Marcin Kurzyna

Pulmonary arterial hypertension (PAH) is a rare disease with poor prognosis. The same treatment is recommended in patients with PAH associated with connective tissue disease (CTD) and idiopathic PAH (IPAH). However, the effectiveness of PAH‐specific treatment in these both groups is inconsistent. The study incorporated data from the prospective, multicentre polish registry (BNP‐PL) by comparison of baseline versus 1‐year follow‐up clinical, laboratory, echocardiographic and hemodynamic parameters in PAH‐CTD versus IPAH group. The all‐cause 1‐year mortality was also analysed. 624 patients were included in the study: 176 (28%) PAH‐CTD and 448 (72%) IPAH. 48 (8% of the total 624) patients died during 1‐year follow up: 32 (7%) with IPAH and 16 (9%) with PAH‐CTD ( p = 0.4). The effectiveness of treatment was examined in 421 patients: 115 (27%) PAH‐CTD and 306 (73%) IPAH. The improvement of treatment was effective in both groups in terms of WHO FC ( p < 0.001 in both groups), 4‐strata risk model ( p < 0.001 in both groups), 6 min walking test (6MWT, p < 0.001 in IPAH, p = 0.001 in PAH‐CTD), Δ6MWT ( p = 0.19 between PAH‐CTD and IPAH), tricuspid annular plane systolic excursion ( p < 0.001 in both groups), NT‐ proBNP ( p < 0.001 in IPAH and p < 0.01 in PAH‐CTD), mean pulmonary arterial pressure ( p = 0.043 in IPAH and p = 0.01 in PAH‐CTD), pulmonary vascular resistance ( p < 0.001 in both groups) and cardiac output ( p < 0.001 in IPAH and p = 0.034 in PAH‐CTD). PAH specific treatment in PAH‐CTD patients is as effective as in IPAH patients regarding improvement in WHO FC, 4‐strata risk model, 6MWT, Δ6MWT, TAPSE, NT‐proBNP, mPAP, PVR and CO at 1‐year follow‐up. 1‐year all‐cause mortality was not significantly different between PAH‐CTD and IPAH patients.

Background/Objectives: Pulmonary arterial hypertension (PAH) impacts various aspects of patients’ lives. Some questionnaires assessing health-related quality of life are specific to PAH patients. The aims of the study were to translate and investigate the factor structure and psychometric properties of the Polish version of the EmPHasis-10 health-related quality of life questionnaire in a group of adults with PAH. Construct validity was explored by the relationship with results of the 36-Item Short Form Survey (SF-36) and non-invasive prognostic factors: WHO functional class, 6 min walk distance (6MWD) and NTproBNP level were measured. Methods: In a single-center study, PAH patients were included. The diagnosis of PAH was confirmed by right heart catheterization. The demographic and clinical data were obtained. The EmPHasis-10 and the SF-36 questionnaires were administered to all patients. Results: Data from 120 PAH patients, median age 57 (IQR 45–68.7) years, 88 (73%) women, were obtained. Most of the patients suffered from IPAH (73, 61%). Results revealed a unidimensional structure of the EmPHasis-10 questionnaire and demonstrated satisfactory reliability (Cronbach α = 0.94). The EmPHasis-10 showed an adequate relationship with both SF-36 dimensions and three non-invasive prognostic parameters, i.e., WHO functional class, 6MWD and NTproBNP level. Regression analysis indicated that the 6MWD was the only predictor of the EmPHasis-10. Conclusions: The obtained results showed very good psychometric properties and adequate internal consistency of the Polish version of EmPHasis-10 in PAH patients. The results showed a unidimensional structure and very good psychometric properties, including satisfactory internal consistency and external validity of the Polish version of the EmPHasis-10 scale in patients with PAH.

