Premium
Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning
Author(s) -
Cooper Jason P.,
Perkins James D.,
Warner Paul R.,
Shingina Alexandra,
Biggins Scott W.,
Abkowitz Janis L.,
Reyes Jorge D.
Publication year - 2022
Publication title -
liver transplantation
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.814
H-Index - 150
eISSN - 1527-6473
pISSN - 1527-6465
DOI - 10.1002/lt.26318
Subject(s) - medicine , receiver operating characteristic , logistic regression , complication , population , transplantation , graft versus host disease , liver transplantation , ensemble learning , disease , retrospective cohort study , machine learning , computer science , environmental health
Acute graft‐versus‐host disease (GVHD) is a rare complication after orthotopic liver transplantation (OLT) that carries high mortality. We hypothesized that machine‐learning algorithms to predict rare events would identify patients at high risk for developing GVHD. To develop a predictive model, we retrospectively evaluated the clinical features of 1938 donor‐recipient pairs at the time they underwent OLT at our center; 19 (1.0%) of these recipients developed GVHD. This population was divided into training (70%) and test (30%) sets. A total of 7 machine‐learning classification algorithms were built based on the training data set to identify patients at high risk for GVHD. The C5.0, heterogeneous ensemble, and generalized gradient boosting machine (GGBM) algorithms predicted that 21% to 28% of the recipients in the test data set were at high risk for developing GVHD, with an area under the receiver operating characteristic curve (AUROC) of 0.83 to 0.86. The 7 algorithms were then evaluated in a validation data set of 75 more recent donor‐recipient pairs who underwent OLT at our center; 2 of these recipients developed GVHD. The logistic regression, heterogeneous ensemble, and GGBM algorithms predicted that 9% to 11% of the validation recipients were at high risk for developing GVHD, with an AUROC of 0.93 to 0.96 that included the 2 recipients who developed GVHD. In conclusion, we present a practical model that can identify patients at high risk for GVHD who may warrant additional monitoring with peripheral blood chimerism testing.