Improvement of Left Ventricular Ejection Fraction and Pulmonary Hypertension Are Significant Prognostic Factors in Heart Failure with Reduced Ejection Fraction Patients

Pulmonary hypertension associated to left heart disease: Phenotypes and treatment

Pulmonary hypertension associated to left heart disease (PH-LHD) refers to a clinical and haemodynamic condition of pulmonary hypertension associated with a heterogeneous group of diseases affecting any of the compartments that form the left ventricle and left atrium. PH-LHD is the most common cause of PH, accounting for 65-80 % of diagnoses. Based on the haemodynamic phase of the disease, PH-LDH is classified into three subgroups: postcapillary PH, isolated postcapillary PH and combined pre-postcapillary PH (CpcPH). Several signaling pathways involved in the regulation of vascular tone are dysfunctional in PH-LHD, including nitric oxide, MAP kinase and endothelin-1 pathways. These pathways are the same as those altered in PH group 1, however PH-LHD can heardly be treated by specific drugs that act on the pulmonary circulation. In this manuscript we provide a state of the art of the available clinical trials investigating the safety and efficacy of PAH-specific drugs, as well as drugs active in patients with heart failure and PH-LHD. We also discuss the different phenotypes of PH-LHD, as well as molecular targets and signaling pathways potentially involved in the pathophysiology of the disease. Finally we will mention some new emerging therapies that can be used to treat this form of PH.

Interpretable prediction of 3-year all-cause mortality in patients with chronic heart failure based on machine learning

BACKGROUND

The goal of this study was to assess the effectiveness of machine learning models and create an interpretable machine learning model that adequately explained 3-year all-cause mortality in patients with chronic heart failure.

METHODS

The data in this paper were selected from patients with chronic heart failure who were hospitalized at the First Affiliated Hospital of Kunming Medical University, from 2017 to 2019 with cardiac function class III-IV. The dataset was explored using six different machine learning models, including logistic regression, naive Bayes, random forest classifier, extreme gradient boost, K-nearest neighbor, and decision tree. Finally, interpretable methods based on machine learning, such as SHAP value, permutation importance, and partial dependence plots, were used to estimate the 3-year all-cause mortality risk and produce individual interpretations of the model's conclusions.

RESULT

In this paper, random forest was identified as the optimal aools lgorithm for this dataset. We also incorporated relevant machine learning interpretable tand techniques to improve disease prognosis, including permutation importance, PDP plots and SHAP values for analysis. From this study, we can see that the number of hospitalizations, age, glomerular filtration rate, BNP, NYHA cardiac function classification, lymphocyte absolute value, serum albumin, hemoglobin, total cholesterol, pulmonary artery systolic pressure and so on were important for providing an optimal risk assessment and were important predictive factors of chronic heart failure.

CONCLUSION

The machine learning-based cardiovascular risk models could be used to accurately assess and stratify the 3-year risk of all-cause mortality among CHF patients. Machine learning in combination with permutation importance, PDP plots, and the SHAP value could offer a clear explanation of individual risk prediction and give doctors an intuitive knowledge of the functions of important model components.

Decreased Peak Left Atrial Longitudinal Strain Is Associated with Persistent Pulmonary Hypertension Associated with Left Heart Disease

Pulmonary hypertension (PH) associated with left heart disease (PH-LHD) is the most common form of PH and has significantly higher morbidity and mortality. We estimated the prevalence of PH-LHD on the follow-up echocardiography and the role of left atrial (LA) function in PH-LHD. From the STRATS-AHF registry composed of 4312 acute heart failure (HF) patients, we analyzed peak atrial longitudinal strain (PALS) in 1729 patients with follow-up echocardiographic examinations during mean 18.1 ± 13.5 months. PH was determined by the maximal velocity of tricuspid regurgitation (TR Vmax ≥ 3.4 m/s). Persistent PH was found in 373 patients (21.6%). The PH-LHD group was significantly older, and the prevalence of atrial fibrillation (AF), hypertension, diabetes, and heart failure with preserved ejection fraction were higher compared with the no PH-LHD group. Baseline left ventricular end-systolic volume and PALS were lower, and LA diameter, mitral E/E’ ratio, and TR Vmax were higher in the PH-LHD group. In the multivariate analysis, PALS (HR = 1.024, p = 0.040) was a significant variable after adjustment of LA diameter and mitral E/E’. A decreased PALS of <12.5% was the best cutoff value in the prediction of persistent PH-LHD (AUC = 0.594, sensitivity = 65.3%, specificity = 46.1%). PH-LHD was associated with increased HF hospitalization (HR = 2.344, p < 0.001) and mortality (HR = 2.015, p < 0.001) after adjusting for age and sex. In conclusion, persistent PH-LHD was found in 21.6% in the follow-up echocardiography and was associated with decreased PALS (<12.5%). PH-LHD persistence was associated with poor clinical outcomes. Thus, AHF patients with decreased PALS, especially <12.5%, should be followed with caution.