A registry-based algorithm to predict ejection fraction in patients with heart failure

Open Access

Abstract

Aims Left ventricular ejection fraction (EF) is required to categorize heart failure (HF) [i.e. HF with preserved (HFpEF), mid-range (HFmrEF), and reduced (HFrEF) EF] but is often not captured in population-based cohorts or non-HF registries. The aim was to create an algorithm that identifies EF subphenotypes for research purposes. Methods and results We included 42 061 HF patients from the Swedish Heart Failure Registry. As primary analysis, we performed two logistic regression models including 22 variables to predict (i) EF >= vs. = vs. = 50% and 0.76 (95% CI 0.75-0.76) for EF >= 40%. Similar results were achieved for HFrEF and HFpEF in the multinomial model, but the C-statistic for HFmrEF was lower: 0.63 (95% CI 0.63-0.64). The external validation showed similar discriminative ability to the development cohort. Conclusions Routine clinical characteristics could potentially be used to identify different EF subphenotypes in databases where EF is not readily available. Accuracy was good for the prediction of HFpEF and HFrEF but lower for HFmrEF. The proposed algorithm enables more effective research on HF in the big data setting. ; Funding Agencies|Swedish National Board of Health and Welfare; Swedish Association of Local Authorities and Regions; Swedish Society of Cardiology; Swedish Heart-Lung FoundationSwedish Heart-Lung Foundation; Servier, the NetherlandsNetherlands Government; EU/EFPIA Innovative Medicines Initiative 2 Joint Undertaking BigData@Heart [116074]; Swedish Research CouncilSwedish Research Council [2013-23897-104604-23, 523-2014-2336]; Swedish Heart Lung FoundationSwedish Heart-Lung Foundation [20150557, 20170841]; Stockholm County CouncilStockholm County Council [20140220, 20170112]; UCL Hospitals NIHR Biomedical Research Centre; Dutch Heart Foundation, a part of Facts and Figures