Heart failure & cardiomyopathies
Mortality Prediction in Patients With or Without Heart Failure Using a Machine Learning Model
Authors' conclusion
MARKER-HF predicts mortality for patients with HF as well as for patients suffering from a variety of diseases.
Study context
- Population
- Consecutive patients undergoing echocardiography in a tertiary referral hospital
- Participants
- 41,749 patients
- Exposure
- MARKER-HF prediction of 1-year mortality in patients with vs without heart failure (HF)
- HFn = 4,640
- Without HFn = 37,109
- Outcome
- MARKER-HF prediction of mortality (AUC)
- Follow-up
- 1 year
Methodological detailssingle-centre, consecutive patients
- Single-centre
- Consecutive patients
Main finding
As reported in the abstract
1-year mortality prediction by MARKER-HF
| Group | AUC |
|---|---|
| HF | 0.729 (95% CI: 0.706-0.752) |
| Without HF | 0.770 (95% CI: 0.760-0.780) |
AUC
HF0.729 (95% CI: 0.706-0.752)
Without HF0.770 (95% CI: 0.760-0.780)
Observational data: associations, not effects.
Further findings
Mortality prediction by subgroup (with/without CVD, ACS, AF, COPD, CKD, DM, hypertension)
- MARKER-HF prediction of mortality consistent across subgroups
- Without HF: with CVD n = 22,946; without CVD n = 14,163
Mortality in patients with malignancy
- Higher mortality at a given MARKER-HF score than other groups
Original publication
Mortality Prediction in Patients With or Without Heart Failure Using a Machine Learning Model. JACC Adv. Published 22 August 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →