A multi-center study of COVID-19 patient prognosis using deep learning-based CT image analysis and electronic health records

•Deep learning method can robustly segment lung infection regions from CT images of COVID-19 patients. The correlation coefficient of the network prediction and manual segmentation was high to very high.•Combining CT-derived biomarkers with electronic health records can achieve the best prognosis prediction with AUC’s ranging between 85–93.•Prognosis results indicated that age, Oxygen saturation, CT-derived biomarkers, platelet count, and white blood cell count were the most important prognostic predictors of COVID-19.