Echocardiographic assessment for cardiopulmonary function in patients with congenital heart disease-related pulmonary arterial hypertension.

BACKGROUND: For patients with congenital heart disease-related pulmonary arterial hypertension (CHD-PAH), cardiopulmonary exercise testing (CPET) can reflect cardiopulmonary reserve function. However, CPET may not be readily accessible for patients with high-risk conditions or limited mobility due to disability. Echocardiography, on the other hand, serves as a widely available diagnostic tool for all CHD-PAH patients. This study was aimed to identify the parameters of echocardiography that could serve as indicators of cardiopulmonary function and exercise capacity. METHODS: A cohort of 70 patients contributed a total of 110 paired echocardiogram and CPET results to this study, with 1 year interval for repeated examinations. Echocardiography and exercise testing were conducted following standardized procedures, and the data were collected together with clinically relevant indicators for subsequent statistical analysis. Demographic comparisons were performed using t-tests and chi-square tests. Univariate and multivariate analyses were conducted to identify potential predictors of peak oxygen uptake (peak VO2) and the carbon dioxide ventilation equivalent slope (VE/VCO2 slope). Receiver operating characteristic (ROC) analysis was used to assess the performance of the parameters. RESULTS: The ratio of tricuspid annular plane systolic excursion to pulmonary artery systolic pressure (TAPSE/PASP) was found to be the only independent indicator significantly associated with both peak VO2 and VE/VCO2 slope (both p < 0.05). Additionally, left ventricular ejection fraction (LVEF) and right ventricular fractional area change (FAC) were independently correlated with the VE/VCO2 slope (both p < 0.05). TAPSE/PASP showed the highest area under the ROC curve (AUC) for predicting both a peak VO2 ≤ 15 mL/kg/min and a VE/VCO2 slope ≥ 36 (AUC = 0.91, AUC = 0.90, respectively). The sensitivity and specificity of TAPSE/PASP at the optimal threshold exceeded 0.85 for both parameters. CONCLUSIONS: TAPSE/PASP may be a feasible echocardiographic indicator for evaluating exercise tolerance.

New risk model by right ventricle - pulmonary arterial coupling and inferior vena cava from echocardiography in patients with conventional low-intermediate risk pulmonary artery hypertension under targeted treatment.

BACKGROUND: Accurately stratifying patients with pulmonary arterial hypertension (PAH) is very important, and traditional risk scores still have internal heterogeneity. This study aimed to construct a risk stratification model that can accurately identify clinical worsening (CW) events in conventional low-intermediate risk patients with pulmonary hypertension under targeted drug treatment by using echocardiographic parameters. METHODS: This study is a single-center, prospective study, including 105 PAH patients who underwent regular follow-up at Guangdong Provincial People's Hospital from October 2021 to April 2023. The primary endpoint was the occurrence of CW, including death, hospitalization due to pulmonary hypertension, escalation of targeted drug therapy, and worsening of PAH. The predictive value of the echocardiography-based three-strata risk model was assessed using Kaplan-Meier curves and COX regression analysis. RESULTS: A total of 98 PAH patients were ultimately included in this study. The median follow-up duration was 26 months (range 7-28 months). The echocardiography-based three-strata model included the ratio of tricuspid annular plane systolic excursion and pulmonary artery systolic pressure (TAPSE/PASP) and inferior vena cava (IVC). The echocardiography-based three-strata model had higher diagnostic value (C-index = .76) compared to the 2022 ESC/ERS three-strata model and four-strata model (C-index = .66 and C-index = .61, respectively). PAH patients with lower TAPSE/PASP and wider IVC showed a higher CW rate compared to patients with higher TAPSE/PASP and normal IVC (HR = 15.1, 95%CI:4.4-51.9, p < .001). CONCLUSION: The echocardiography-based three-strata model based on TAPSE/PASP and IVC can effectively improve the stratification of low-intermediate risk PAH patients under targeted treatment.

Automatic echocardiographic evaluation of the probability of pulmonary hypertension using machine learning.

Echocardiography, a simple and noninvasive tool, is the first choice for screening pulmonary hypertension (PH). However, accurate assessment of PH, incorporating both the pulmonary artery pressures and additional signs for PH remained unsatisfied. Thus, this study aimed to develop a machine learning (ML) model that can automatically evaluate the probability of PH. This cohort included data from 346 (275 for training set and internal validation set and 71 for external validation set) patients with suspected PH patients and receiving right heart catheterization. Echocardiographic images on parasternal short axis-papillary muscle level (PSAX-PML) view from all patients were collected, labeled, and preprocessed. Local features from each image were extracted and subsequently integrated to build a ML model. By adjusting the parameters of the model, the model with the best prediction effect is finally constructed. We used receiver-operating characteristic analysis to evaluate model performance and compared the ML model with the traditional methods. The accuracy of the ML model for diagnosis of PH was significantly higher than the traditional method (0.945 vs. 0.892, p = 0.027 [area under the curve [AUC]]). Similar findings were observed in subgroup analysis and validated in the external validation set (AUC = 0.950 [95% CI: 0.897-1.000]). In summary, ML methods could automatically extract features from traditional PSAX-PML view and automatically assess the probability of PH, which were found to outperform traditional echocardiographic assessments.