Heart failure & cardiomyopathiesCohort study
Improved Risk Assessment in Parvovirus B19-Positive Patients with Heart Failure By Multiparametric Analysis of Endomyocardial Biopsy Using Machine Learning Methods
- Retrospective cohort study
- machine learning prognostic model
Authors' conclusion
Intramyocardial inflammation and B19V viral activity were detected more frequently in patients with poor clinical outcome, suggesting that they are risk factors for death and LV dysfunction. Using multiparametric EMB data, we present an ML-based prognostic tool that can determine the clinical outcome of patients with a high degree of accuracy.
Study context
- Population
- B19V-positive patients with heart failure (HF) undergoing endomyocardial biopsy
- Participants
- 263 patients
- Exposure
- Machine learning (ML) models using multiparametric endomyocardial biopsies (EMB) markers for risk prediction
- Outcome
- Combined endpoint: all-cause mortality, left ventricular (LV) deterioration and persistent LV systolic dysfunction
- Follow-up
- Median 22 months (IQR 4-35 months)
Main finding
As reported in the abstract
Intramyocardial inflammation and B19V viral activity associated with poor clinical outcome: HR
3.50 (95% CI 1.96-6.23, p < 0.001)
Single features, AUC
0.724
Linear combination of demographic and clinical data with multiparametric EMB markers, AUC
0.724
Gradient boosting ML, AUC
0.926
Observational data: associations, not effects.
Original publication
Summarised from the published abstract; every number is checked against it