JMIR Publications

ABSTRACT

Background:

Scoring systems developed for predicting survival after allogeneic hematopoietic cell transplantation (HCT) show suboptimal prediction power, and various factors affect post-transplantation outcomes.

Objective:

A prediction model using a machine learning-based algorithm can be an alternative for concurrently applying multiple variables and reduce potential biases. In this regard, we aimed to establish and validate the machine learning-based predictive model for survival after allogeneic HCT in hematologic malignancies.

Methods:

Data from 1,470 patients with hematologic malignancies who underwent allogeneic HCT between December 1993 and June 2020 at Asan Medical Center were retrospectively analyzed. Using the gradient boosting machine algorithm, we evaluated a model predicting the 5-year post-transplantation survival through 10-fold cross-validation.

Results:

The prediction model showed good performance with a mean area under the receiver operating characteristic curve of 0.788 ± 0.03. Furthermore, we developed a risk score predicting probabilities of post-transplantation survival in 294 randomly selected patients, and an agreement between the estimated predicted and observed risks of overall death, non-relapse mortality, and relapse incidences was observed according to the risk score. Additionally, the calculated score showed the possibility of predicting survival according to the different transplantation-related factors with the visualization of the importance of each variable.

Conclusions:

We developed a machine learning-based model for predicting long-term survival after allogeneic HCT in patients with hematologic malignancies. Our model provides a method for making decisions regarding patient and donor candidates or selecting transplantation-related resources, such as conditioning regimens.