MetaWise: Combined Feature Selection and Weighting Method to Link the Serum Metabolome to Treatment Response and Survival in Glioblastoma.

Glioblastoma (GBM) is a highly malignant and devastating brain cancer characterized by its ability to rapidly and aggressively grow, infiltrating brain tissue, with nearly universal recurrence after the standard of care (SOC), which comprises maximal safe resection followed by chemoirradiation (CRT). The metabolic triggers leading to the reprogramming of tumor behavior and resistance are an area increasingly studied in relation to the tumor molecular features associated with outcome. There are currently no metabolomic biomarkers for GBM. Studying the metabolomic alterations in GBM patients undergoing CRT could uncover the biochemical pathways involved in tumor response and resistance, leading to the identification of novel biomarkers and the optimization of the treatment response. The feature selection process identifies key factors to improve the model's accuracy and interpretability. This study utilizes a combined feature selection approach, incorporating both Least Absolute Shrinkage and Selection Operator (LASSO) and Minimum Redundancy-Maximum Relevance (mRMR), alongside a rank-based weighting method (i.e., MetaWise) to link metabolomic biomarkers to CRT and the 12-month and 20-month overall survival (OS) status in patients with GBM. Our method shows promising results, reducing feature dimensionality when employed on serum-based large-scale metabolomic datasets (University of Florida) for all our analyses. The proposed method successfully identified a set of eleven serum biomarkers shared among three datasets. The computational results show that the utilized method achieves 96.711%, 92.093%, and 86.910% accuracy rates with 48, 46, and 33 selected features for the CRT, 12-month, and 20-month OS-based metabolomic datasets, respectively. This discovery has implications for developing personalized treatment plans and improving patient outcomes.

MGMT ProFWise: Unlocking a New Application for Combined Feature Selection and the Rank-Based Weighting Method to Link MGMT Methylation Status to Serum Protein Expression in Patients with Glioblastoma.

Glioblastoma (GBM) is a fatal brain tumor with limited treatment options. O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation status is the central molecular biomarker linked to both the response to temozolomide, the standard chemotherapy drug employed for GBM, and to patient survival. However, MGMT status is captured on tumor tissue which, given the difficulty in acquisition, limits the use of this molecular feature for treatment monitoring. MGMT protein expression levels may offer additional insights into the mechanistic understanding of MGMT but, currently, they correlate poorly to promoter methylation. The difficulty of acquiring tumor tissue for MGMT testing drives the need for non-invasive methods to predict MGMT status. Feature selection aims to identify the most informative features to build accurate and interpretable prediction models. This study explores the new application of a combined feature selection (i.e., LASSO and mRMR) and the rank-based weighting method (i.e., MGMT ProFWise) to non-invasively link MGMT promoter methylation status and serum protein expression in patients with GBM. Our method provides promising results, reducing dimensionality (by more than 95%) when employed on two large-scale proteomic datasets (7k SomaScan® panel and CPTAC) for all our analyses. The computational results indicate that the proposed approach provides 14 shared serum biomarkers that may be helpful for diagnostic, prognostic, and/or predictive operations for GBM-related processes, given further validation.

Intra-individual comparison of 18F-sodium fluoride PET-CT and 99mTc bone scintigraphy with SPECT in patients with prostate cancer or breast cancer at high risk for skeletal metastases (MITNEC-A1): a multicentre, phase 3 trial.

