Ross Upton, Founder, CEO and Chief Scientific Officer at Ultromics , posted on LinkedIn, about recent paper he and collagues co-authored:
“New Publication.
Thrilled to share that our paper “External validation of artificial intelligence for detection of heart failure with preserved ejection fraction (HFpEF)” has just been published in Nature Portfolio Communications!
Why it matters:
- Diagnosing HFpEF remains one of the toughest challenges in cardiovascular medicine.
- Traditional multiparametric clinical scores like H2FPEF and HFA-PEFF often return indeterminate results, leaving clinicians unsure about next steps.
In this external validation study, we evaluated the updated EchoGo Heart Failure v2 AI model against these clinical scores in a complex and diverse real-world population at Beth Israel Deaconess Medical Center.
What we found:
- EchoGo HF produced fewer indeterminate results vs clinical scores (15% vs 62%)
- A diagnostic positive EchoGo HF result was associated with almost 3x higher risk of HF hospitalization
- Combining EchoGo HF and clinical scores increases correct management decisions
This work highlights how AI can meaningfully augment HFpEF diagnosis, reducing diagnostic uncertainty and supporting earlier intervention.”
Authors: Ashley P. Akerman, Nora Al-Roub, Constance Angell-James, Madeline A. Cassidy, Rasheed Thompson, Lorenzo Bosque, Katharine Rainer, William Hawkes, Hania Piotrowska, Paul Leeson, Gary Woodward, Patricia A. Pellikka, Ross Upton, Jordan B. Strom
