American Physiological Society, American Journal of Physiology - Heart and Circulatory Physiology, 5(322), p. H798-H805, 2022
DOI: 10.1152/ajpheart.00497.2021
Full text: Unavailable
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.