Veradigm Advances GLP-1 Real-World Evidence Generation with AI-Driven EHR Data Curation

CHICAGO--(BUSINESS WIRE)--Veradigm^® (OTCMKTS: MDRX), a leading provider of healthcare data and technology solutions, announced today an advancement in the use of artificial intelligence (AI) to scale the generation of real-world evidence (RWE) for GLP-1 receptor agonists (GLP-1 RAs), including semaglutide and tirzepatide. By applying AI to electronic health record (EHR) deidentified data within the Veradigm Network, researchers can now surface rich, contextual insights—such as side effects, discontinuation reasons, and social determinants of health (SDoH)—that traditionally required intensive manual curation.

“AI-powered curation allows us to unlock clinically meaningful insights from millions of patient records—insights that have traditionally been hidden in unstructured and semi-structured fields of EHR systems." -Stuart Green, SVP & GM Veradigm Life Sciences

Share

GLP-1 therapies are transforming the management of type 2 diabetes and obesity, yet significant gaps remain in understanding real-world usage, especially in identifying reasons for discontinuation or capturing side effects hidden in physician notes. Veradigm’s AI-driven approach enables scalable extraction of clinical signals from unstructured data, offering life science organizations deeper, real-time insight into patient experiences and outcomes.

“AI-powered curation allows us to unlock clinically meaningful insights from millions of patient records—insights that have traditionally been hidden in unstructured and semi-structured fields of EHR systems,” said Stuart Green, SVP & General Manager, Veradigm Life Sciences. “This is especially critical for GLP-1 therapies, where understanding why patients discontinue, or which side effects matter most can significantly improve patient outcomes and therapeutic strategy.”

Key Capabilities and Insights from Veradigm’s AI-Driven Curation Include:

• Discontinuation Drivers – Automatically extracts reasons for stopping therapy (e.g., side effects, cost, perceived inefficacy) from clinician notes
• Side Effects Monitoring – Detects and stratifies severity of gastrointestinal and side effects, such as gallbladder issues or psychiatric symptoms, through contextual analysis of progress notes
• Off-Brand Use Identification – Flags mentions of compounded or unapproved formulations (e.g., “semaglutide from weight-loss clinic”), supporting safety and market surveillance
• Outcome Tracking – Tracks comorbidities (e.g., cardiovascular events) and treatment responses not typically captured in structured EHR fields
• Social and Behavioral Context – Surfaces SDoH that influence adherence and health outcomes

This new offering leverages the national footprint of Veradigm Network EHR Data, capturing both structured and unstructured data across diverse patient populations and geographies. By pairing AI with clinical validation, Veradigm ensures data accuracy and applicability for life science research, regulatory engagement, and value-based decision-making.

Veradigm will present a research poster based on this data at ISPOR 2025 during Poster Session 2 on Wednesday, May 14, from 4:00–7:00 PM EDT. The poster will focus on GLP-1 persistence and the real-world reasons for therapy discontinuation. To learn more, view the poster abstract.

About Veradigm®

Veradigm is a healthcare technology company that drives value through its unique combination of platforms, data, expertise, connectivity, and scale. The Veradigm Network features a dynamic community of solutions and partners providing advanced insights, technology, and data-driven solutions for the healthcare provider, payer, and biopharma markets. For more information about how Veradigm is fulfilling its mission of Transforming Health, Insightfully, visit www.veradigm.com, or find Veradigm on LinkedIn, Facebook, Twitter, Instagram, and YouTube.

© 2025 Veradigm LLC and/or its affiliates. All rights reserved. Cited marks are the property of Veradigm LLC and/or its affiliates. All other product or company names are the property of their respective holders, all rights reserved.