Validation and Optimization of a Web-Based Nomogram for Predicting Survival of Patients with Newly Diagnosed Glioblastoma

Kim, N.; Chang, Jee Suk; Wee, Chan Woo; Kim, I.A.; Chang, Jong Hee; Lee, H.S.; Cho, J.H.; Kim, S.H.; Kang, Sujin; Kim, J.W.; Hong, Chang Ki; Kim, E.; Kim, T.M.; Kim, Y.J.; Park, C.K.; Kim, C.; Sw, Choi; Kim, J.H.; Park, S.H.; Choe, Gyu-Ha; Lee, S.T.; Kim, I.H.; Suh, C.

doi:10.1016/j.ijrobp.2018.07.866

Cited by 4 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, owing to censored observations in survival data, RMSEs and correlation coefficients are not ideal evaluation metrics for survival-prediction models. Moreover, several critical clinical factors known to be significantly associated with the survival outcomes of glioblastoma (such as performance status and resection margin status) were not used in the study [ 4 , 5 , 30 , 31 ]. In contrast, our study calculated the C-index and iAUC values, which are more appropriate metrics for evaluating the predictive performance of survival-prediction models than the RMSE or correlation coefficient.…”

Section: Discussionmentioning

confidence: 99%

“…Even with surgery and postoperative concurrent chemoradiotherapy (CCRT), the five-year overall survival (OS) rate for glioblastoma is 9.8%, and the approximate median OS is only about 15 months [ 2 , 3 ]. However, the survival outcomes of glioblastoma are heterogeneous among patients and are known to be relevant to numerous clinical and genetic factors [ 4 , 5 , 6 , 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Parametric Deep Learning Model for Prediction of Overall Survival after Postoperative Concurrent Chemoradiotherapy in Glioblastoma Patients

Yoon

Cheon

Jeong

et al. 2020

Cancers

View full text Add to dashboard Cite

This study aimed to investigate the performance of a deep learning-based survival-prediction model, which predicts the overall survival (OS) time of glioblastoma patients who have received surgery followed by concurrent chemoradiotherapy (CCRT). The medical records of glioblastoma patients who had received surgery and CCRT between January 2011 and December 2017 were retrospectively reviewed. Based on our inclusion criteria, 118 patients were selected and semi-randomly allocated to training and test datasets (3:1 ratio, respectively). A convolutional neural network–based deep learning model was trained with magnetic resonance imaging (MRI) data and clinical profiles to predict OS. The MRI was reconstructed by using four pulse sequences (22 slices) and nine images were selected based on the longest slice of glioblastoma by a physician for each pulse sequence. The clinical profiles consist of personal, genetic, and treatment factors. The concordance index (C-index) and integrated area under the curve (iAUC) of the time-dependent area-under-the-curve curves of each model were calculated to evaluate the performance of the survival-prediction models. The model that incorporated clinical and radiomic features showed a higher C-index (0.768 (95% confidence interval (CI): 0.759, 0.776)) and iAUC (0.790 (95% CI: 0.783, 0.797)) than the model using clinical features alone (C-index = 0.693 (95% CI: 0.685, 0.701); iAUC = 0.723 (95% CI: 0.716, 0.731)) and the model using radiomic features alone (C-index = 0.590 (95% CI: 0.579, 0.600); iAUC = 0.614 (95% CI: 0.607, 0.621)). These improvements to the C-indexes and iAUCs were validated using the 1000-times bootstrapping method; all were statistically significant (p < 0.001). This study suggests the synergistic benefits of using both clinical and radiomic parameters. Furthermore, it indicates the potential of multi-parametric deep learning models for the survival prediction of glioblastoma patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-Parametric Deep Learning Model for Prediction of Overall Survival after Postoperative Concurrent Chemoradiotherapy in Glioblastoma Patients

Yoon

Cheon

Jeong

et al. 2020

Cancers

View full text Add to dashboard Cite

show abstract

“…Then, they added concurrent chemoradiotherapy and confirmed its predictive value in a subsequent nomogram of a wild type IDH nGBM cohort ( 17 ). Although there remain some nomograms that were developed using other prognostic factors ( 20 – 22 ), little attention has been paid to the extent of neurosurgical resection of NCE.…”

