AI heads to hospital
Marzyeh Ghassemi has designed a series of machine-learning methods to turn untidy clinical data into useful forecasts about how patients will do during a hospital stay. And that has made her one of MIT Technology Review’s top 25 innovators under 35.
Her algorithms take diverse clinical data and accurately predict things like how long patients will stay in hospital, how likely they are to die, and whether they’ll need interventions such as blood transfusions or ventilators.
Ghassemi joins the University of Toronto and the Vector Institute for Artificial Intelligence, where she’s hoping to test her algorithms at local hospitals.
Image: MIT Technology Review