Heart failure & cardiomyopathies
Design and Architecture of a Generative-AI-Supported, Nonphysician-Delivered Model for Guideline-directed Medical Therapy (GDMT) Optimization in HFrEF: The ASSIST-HF Trial
Authors' conclusion
Treatment by an artificial intelligence-powered VA, run by nonmedical staff, with minimal remote medical supervision, is acceptable to patients, and can safely and effectively optimize GDMT, representing a scalable strategy to optimize treatment and health care resource utilization.
Study context
- Population
- Patients with new heart failure with reduced ejection fraction
- Participants
- 60 patients
- Exposure
- Virtual assistant (VA)-guided care vs standard-of-care treatment delivered by doctors or nurses
- Outcome
- GDMT optimization, N-terminal pro-B-type natriuretic peptide, hospitalizations
- Follow-up
- 12 weeks
Methodological detailsrandomized
- Randomized
Main finding
As reported in the abstract
- VA arm had superior GDMT optimization across all medication classes, lower N-terminal pro-B-type natriuretic peptide, and fewer hospitalizations
Observational data: associations, not effects.
Further findings
Patient-reported acceptability, appropriateness and feasibility scores
- Scores were high
Safety disagreements between VA and clinician recommendations
- No safety disagreements between VA and clinician recommendations
Original publication
Design and Architecture of a Generative-AI-Supported, Nonphysician-Delivered Model for GDMT Optimization in HFrEF: The ASSIST-HF Trial. JACC Adv. Published 11 February 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →