Personalized risk predictor for acute cellular rejection in lung transplant using soluble CD31

We evaluated the contribution of artificial intelligence in predicting the risk of acute cellular rejection (ACR) using early plasma levels of soluble CD31 (sCD31) in combination with recipient haematosis, which was measured by the ratio of arterial oxygen partial pressure to fractional oxygen inspired (PaO2/FiO(2)) and respiratory SOFA (Sequential Organ Failure Assessment) within 3 days of lung transplantation (LTx). CD31 is expressed on endothelial cells, leukocytes and platelets and acts as a peace-maker at the blood/vessel interface. Upon nonspecific activation, CD31 can be cleaved, released, and detected in the plasma (sCD31). The study included 40 lung transplant recipients, seven (17.5%) of whom experienced ACR. We modelled the plasma levels of sCD31 as a nonlinear dependent variable of the PaO2/FiO(2) and respiratory SOFA over time using multivariate and multimodal models. A deep convolutional network classified the time series models of each individual associated with the risk of ACR to each individual in the cohort.

Automated summary

The contribution of artificial intelligence in predicting the risk of acute cellular rejection after lung transplantation was evaluated by combining early plasma levels of sCD31 with recipient oxygen status and respiratory SOFA score. The study is significant for understanding the predictive mechanisms of ACR.