Machine learning platform cuts intracranial hemorrhage diagnosis time by 96%
A group of doctors and researchers at Geisinger Health System in Pennsylvania created a machine learning platform able to read CT scans that reduced the time to detect a life-threatening form of internal bleeding by 96 percent.
Recently at the health system, the algorithm flagged the CT scan of an 88-year-old woman for urgent attention, whereby she was rushed to the emergency department (ED). Originally, her condition was attributed to a medication complication, but she was actually suffering from an intracranial hemorrhage. Her situation was resolved in the ED.
"This is not about replacing doctors with machines," said Aalpen Patel, MD, chair, Geisinger System Radiology in a statement. "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.”
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.