There’s been a big push on reducing hospital readmissions, in recent years, and it’s no surprise the providers are turning to AI for help.
At HIMSS21 in Las Vega, in a session titled, ”Applying Clinical AI to Reduce Readmissions by More Than 20%, ” Dr. Zenobia Brown, vice president and medical director at Northwell Health, a health system based in Manhasset, New York, will be discussing how her organization has been applying clinical AI to augment their post-discharge workflows and have reduced readmissions by 23.6% along the way.
As our colleague Bill Siwicki explained recently in an article at HealthcareIT News, clinicians at Northwell, the largest provider in New York State, “studied clinical AI stratified patients for their risk of readmissions, identified the clinical and nonclinical factors driving their risk, and recommended targeted outreach and interventions to reduce patient risk.”
According to Dr. Brown, “(p)redictive analytics as a whole is a powerful tool using a combination of historical data, statistical modeling, data mining and machine learning in order to predict events and identify patterns.”
Predictive analytics, she explained, uses predictive modeling to make specific recommendations across a matrix of potential decision points, thus adding the capacity to operationalize any given information.
"When orienting clinical teams to prescriptive analytics, I liken it to how we as providers make recommendations based on our understanding of the clinical data and our experience over time, which [lead] us to the 'right clinical decision,’” she said. "I ask my teams to imagine how much better their decision-making would be if they had one million times the experiences in that set of clinical data, and the experience of treating the disease one million different ways in a million different types of patients. This is what prescriptive analytics supports; a way to make decisions in managing the complexity represented by patients beyond the data set that is limited by the human brain."
So how does clinical AI integrate into the clinical workflow to augment transitions of care and prevent readmissions post-discharge?
First, said Brown, providers need to trust their technology.
"If they don't believe it works, or don't see the value in how it helps their time or helps the patient, there is zero chance of good operational integration.”
And part of gaining that trust, she added, “was sharing these cases of patterns that otherwise would have been missed; the 'good catches.’ This reinforced the value of the tool. Also important was making sure the predictions and recommendations were timely, such that the team had appropriate lead time to impact each patient.”
For the team, that meant that the AI/predictive modeling tool was being refreshed multiple times per day, while the patients were still in the hospital, so that the identification of the high-risk patients could happen as far upstream as possible.
Dr. Brown’s session at HIMSS21 is scheduled for August 11, from 4:15 to 5:15 p.m., in Venetian Murano 3201A.
Photo by vmjpg/Getty Photo