Evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomas

BackgroundWhen selecting treatment strategies, elderly high-grade glioma (eHGG) patients face challenges due to aging, comorbidities, surgical complications, and limited tolerance for intensive treatments. This study aims to evaluate the benefit of treatment strategies and develop a treatment recomm...

Full description

Saved in:
Bibliographic Details
Main Authors: Feiling Xiang, Mengyuan Fu, Xuelian Yang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Oncology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fonc.2025.1597925/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849396134699597824
author Feiling Xiang
Feiling Xiang
Mengyuan Fu
Mengyuan Fu
Xuelian Yang
Xuelian Yang
author_facet Feiling Xiang
Feiling Xiang
Mengyuan Fu
Mengyuan Fu
Xuelian Yang
Xuelian Yang
author_sort Feiling Xiang
collection DOAJ
description BackgroundWhen selecting treatment strategies, elderly high-grade glioma (eHGG) patients face challenges due to aging, comorbidities, surgical complications, and limited tolerance for intensive treatments. This study aims to evaluate the benefit of treatment strategies and develop a treatment recommendation system for eHGG patients.MethodsBy propensity score matching and survival analysis, we compared the prognosis of treatment strategies, including surgery versus none, adjuvant therapies versus none, and gross total resection (GTR) versus subtotal resection (STR), among patients aged 65 and older with high-grade gliomas. A machine learning model, random survival forest, was developed to provide predictions on prognosis. The machine learning model was then used to create a personalized treatment recommendation system. An independent validation cohort was obtained from the First Affiliated Hospital of Chongqing Medical University to validate the machine learning model and the treatment recommendation system. The time-dependent AUC (tdAUC), C-index, and integrated Brier score (IBS) in the testing sets were obtained.ResultsCompared to the surgery-alone group, patients who received surgery plus adjuvant therapy had significantly better overall survival. Surgery plus adjuvant therapy improved survival compared to adjuvant therapy alone. Additionally, GTR combined with adjuvant therapy showed superior overall survival compared to STR with adjuvant therapy. Subgroup analysis indicated that patients with GBM, tumor size >3 cm, localized stage, white race, Grade IV tumors, and those aged 65–72 had better survival outcomes with GTR and adjuvant therapy. The C-index, tdAUC, and 1-IBS values for the external testing cohort were 0.813, 0.876, and 0.893. We successfully developed a web-based treatment recommendation system at https://gliomas.shinyapps.io/EHGG/. This system allows users to input patient-specific features and obtain individualized treatment recommendations and detailed survival probabilities.ConclusionAggressive treatment, including GTR and adjuvant therapy, can enhance survival outcomes in elderly patients with high-grade gliomas. The machine learning-based personalized treatment recommendation system presents a promising reference tool for treatment decisions.
format Article
id doaj-art-4b707b5ceee64484ac4d571da4973210
institution Kabale University
issn 2234-943X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Oncology
spelling doaj-art-4b707b5ceee64484ac4d571da49732102025-08-20T03:39:26ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-08-011510.3389/fonc.2025.15979251597925Evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomasFeiling Xiang0Feiling Xiang1Mengyuan Fu2Mengyuan Fu3Xuelian Yang4Xuelian Yang5Department of Neurosurgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Nursing, The First Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Neurosurgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Nursing, The First Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Neurosurgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Nursing, The First Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaBackgroundWhen selecting treatment strategies, elderly high-grade glioma (eHGG) patients face challenges due to aging, comorbidities, surgical complications, and limited tolerance for intensive treatments. This study aims to evaluate the benefit of treatment strategies and develop a treatment recommendation system for eHGG patients.MethodsBy propensity score matching and survival analysis, we compared the prognosis of treatment strategies, including surgery versus none, adjuvant therapies versus none, and gross total resection (GTR) versus subtotal resection (STR), among patients aged 65 and older with high-grade gliomas. A machine learning model, random survival forest, was developed to provide predictions on prognosis. The machine learning model was then used to create a personalized treatment recommendation system. An independent validation cohort was obtained from the First Affiliated Hospital of Chongqing Medical University to validate the machine learning model and the treatment recommendation system. The time-dependent AUC (tdAUC), C-index, and integrated Brier score (IBS) in the testing sets were obtained.ResultsCompared to the surgery-alone group, patients who received surgery plus adjuvant therapy had significantly better overall survival. Surgery plus adjuvant therapy improved survival compared to adjuvant therapy alone. Additionally, GTR combined with adjuvant therapy showed superior overall survival compared to STR with adjuvant therapy. Subgroup analysis indicated that patients with GBM, tumor size >3 cm, localized stage, white race, Grade IV tumors, and those aged 65–72 had better survival outcomes with GTR and adjuvant therapy. The C-index, tdAUC, and 1-IBS values for the external testing cohort were 0.813, 0.876, and 0.893. We successfully developed a web-based treatment recommendation system at https://gliomas.shinyapps.io/EHGG/. This system allows users to input patient-specific features and obtain individualized treatment recommendations and detailed survival probabilities.ConclusionAggressive treatment, including GTR and adjuvant therapy, can enhance survival outcomes in elderly patients with high-grade gliomas. The machine learning-based personalized treatment recommendation system presents a promising reference tool for treatment decisions.https://www.frontiersin.org/articles/10.3389/fonc.2025.1597925/fullsurgerygross total resectionsubtotal resectionadjuvant therapytreatment recommendation
spellingShingle Feiling Xiang
Feiling Xiang
Mengyuan Fu
Mengyuan Fu
Xuelian Yang
Xuelian Yang
Evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomas
Frontiers in Oncology
surgery
gross total resection
subtotal resection
adjuvant therapy
treatment recommendation
title Evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomas
title_full Evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomas
title_fullStr Evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomas
title_full_unstemmed Evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomas
title_short Evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomas
title_sort evaluating treatment strategies and machine learning based treatment recommendation system for elderly patients with high grade gliomas
topic surgery
gross total resection
subtotal resection
adjuvant therapy
treatment recommendation
url https://www.frontiersin.org/articles/10.3389/fonc.2025.1597925/full
work_keys_str_mv AT feilingxiang evaluatingtreatmentstrategiesandmachinelearningbasedtreatmentrecommendationsystemforelderlypatientswithhighgradegliomas
AT feilingxiang evaluatingtreatmentstrategiesandmachinelearningbasedtreatmentrecommendationsystemforelderlypatientswithhighgradegliomas
AT mengyuanfu evaluatingtreatmentstrategiesandmachinelearningbasedtreatmentrecommendationsystemforelderlypatientswithhighgradegliomas
AT mengyuanfu evaluatingtreatmentstrategiesandmachinelearningbasedtreatmentrecommendationsystemforelderlypatientswithhighgradegliomas
AT xuelianyang evaluatingtreatmentstrategiesandmachinelearningbasedtreatmentrecommendationsystemforelderlypatientswithhighgradegliomas
AT xuelianyang evaluatingtreatmentstrategiesandmachinelearningbasedtreatmentrecommendationsystemforelderlypatientswithhighgradegliomas