Doctoral Dissertation Defense of Amanda Petrik, MS: The Use of Predictive Analytics for Population Health Management, Integrating Multilevel Data to Predict Colorectal Cancer Screening
September 28 @ 11:00 am - 1:00 pm
Doctoral Dissertation Defense: The Use of Predictive Analytics for Population Health Management, Integrating Multilevel Data to Predict Colorectal Cancer Screening
by Amanda Petrik, MS
The use of predictive analytics can help health systems target the right services to the right patients at the right time. Multilevel data may be used to improve risk prediction by providing information about a patient and the many groups to which they belong. This study assessed the availability of multilevel data, the improvement of predictive models, and health system leader’s perspectives when used to predict colorectal cancer screening. Multilevel data is available and usable, but not consistently at all levels. The predictive models developed were sufficient for predicting patient’s likelihood of screening for colorectal cancer, but multilevel data did not improve the performance of predictive models. Stakeholders found the models useful. Multilevel data should continue to be explored as potential predictors of health outcomes.
This is a virtual event. Please contact Amanda at petrik[at]pdx.edu for the link.