A recent study conducted by researchers in Canada assessed the effectiveness of CHARTWatch, an artificial intelligence (AI) early warning system developed at Unity Health Toronto. This system monitors hospitalised patients in real-time, identifies individuals at high risk of an unexpected death or transfer to an intensive care unit, and promptly alerts doctors and nurses to intervene early.
The study, published in the Canadian Medical Association Journal, showed a drop of 26 per cent in unanticipated mortality after the tool was executed in the general internal medicine ward of Unity Health Toronto’s St. Michael’s Hospital.
Also Read: This corporate employee-focused women-led startup uses AI to inspire people to prioritise self-care
“As AI tools are increasingly being used in medicine, it is important that they are evaluated carefully to ensure that they are safe and effective,” said lead author Amol Verma, general internist at Unity Health and professor at the University of Toronto’s Temerty Faculty of Medicine who led the development and implementation of CHARTWatch.
He mentioned that the study’s findings suggested that AI-based early warning systems were promising for reducing unexpected deaths in hospitals.
The study analyzed data from 13,649 patients aged 55 to 80 years old. This included 9,626 patients in the pre-intervention period and 4,023 patients using CHARTWatch, who were admitted to the general internal medicine unit. Additionally, 8,470 patients admitted to subspecialty units did not use CHARTWatch.
“This important study evaluates the outcomes associated with the complex deployment of the entire AI solution, which is critical to understanding the real-world impacts of this promising technology,” said study co-author Muhammad Mamdani, VP of data science and advanced analytics at Unity Health and director of U of T’s Temerty Centre for Artificial Intelligence Research and Education in Medicine.
Verma mentioned that the CHARTWatch project started when patients, clinicians, and hospital leaders were asked what they would like to use AI for?
Also Read: This Indian healthcare firm explores Google’s AI model to detect disease based on coughs
“If you could predict one thing AI would tell you, what should that be? And one of the leading priorities of everyone was to be able to predict in advance which patients might become so sick in hospital that they need ICU or might die,” he said.
The CHARTWatch system analyzes over 100 aspects of a patient’s medical history and current health status, which are regularly stored in the hospital’s electronic medical record. It examines how these inputs interact and change over time to categorize each patient based on their risk for deterioration. It then sends an alert to prioritize treatment.