Search

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.

The tyrosine kinase receptor Axl is expressed in the vasculature, and growth arrest-specific protein 6 (Gas6) is its ligand. Plasma Gas6 levels have been shown to be associated with endothelial dysfunction markers and cardiovascular events. We set out to determine the plasma Gas6 levels in patients undergoing coronary artery bypass grafting (CABG) and investigate the expression of Gas6 and Axl in the aorta.Immunoassays were used to investigate plasma Gas6 levels in CABG patients (n = 19) and control subjects (n = 20). The expression of Gas6 and Axl in the injured aorta were examined by reverse transcription-polymerase chain reactions, real-time reverse transcription-polymerase chain reactions, western blotting, and immunohistochemical staining. Plasma Gas6 levels were significantly lower in CABG patients than in matched control subjects. In CABG patients, plasma Gas6 levels were negatively correlated with fasting glucose, E-selectin, and vascular cell adhesion molecule-1 levels. The levels predicted the operative mortality rate and were positively correlated with plasma soluble Axl (sAxl) levels and Gas6 expression in the aorta. Moreover, Gas6 expression was positively correlated with Axl expression in the aorta.We concluded that plasma Gas6 is associated with fasting glucose, endothelial dysfunction markers, sAxl values, and vascular Gas6 expression in CABG patients, and it predicts the operative mortality of these patients. These findings suggest that the Gas6/Axl system is crucial in vascular biology.