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.”
Simon is one of the principal investigators on a new project, supported by a $1.4 million Minnesota state grant, to develop better methods and risk management processes for clinical AI and machine learning involved in patient care. The research will focus on AI tools used to support clinical decisions in three areas: postoperative complications, sepsis, and rapid deterioration of patients.
This article is exclusive to STAT+ subscribers
Unlock this article — and get additional analysis of the technologies disrupting health care — by subscribing to STAT+.
Already have an account? Log in
Already have an account? Log in
To submit a correction request, please visit our Contact Us page.
STAT encourages you to share your voice. We welcome your commentary, criticism, and expertise on our subscriber-only platform, STAT+ Connect