Heart Failure With Improved Ejection Fraction and Deep Learning

Deep Learning-Based Prediction Model of Heart Failure With Improved Ejection Fraction

The aim of this study was to design a deep learning-based trained model to assist in HFimpEF diagnosis.

Inclusion Criteria:

1. Age >18 years.
2. The diagnostic criteria of HF follows the 2018 Chinese Guidelines for the Diagnosis and Treatment of Heart Failure, having symptoms of dyspnea, fatigue or decreased activity tolerance, having signs of fluid retention (such as pulmonary congestion and peripheral edema), having echocardiogram abnormalities in cardiac structure and/or function, showing elevated natriuretic peptide levels (BNP>35 ng/L or/and N-terminal pro-BNP >125 ng/L).
3. Have reviewing echocardiography after discharge.

Exclusion Criteria:

1. Patients with hypertrophic, restrictive, or invasive cardiomyopathy and congenital or rheumatic heart disease.
2. Patients with heart transplantation during follow-up.