BACKGROUND: Detection of skeletal metastases in patients with prostate cancer or breast cancer remains a major clinical challenge. We aimed to compare the diagnostic performance of 99mTc-methylene diphosphonate (99mTc-MDP) single-photon emission CT (SPECT) and 18F-sodium fluoride (18F-NaF) PET-CT for the detection of osseous metastases in patients with high-risk prostate or breast cancer. METHODS: MITNEC-A1 was a prospective, multicentre, single-cohort, phase 3 trial conducted in ten hospitals across Canada. Patients aged 18 years or older with breast or prostate cancer with a WHO performance status of 0-2 and with high risk or clinical suspicion for bone metastasis, but without previously documented bone involvement, were eligible. 18F-NaF PET-CT and 99mTc-MDP SPECT were done within 14 days of each other for each participant. Two independent reviewers interpreted each modality without knowledge of other imaging findings. The primary endpoint was the overall accuracy of 99mTc-MDP SPECT and 18F-NaF PET-CT scans for the detection of bone metastases in the per-protocol population. A combination of histopathological, clinical, and imaging follow-up for up to 24 months was used as the reference standard to assess the imaging results. Safety was assessed in all enrolled participants. This study is registered with ClinicalTrials.gov, NCT01930812, and is complete. FINDINGS: Between July 11, 2014, and March 3, 2017, 290 patients were screened, 288 of whom were enrolled (64 participants with breast cancer and 224 with prostate cancer). 261 participants underwent both 18F-NaF PET-CT and 99mTc-MDP SPECT and completed the required follow-up for statistical analysis. Median follow-up was 735 days (IQR 727-750). Based on the reference methods used, 109 (42%) of 261 patients had bone metastases. In the patient-based analysis, 18F-NaF PET-CT was more accurate than 99mTc-MDP SPECT (84·3% [95% CI 79·9-88·7] vs 77·4% [72·3-82·5], difference 6·9% [95% CI 1·3-12·5]; p=0·016). No adverse events were reported for the 288 patients recruited. INTERPRETATION: 18F-NaF has the potential to displace 99mTc-MDP as the bone imaging radiopharmaceutical of choice in patients with high-risk prostate or breast cancer. FUNDING: Canadian Institutes of Health Research.

Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics.

Determining the aggressiveness of gliomas, termed grading, is a critical step toward treatment optimization to increase the survival rate and decrease treatment toxicity for patients. Streamlined grading using molecular information has the potential to facilitate decision making in the clinic and aid in treatment planning. In recent years, molecular markers have increasingly gained importance in the classification of tumors. In this study, we propose a novel hierarchical voting-based methodology for improving the performance results of the feature selection stage and machine learning models for glioma grading with clinical and molecular predictors. To identify the best scheme for the given soft-voting-based ensemble learning model selections, we utilized publicly available TCGA and CGGA datasets and employed four dimensionality reduction methods to carry out a voting-based ensemble feature selection and five supervised models, with a total of sixteen combination sets. We also compared our proposed feature selection method with the LASSO feature selection method in isolation. The computational results indicate that the proposed method achieves 87.606% and 79.668% accuracy rates on TCGA and CGGA datasets, respectively, outperforming the LASSO feature selection method.

Type and timing of systemic therapy use predict overall survival for patients with brain metastases treated with radiation therapy.

INTRODUCTION: This study aimed to investigate whether systemic therapy (ST) use surrounding radiation therapy (RT) predicts overall survival (OS) after RT for patients with brain metastases (BMs). METHODS: Provincial RT and pharmacy databases were used to review all adult patients in British Columbia, Canada, who received a first course of RT for BMs between 2012 and 2016 (n = 3095). Multivariate analysis on a randomly selected subset was used to develop an OS nomogram. RESULTS: In comparison to the 2096 non-recipients of ST after RT, the median OS of the 999 recipients of ST after RT was 5.0 (95% Confidence interval (CI) 4.1-6.0) months longer (p < 0.0001). Some types of ST after RT were independently predictive of OS: targeted therapy (hazard ratio (HR) 0.42, CI 0.37-0.48), hormone therapy (HR 0.45, CI 0.36-0.55), cytotoxic chemotherapy (HR 0.71, CI 0.64-0.79), and immunotherapy (HR 0.64, CI 0.37-1.06). Patients who discontinued ST after RT had 0.9 (CI 0.3-1.4) months shorter median OS than patients who received no ST before or after RT (p < 0.0001). In the multivariate analysis of the 220-patient subset, established prognostic variables (extracranial disease, performance status, age, cancer diagnosis, and number of BMs), and the novel variables "ST before RT" and "Type of ST after RT" independently predicted OS. The nomogram predicted 6- and 12-month OS probability and median OS (bootstrap-corrected Harrell's Concordance Index = 0.70). CONCLUSIONS: The type and timing of ST use surrounding RT predict OS for patients with BMs.

Molecular Biology in Treatment Decision Processes-Neuro-Oncology Edition.

Computational approaches including machine learning, deep learning, and artificial intelligence are growing in importance in all medical specialties as large data repositories are increasingly being optimised. Radiation oncology as a discipline is at the forefront of large-scale data acquisition and well positioned towards both the production and analysis of large-scale oncologic data with the potential for clinically driven endpoints and advancement of patient outcomes. Neuro-oncology is comprised of malignancies that often carry poor prognosis and significant neurological sequelae. The analysis of radiation therapy mediated treatment and the potential for computationally mediated analyses may lead to more precise therapy by employing large scale data. We analysed the state of the literature pertaining to large scale data, computational analysis, and the advancement of molecular biomarkers in neuro-oncology with emphasis on radiation oncology. We aimed to connect existing and evolving approaches to realistic avenues for clinical implementation focusing on low grade gliomas (LGG), high grade gliomas (HGG), management of the elderly patient with HGG, rare central nervous system tumors, craniospinal irradiation, and re-irradiation to examine how computational analysis and molecular science may synergistically drive advances in personalised radiation therapy (RT) and optimise patient outcomes.

