
A study of 204 patients developed a nomogram incorporating echocardiogram, phonocardiogram, and clinical data to enhance heart failure with preserved ejection fraction (HFpEF) diagnosis. Using LASSO and logistic regression, five indicators, including NT-proBNP and LAVI, were selected. The model achieved an AUC of 0.945 in the training set, outperforming models without phonocardiogram data. Calibration and decision curve analyses confirmed the model’s accuracy and clinical usefulness, supporting it as a valuable tool for HFpEF diagnostics.
Like
Save
Share