Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia
Abstract We used the eXtreme Gradient Boosting algorithm, an optimized gradient boosting machine learning library, and established a model to predict events in Philadelphia chromosome-positive acute lymphoblastic leukemia using a machine learning-aided method. A model was constructed using a trainin...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-02-01
|
Series: | Biomarker Research |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40364-021-00268-x |
id |
doaj-daa0493c46a44ee9abff03074f4a1788 |
---|---|
record_format |
Article |
spelling |
doaj-daa0493c46a44ee9abff03074f4a17882021-02-21T12:15:38ZengBMCBiomarker Research2050-77712021-02-01911410.1186/s40364-021-00268-xMachine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemiaSatoshi Nishiwaki0Isamu Sugiura1Daisuke Koyama2Yukiyasu Ozawa3Masahide Osaki4Yuichi Ishikawa5Hitoshi Kiyoi6Department of Advanced Medicine, Nagoya University HospitalDivision of Hematology and Oncology, Toyohashi Municipal HospitalDivision of Hematology and Oncology, Toyohashi Municipal HospitalDepartment of Hematology, Japanese Red Cross Nagoya Daiichi HospitalDepartment of Hematology, Japanese Red Cross Nagoya Daiichi HospitalDepartment of Hematology and Oncology, Nagoya University Graduate School of MedicineDepartment of Hematology and Oncology, Nagoya University Graduate School of MedicineAbstract We used the eXtreme Gradient Boosting algorithm, an optimized gradient boosting machine learning library, and established a model to predict events in Philadelphia chromosome-positive acute lymphoblastic leukemia using a machine learning-aided method. A model was constructed using a training set (80%) and prediction was tested using a test set (20%). According to the feature importance score, BCR-ABL lineage, polymerase chain reaction value, age, and white blood cell count were identified as important features. These features were also confirmed by the permutation feature importance for the prediction using the test set. Both event-free survival and overall survival were clearly stratified according to risk groups categorized using these features: 80 and 100% in low risk (two or less factors), 42 and 47% in intermediate risk (three factors), and 0 and 10% in high risk (four factors) at 4 years. Machine learning-aided analysis was able to identify clinically useful prognostic factors using data from a relatively small number of patients.https://doi.org/10.1186/s40364-021-00268-xeXtreme gradient boosting algorithmMachine learningPhiladelphia chromosome-positive acute lymphoblastic leukemiaPrognostic factorSurvival stratification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Satoshi Nishiwaki Isamu Sugiura Daisuke Koyama Yukiyasu Ozawa Masahide Osaki Yuichi Ishikawa Hitoshi Kiyoi |
spellingShingle |
Satoshi Nishiwaki Isamu Sugiura Daisuke Koyama Yukiyasu Ozawa Masahide Osaki Yuichi Ishikawa Hitoshi Kiyoi Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia Biomarker Research eXtreme gradient boosting algorithm Machine learning Philadelphia chromosome-positive acute lymphoblastic leukemia Prognostic factor Survival stratification |
author_facet |
Satoshi Nishiwaki Isamu Sugiura Daisuke Koyama Yukiyasu Ozawa Masahide Osaki Yuichi Ishikawa Hitoshi Kiyoi |
author_sort |
Satoshi Nishiwaki |
title |
Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia |
title_short |
Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia |
title_full |
Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia |
title_fullStr |
Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia |
title_full_unstemmed |
Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia |
title_sort |
machine learning-aided risk stratification in philadelphia chromosome-positive acute lymphoblastic leukemia |
publisher |
BMC |
series |
Biomarker Research |
issn |
2050-7771 |
publishDate |
2021-02-01 |
description |
Abstract We used the eXtreme Gradient Boosting algorithm, an optimized gradient boosting machine learning library, and established a model to predict events in Philadelphia chromosome-positive acute lymphoblastic leukemia using a machine learning-aided method. A model was constructed using a training set (80%) and prediction was tested using a test set (20%). According to the feature importance score, BCR-ABL lineage, polymerase chain reaction value, age, and white blood cell count were identified as important features. These features were also confirmed by the permutation feature importance for the prediction using the test set. Both event-free survival and overall survival were clearly stratified according to risk groups categorized using these features: 80 and 100% in low risk (two or less factors), 42 and 47% in intermediate risk (three factors), and 0 and 10% in high risk (four factors) at 4 years. Machine learning-aided analysis was able to identify clinically useful prognostic factors using data from a relatively small number of patients. |
topic |
eXtreme gradient boosting algorithm Machine learning Philadelphia chromosome-positive acute lymphoblastic leukemia Prognostic factor Survival stratification |
url |
https://doi.org/10.1186/s40364-021-00268-x |
work_keys_str_mv |
AT satoshinishiwaki machinelearningaidedriskstratificationinphiladelphiachromosomepositiveacutelymphoblasticleukemia AT isamusugiura machinelearningaidedriskstratificationinphiladelphiachromosomepositiveacutelymphoblasticleukemia AT daisukekoyama machinelearningaidedriskstratificationinphiladelphiachromosomepositiveacutelymphoblasticleukemia AT yukiyasuozawa machinelearningaidedriskstratificationinphiladelphiachromosomepositiveacutelymphoblasticleukemia AT masahideosaki machinelearningaidedriskstratificationinphiladelphiachromosomepositiveacutelymphoblasticleukemia AT yuichiishikawa machinelearningaidedriskstratificationinphiladelphiachromosomepositiveacutelymphoblasticleukemia AT hitoshikiyoi machinelearningaidedriskstratificationinphiladelphiachromosomepositiveacutelymphoblasticleukemia |
_version_ |
1724258319273558016 |