Real-World Scenario of Heart Failure Treatment - Prediction of Functional Capacity Improvement of the Left Ventricle under Treatment with an Angiotensin Receptor-Neprilysin Inhibitor

Florian Appenzeller (Tübingen)1, T. Harm (Tübingen)1, M. Gawaz (Tübingen)2, K. A. L. Müller (Tübingen)2

1Universitätsklinikum Tübingen Innere Medizin III, Kardiologie und Angiologie Tübingen, Deutschland; 2Universitätsklinikum Tübingen Innere Medizin III, Kardiologie und Kreislauferkrankungen Tübingen, Deutschland


Background and aims
Heart failure (HF) patients may lack improvement of left ventricular ejection fraction (LVEF) despite optimal HF medication comprising an angiotensin receptor-neprilysin inhibitor (ARNI). Therefore, we aimed to identify novel predictors for functional capacity improvement and reverse cardiac remodeling in HF patients on ARNI treatment.


We retrospectively analyzed 294 consecutive patients with reduced (HFrEF) or mildly reduced (HFmrEF) LVEF in our “EnTruth” registry. LVEF was determined by echocardiography at initiation of ARNI and at one-year follow-up. We evaluated the predictive value of clinical parameters with changes of LVEF including machine learning.


By training models on relevant clinical parameters including ARNI medication, stratification of LVEF improvement resulted in a phenotyping of HF patients. Distinct clusters of patients share a high therapeutic response to ARNI treatment and important patient criterions are associated with an increment in LVEF and independently predict cardiac remodelling. Notably, the stratification of HF patients led to an increased diagnostic accuracy of LVEF improvement. Finally, patients with a high likelihood of LVEF improvement are at lower risk for all-cause mortality.


Recognition of important clinical factors may help to identify patients benefiting from improvement of LVEF following ARNI treatment. Early identification of HF patients with a high response to ARNI treatment may allow for a more refined selection of patients benefiting from an early escalation of HF treatment. Machine learning with integration of clinical data may help to tailor and to individualize therapeutic strategies such as cardiac devices to improve clinical outcome in HF.

Diese Seite teilen