By: Jeff Deal, Conference Chair, Predictive Analytics World for Healthcare
In anticipation of his upcoming conference presentation at Predictive Analytics World for Healthcare Las Vegas, June 16-20, 2019, we asked Cal Zemelman, Director, Lead Data Scientist at CVP, a few questions about their deployment of predictive analytics. Catch a glimpse of his presentation, Explainable AI – What Factors are Important for Hospital Readmission?, and see what’s in store at the PAW Healthcare conference in Las Vegas.
Q: In your work with predictive analytics, what area of healthcare are you focused on?
A: We use ML for a variety of applications in healthcare. For this presentation, we’ll be talking about using it for predicting hospital readmissions. A study commissioned by Medicare in 2011 found there were approximately $17 billion in avoidable readmissions annually.
Q: What outcomes do your models predict?
A: Whether or not a patient with a certain condition might be readmitted or not. We initially focused on complications due to diabetes and are now looking into pneumonia.
Q: How does predictive analytics deliver value at your organization? What is one specific way in which it actively drives decisions or impacts operations?
A: By predicting who might be readmitted for a certain condition, we can design one or more interventions that may prevent or minimize the cost. For example, patients at a high likelihood of readmission for complications due to diabetes could receive a follow up call from a nurse checking on if they are managing their insulin levels well.
Q: Can you describe a successful result, such as the predictive lift of your model or the ROI of an analytics initiative?
A: Our first proof of concept model was 66% accurate on a hold-out dataset.
Q: What areas of healthcare do you think have seen the greatest advances or ROI from the use of predictive analytics?
A: I think radiology and other use cases where AI/ML can be used to analyze an image have been the most successful so far. I think it is only a matter of years before most large health/hospital systems are using predictive analytics for a dozen different initiatives.
Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.
A: We are going to break open the “black box” of an ML model and look at what factors increased the probability of hospital readmission at both the individual case and overall levels.
—————————–
Don’t miss Cal’s presentation, Explainable AI – What Factors are Important for Hospital Readmission?, at PAW Healthcare on Tuesday, June 18, 2019 from 2:40 to 3:20 PM. Click here to register for attendance.
By: Jeff Deal, Conference Chair, Predictive Analytics World for Healthcare
This content is restricted to site members. If you are an existing user, please log in on the right (desktop) or below (mobile). If not, register today and gain free access to original content and industry news. See the details here.
 |
 |
 |
