Cargando…
Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning
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...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley and Sons Inc.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9297869/ https://www.ncbi.nlm.nih.gov/pubmed/34587357 http://dx.doi.org/10.1002/lt.26318 |
_version_ | 1784750567611957248 |
---|---|
author | Cooper, Jason P. Perkins, James D. Warner, Paul R. Shingina, Alexandra Biggins, Scott W. Abkowitz, Janis L. Reyes, Jorge D. |
author_facet | Cooper, Jason P. Perkins, James D. Warner, Paul R. Shingina, Alexandra Biggins, Scott W. Abkowitz, Janis L. Reyes, Jorge D. |
author_sort | Cooper, Jason P. |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-9297869 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | John Wiley and Sons Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-92978692022-07-21 Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning Cooper, Jason P. Perkins, James D. Warner, Paul R. Shingina, Alexandra Biggins, Scott W. Abkowitz, Janis L. Reyes, Jorge D. Liver Transpl Original Articles 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. John Wiley and Sons Inc. 2021-11-05 2022-03 /pmc/articles/PMC9297869/ /pubmed/34587357 http://dx.doi.org/10.1002/lt.26318 Text en Copyright © 2021 The Authors. Liver Transplantation published by Wiley Periodicals LLC on behalf of American Association for the Study of Liver Diseases. https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ (https://creativecommons.org/licenses/by-nc-nd/4.0/) License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made. |
spellingShingle | Original Articles Cooper, Jason P. Perkins, James D. Warner, Paul R. Shingina, Alexandra Biggins, Scott W. Abkowitz, Janis L. Reyes, Jorge D. Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning |
title | Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning |
title_full | Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning |
title_fullStr | Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning |
title_full_unstemmed | Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning |
title_short | Acute Graft‐Versus‐Host Disease After Orthotopic Liver Transplantation: Predicting This Rare Complication Using Machine Learning |
title_sort | acute graft‐versus‐host disease after orthotopic liver transplantation: predicting this rare complication using machine learning |
topic | Original Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9297869/ https://www.ncbi.nlm.nih.gov/pubmed/34587357 http://dx.doi.org/10.1002/lt.26318 |
work_keys_str_mv | AT cooperjasonp acutegraftversushostdiseaseafterorthotopiclivertransplantationpredictingthisrarecomplicationusingmachinelearning AT perkinsjamesd acutegraftversushostdiseaseafterorthotopiclivertransplantationpredictingthisrarecomplicationusingmachinelearning AT warnerpaulr acutegraftversushostdiseaseafterorthotopiclivertransplantationpredictingthisrarecomplicationusingmachinelearning AT shinginaalexandra acutegraftversushostdiseaseafterorthotopiclivertransplantationpredictingthisrarecomplicationusingmachinelearning AT bigginsscottw acutegraftversushostdiseaseafterorthotopiclivertransplantationpredictingthisrarecomplicationusingmachinelearning AT abkowitzjanisl acutegraftversushostdiseaseafterorthotopiclivertransplantationpredictingthisrarecomplicationusingmachinelearning AT reyesjorged acutegraftversushostdiseaseafterorthotopiclivertransplantationpredictingthisrarecomplicationusingmachinelearning |