How can big data improve clinical decision-making in behavior analysis? In this episode of the Cooperant Learning Podcast, host Kyle Steury welcomes Dr. David Cox—PhD behavior analyst, researcher at Endicott College, and expert in AI and clinical modeling—to discuss data-driven approaches to recommending ABA service hours.

What You’ll Learn in This Episode:

• Why current hour recommendations in ABA may be more guesswork than science
• How Dr. Cox’s team analyzed data from nearly 40,000 cases
• The role of dose-response curves and cluster analysis in identifying optimal therapy levels
• How data indicate that more isn’t always better when it comes to ABA hours
• Implications for adult services, funding decisions, and the ethics of using AI in clinical care
• How real-time data could one day guide session-level decisions for RBTs and BCBAs

David Cox holds a PhD in Behavior Analysis from University of Florida where he focused on basic choice processes, the role of VB in choice, and application to clinical and ethical decision-making. He completed a post-doc at Johns Hopkins University School of Medicine in Behavioral Pharmacology and from Insight! Data Science in Data Science. David has been with Endicott since 2019 and now teaches the PhD program with a research lab of 6 doctoral students. His research blends big data analytics, artificial intelligence, and his continued work in clinical decision-making. He has also partnered with various industry companies since 2020. Currently, he works as VP of Data Science for Mosaic Pediatric Therapy. 

Interested in how behavioral science and machine learning can work together to improve client outcomes? This episode is for you.

Brought to you by Sparks Behavioral ServicesThe BACB® does not endorse, approve, or assume responsibility for this course or its content. Completion of this course provides ACE-approved continuing education credit toward BACB® recertification requirements.