Poster on Results from PredictCME Analysis Presented at 2017 Society for Academic Continuing Medical Education (SACME) Conference

Share Article

Findings showed confidence to be the strongest predictor of practice behavior, with number of patients seen as a secondary predictor

CME Outfitters (CMEO), a leading accredited provider in continuing medical education, is excited to have presented findings from their exclusive PredictCME analysis of outcomes from an educational activity on Alzheimer’s disease (AD). Jamie Reiter, PhD, Director of Educational Outcomes, presented findings in a rapid-fire-style (3-minute) format at the 2017 Society for Academic Continuing Medical Education (SACME) Conference in Scottsdale, AZ, on May 18th. Posters were available for viewing during the entire conference.

The presentation focused on PredictCME, CMEO’s latest offering for adding value and dimension to its outcomes studies. “Traditional statistical comparisons of pre- versus post-activity performance are important for demonstrating performance improvement,” said Dr. Reiter. “However, they do not provide information regarding the factors that influence practice behaviors, which will help guide needs assessments for future activities and ensure the appropriate topics, formats, questions, and audiences are targeted.”

PredictCME is based on a form of predictive modeling, known as CHAID (chi-square automatic interaction detection). CHAID is often used in data mining, but CMEO is the first provider to use it in medical education. PredictCME is CME Outfitters’ exclusive method for applying CHAID to their educational activities, so that they can design future activities with a scientific basis for what impacts performance. PredictCME has advantages over linear and logistic regression, including the ability to incorporate both continuous and categorical data, as well as output in the form of a classification (or decision) tree. The visual output provides a detailed and intuitive representation of the interplay between predictor and response variables, as well as how the variable categories are broken down.

In this particular study, outcomes data from 262 HCPs participating in an educational activity on AD were analyzed using PredictCME. A question related to practice behavior was entered into the model as the response variable, with variables such as knowledge, number of patients seen with AD, years in practice, and confidence entered as predictor variables. Results showed that the strongest predictor of practice behavior was confidence, with a secondary predictor being the number of patients with AD seen by the learners.

Findings reported from this study are being used to develop future activities on AD by evaluating ways to improve HCP confidence, address the needs of HCPs who don’t see a large number of patients with AD, and address barriers of HCPs whose sheer volume of patients may impede their ability to make meaningful changes to their practices. In addition, as this study involved a single activity and therapeutic area, additional PredictCME analyses are currently underway for both individual activities and a meta-analysis format, examining different formats, audiences, and therapeutic areas. “The idea is to develop a framework for developing activities based on the differing needs of learners,” said Reiter. “For example, although this study showed confidence and number of patients seen as the strongest predictors of behavior in AD, preliminary findings of other PredictCME analyses found confidence and specialty to predict behavior in multiple sclerosis, and practice setting to be the strongest predictor of knowledge for rheumatologists. So, as many professionals in this industry have suspected, medical education is clearly not one-size-fits all, and we need to start understanding what these differences are and how to address them.”

“These findings demonstrate not only the innovative approach to applying PredictCME to medical education,” explained Reiter, “but also in demonstrating its value for better understanding the influences of practice behavior, which in turn will help maximize the impact of future activities, and ultimately patient outcomes.”

A copy of the poster is available at the CMEO website, click here to view.

About CME Outfitters, LLC
CME Outfitters develops and distributes live, recorded and web-based, outcomes- and evidence-based educational activities to thousands of clinicians each year and offers expert accreditation and outcome services for non-accredited organizations. CME Outfitters focuses on delivering education to specialty audiences, with strong expertise in neuroscience, inflammatory, infectious, and autoimmune diseases, and cardiovascular disease. For a complete list of certified activities and more information, visit or call 877.CME.PROS (877.263.7767).

“CME Outfitters …
Improving Clinical Behavior … One Change at a Time”

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Anna Larkin
CME Outfitters LLC
Email >
Follow us on