Search

Pulmonary embolism (PE) is a life-threatening condition associated with ~10% of deaths of hospitalized patients. Machine learning algorithms (MLAs) which predict the onset of pulmonary embolism (PE) could enable earlier treatment and improve patient outcomes. However, the extent to which they generalize to broader patient populations impacts their clinical utility.To conduct the first large-scale external validation of a machine learning-based PE prediction model which uses EHR data from the first three hours of a patient's hospital stay to predict the occurrence of PE within the next 10 days of the inpatient stay.This retrospective study included approximately two million adult hospital admissions across 44 medical institutions in the US from 2011 to 2017. Demographics, vital signs, and lab tests from adult inpatients at 12 institutions (n = 331,268; 3.3% PE positive) were used for training an XGBoost model. External validation of the model was conducted on patient populations from each of 32 medical institutions (total n = 1,660,715; 3.7% PE positive) without retraining. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC). Backward elimination regression was used to identify correlations between characteristics of the external validation sets and AUROC.The model performed well (AUROC = 0.87) on the 20% hold-out subset of the training set. Despite demographic differences between the 32 external validation populations (percent PE positive: min = 1.54%, max = 6.47%), without retraining, the model had excellent discrimination, with a mean AUROC of 0.88 (min = 0.79, max = 0.93). Fixing sensitivity at 0.80, the model had a mean specificity of 0.85 (min = 0.64, max = 0.93). Backward elimination regression identified a negative association (β = -0.015, p 0.001) between the percentage of PE positive encounters and AUROC.A PE prediction model performed remarkably well across 32 different external patient populations without retraining and despite significant differences in demographic characteristics, demonstrating its generalizability and potential as a clinical decision support tool to aid PE detection and improve patient outcomes in a clinical setting.

Vasculogenesis involves the differentiation of vascular endothelial progenitors de novo from undifferentiated mesoderm, their migration and coalescence to form the major embryonic vessels and the acquisition of arterial or venous identity. Vascular Endothelial Growth Factor (Vegf) signaling plays multiple roles during vascular development. However, its function during embryonic vasculogenesis has been controversial. Previous studies have implicated Vegf signaling in either regulating arteriovenous specification or overall vascular endothelial differentiation. To clarify the role of Vegf in embryonic vasculogenesis and identify its downstream targets, we used chemical inhibitors of Vegf receptor (Vegfr) signaling in zebrafish embryos as well as zebrafish genetic mutants. A high level of chemical inhibition of Vegfr signaling resulted in the reduction of overall vascular endothelial marker gene expression, including downregulation of both arterial and venous markers, ultimately leading to the apoptosis of vascular endothelial cells. In contrast, a low level of Vegfr inhibition specifically blocked arterial specification while the expression of venous markers appeared largely unaffected or increased. Inhibition of Vegfr signaling prior to the initiation of vasculogenesis reduced overall vascular endothelial differentiation, while inhibition of Vegfr signaling starting at mid-somitogenesis stages largely inhibited arterial specification. Conversely, Vegf overexpression resulted in the expansion of both arterial and pan-endothelial markers, while the expression of several venous-specific markers was downregulated. We further show that Vegf signaling affects overall endothelial differentiation by modulating the expression of the ETS transcription factor etv2/ etsrp. etv2 expression was downregulated in Vegfr- inhibited embryos, and expanded in Vegfaa-overexpressing embryos. Furthermore, vascular-specific overexpression of etv2 in Vegfr-inhibited embryos rescued defects in vascular endothelial differentiation. Similarly, vegfaa genetic mutants displayed a combination of the two phenotypes observed with chemical Vegfr inhibition: the expression of arterial and pan-endothelial markers including etv2 was downregulated while the expression of most venous markers was either expanded or unchanged. Based on these results we propose a revised model which explains the different phenotypes observed upon inhibition of Vegf signaling: low levels of Vegf signaling promote overall vascular endothelial differentiation and cell survival by upregulating etv2 expression, while high levels of Vegf signaling promote arterial and inhibit venous specification.