STAT+: In Minnesota, researchers explore how to audit health AI models on a patient level
As hospitals and companies continue to leverage artificial intelligence in medicine, researchers are also grappling with how to check the AI systems to protect patient safety.
“Risk management is a tricky business,” said Gyorgy Simon, scientific co-director for the University of Minnesota’s clinical AI program. “Treatment models are changing, the population is changing. So a model [from] two years ago that was working perfectly may not be working perfectly today for a particular patient.”
