Decline in arterial partial pressure of oxygen after exercise: a surrogate marker of pulmonary vascular obstructive disease in patients with atrial septal defect and severe pulmonary hypertension

Machine learning for clustering and postclosure outcome of adult CHD-PAH patients with borderline hemodynamics

BACKGROUND

Patients with uncorrected isolated simple shunts associated pulmonary arterial hypertension (PAH) had increased mortality. Treatment strategies for borderline hemodynamics remain controversial. This study aims to investigate preclosure characteristics and its association with postclosure outcome in this group of patients.

METHODS

Adults with uncorrected isolated simple shunts associated PAH were included. Peak tricuspid regurgitation velocity<2.8 m/sec with normalized cardiac structures was defined as the favorable study outcome. We applied unsupervised and supervised machine learning for clustering analysis and model constructions.

RESULTS

Finally, 246 patients were included. During a median follow-up of 414days, 58.49% (62/106) of patients with pretricuspid shunts achieved favorable outcome while 32.22% (46/127) of patients with post-tricuspid shunts. In unsupervised learning, two clusters were identified in both types of shunts. Generally, the oxygen saturation, pulmonary blood flow, cardiac index, dimensions of the right and left atrium, were the major features that characterized the identified clusters. Specifically, mean right atrial pressure, right ventricular dimension, and right ventricular outflow tract helped differentiate clusters in pretricuspid shunts while age, aorta dimension, and systemic vascular resistance helped differentiate clusters for post-tricuspid shunts. Notably, cluster 1 had better postclosure outcome than cluster 2 (70.83% vs 32.55%, p < .001 for pretricuspid and 48.10% vs 16.67%, p < .001 for post-tricuspid). However, models constructed from supervised learning methods did not achieve good accuracy for predicting the postclosure outcome.

CONCLUSIONS

There were two main clusters in patients with borderline hemodynamics, in which one cluster had better postclosure outcome than the other.

Challenges and Special Aspects of Pulmonary Hypertension in Middle- to Low-Income Regions: JACC State-of-the-Art Review

Challenges and special aspects related to the management and prognosis of pulmonary hypertension (PH) in middle- to low-income regions (MLIRs) range from late presentation to comorbidities, lack of resources and expertise, cost, and rare options of lung transplantation. Expert consensus recommendations addressing the specific challenges for prevention and therapy of PH in MLIRs with limited resources have been lacking. To date, 6 MLIR-PH registries containing mostly adult patients with PH exist. Importantly, the global prevalence of PH is much higher in MLIRs compared with high-income regions: group 2 PH (left heart disease), pulmonary arterial hypertension associated with unrepaired congenital heart disease, human immunodeficiency virus, or schistosomiasis are highly prevalent. This consensus statement provides selective, tailored modifications to the current PH guidelines to address the specific challenges faced in MLIRs, resulting in the first pragmatic and cost-effective consensus recommendations for PH care providers, patients, and their families.

Atrial septal defect with pulmonary hypertension: when/how can we consider closure?

Patients having atrial septal defect (ASD) with moderate and more importantly severe pulmonary arterial hypertension (PAH) pose a clinical dilemma. Closing ASD in those with irreversible PAH and not closing it when the PAH is reversible can cost patients dearly, both in terms of quality of life and longevity. In our experience, there is no single parameter that can help in decision making in this difficult subset of patients and therefore we recommend a multi-dimensional approach, which takes into consideration clinical, radiological, electrocardiographic and hemodynamic variables as a whole. ASD with restrictive left ventricular (LV) physiology can lead to pulmonary venous hypertension, which can manifest as life threatening acute pulmonary edema following device closure. All high-risk candidates prone to having this combination should be prepared with diuretics and vasodilators prior to bringing them to catheterization laboratory and should be assessed with temporary balloon/device occlusion prior to permanent closure of the defect. In those cases of ASD with borderline operability either due to severe PAH or LV restrictive physiology, perforated device may be helpful in preventing acute or long-term complications of complete closure.

Do preoperative haemodynamic data and reactivity test predict the postoperative reversibility of pulmonary arterial hypertension in patients with large ventricular septal defect and borderline operability?

BACKGROUND

Decisions to operate on patients with shunt lesions presenting late with severe pulmonary arterial hypertension (PAH) and borderline operability are often not based on precise cut off values of haemodynamic data owing to paucity of studies.

OBJECTIVE

To assess the reliability of the preoperative haemodynamic data and reactivity test in predicting the postoperative reversibility of PAH in patients with isolated large ventricular septal defects (VSDs) and borderline operability.

PATIENTS AND METHOD

Between 2004 and 2010, 30 patients underwent VSD closure surgically; no early deaths occurred. Twenty-six patients were followed up regularly (mean 39.6±16 months) and one late postoperative death occurred. Fourteen patients who had been followed up for at least 1 year postoperatively underwent cardiac catheterisation.

RESULTS

There were 3 responders (asymptomatic patients with pulmonary vascular resistance (PVR) index <3 WU.m(2)) and 12 non-responders. The following were lower among responders: mean age at surgery (3.2±0.42 vs 11.55±3.29 years, p=0.227), mean baseline PVR index (3.69±0.8 vs 10.57±9.1, p=0.204), average resistance ratio (RR=0.25±0.01 vs 0.59±0.25, p=0.049) and ratio of pulmonary and systemic mean pressures (PAm:SAm ratio) (0.70±0.009 vs 0.87±0.118, p=0.003).

CONCLUSIONS

Preoperative 'base line' PAm:SAm and RR appear to be better predictors of postoperative outcome than other baseline parameters. Preoperative reactivity test had no significant role in predicting postoperative reversibility of PAH at mid-term.