410. Generating Real-World Nutrition Data in the Era of Artificial Intelligence
Healthy nutrition behavior is critical for managing weight and chronic disease. While randomized control trials have shown healthy behaviors can lead to better outcomes, they are conducted on very selective populations. Meanwhile, real-world populations are more heterogeneous. Using the Academy’s Health Informatics Infrastructure (ANDHII) to collect outcomes using Nutrition Care Process terminology enables analysis of practice-based data at scale, creating new opportunities for understanding the impact of nutrition behavioral heterogeneity. The session will explore how to generate evidence from ANDHII’s Dietetics Outcomes Registry (DOR) as part of a joint IBM Research and Academy study. Opportunities and challenges facing the use of data-driven and knowledge-driven approaches in understanding how real-world patients respond to nutritional interventions will be discussed. By participating in real-world data collection, RDNs can support machine learning that may help predict improved personalized nutrition care pathways.
- Explain how the Dietetic Outcomes Registry can impact real-world evidence generation using the IBM Research and Academy collaboration case study as an example.
- Identify the opportunities and challenges in applying data-driven and knowledge-driven approaches in understanding nutrition health behaviors.
- Outline the new leading role of dietitians in quality data production for front-tier research based on observational data from practice.
Learning Need Codes:
- 9030 Outcomes research, cost-benefit analysis
- 9010 Data analysis, statistics
- 1065 Informatics
- 12.5.4 Develops recommendations considering evaluation data, needs of the population, trending data, cost-benefit analysis and funding source.
- 5.1.1 Demonstrates proficient use of technical operating systems and software to communicate and disseminate information; to collect, track and retrieve data; and to create documents, spreadsheets and presentations.
- 6.3.7 Interprets data to make recommendations and to form realistic and valid conclusions.
Rosa Hand, PhD, RDN, LD, FAND
Department of Nutrition, Case Western Reserve University
Carrie Hamady, MS, RDN, LD
Director, Undergraduate Didactic Program in Nutrition and Dietetics
Bowling Green State University
Pei-Yun Sabrina Hsueh, PhD
Research Staff Member
IBM Research, Center for Computational Health, IBM T.J. Watson Research Center