At ISPOR 2026, Forian presented new findings exploring why some patients identified as high risk for congestive heart failure (CHF) progress to disease while others remain stable. Using Forian's CHRONOS real-world data ecosystem and machine learning models, the study examined demographic, clinical, and care-delivery factors associated with different patient trajectories, revealing important insights that go beyond traditional risk scoring methods.
In a recent Q&A with The Evidence Base, our researchers Mike Sicilia and Wouter van der Pluijm discuss the study's methodology, key findings, and the potential role of machine learning in identifying actionable opportunities for earlier intervention. The research suggests that factors such as preventive care, specialist engagement, and treatment patterns may influence outcomes even among patients already classified as high risk.
Read the full interview to learn how these insights could help inform future heart failure prevention and risk stratification strategies.