The present Reply addresses the commentary by Pagnoni et al. on our recent study exploring explainable artificial intelligence (AI) for mortality risk prediction in pulmonary arterial hypertension (PAH). We acknowledge the importance of several key issues raised by the authors, including endpoint selection, calibration, decision thresholds, and external validation, all of which are central to translating AI-based prognostic models into clinical practice. Our original endpoint, defined as death by the next follow-up visit, was driven by the structure of nationwide registry data and reflects real-world clinical workflows, although we recognize the advantages of predefined time horizons and time-to-event approaches for future analyses. We discuss the trade-off between sensitivity and precision, emphasizing our deliberate prioritization of minimizing false-negative classifications in high-risk patients, while acknowledging the need for structured clinical pathways to manage false-positive results. We further address calibration and threshold selection, underscoring the necessity of additional clinical studies to support intervention-oriented recommendations. The role of phenotypic determinants and modifiable risk factors in enhancing personalization is highlighted as a key direction for future model development. We reaffirm the value of SHAP-based explainability for improving model transparency, while recognizing the need for continued refinement and clinical validation. Finally, we emphasize the strengths and challenges inherent to registry-based analyses, the importance of external validation, and the need for methodologically sound comparisons with established risk calculators. Overall, this exchange underscores the critical role of interdisciplinary collaboration in advancing clinically actionable and interpretable AI solutions for PAH.

Background/Objectives: Pulmonary arterial hypertension (PAH) is a complex cardiovascular disease with a high burden of morbidity and mortality. Although several risk prediction models have been proposed, the exact significance of distinct clinical parameters in predicting survival in PAH remains unclear. It is important to emphasize that this study does not aim to validate or contradict existing clinical risk assessment calculators provided by the ESC or other scientific societies. Instead, the goal of this research is to identify and rank clinical parameters according to their importance in predicting mortality in PAH patients using machine learning techniques. Methods: Using the Database of Pulmonary Hypertension in the Polish population (BNP-PL) registry, 1755 adult patients with PAH were selected. Feature engineering was conducted using domain knowledge, guided by European Society of Cardiology (ESC) recommendations. Features were reduced using LASSO regression and sequential feature elimination algorithms. A classification model was built using the XGBoost algorithm, utilizing 17 features. The model was tested on a preselected subset of the BNP-PL data. The Shapley Additive Explanations (SHAP) method was used to explain the model’s predictions and to rank feature importance. Results: The model achieved satisfactory results across evaluated metrics, including an area under the curve of 0.767, accuracy of 0.738, specificity of 0.733, and sensitivity of 0.800. SHAP values effectively ranked the features, corroborating the significance of parameters present in the ESC risk stratification tables. Furthermore, local interpretation of results using SHAP enabled individualized assessment of feature importance, enhancing clinical applicability. Conclusions: The proposed artificial intelligence-based model demonstrates satisfactory predictive capability, highlighting the potential of machine learning techniques to support more personalized approaches to the management of PAH patients. This approach offers complementary insights into traditional risk assessment methods, providing clinicians with a novel tool for individualized risk evaluation and decision-making.

Background: Pulmonary arterial hypertension (PAH) requires a complex and multidisciplinary care approach with regular follow-up visits to monitor disease progression and adaptation of treatment regimens. Current ESC/ERS Guidelines recommend initial double oral treatment (endothelin-receptor antagonist + phosphodiesterase type 5 inhibitor) in patients presenting at diagnosis with intermediate risk according to the three-strata risk score. Retrospective data analyses indicate a clinical benefit for upfront triple combination therapy including parenteral prostacyclins (PCA) in intermediate and high-risk patients. The multicentric TripleTRE trial aims to investigate the effect of initial triple combination therapy including parenteral PCA on risk status, compared to double oral in a prospective setting in patients at intermediate–high risk at diagnosis according to the four-strata risk score. Methods: A phase IV, multicentre, prospective, randomised, two-arm, open-label trial will be conducted. The study will enrol a total of 110 patients with intermediate–high risk of death at PAH diagnosis. Patients are randomised (1:1) to receive either initial double-oral treatment or upfront triple combination treatment including parenteral treprostinil. The primary end-point is the achievement of a low-risk status between week 24 and 48 assessed with the simplified four-strata risk assessment tool. Discussion: Despite retrospective evidence for greater benefit, prospective investigation of upfront triple therapy including a parenteral PCA is lacking. The TripleTRE trial aims to fill this gap and test the hypothesis of “hit hard and early” in patients with newly diagnosed PAH.

