The University of California San Francisco will put machine-learning capabilities in the hands of clinicians under a program that will allow them to access actionable data and images with greater speed, said Michael Blum, M.D., associate vice chancellor of informatics at UCSF, in an announcement.
“There’s tremendous opportunity to look at large datasets, like medical images, to predict how patients will do,” Blum told FastCompany.
The aim is to help clinicians use data in a way that helps them treat common and complex conditions faster and more effectively. Radiologists in particular could benefit from integrated data collected from imaging technologies already in use, such as CT scans, MRIs and x-rays, the announcement says.
RELATED: 3 ways machine learning will transform healthcare
The deep-learning algorithms are trained to figure out problems that can only be solved with expansive computing power and data sets.
"The collaboration is initially focused on high-volume, high-impact imaging to create algorithms that reliably distinguish between what is considered a normal result and what requires follow up or acute intervention," according to the announcement. "One early example of an algorithm under development is a solution for pneumothorax, or a collapsed lung. The algorithm will be focused on teaching machines to distinguish between normal and abnormal scans so clinicians can prioritize and more quickly treat patients with pneumothorax, which can be a life-threatening condition."
RELATED: EHRs at the Olympics: Boon, bane or both?
The organization is partnering with GE Healthcare on the program. GE previously partnered with the International Olympic Committee to collect data for studying population health.