Dataset Information

Machine learning classifiers for predicting 3-year progression-free survival and overall survival in patients with gliomas after surgery.

ABSTRACT: Background: To develop machine-learning based models to predict the progression-free survival (PFS) and overall survival (OS) in patients with gliomas and explore the effect of different feature selection methods on the prediction. Methods: We included 505 patients (training cohort, n = 354; validation cohort, n = 151) with gliomas between January 1, 2011 and December 31, 2016. The clinical, neuroimaging, and molecular genetic data of patients were retrospectively collected. The multi-causes discovering with structure learning (McDSL) algorithm, least absolute shrinkage and selection operator regression (LASSO), and Cox proportional hazards regression model were employed to discover the predictors for 3-year PFS and OS, respectively. Eight machine learning classifiers with 5-fold cross-validation were developed to predict 3-year PFS and OS. The area under the curve (AUC) was used to evaluate the prognostic performance of classifiers. Results: McDSL identified four causal factors (tumor location, WHO grade, histologic type, and molecular genetic group) for 3-year PFS and OS, whereas LASSO and Cox identified wide-range number of factors associated with 3-year PFS and OS. The performance of each machine learning classifier based on McDSL, LASSO, and Cox was not significantly different. Logistic regression yielded the optimal performance in predicting 3-year PFS based on the McDSL (AUC, 0.872, 95% confidence interval [CI]: 0.828-0.916) and 3-year OS based on the LASSO (AUC, 0.901, 95% CI: 0.861-0.940). Conclusions: McDSL is more reproducible than LASSO and Cox model in the feature selection process. Logistic regression model may have the highest performance in predicting 3-year PFS and OS of gliomas.

SUBMITTER: Zhang B

PROVIDER: S-EPMC7890310 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning classifiers for predicting 3-year progression-free survival and overall survival in patients with gliomas after surgery.

Zhang Bin B Yan Jing J Chen Weiqi W Dong Yuhao Y Zhang Lu L Mo Xiaokai X Chen Qiuying Q Cheng Jingliang J Liu Xianzhi X Wang Weiwei W Zhang Zhenyu Z Zhang Shuixing S

Journal of Cancer 20210115 6

<b>Background:</b> To develop machine-learning based models to predict the progression-free survival (PFS) and overall survival (OS) in patients with gliomas and explore the effect of different feature selection methods on the prediction. <b>Methods:</b> We included 505 patients (training cohort, n = 354; validation cohort, n = 151) with gliomas between January 1, 2011 and December 31, 2016. The clinical, neuroimaging, and molecular genetic data of patients were retrospectively collected. The mu ...[more]

PMID: 33613747

Similar Datasets

Project description:BackgroundSupratotal resection is advocated in lower-grade gliomas (LGGs) based on theoretical advantages but with limited verification of functional risk and data on oncological outcomes. We assessed the association of supratotal resection in molecularly defined LGGs with oncological outcomes.MethodsIncluded were 460 presumptive LGGs; 404 resected; 347 were LGGs, 319 isocitrate dehydrogenase (IDH)-mutated, 28 wildtype. All patients had clinical, imaging, and molecular data. Resection aimed at supratotal resection without any patient or tumor a priori selection. The association of extent of resection (EOR), categorized on volumetric fluid attenuated inversion recovery images as residual tumor volume, along with postsurgical management with progression-free survival (PFS), malignant (M)PFS, and overall survival (OS) assessed by univariate, multivariate, and propensity score analysis. The study mainly focused on IDH-mutated LGGs, the "typical LGGs."ResultsMedian follow-up was 6.8 years (interquartile range, 5-8). Out of 319 IDH-mutated LGGs, 190 (59.6%) progressed, median PFS: 4.7 years (95% CI: 4-5.3). Total and supratotal resection obtained in 39% and 35% of patients with IDH1-mutated tumors. In IDH-mutated tumors, most patients in the partial/subtotal group progressed, 82.4% in total, only 6 (5.4%) in supratotal. Median PFS was 29 months (95% CI: 25-36) in subtotal, 46 months (95% CI: 38-48) in total, while at 92 months, PFS in supratotal was 94.0%. There was no association with molecular subtypes and grade. At random forest analysis, PFS strongly associated with EOR, radiotherapy, and previous treatment. In the propensity score analysis, EOR associated with PFS (hazard ratio, 0.03; 95% CI: 0.01-0.13). MPFS occurred in 32.1% of subtotal total groups; 1 event in supratotal. EOR, grade III, previous treatment correlated to MPFS. At random forest analysis, OS associated with EOR as well.ConclusionsSupratotal resection strongly associated with PFS, MPFS, and OS in LGGs, regardless of molecular subtypes and grade, right from the beginning of clinical presentation.

Project description:BackgroundAccurately predicting the survival rate of breast cancer patients is a major issue for cancer researchers. Machine learning (ML) has attracted much attention with the hope that it could provide accurate results, but its modeling methods and prediction performance remain controversial. The aim of this systematic review is to identify and critically appraise current studies regarding the application of ML in predicting the 5-year survival rate of breast cancer.MethodsIn accordance with the PRISMA guidelines, two researchers independently searched the PubMed (including MEDLINE), Embase, and Web of Science Core databases from inception to November 30, 2020. The search terms included breast neoplasms, survival, machine learning, and specific algorithm names. The included studies related to the use of ML to build a breast cancer survival prediction model and model performance that can be measured with the value of said verification results. The excluded studies in which the modeling process were not explained clearly and had incomplete information. The extracted information included literature information, database information, data preparation and modeling process information, model construction and performance evaluation information, and candidate predictor information.ResultsThirty-one studies that met the inclusion criteria were included, most of which were published after 2013. The most frequently used ML methods were decision trees (19 studies, 61.3%), artificial neural networks (18 studies, 58.1%), support vector machines (16 studies, 51.6%), and ensemble learning (10 studies, 32.3%). The median sample size was 37256 (range 200 to 659820) patients, and the median predictor was 16 (range 3 to 625). The accuracy of 29 studies ranged from 0.510 to 0.971. The sensitivity of 25 studies ranged from 0.037 to 1. The specificity of 24 studies ranged from 0.008 to 0.993. The AUC of 20 studies ranged from 0.500 to 0.972. The precision of 6 studies ranged from 0.549 to 1. All of the models were internally validated, and only one was externally validated.ConclusionsOverall, compared with traditional statistical methods, the performance of ML models does not necessarily show any improvement, and this area of research still faces limitations related to a lack of data preprocessing steps, the excessive differences of sample feature selection, and issues related to validation. Further optimization of the performance of the proposed model is also needed in the future, which requires more standardization and subsequent validation.

Dataset Information

Machine learning classifiers for predicting 3-year progression-free survival and overall survival in patients with gliomas after surgery.

Publications

Machine learning classifiers for predicting 3-year progression-free survival and overall survival in patients with gliomas after surgery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure