Hospitals in Northeast Ohio are using artificial intelligence to help detect sepsis, a reaction to infection that can quickly turn deadly if not treated in time.
At Cleveland Clinic, an AI platform has been rolled out across hospitals to monitor patient data in real time. The system scans vital signs, lab results and medical history to identify patterns that may signal a patient is getting worse. Akron-based Summa Health also has an .
Sepsis affects about 1.7 million Americans each year and can be difficult to diagnose because symptoms vary widely. Early treatment is critical to survival.
Dr. James Morrison, an emergency physician at the Clinic, said the technology is designed to support clinicians, not replace them.
鈥淭his isn't about AI solving sepsis,鈥� he said. 鈥淚t's about helping the clinicians recognize sepsis and intervene in a timely manner.鈥�
The tool, developed with the private health-care firm Bayesian Health, runs in the background and alerts providers when a patient may be at risk. In pilot programs, it identified more cases while reducing false alarms. In some cases, it flagged problems hours earlier than traditional methods, giving doctors more time to treat patients.
Still, Morrison said he worries about overreliance on the technology and the risk of errors or bias.
鈥淎nd also if everything happens by the AI, and clinicians鈥� ability to detect (sepsis) atrophies, what happens if the AI isn鈥檛 there?鈥� he said.
For now, Morrison said, the tool is just one part of clinical decision-making, with physicians continuing to lead patient care while the system is closely monitored and refined over time.