Section: Discussionmentioning

confidence: 99%

A Nomogram Predicts Individual Prognosis in Patients With Newly Diagnosed Glioblastoma by Integrating the Extent of Resection of Non-Enhancing Tumors

et al. 2020

View full text Add to dashboard Cite

BackgroundThe extent of resection of non-contrast enhancing tumors (EOR-NCEs) has been shown to be associated with prognosis in patients with newly diagnosed glioblastoma (nGBM). This study aimed to develop and independently validate a nomogram integrated with EOR-NCE to assess individual prognosis.MethodsData for this nomogram were based on 301 patients hospitalized for nGBM from October 2011 to April 2019 at the Beijing Tiantan Hospital, Capital Medical University. These patients were randomly divided into derivation (n=181) and validation (n=120) cohorts at a ratio of 6:4. To evaluate predictive accuracy, discriminative ability, and clinical net benefit, concordance index (C-index), receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were calculated for the extent of resection of contrast enhancing tumor (EOR-CE) and EOR-NCE nomograms. Comparison between these two models was performed as well.ResultsThe Cox proportional hazards model was used to establish nomograms for this study. Older age at diagnosis, Karnofsky performance status (KPS)<70, unmethylated O6-methylguanine-DNA methyltransferase (MGMT) status, wild-type isocitrate dehydrogenase enzyme (IDH), and lower EOR-CE and EOR-NCE were independent factors associated with shorter survival. The EOR-NCE nomogram had a higher C-index than the EOR-CE nomogram. Its calibration curve for the probability of survival exhibited good agreement between the identical and actual probabilities. The EOR-NCE nomogram showed superior net benefits and improved performance over the EOR-CE nomogram with respect to DCA and ROC for survival probability. These results were also confirmed in the validation cohort.ConclusionsAn EOR-NCE nomogram assessing individualized survival probabilities (12-, 18-, and 24-month) for patients with nGBM could be useful to provide patients and their relatives with health care consultations on optimizing therapeutic approaches and prognosis.

show abstract

“…Treatments and follow-up for every patient were performed by a multidisciplinary neuro-oncology board, including neurosurgeons, radiation oncologists, neuro-radiologists, neuropathologists, and medical oncologists [ 2 ]. All patients were evaluated based on perioperative and follow-up magnetic resonance images (MRI) and clinical symptoms.…”

Section: Methodsmentioning

confidence: 99%

“…This poor prognosis has been attributed to the intrinsic radio- and chemo-resistance of the tumor [ 1 ]. Although there are several clinical and molecular factors known to be prognostic factors for high-grade glioma, including methylation of O-6-methylguanine-DNA methyltransferase ( MGMT ) promoter, age, involvement of the subventricular zone (SVZ), extent of resection, and sex [ 2 ], most patients are treated with a uniform adjuvant treatment approach (i.e., one-size-fits-all).…”

Section: Introductionmentioning

confidence: 99%

ATM mutations improve radio-sensitivity in wild-type isocitrate dehydrogenase-associated high-grade glioma: retrospective analysis using next-generation sequencing data

Kim

Kang

et al. 2020

Radiat Oncol

View full text Add to dashboard Cite

Background: To identify the association between somatic ataxia-telangiectasia mutated (ATM) mutations and improved radio-sensitivity, we retrospectively reviewed next-generation sequencing data from patients diagnosed with isocitrate dehydrogenase (IDH)-wildtype high-grade glioma. Methods: We included 39 individuals with (IDH)-wildtype high-grade glioma (diffuse astrocytoma n = 2, anaplastic astrocytoma n = 10, and glioblastoma n = 27) not subjected to gross tumor resection and undergoing radiation therapy with a median total dose of 60 Gy in 30 fractions. The mutational status of the ATM gene was obtained through next-generation sequencing using a TruSight Tumor 170 cancer panel. Disease progression was defined according to the Response Assessment in Neuro-Oncology (RANO) criteria as well as neurologic and clinical findings. Results: Among the 39 samples, ATM mutations (ATM mut(+)) were detected in 26% of cases (n = 10). No significant differences were observed in the characteristics of the patients or tumors. Among the 10 patients in the ATM mut(+) group, there were 6 patients with glioblastoma and 4 patients with anaplastic astrocytoma. Most mutations were missense mutations (n = 8, 80%). With a median follow-up of 16.5 mo (interquartile range, 11.4-19.8), ATM mut(+) exhibited 1-year in-field control of 100% compared with 44.1% in the ATM mut(−) group (p = 0.002). There was no difference in the out-field control rate or overall survival between the two groups (p = 0.861 and p = 0.247, respectively).

show abstract

Validation and Optimization of a Web-Based Nomogram for Predicting Survival of Patients with Newly Diagnosed Glioblastoma

Cited by 4 publications

References 0 publications

Multi-Parametric Deep Learning Model for Prediction of Overall Survival after Postoperative Concurrent Chemoradiotherapy in Glioblastoma Patients

Multi-Parametric Deep Learning Model for Prediction of Overall Survival after Postoperative Concurrent Chemoradiotherapy in Glioblastoma Patients

A Nomogram Predicts Individual Prognosis in Patients With Newly Diagnosed Glioblastoma by Integrating the Extent of Resection of Non-Enhancing Tumors

ATM mutations improve radio-sensitivity in wild-type isocitrate dehydrogenase-associated high-grade glioma: retrospective analysis using next-generation sequencing data

Contact Info

Product

Resources

About