Litcius/Paper detail

Ensemble machine learning model identifies patients with HFpEF from matrix-related plasma biomarkers

Michael M. Ward, Amirreza Yeganegi, Catalin F. Baicu, Amy D. Bradshaw, Francis G. Spinale, Michael R. Zile, William J. Richardson

2022American Journal of Physiology-Heart and Circulatory Physiology16 citationsDOIOpen Access PDF

Abstract

Machine learning algorithms correctly classified patients with heart failure with preserved ejection fraction with over 90% area under receiver-operating-characteristic curves. Classifications using multidomain features (demographics and circulating biomarkers and echo-based ventricle metrics) proved more accurate than previous studies using single-domain features alone. Excitingly, HFpEF diagnoses were generally accurate even without echo-based measurements, demonstrating that such algorithms could provide an early screening tool using blood-based measurements before sophisticated imaging.

Topics & Concepts

Heart failure with preserved ejection fractionReceiver operating characteristicCardiologyInternal medicineMedicineHeart failureMachine learningVentricleArtificial intelligenceEjection fractionLeft ventricular hypertrophyPopulationComputer scienceBlood pressureEnvironmental healthCardiovascular Function and Risk FactorsCardiovascular Disease and AdiposityHeart Failure Treatment and Management
Ensemble machine learning model identifies patients with HFpEF from matrix-related plasma biomarkers | Litcius