Citations

ABSTRACT Pulmonary hypertension (PH) comprises a heterogeneous group of disorders characterized by elevated pressure in the pulmonary arteries. Despite advances in awareness, utilization of non‐invasive screening with echocardiography, increasing number of targeted therapies, and evolving clinical guidelines emphasizing referral to PH specialty centers, barriers to timely diagnosis and treatment persist. Key challenges span patient‐related and system‐level domains that hinder the effective diagnosis, management, and treatment of PH, particularly pulmonary arterial hypertension (PAH). In this article, the obstacles to PH care are examined and actionable recommendations are proposed. By integrating patient‐related and system‐level perspectives, this review provides a framework to bridge persistent gaps in PH care delivery in the United States.

OBJECTIVES Early warning scores detecting clinical deterioration in pediatric inpatients have wide-ranging performance and use a limited number of clinical features. This study developed a machine learning model leveraging multiple static and dynamic clinical features from the electronic health record to predict the composite outcome of unplanned transfer to the ICU within 24 hours and inpatient mortality within 48 hours in hospitalized children. METHODS Using a retrospective development cohort of 17 630 encounters across 10 388 patients, 2 machine learning models (light gradient boosting machine [LGBM] and random forest) were trained on 542 features and compared with our institutional Pediatric Early Warning Score (I-PEWS). RESULTS The LGBM model significantly outperformed I-PEWS based on receiver operating characteristic curve (AUROC) for the composite outcome of ICU transfer or mortality for both internal validation and temporal validation cohorts (AUROC 0.785 95% confidence interval [0.780–0.791] vs 0.708 [0.701–0.715] for temporal validation) as well as lead-time before deterioration events (median 11 hours vs 3 hours; P = .004). However, LGBM performance as evaluated by precision recall curve was lesser in the temporal validation cohort with associated decreased positive predictive value (6% vs 29%) and increased number needed to evaluate (17 vs 3) compared with I-PEWS. CONCLUSIONS Our electronic health record based machine learning model demonstrated improved AUROC and lead-time in predicting clinical deterioration in pediatric inpatients 24 to 48 hours in advance compared with I-PEWS. Further work is needed to optimize model positive predictive value to allow for integration into clinical practice.