Improving survival prediction of high-grade glioma via machine learning techniques based on MRI radiomic, genetic and clinical risk factors

Tan, Yan; Mu, Wei; Wang, Xiaochun; Yang, Guoqiang; Gillies, Robert J.; Zhang, Hui

doi:10.1016/j.ejrad.2019.07.010

Cited by 60 publications

(47 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning (ML), a branch of artificial intelligence, has been employed to predict prognosis in a variety of cancer types. Noticeably, series of studies applying ML algorithms to predict the survival of HGG under standard photon-based radiotherapy have reported good performance in recent years (8)(9)(10)(11)(12)(13). However, it is still controversial that which methods among ML algorithms and conventional modeling can achieve better performance in survival analysis, particularly in terms of time-to-event censored data (14)(15)(16).…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2020

View full text Add to dashboard Cite

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 Cindex (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

show abstract

Section: Introductionmentioning

confidence: 99%

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

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Recently, machine learning (ML)-based on set of algorithms has been used for diverse scenarios to allow precision in classification, progression, treatment and OS of certain diseases including glioma [32][33][34][35]. ML has been used on gliomas to predict OS using various datasets, especially TCGA [32], studying IDH mutation [35,36] and MGMT promoter methylation [37]. However, these studies still do not show improvement over the traditional statistical methods for clinical biomarkers [33].…”

mentioning

confidence: 99%

Favorable Role of IDH 1/2 Mutations Aided With MGMT Promoter Gene Methylation in the Outcome of Patients With Malignant Glioma

et al. 2020

View full text Add to dashboard Cite

Aim: The implications of molecular biomarkers IDH1/2 mutations and MGMT gene promoter methylation were evaluated for prognostic outcome of glioma patients. Materials & methods: Glioma cases were analyzed for IDH1/2 mutations and MGMT promoter methylation by DNA sequencing and methylation-specific PCR, respectively. Results: Mutations found in IDH1/2 genes totaled 63.4% (N = 40) wherein IDH1 mutations were significantly associated with oligidendrioglioma (p = 0.005) and astrocytoma (p = 0.0002). IDH1 mutants presented more, 60.5% in MGMT promoter-methylated cases (p = 0.03). IDH1 mutant cases had better survival for glioblastoma and oligodendrioglioma (log-rank p = 0.01). Multivariate analysis confirmed better survival in MGMT methylation carriers (hazard ratio [HR]: 0.59; p = 0.031). Combination of both biomarkers showed better prognosis on temozolomide (p < 0.05). Conclusion: IDH1/2 mutations proved independent prognostic factors in glioma and associated with MGMT methylation for better survival.

show abstract

“…The higher accuracy and better performance of the RSF model make it highly valuable for predicting survival in HGG patients. In fact, a few researchers have expended great effort to develop a prognostic prediction model for this highly malignant cancer, proposing a survival prediction model for HGG based on MRI radiomic features combined with genetic and clinical risk factors 26–29 . Imaging features from fluorodeoxyglucose‐positron emission tomography (FDG‐PET) have also been used to predict survival in recurrent HGG 30 .…”

Section: Discussionmentioning

confidence: 99%

A machine learning‐based survival prediction model of high grade glioma by integration of clinical and dose‐volume histogram parameters

Chen

Zheng

et al. 2021

Cancer Medicine

View full text Add to dashboard Cite

Purpose Glioma is the most common type of primary brain tumor in adults, and it causes significant morbidity and mortality, especially in high‐grade glioma (HGG) patients. The accurate prognostic prediction of HGG is vital and helpful for clinicians when developing therapeutic strategies. Therefore, we propose a machine learning‐based survival prediction model by analyzing clinical and dose‐volume histogram (DVH) parameters, to improve the performance of the risk model in HGG patients. Methods Eight clinical variables and 39 DVH parameters were extracted for each patient, who received radiotherapy for HGG with active follow‐up. Ninety‐five patients were randomly divided into training and testing cohorts, and we employed random survival forest (RSF), support vector machine (SVM), and Cox proportional hazards (CPHs) models to predict survival. Calibration plots, concordance indexes, and decision curve analyses were used to evaluate the calibration, discrimination, and clinical utility of these three models. Results The RSF model showed the best performance among the three models, with concordance indexes of 0.824 and 0.847 in the training and testing sets, respectively, followed by the SVM (0.792/0.823) and CPH (0.821/0.811) models. Specifically, in the RSF model, we identified age, gross tumor volume (GTV), grade, Karnofsky performance status (KPS), isocitrate dehydrogenase (IDH), and D99 as important variables associated with survival. The AUCs of the testing set were 92.4%, 87.7%, and 84.0% for 1‐, 2‐, and 3‐year survival, respectively. According to this model, HGG patients can be divided into high‐ and low‐risk groups. Conclusion The machine learning‐based RSF model integrating both clinical and DVH variables is an improved and useful tool for predicting the survival of HGG patients.

show abstract

Improving survival prediction of high-grade glioma via machine learning techniques based on MRI radiomic, genetic and clinical risk factors

Cited by 60 publications

References 28 publications

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

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

Favorable Role of IDH 1/2 Mutations Aided With MGMT Promoter Gene Methylation in the Outcome of Patients With Malignant Glioma

A machine learning‐based survival prediction model of high grade glioma by integration of clinical and dose‐volume histogram parameters

Contact Info

Product

Resources

About