Time-dependent prediction of mortality and cytomegalovirus reactivation after allogeneic hematopoietic cell transplantation using machine learning

Allogeneic hematopoietic cell transplantation (HCT) treats high-risk hematologic diseases effectively but can entail HCT-specific complications, which may be minimized by appropriate patient management and accurate, individual risk estimation. Existing clinical scores typically provide a single risk assessment before HCT and do not incorporate additional data as it becomes available. We developed machine learning models which integrate both baseline patient data and time-dependent laboratory measurements to individually predict mortality and cytomegalovirus (CMV) reactivation after HCT at multiple time points per patient. These models provide well-calibrated time-dependent risk predictions and achieved areas under the receiver-operating characteristic of 0.92 and 0.83 and areas under the precision-recall curve of 0.58 and 0.62 for prediction of mortality and CMV reactivation, respectively, in a 21-day time window. Both were successfully validated in a non-interventional, prospective study and performed on par with expert hematologists in a pilot comparison.