A phase I trial of lenalidomide and radiotherapy in children with diffuse intrinsic pontine gliomas or high-grade gliomas.

PURPOSE: This study was performed to determine the maximum tolerated dose (MTD) or recommended phase 2 dose (RP2D) of the immunomodulatory agent, lenalidomide, when administered daily during 6 weeks of radiation therapy to children with newly diagnosed diffuse intrinsic pontine glioma (DIPG) or high-grade glioma (HGG) PATIENTS & METHODS: Children and young adults < 22 years of age with newly diagnosed disease and no prior chemotherapy or radiation therapy were eligible. Children with HGG were required to have an inoperable or incompletely resected tumor. Eligible patients received standard radiation therapy to a prescription dose of 54-59.4 Gy, with concurrent administration of lenalidomide daily during radiation therapy in a standard 3 + 3 Phase I dose escalation design. Following completion of radiation therapy, patients had a 2-week break followed by maintenance lenalidomide at 116 mg/m2/day × 21 days of a 28-day cycle. RESULTS: Twenty-nine patients (age range 4-19 years) were enrolled; 24 were evaluable for dose finding (DIPG, n = 13; HGG, n = 11). The MTD was not reached at doses of lenalidomide up to 116 mg/m2/day. Exceptional responses were noted in DIPG and malignant glioma (gliomatosis cerebri) notably at higher dose levels and at higher steady state plasma concentrations. The primary toxicity was myelosuppression. CONCLUSION: The RP2D of lenalidomide administered daily during radiation therapy is 116 mg/m2/day. Children with malignant gliomas tolerate much higher doses of lenalidomide during radiation therapy compared to adults. This finding is critical as activity was observed primarily at higher dose levels suggesting a dose response.

Differentiating pseudoprogression from true progression: analysis of radiographic, biologic, and clinical clues in GBM.

INTRODUCTION: Pseudoprogression (PsP) is a diagnostic dilemma in glioblastoma (GBM) after chemoradiotherapy (CRT). Magnetic resonance imaging (MRI) features may fail to distinguish PsP from early true progression (eTP), however clinical findings may aid in their distinction. METHODS: Sixty-seven patients received CRT for GBM between 2003 and 2016, and had pre- and post-treatment imaging suitable for retrospective evaluation using RANO criteria. Patients with signs of progression within the first 12-weeks post-radiation (P-12) were selected. Lesions that improved or stabilized were defined as PsP, and lesions that progressed were defined as eTP. RESULTS: The median follow up for all patients was 17.6 months. Signs of progression developed in 35/67 (52.2%) patients within P-12. Of these, 20/35 (57.1%) were subsequently defined as eTP and 15/35 (42.9%) as PsP. MRI demonstrated increased contrast enhancement in 84.2% of eTP and 100% of PsP, and elevated CBV in 73.7% for eTP and 93.3% for PsP. A decrease in FLAIR was not seen in eTP patients, but was seen in 26.7% PsP patients. Patients with eTP were significantly more likely to require increased steroid doses or suffer clinical decline than PsP patients (OR 4.89, 95% CI 1.003-19.27; p = 0.046). KPS declined in 25% with eTP and none of the PsP patients. CONCLUSIONS: MRI imaging did not differentiate eTP from PsP, however, KPS decline or need for increased steroids was significantly more common in eTP versus PsP. Investigation and standardization of clinical assessments in response criteria may help address the diagnostic dilemma of pseudoprogression after frontline treatment for GBM.

The evolving role for re-irradiation in the management of recurrent grade 4 glioma.

Although significant gains have been realized in the management of grade 4 glioma, the majority of these patients will ultimately suffer local recurrence within the prior field of treatment. Clearly, novel local treatment strategies are required to improve patient outcomes. Concerns of toxicity have limited enthusiasm for the utilization of re-irradiation as a treatment option. However, using modern imaging technology and precision radiotherapy delivery techniques re-irradiation has proven a feasible option achieving both a palliative benefit and prolongation of survival with low toxicity rates. The evolution of re-irradiation as a treatment modality for recurrent grade 4 glioma is reviewed. In addition, potential targeted radiosensitizers to be used in conjunction with re-irradiation are also discussed.

