Cargando…

A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy

BACKGROUND: Machine learning (ML) algorithms are increasingly explored in glioma prognostication. Random survival forest (RSF) is a common ML approach in analyzing time-to-event survival data. However, it is controversial which method between RSF and traditional cornerstone method Cox proportional h...

Descripción completa

Detalles Bibliográficos
Autores principales: Qiu, Xianxin, Gao, Jing, Yang, Jing, Hu, Jiyi, Hu, Weixu, Kong, Lin, Lu, Jiade J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7662123/
https://www.ncbi.nlm.nih.gov/pubmed/33194609
http://dx.doi.org/10.3389/fonc.2020.551420
_version_ 1783609333760655360
author Qiu, Xianxin
Gao, Jing
Yang, Jing
Hu, Jiyi
Hu, Weixu
Kong, Lin
Lu, Jiade J.
author_facet Qiu, Xianxin
Gao, Jing
Yang, Jing
Hu, Jiyi
Hu, Weixu
Kong, Lin
Lu, Jiade J.
author_sort Qiu, Xianxin
collection PubMed
description BACKGROUND: Machine learning (ML) algorithms are increasingly explored in glioma prognostication. Random survival forest (RSF) is a common ML approach in analyzing time-to-event survival data. However, it is controversial which method between RSF and traditional cornerstone method Cox proportional hazards (CPH) is better fitted. The purpose of this study was to compare RSF and CPH in predicting tumor progression of high-grade glioma (HGG) after particle beam radiotherapy (PBRT). METHODS: The study enrolled 82 consecutive HGG patients who were treated with PBRT at Shanghai Proton and Heavy Ion Center between 6/2015 and 11/2019. The entire cohort was split into the training and testing set in an 80/20 ratio. Ten variables from patient-related, tumor-related and treatment-related information were utilized for developing CPH and RSF for predicting progression-free survival (PFS). The model performance was compared in concordance index (C-index) for discrimination (accuracy), brier score (BS) for calibration (precision) and variable importance for interpretability. RESULTS: The CPH model demonstrated a better performance in terms of integrated C-index (62.9%) and BS (0.159) compared to RSF model (C-index = 61.1%, BS = 0.174). In the context of variable importance, CPH model indicated that age (P = 0.024), WHO grade (P = 0.020), IDH gene (P = 0.019), and MGMT promoter status (P = 0.040) were significantly correlated with PFS in the univariate analysis; multivariate analysis showed that age (P = 0.041), surgical completeness (P = 0.084), IDH gene (P = 0.057), and MGMT promoter (P = 0.092) had a significant or trend toward the relation with PFS. RSF showed that merely IDH and age were of positive importance for predicting PFS. A final nomogram was developed to predict tumor progression at the individual level based on CPH model. CONCLUSIONS: In a relatively small dataset with HGG patients treated with PBRT, CPH outperformed RSF for predicting tumor progression. A comprehensive criterion with accuracy, precision, and interpretability is recommended in evaluating ML prognostication approaches for clinical deployment.
format Online
Article
Text
id pubmed-7662123
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-76621232020-11-13 A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy Qiu, Xianxin Gao, Jing Yang, Jing Hu, Jiyi Hu, Weixu Kong, Lin Lu, Jiade J. Front Oncol Oncology BACKGROUND: Machine learning (ML) algorithms are increasingly explored in glioma prognostication. Random survival forest (RSF) is a common ML approach in analyzing time-to-event survival data. However, it is controversial which method between RSF and traditional cornerstone method Cox proportional hazards (CPH) is better fitted. The purpose of this study was to compare RSF and CPH in predicting tumor progression of high-grade glioma (HGG) after particle beam radiotherapy (PBRT). METHODS: The study enrolled 82 consecutive HGG patients who were treated with PBRT at Shanghai Proton and Heavy Ion Center between 6/2015 and 11/2019. The entire cohort was split into the training and testing set in an 80/20 ratio. Ten variables from patient-related, tumor-related and treatment-related information were utilized for developing CPH and RSF for predicting progression-free survival (PFS). The model performance was compared in concordance index (C-index) for discrimination (accuracy), brier score (BS) for calibration (precision) and variable importance for interpretability. RESULTS: The CPH model demonstrated a better performance in terms of integrated C-index (62.9%) and BS (0.159) compared to RSF model (C-index = 61.1%, BS = 0.174). In the context of variable importance, CPH model indicated that age (P = 0.024), WHO grade (P = 0.020), IDH gene (P = 0.019), and MGMT promoter status (P = 0.040) were significantly correlated with PFS in the univariate analysis; multivariate analysis showed that age (P = 0.041), surgical completeness (P = 0.084), IDH gene (P = 0.057), and MGMT promoter (P = 0.092) had a significant or trend toward the relation with PFS. RSF showed that merely IDH and age were of positive importance for predicting PFS. A final nomogram was developed to predict tumor progression at the individual level based on CPH model. CONCLUSIONS: In a relatively small dataset with HGG patients treated with PBRT, CPH outperformed RSF for predicting tumor progression. A comprehensive criterion with accuracy, precision, and interpretability is recommended in evaluating ML prognostication approaches for clinical deployment. Frontiers Media S.A. 2020-10-30 /pmc/articles/PMC7662123/ /pubmed/33194609 http://dx.doi.org/10.3389/fonc.2020.551420 Text en Copyright © 2020 Qiu, Gao, Yang, Hu, Hu, Kong and Lu http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Qiu, Xianxin
Gao, Jing
Yang, Jing
Hu, Jiyi
Hu, Weixu
Kong, Lin
Lu, Jiade J.
A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy
title A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy
title_full A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy
title_fullStr A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy
title_full_unstemmed A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy
title_short A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy
title_sort comparison study of machine learning (random survival forest) and classic statistic (cox proportional hazards) for predicting progression in high-grade glioma after proton and carbon ion radiotherapy
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7662123/
https://www.ncbi.nlm.nih.gov/pubmed/33194609
http://dx.doi.org/10.3389/fonc.2020.551420
work_keys_str_mv AT qiuxianxin acomparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT gaojing acomparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT yangjing acomparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT hujiyi acomparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT huweixu acomparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT konglin acomparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT lujiadej acomparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT qiuxianxin comparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT gaojing comparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT yangjing comparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT hujiyi comparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT huweixu comparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT konglin comparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy
AT lujiadej comparisonstudyofmachinelearningrandomsurvivalforestandclassicstatisticcoxproportionalhazardsforpredictingprogressioninhighgradegliomaafterprotonandcarbonionradiotherapy