Early in her shift, the resident on call checked on her patient and reviewed the chart. Everything looked fine. A few hours later, though, that changed. She got a high-risk alert via CHARTWATCH, letting her know that things were no longer fine. She quickly called the ICU team. The resident credits CHARTWATCH for raising the alarm, and quite possibly saving the patient’s life.
CHARTWATCH is an early-warning AI program developed at St. Michael’s that looks at 100 different variables in a patient’s chart, including lab results and vital signs, and determines whether the patient is at a low, moderate or high risk of needing ICU care within the next 24 hours. CHARTWATCH updates the risk category for every patient every hour. When the tool flags a patient as having a high risk of going to the ICU, health-care teams know to intervene fast.
Staff cannot always tell when a patient’s condition is about to worsen; patients could have arrived at the ICU too late or could have avoided the ICU altogether if their condition had been recognized and treated earlier. There have already been situations where the algorithms picked up problems the clinicians had missed. That’s why we created CHARTWATCH. And why we’ve partnered with Signal 1, a health start-up that is using machine learning to save lives: CHARTWATCH is one of the first projects we’re collaborating on.
One big advantage offered by CHARTWATCH is the opportunity for doctors whose patients are destined for the ICU to have a conversation with them before they enter that confusing and stress-filled situation – to explain to them what is likely to happen, talk to them about decisions that might have to be made, and make sure they are as prepared for the experience as possible.
Donate to St. Michael's Foundation.