Optimizing the Benefit of CNS Radiation Therapy in the Pediatric Population-PART 1: Understanding and Managing Acute and Late Toxicities.

Radiation therapy continues to be a key component in the management of pediatric malignancies. Increasing the likelihood of cure while minimizing late treatment toxicity in these young patients remains the primary goal. Within the realm of central nervous system neoplasms, efforts to further improve the efficacy of radiation therapy continue, while balancing risks of damage to uninvolved tissue. Radiation therapy can result in second malignancies, as well as cerebrovascular, neurotoxic, neurocognitive, endocrine, psychosocial, and quality-of-life effects. In this article we describe these acute and late effects and their implications, and we highlight strategies that have emerged to reduce both the volume of tissue that is irradiated and the radiation dose delivered. The feasibility, efficacy, and risks of these newer approaches to radiation therapy continue to be evaluated and monitored; robust outcome data are needed.

Optimizing the Benefit of CNS Radiation Therapy in the Pediatric Population-PART 2: Novel Methods of Radiation Delivery.

Newer approaches in the field of radiation therapy have raised the bar in the treatment of central nervous system (CNS) malignancies, with recognized advances that have aimed to increase the therapeutic index by improving conformality of the radiation dose to the planned target volume. Beyond these advances, the continued evolution of more effective systems for delivery of radiation to the CNS may offer further benefit not only to adults but also to pediatric patients, a cohort of the population that may be more sensitive to the long-term effects of radiation. This article describes several novel irradiation techniques under investigation that hold promise in the pediatric population. These include newer approaches to intensity-modulated radiation therapy; stereotactic radiosurgery and radiation therapy; particle therapy, most notably proton therapy, which may be of particular benefit in enabling young patients to avoid radiation-related adverse effects; and radioimmunotherapy strategies that spare healthy tissue from radiotoxicity by delivering therapy directly to tumor tissue. Although emerging strategies for the delivery of radiation therapy hold promise for improved outcomes in pediatric patients, there must be rigorous long-term evaluation of consequences associated with the various techniques employed, to weigh risks, benefits, and impact on quality of life.

A randomized phase I/II study of ABT-888 in combination with temozolomide in recurrent temozolomide resistant glioblastoma: an NRG oncology RTOG group study.

This study tested the hypothesis that ABT-888 (velparib), a poly (ADP-ribose) polymerase (PARP) inhibitor, can modulate temozolomide (TMZ) resistance in recurrent TMZ refractory glioblastoma patients. The combination regimen (TMZ/ABT-888) was tested using two randomized schedules (5 vs. 21 days), with 6-month progression free survival (PFS6) as the primary endpoint. The maximum tolerated dose (MTD) for TMZ using the 21 day of 28 TMZ schedule, in concert with 40 mg BID ABT-888 was determined in a phase I portion of this study, and previously reported to be 75 mg/m(2) (arm1). The MTD for ABT-888 (40 mg BID) and the 5 of 28 day TMZ (150-200 mg/m(2)) schedule was known from prior trials (arm2). Two cohorts were studied: bevacizumab (BEV) naïve (n = 151), and BEV refractory (n = 74). Overall ten patients were ineligible. The incidence rate of grade 3/4 myelosuppression over all was 20.0 %. For the BEV refractory cohort, the PFS 6 was 4.4 %; for the BEV naïve cohort, PFS6 was 17 %. Overall survival was similar for both arms in both the BEV naïve [median survival time (MST) 10.3 M; 95 % CI 8.4-12] and BEV refractory cohort (MST 4.7 M; 95 %CI 3.5-5.6). The median PFS was essentially the same for both arms and both cohorts at ~2.0 M (95 % CI 1.9-2.1).

Diagnosing Progression in Glioblastoma-Tackling a Neuro-Oncology Problem Using Artificial-Intelligence-Derived Volumetric Change over Time on Magnetic Resonance Imaging to Examine Progression-Free Survival in Glioblastoma.

