Speakers
Description
Authors: Damon Jones (Penn State University), Joel Segel (Penn State University), Michael Donovan (The Pennsylvania State University)
Background: Effective prevention policy requires decision-makers to rapidly interpret complex, cross-sector data and translate research into actionable strategies. This session explores technological and methodological innovations that bridge research, practice, and policy, focusing on tools that enhance evidence-based decision-making and research translation.
Methods: This session showcases a suite of decision-support tools and translational strategies developed within existing research and practice contexts. These research programs typically employ both quantitative and qualitative methods.
Results: Discussion includes lessons learned from:
• An AI-supported Early Warning System (EWS) for substance use threats that demonstrated improved detection of acute substance use threats, enabling faster, more targeted interventions.
• An AI chatbot designed to help policymakers and practitioners navigate evidence-based prevention resources.
• A demonstration of a Tableau-based tool for approximating monetary benefits of a known evidence-based programs across multiple policy areas, illustrating how data visualization can inform resource allocation and maximize programmatic impact in the US context.
Discussion: Integrating advanced analytics, AI, and visualization tools into prevention policy decision-making accelerates the translation of research into practice, fosters cross-sector collaboration, and improves the timeliness and quality of interventions. Effective research translation hinges on partnerships, tailored communication, and interoperable data systems that connect researchers, policymakers, and practitioners. These innovations collectively advance the prevention continuum, ensuring that policy decisions are informed by robust evidence, responsive to local needs, and positioned for real-world impact.
| Conflict of interest | None |
|---|
