St. Michael's Hospital reduces unplanned mortality by over 20% with AI patient support prediction

Hospitals face growing numbers of complex patients with insufficient physician resources to assess acuity and allocate support appropriately. Clinicians needed better tools to predict which patients would require higher levels of intervention before outcomes deteriorated.

Researchers at Unity Health Toronto deployed AI tools at St. Michael's Hospital to predict the level of support each patient would need, enabling earlier and more targeted interventions while helping balance physician workloads.

Since the program's deployment at St. Michael's, unplanned mortality has fallen by over 20 per cent, demonstrating meaningful improvement in patient outcomes alongside reduced physician workload pressure.

• AI-driven patient acuity prediction can materially reduce preventable deaths in hospital settings.
• Clinical decision support AI can address both patient outcomes and physician workload simultaneously.
• Academic medical centers are early adopters able to validate AI tools before broader health-system rollout.