Glioblastoma (GBM) is the most aggressive and the most common primary brain tumor, defined by nearly uniform rapid progression despite the current standard of care involving maximal surgical resection followed by radiation therapy (RT) and temozolomide (TMZ) or concurrent chemoirradiation (CRT), with an overall survival (OS) of less than 30% at 2 years. The diagnosis of tumor progression in the clinic is based on clinical assessment and the interpretation of MRI of the brain using Response Assessment in Neuro-Oncology (RANO) criteria, which suffers from several limitations including a paucity of precise measures of progression. Given that imaging is the primary modality that generates the most quantitative data capable of capturing change over time in the standard of care for GBM, this renders it pivotal in optimizing and advancing response criteria, particularly given the lack of biomarkers in this space. In this study, we employed artificial intelligence (AI)-derived MRI volumetric parameters using the segmentation mask output of the nnU-Net to arrive at four classes (background, edema, non-contrast enhancing tumor (NET), and contrast-enhancing tumor (CET)) to determine if dynamic changes in AI volumes detected throughout therapy can be linked to PFS and clinical features. We identified associations between MR imaging AI-generated volumes and PFS independently of tumor location, MGMT methylation status, and the extent of resection while validating that CET and edema are the most linked to PFS with patient subpopulations separated by district rates of change throughout the disease. The current study provides valuable insights for risk stratification, future RT treatment planning, and treatment monitoring in neuro-oncology.

Correction: Tasci et al. RadWise: A Rank-Based Hybrid Feature Weighting and Selection Method for Proteomic Categorization of Chemoirradiation in Patients with Glioblastoma. Cancers 2023, 15, 2672.

In the original publication [...].

Advances in the field of developing biomarkers for re-irradiation: a how-to guide to small, powerful data sets and artificial intelligence.

Introduction: Patient selection remains challenging as the clinical use of re-irradiation (re-RT) increases. Re-RT data is limited to retrospective studies and small prospective single-institution reports, resulting in small, heterogenous data sets. Validated prognostic and predictive biomarkers are derived from large-volume studies with long-term follow-up. This review aims to examine existing re-RT publications and available data sets and discuss strategies using artificial intelligence (AI) to approach small data sets to optimize the use of re-RT data. Methods: Re-RT publications were identified where associated public data was present. The existing literature on small data sets to identify biomarkers was also explored. Results: Publications with associated public data were identified, with glioma and nasopharyngeal cancers emerging as the most common tumor sites where the use of re-RT was the primary management approach. Existing and emerging AI strategies have been used to approach small data sets including data generation, augmentation, discovery, and transfer learning. Conclusions: Further data is needed to generate adaptive frameworks, improve the collection of specimens for molecular analysis, and improve the interpretability of results in re-RT data.

Corrigendum: Glioblastoma survival is associated with distinct proteomic alteration signatures post chemoirradiation in a large-scale proteomic panel.

[This corrects the article DOI: 10.3389/fonc.2023.1127645.].

Serum CD133-Associated Proteins Identified by Machine Learning Are Connected to Neural Development, Cancer Pathways, and 12-Month Survival in Glioblastoma.

Glioma is the most prevalent type of primary central nervous system cancer, while glioblastoma (GBM) is its most aggressive variant, with a median survival of only 15 months when treated with maximal surgical resection followed by chemoradiation therapy (CRT). CD133 is a potentially significant GBM biomarker. However, current clinical biomarker studies rely on invasive tissue samples. These make prolonged data acquisition impossible, resulting in increased interest in the use of liquid biopsies. Our study, analyzed 7289 serum proteins from 109 patients with pathology-proven GBM obtained prior to CRT using the aptamer-based SOMAScan® proteomic assay technology. We developed a novel methodology that identified 24 proteins linked to both serum CD133 and 12-month overall survival (OS) through a multi-step machine learning (ML) analysis. These identified proteins were subsequently subjected to survival and clustering evaluations, categorizing patients into five risk groups that accurately predicted 12-month OS based on their protein profiles. Most of these proteins are involved in brain function, neural development, and/or cancer biology signaling, highlighting their significance and potential predictive value. Identifying these proteins provides a valuable foundation for future serum investigations as validation of clinically applicable GBM biomarkers can unlock immense potential for diagnostics and treatment monitoring.

GradWise: A Novel Application of a Rank-Based Weighted Hybrid Filter and Embedded Feature Selection Method for Glioma Grading with Clinical and Molecular Characteristics.

