Machine learning to differentiate pulmonary hypertension due to left heart disease from pulmonary arterial hypertension.

Background and aims: Pulmonary hypertension due to left heart disease (PH-LHD) is the most frequent form of PH. As differential diagnosis with pulmonary arterial hypertension (PAH) has therapeutic implications, it is important to accurately and noninvasively differentiate PH-LHD from PAH before referral to PH centres. The aim was to develop and validate a machine learning (ML) model to improve prediction of PH-LHD in a population of PAH and PH-LHD patients. Methods: Noninvasive PH-LHD predictors from 172 PAH and 172 PH-LHD patients from the PH centre database at the University Hospitals of Leuven (Leuven, Belgium) were used to develop an ML model. The Jacobs score was used as performance benchmark. The dataset was split into a training and test set (70:30) and the best model was selected after 10-fold cross-validation on the training dataset (n=240). The final model was externally validated using 165 patients (91 PAH, 74 PH-LHD) from Erasme Hospital (Brussels, Belgium). Results: In the internal test dataset (n=104), a random forest-based model correctly diagnosed 70% of PH-LHD patients (sensitivity: n=35/50), with 100% positive predicted value, 78% negative predicted value and 100% specificity. The model outperformed the Jacobs score, which identified 18% (n=9/50) of the patients with PH-LHD without false positives. In external validation, the model had 64% sensitivity at 100% specificity, while the Jacobs score had a sensitivity of 3% for no false positives. Conclusions: ML significantly improves the sensitivity of PH-LHD prediction at 100% specificity. Such a model may substantially reduce the number of patients referred for invasive diagnostics without missing PAH diagnoses.

Learning from registries in pulmonary arterial hypertension: pitfalls and recommendations.

Pulmonary arterial hypertension is a rare and incurable chronic disease characterised by a progressive increase in pulmonary vascular resistance and right heart failure. Patient registries collecting observational data can be of great value in the understanding of clinical problems. While clinical trials provide data in selected patient populations, registries better depict real-life practice. This review aims to reflect the input of patient registries in the general knowledge of the disease. Advances in epidemiology of the different subgroups, including data on incidence and/or prevalence, increasing age at presentation and stagnating diagnostic delay are reported. The importance of haemodynamic definition criteria and cardiac comorbidities are underscored. The review also shows the major transformation that pulmonary arterial hypertension therapeutic management has undergone, with still insufficient use of combination therapies; consecutive improvement in outcome; upcoming evidence in disfavour of anticoagulation; and validity of the available risk-stratification tools derived from large registries. Product registries are also briefly presented. Finally, the benefits of registries and methodological aspects are discussed, including immortal time bias, registry data quality and recommendations from EU organisations (EUCERD and PARENT).