An Independently Validated Nomogram for Individualized Estimation of Survival Among Patients With Newly Diagnosed Glioblastoma: NRG Oncology/RTOG 0525 and 0825

Multiple Survival Outcome Prediction of Glioblastoma Patients Based on Multiparametric MRI

PURPOSE

Construction of radiomics models for the individualized estimation of multiple survival stratification in glioblastoma (GBM) patients using the multiregional information extracted from multiparametric MRI that could facilitate clinical decision-making for GBM patients.

MATERIALS AND METHODS

A total of 134 eligible GBM patients were selected from The Cancer Genome Atlas. These patients were separated into the long-term and short-term survival groups according to the median of individual survival indicators: overall survival (OS), progression-free survival (PFS), and disease-specific survival (DSS). Then, the patients were divided into a training set and a validation set in a ratio of 2:1. Radiomics features (n = 5,152) were extracted from multiple regions of the GBM using multiparametric MRI. Then, radiomics signatures that are related to the three survival indicators were respectively constructed using the analysis of variance (ANOVA) and the least absolute shrinkage and selection operator (LASSO) regression for each patient in the training set. Based on a Cox proportional hazards model, the radiomics model was further constructed by combining the signature and clinical risk factors.

RESULTS

The constructed radiomics model showed a promising discrimination ability to differentiate in the training set and validation set of GBM patients with survival indicators of OS, PFS, and DSS. Both the four MRI modalities and five tumor subregions have different effects on the three survival indicators of GBM. The favorable calibration and decision curve analysis indicated the clinical decision value of the radiomics model. The performance of models of the three survival indicators was different but excellent; the best model achieved C indexes of 0.725, 0.677, and 0.724, respectively, in the validation set.

CONCLUSION

Our results show that the proposed radiomics models have favorable predictive accuracy on three survival indicators and can provide individualized probabilities of survival stratification for GBM patients by using multiparametric and multiregional MRI features.

Interval brain imaging for adults with cerebral glioma

BACKGROUND

Clinical practice guidelines suggest that magnetic resonance imaging (MRI) of the brain should be performed at certain time points or intervals distant from diagnosis (interval or surveillance imaging) of cerebral glioma, to monitor or follow up the disease; it is not known, however, whether these imaging strategies lead to better outcomes among patients than triggered imaging in response to new or worsening symptoms.

OBJECTIVES

To determine the effect of different imaging strategies (in particular, pre-specified interval or surveillance imaging, and symptomatic or triggered imaging) on health and economic outcomes for adults with glioma (grades 2 to 4) in the brain.

SEARCH METHODS

The Cochrane Gynaecological, Neuro-oncology and Orphan Cancers (CGNOC) Group Information Specialist searched the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE and Embase up to 18 June 2019 and the NHS Economic Evaluation Database (EED) up to December 2014 (database closure).

SELECTION CRITERIA

We included randomised controlled trials, non-randomised controlled trials, and controlled before-after studies with concurrent comparison groups comparing the effect of different imaging strategies on survival and other health outcomes in adults with cerebral glioma; and full economic evaluations (cost-effectiveness analyses, cost-utility analyses and cost-benefit analyses) conducted alongside any study design, and any model-based economic evaluations on pre- and post-treatment imaging in adults with cerebral glioma.

DATA COLLECTION AND ANALYSIS

We used standard Cochrane review methodology with two authors independently performing study selection and data collection, and resolving disagreements through discussion. We assessed the certainty of the evidence using the GRADE approach.

MAIN RESULTS

We included one retrospective, single-institution study that compared post-operative imaging within 48 hours (early post-operative imaging) with no early post-operative imaging among 125 people who had surgery for glioblastoma (GBM: World Health Organization (WHO) grade 4 glioma). Most patients in the study underwent maximal surgical resection followed by combined radiotherapy and temozolomide treatment. Although patient characteristics in the study arms were comparable, the study was at high risk of bias overall. Evidence from this study suggested little or no difference between early and no early post-operative imaging with respect to overall survival (deaths) at one year after diagnosis of GBM (risk ratio (RR) 0.86, 95% confidence interval (CI) 0.61 to 1.21; 48% vs 55% died, respectively; very low certainty evidence) and little or no difference in overall survival (deaths) at two years after diagnosis of GBM (RR 1.06, 95% CI 0.91 to 1.25; 86% vs 81% died, respectively; very low certainty evidence). No other review outcomes were reported. We found no evidence on the effectiveness of other imaging schedules. In addition, we identified no relevant economic evaluations assessing the efficiency of the different imaging strategies.

AUTHORS' CONCLUSIONS

The effect of different imaging strategies on survival and other health outcomes remains largely unknown. Existing imaging schedules in glioma seem to be pragmatic rather than evidence-based. The limited evidence suggesting that early post-operative brain imaging among GBM patients who will receive combined chemoradiation treatment may make little or no difference to survival needs to be further researched, particularly as early post-operative imaging also serves as a quality control measure that may lead to early re-operation if residual tumour is identified. Mathematical modelling of a large glioma patient database could help to distinguish the optimal timing of surveillance imaging for different types of glioma, with stratification of patients facilitated by assessment of individual tumour growth rates, molecular biomarkers and other prognostic factors. In addition, paediatric glioma study designs could be used to inform future research of imaging strategies among adults with glioma.

Information-Based Medicine in Glioma Patients: A Clinical Perspective

Glioma constitutes the most common type of primary brain tumor with a dismal survival, often measured in terms of months or years. The thin line between treatment effectiveness and patient harm underpins the importance of tailoring clinical management to the individual patient. Randomized trials have laid the foundation for many neuro-oncological guidelines. Despite this, their findings focus on group-level estimates. Given our current tools, we are limited in our ability to guide patients on what therapy is best for them as individuals, or even how long they should expect to survive. Machine learning, however, promises to provide the analytical support for personalizing treatment decisions, and deep learning allows clinicians to unlock insight from the vast amount of unstructured data that is collected on glioma patients. Although these novel techniques have achieved astonishing results across a variety of clinical applications, significant hurdles remain associated with the implementation of them in clinical practice. Future challenges include the assembly of well-curated cross-institutional datasets, improvement of the interpretability of machine learning models, and balancing novel evidence-based decision-making with the associated liability of automated inference. Although artificial intelligence already exceeds clinical expertise in a variety of applications, clinicians remain responsible for interpreting the implications of, and acting upon, each prediction.

American Society for Radiation Oncology 2016 Annual Meeting: Central Nervous System Abstracts

The American Society for Radiation Oncology's (ASTRO) 2016 scientific program presented a number of excellent abstracts focusing on brain and spine tumors. Selected abstracts will be reviewed in this article.