Glioma grading plays a pivotal role in guiding treatment decisions, predicting patient outcomes, facilitating clinical trial participation and research, and tailoring treatment strategies. Current glioma grading in the clinic is based on tissue acquired at the time of resection, with tumor aggressiveness assessed from tumor morphology and molecular features. The increased emphasis on molecular characteristics as a guide for management and prognosis estimation underscores is driven by the need for accurate and standardized grading systems that integrate molecular and clinical information in the grading process and carry the expectation of the exposure of molecular markers that go beyond prognosis to increase understanding of tumor biology as a means of identifying druggable targets. In this study, we introduce a novel application (GradWise) that combines rank-based weighted hybrid filter (i.e., mRMR) and embedded (i.e., LASSO) feature selection methods to enhance the performance of feature selection and machine learning models for glioma grading using both clinical and molecular predictors. We utilized publicly available TCGA from the UCI ML Repository and CGGA datasets to identify the most effective scheme that allows for the selection of the minimum number of features with their names. Two popular feature selection methods with a rank-based weighting procedure were employed to conduct comprehensive experiments with the five supervised models. The computational results demonstrate that our proposed method achieves an accuracy rate of 87.007% with 13 features and an accuracy rate of 80.412% with five features on the TCGA and CGGA datasets, respectively. We also obtained four shared biomarkers for the glioma grading that emerged in both datasets and can be employed with transferable value to other datasets and data-based outcome analyses. These findings are a significant step toward highlighting the effectiveness of our approach by offering pioneering results with novel markers with prospects for understanding and targeting the biologic mechanisms of glioma progression to improve patient outcomes.

An Overview of CD133 as a Functional Unit of Prognosis and Treatment Resistance in Glioblastoma.

Biomarkers for resistance in Glioblastoma multiforme (GBM) are lacking, and progress in the clinic has been slow to arrive. CD133 (prominin-1) is a membrane-bound glycoprotein on the surface of cancer stem cells (CSCs) that has been associated with poor prognosis, therapy resistance, and tumor recurrence in GBM. Due to its connection to CSCs, to which tumor resistance and recurrence have been partially attributed in GBM, there is a growing field of research revolving around the potential role of CD133 in each of these processes. However, despite encouraging results in vitro and in vivo, the biological interplay of CD133 with these components is still unclear, causing a lack of clinical application. In parallel, omic data from biospecimens that include CD133 are beginning to emerge, increasing the importance of understanding CD133 for the effective use of these highly dimensional data sets. Given the significant mechanistic overlap, prioritization of the most robust findings is necessary to optimize the transition of CD133 to clinical applications using patient-derived biospecimens. As a result, this review aims to compile and analyze the current research regarding CD133 as a functional unit in GBM, exploring its connections to prognosis, the tumor microenvironment, tumor resistance, and tumor recurrence.

RadWise: A Rank-Based Hybrid Feature Weighting and Selection Method for Proteomic Categorization of Chemoirradiation in Patients with Glioblastoma.

Glioblastomas (GBM) are rapidly growing, aggressive, nearly uniformly fatal, and the most common primary type of brain cancer. They exhibit significant heterogeneity and resistance to treatment, limiting the ability to analyze dynamic biological behavior that drives response and resistance, which are central to advancing outcomes in glioblastoma. Analysis of the proteome aimed at signal change over time provides a potential opportunity for non-invasive classification and examination of the response to treatment by identifying protein biomarkers associated with interventions. However, data acquired using large proteomic panels must be more intuitively interpretable, requiring computational analysis to identify trends. Machine learning is increasingly employed, however, it requires feature selection which has a critical and considerable effect on machine learning problems when applied to large-scale data to reduce the number of parameters, improve generalization, and find essential predictors. In this study, using 7k proteomic data generated from the analysis of serum obtained from 82 patients with GBM pre- and post-completion of concurrent chemoirradiation (CRT), we aimed to select the most discriminative proteomic features that define proteomic alteration that is the result of administering CRT. Thus, we present a novel rank-based feature weighting method (RadWise) to identify relevant proteomic parameters using two popular feature selection methods, least absolute shrinkage and selection operator (LASSO) and the minimum redundancy maximum relevance (mRMR). The computational results show that the proposed method yields outstanding results with very few selected proteomic features, with higher accuracy rate performance than methods that do not employ a feature selection process. While the computational method identified several proteomic signals identical to the clinical intuitive (heuristic approach), several heuristically identified proteomic signals were not selected while other novel proteomic biomarkers not selected with the heuristic approach that carry biological prognostic relevance in GBM only emerged with the novel method. The computational results show that the proposed method yields promising results, reducing 7k proteomic data to 7 selected proteomic features with a performance value of 93.921%, comparing favorably with techniques that do not employ feature selection.