A Convolutional Neural Network-based Model That Predicts Acute Graft-versus-host Disease After Allogeneic Hematopoietic Stem Cell Transplantation

This study used a CNN-based model to predict the risk of acute Graft-versus-Host Disease (aGVHD) after Hematopoietic Stem Cell Transplantation (HSCT). The model was able to extract discriminating features from comprehensive patient characteristics, and successfully visualized the weight of each clinical factor. Raw HLA data was also utilized by the model, and the influences of factors other than HLA disparity on the risk of aGVHD were clarified.