Search

Pulmonary hypertension (PH) is a condition of multiple aetiologies with underestimated prevalence and incidence. Indeed, despite access to modern therapies, pulmonary hypertensive vascular disease (PHVD) remains a progressive, usually life-limiting condition, severely impacting on the patients' well-being. We herein provide practical, expert consensus recommendations on the initial diagnostic work-up, clinical management and follow-up of children and adolescents with PH/PHVD, including a diagnostic algorithm. The major topics and methods that need to be tailored and put into context of the individual patient include PH classification, clinical signs and symptoms, basic diagnostic and advanced imaging measures (ECG, chest X-ray, transthoracic echocardiography, cardiac magnetic resonance, chest CT angiography, cardiac catheterisation, ventilation-perfusion lung scan, abdominal ultrasound), lung function tests, 6 min walk and cardiopulmonary exercise testing, sleep study (polysomnography), laboratory/immunological tests, considerations for elective surgery/ general anaesthesia, physical education and exercise, flying on commercial airplanes, vaccinations, care of central intravenous lines and palliative care. Due to the complexity of PH/PHVD, the clinical care has to be multidisciplinary and coordinated by a dedicated specialist paediatric PH centre, not only to decrease mortality but to allow children with PH/PHVD to reach a reasonable quality of life., (Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/)

Background: Neonatal valvular aortic stenosis (AoS) represents a spectrum of different degrees of hypoplasia and malformation of all left heart structures. Uncertainty exists on threshold values for biventricular circulation of newborns with critical AoS. Our aim was to assess the predictive value of current risk scores for treatment strategies in critical AoS., Methods and Results: The echocardiograms of all newborns with AoS treated by balloon valvuloplasty (AoVP) or Norwood operation between January 2006 and September 2008 were reviewed retrospectively and the Rhodes-, Colan-score and the univentricular repair survival advantage (UVR-SA) tool were applied. The results were compared to the actual outcome. Out of 28 patients 19 were treated by an initial AoVP and nine by an initial Norwood operation. In three a secondary Norwood operation was done. According to the Rhodes-score 24 patients should have been treated by a univentricular strategy but 12 of them (50%) live with biventricular circulation. The Colan-score resulted in 19 univentricular decisions and 7 (37%) of these patients now live with biventricular circulation. Applying the UVR-SA tool 2/12 (17%) patients predicted for a univentricular strategy received successful biventricular circulation and 2/16 (12%) of the suggested biventricular patients have a univentricular circulation. Hence, 14/28 (50%) patients had discordant treatment decisions., Conclusion: No prospectively tested criteria for patient selection (biventricular vs. univentricular) are available for critically ill newborns with AoS. Retrospective application of the current risk scores showed unsatisfactory results. Treatment decisions are based on local experience and expertise.

Introduction: Well-trained staff is needed to interpret cardiopulmonary exercise tests (CPET). We aimed to examine the accuracy of machine learning–based algorithms to classify exercise limitations and their severity in clinical practice compared with expert consensus using patients presenting at a pulmonary clinic. Methods: This study included 200 historical CPET data sets (48.5% female) of patients older than 40 yr referred for CPET because of unexplained dyspnea, preoperative examination, and evaluation of therapy progress. Data sets were independently rated by experts according to the severity of pulmonary–vascular, mechanical–ventilatory, cardiocirculatory, and muscular limitations using a visual analog scale. Decision trees and random forests analyses were calculated. Results: Mean deviations between experts in the respective limitation categories ranged from 1.0 to 1.1 points (SD, 1.2) before consensus. Random forests identified parameters of particular importance for detecting specific constraints. Central parameters were nadir ventilatory efficiency for CO2, ventilatory efficiency slope for CO2 (pulmonary–vascular limitations); breathing reserve, forced expiratory volume in 1 s, and forced vital capacity (mechanical–ventilatory limitations); and peak oxygen uptake, O2 uptake/work rate slope, and % change of the latter (cardiocirculatory limitations). Thresholds differentiating between different limitation severities were reported. The accuracy of the most accurate decision tree of each category was comparable to expert ratings. Finally, a combined decision tree was created quantifying combined system limitations within one patient. Conclusions: Machine learning–based algorithms may be a viable option to facilitate the interpretation of CPET and identify exercise limitations. Our findings may further support clinical decision making and aid the development of standardized rating instruments. [ABSTRACT FROM AUTHOR]