to the emergency department after the machine algorithm flagged her CT scan for urgent attention. As it turns out, she was actually suffering from an intracranial hemorrhage which was safely resolved by medical intervention.
“The use of intelligent computer assistance is imperative in order to sustain and improve medical care,” said Brandon K. Fornwalt, M.D., Ph.D., associate professor and director, Geisinger Department of Imaging Science & Innovation.
“Geisinger is proud to be at the forefront of clinical applications of these technologies,” said Fornwalt, who is applying machine learning in other areas, including patients with congenital heart disease.
About Geisinger
Geisinger is committed to making better health easier for the more than 1 million people it serves. Founded more than 100 years ago by Abigail Geisinger, the system now includes 10 hospital campuses, a health plan with more than half a million members, a research institute and the Geisinger College of Health Sciences, which includes schools of medicine, nursing and graduate education. With more than 25,000 employees and 1,700+ employed physicians, Geisinger boosts its hometown economies in Pennsylvania by billions of dollars annually. Learn more at geisinger.org or connect with us on Facebook, Instagram, LinkedIn and Twitter.
