New artificial intelligence software designed to be an early warning system for sepsis has turned out not as helpful as previously hoped. According to a new U-M study, the model lacked accuracy, having a hard time differentiating between high and low-risk patients. Read more about the findings and the implications for the software’s implementation in hospitals in this article from the Institute for Healthcare Policy and Innovation.
![Group Shot Abrams Deans Symposium Featured 1090x681](https://alumni.umich.edu/wp-content/uploads/group-shot-abrams-deans-symposium-featured-1090x681-1.jpg)