Heart failure & cardiomyopathies
Testing a Novel Design Framework for Patient-Facing Machine Learning–Based Predictions of Heart Failure Decompensation
Authors' conclusion
The prototype demonstrated high levels of patient comprehension, appropriate risk perception, and behavioral intention, suggesting its viability for empowering patients with actionable health insights.
Study context
- Population
- English-speaking adults with implanted, actively transmitting cardiac implantable electronic devices (CIEDs) at a large, urban health systemcompleted the study
- Participants
- 20 adults
- Comparison
- Significant change vs Moderate change vs Little to no change
- Outcome
- Patient objective comprehension of the algorithm's output
Methodological detailssingle health system
- Single health system
Main finding
As reported in the abstract
Comprehension of algorithm output
Comprehension of algorithm output, across conditions
80% to 85%
Secondary outcomes
Comprehension of algorithm's threshold
- Comprehension of threshold, across conditions
- 60% to 85%
Comprehension of CIED sensors contributing to the algorithm
- Comprehension of contributing CIED sensors, across conditions
- 63% to 93%
Risk perception and behavioural intention (significant change condition)
- Moderately worried about worsening cardiac status
- 40%
- Very worried about worsening cardiac status
- 30%
- Would call their doctor
- 80%
Original publication
Testing a Novel Design Framework for Patient-Facing Machine Learning–Based Predictions of Heart Failure Decompensation. JACC Adv. Published 4 September 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →