@ShahidNShah
Diagnostic AI may be vulnerable to cyberattacks, UPMC study shows
A study published in Nature Communications this week investigated whether adversarial images could fool an artificial intelligence model developed to diagnose breast cancer.
University of Pittsburgh researchers were able to simulate an attack that falsified mammogram images, leading the model – and human experts – to draw incorrect conclusions.
"What we want to show with this study is that this type of attack is possible, and it could lead AI models to make the wrong diagnosis – which is a big patient safety issue," senior author Shandong Wu, associate professor of radiology, biomedical informatics and bioengineering at Pitt, said in a statement.
"By understanding how AI models behave under adversarial
Continue reading at healthcareitnews.com
Make faster decisions with community advice
- Big data startup Innovaccer nabs $150M, catapults to $3.2B valuation
- Building the machine learning model isn't enough
- Former CMS chief of staff previews 4 areas of value-based care in 2022
- Precision dosing can create safer and more effective medication
- Sheba Medical Center’s ARC Innovation Center Raises Over $110M in 2021
Next Article
-
Former CMS chief of staff previews 4 areas of value-based care in 2022
Value-based care continues to take root in healthcare. It's clear the future of reimbursement will at minimum include a heaping portion of providers being paid for value as opposed to volume. This is …
Posted Dec 15, 2021 Value-Based Care Consulting