Background: Patients’ experiences of living with pulmonary hypertension are likely to vary by geography and aetiology. The Pulmonary Hypertension Global Patient Survey (PH GPS) aims to understand patients’ perspectives and experiences, to drive healthcare improvements. Methods: PH GPS was collaboratively designed through a multidisciplinary, iterative, consensus-building process and beta-tested by patients. Themes included healthcare provision, self-monitoring and research. It was predominantly disseminated by pulmonary hypertension organisations to patients or their proxies across all pulmonary hypertension groups. Descriptive statistics provided a narrative summary of key results. Results: Data regarding 3329 adult (mean age 52.2 years; 81.7% female) and 135 paediatric patients were analysed, with this article focusing on the adult cohort. Most pulmonary arterial hypertension (PAH) patients reported diagnosis within 12 months of symptom onset. Variability was seen in survey response, pulmonary hypertension management and research participation, favouring the Global North and pulmonary hypertension groups 1 and 4. Genetic testing was reported by 33.9% (401 out of 1183) of patients, where eligible. 58% were experienced in self-monitoring their health. 20.6% of patients with pulmonary hypertension have completed patient-reported outcome measures (PROMs), with 7% feeling they changed management. 19.1% of adult patients have participated in research; however, 72.2% who have not participated would be willing to do so if invited. Discussion: PH GPS is the largest survey of its kind in the pulmonary hypertension field, representing a globally collaborative endeavour. It highlights achievements such as efficient PAH diagnostic time frames. Shortcomings include underappreciating quality of life reported via PROMs. The Global South and pulmonary hypertension groups 2 and 3 were relatively underrepresented. Encouragingly, patients’ experiences of navigating healthcare were often positive, as demonstrated by a willingness to participate in research and being empowered to take charge of their health: findings which cross geographical divides.

Background/Objectives: Several studies describe the sex-specific differences in cardiovascular diseases. However, there is still limited research reporting the difference between men and women with chronic thromboembolic pulmonary hypertension (CTEPH) treated with balloon pulmonary angioplasty (BPA). The aim of this study was to evaluate sex-specific differences in patients with CTEPH treated with BPA. Methods: This retrospective study included CTEPH patients treated with BPA. The patients’ hemodynamic and clinical parameters were assessed at baseline and 3 months after completion of BPA treatment. Results: This study included 94 patients (44 women, 46.8%). At baseline, women had higher systolic pulmonary arterial pressure (sPAP) (76 ± 18.5 vs. 85 ± 17.6 mmHg; p = 0.03) and pulmonary vascular resistance (8.21 [5.55–10.17] vs. 9.89 [6.31–14.06] Wood Units; p = 0.03) compared to men. There were no differences in clinical characteristics between the sexes. At follow-up, women had lower sPAP (49 [41–54] vs. 43 [37–49] mmHg; p = 0.04) and pulmonary capillary wedge pressure (10 [9–14] vs. 9 [8–11] mmHg; p = 0.03), but a higher cardiac index (2.57 ± 0.53 vs. 2.82 ± 0.50 L/min/m²; p = 0.03), as well as better Dyspnea Borg Scale outcomes, compared to men. Women had a greater reduction in mean pulmonary artery pressure (−43% vs. −37%; p = 0.049) than men. Conclusions: At baseline, women with CTEPH had worse hemodynamic parameters than men despite similar clinical symptoms. However, the hemodynamic status of women was better after BPA therapy. Hence, women seem better adapted to the disease at baseline and respond better to BPA. Further data are needed to investigate whether the management of CTEPH patients should be sex-differentiated.