Wise Practitioner – Predictive Analytics Interview Series: John Cromwell, M.D., University of Iowa Hospitals & Clinics
By: Jeff Deal, Program Chair, Predictive Analytics World Healthcare
In anticipation of his upcoming keynote conference presentation at Predictive Analytics World Healthcare in Boston, “Real-Time Modeling of Surgical Site Infections,” we asked John Cromwell, M.D., Associate Professor at University of Iowa Hospitals & Clinics, a few questions about his work in predictive analytics.
Q: In your work with predictive analytics, what area of healthcare are you focused on (i.e., clinical outcomes, insurance, quality improvement, etc.)?
A: Focusing is difficult given the broad array of challenges facing hospitals today. Having said that, our work has been primarily on clinical outcomes and quality improvement.
Q: What clinical outcomes do your models predict?
A: My group works on quality and performance in surgery. In the context of surgical patients, we are modeling readmissions, surgical site infections, and the development other hospital-acquired infections such Clostridium Difficile.
Q: How does predictive analytics deliver value at your organization? What is one specific way in which it actively drives decisions?
A: PA allows us to prioritize use of both institutional and community resources for improving outcomes for a large population. As an example, surgical site infections are dangerous and expensive. Being able to predict surgical site infections from the operating room before a patient’s incision has been closed allows us to change our wound management strategy up front. Targeting of resource-intensive and invasive wound management strategies to patients who will benefit the most is good for everyone.