Dataset Information

Radiomics-Based Machine Learning for Outcome Prediction in a Multicenter Phase II Study of Programmed Death-Ligand 1 Inhibition Immunotherapy for Glioblastoma.

ABSTRACT:

Background and purpose

Imaging assessment of an immunotherapy response in glioblastoma is challenging due to overlap in the appearance of treatment-related changes with tumor progression. Our purpose was to determine whether MR imaging radiomics-based machine learning can predict progression-free survival and overall survival in patients with glioblastoma on programmed death-ligand 1 inhibition immunotherapy.

Materials and methods

Post hoc analysis was performed of a multicenter trial on the efficacy of durvalumab in glioblastoma (n = 113). Radiomics tumor features on pretreatment and first on-treatment time point MR imaging were extracted. The random survival forest algorithm was applied to clinical and radiomics features from pretreatment and first on-treatment MR imaging from a subset of trial sites (n = 60-74) to train a model to predict long overall survival and progression-free survival and was tested externally on data from the remaining sites (n = 29-43). Model performance was assessed using the concordance index and dynamic area under the curve from different time points.

Results

The mean age was 55.2 (SD, 11.5) years, and 69% of patients were male. Pretreatment MR imaging features had a poor predictive value for overall survival and progression-free survival (concordance index = 0.472-0.524). First on-treatment MR imaging features had high predictive value for overall survival (concordance index = 0.692-0.750) and progression-free survival (concordance index = 0.680-0.715).

Conclusions

A radiomics-based machine learning model from first on-treatment MR imaging predicts survival in patients with glioblastoma on programmed death-ligand 1 inhibition immunotherapy.

SUBMITTER: George E

PROVIDER: S-EPMC9089247 | biostudies-literature | 2022 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Radiomics-Based Machine Learning for Outcome Prediction in a Multicenter Phase II Study of Programmed Death-Ligand 1 Inhibition Immunotherapy for Glioblastoma.

George E E Flagg E E Chang K K Bai H X HX Aerts H J HJ Vallières M M Reardon D A DA Huang R Y RY

AJNR. American journal of neuroradiology 20220428 5

<h4>Background and purpose</h4>Imaging assessment of an immunotherapy response in glioblastoma is challenging due to overlap in the appearance of treatment-related changes with tumor progression. Our purpose was to determine whether MR imaging radiomics-based machine learning can predict progression-free survival and overall survival in patients with glioblastoma on programmed death-ligand 1 inhibition immunotherapy.<h4>Materials and methods</h4>Post hoc analysis was performed of a multicenter t ...[more]

PMID: 35483906

Similar Datasets

Project description:BackgroundProgrammed death ligand 1 (PD-L1) expression status, closely related to immunotherapy outcomes, is a reliable biomarker for screening patients who may benefit from immunotherapy. Here, we developed and validated an interpretable machine learning (ML) model based on contrast-enhanced computed tomography (CECT) radiomics for preoperatively predicting PD-L1 expression status in patients with gastric cancer (GC).MethodsWe retrospectively recruited 285 GC patients who underwent CECT and PD-L1 detection from two medical centers. A PD-L1 combined positive score (CPS) of ≥ 5 was considered to indicate a high PD-L1 expression status. Patients from center 1 were divided into training (n = 143) and validation sets (n = 62), and patients from center 2 were considered a test set (n = 80). Radiomics features were extracted from venous-phase CT images. After feature reduction and selection, 11 ML algorithms were employed to develop predictive models, and their performance in predicting PD-L1 expression status was evaluated using areas under receiver operating characteristic curves (AUCs). SHapley Additive exPlanations (SHAP) were used to interpret the optimal model and visualize the decision-making process for a single individual.ResultsNine features significantly associated with PD-L1 expression status were ultimately selected to construct the predictive model. The light gradient-boosting machine (LGBM) model demonstrated the best performance for PD-L1 high expression status prediction in the training, validation, and test sets, with AUCs of 0.841(95% CI: 0.773, 0.908), 0.834 (95% CI:0.729, 0.939), and 0.822 (95% CI: 0.718, 0.926), respectively. The SHAP summary and bar plots illustrated that a feature's value affected the feature's impact attributed to the model. The SHAP waterfall plots were used to visualize the decision-making process for a single individual.ConclusionOur CT radiomics-based LGBM model may aid in preoperatively predicting PD-L1 expression status in GC patients, and the SHAP method may improve the interpretability of this model.

Project description:IntroductionThe clinical successes seen with anti-programmed cell death protein 1/programmed death-ligand 1 (anti-PD-[L]1) agents have galvanized the field of immuno-oncology. We evaluated the landscape and trends in immunotherapy trials involving the PD-(L)1 axis in intrathoracic tumors.MethodsWe identified clinical trials involving anti-PD-(L)1 agents on the ClinicalTrials.gov registry through November 13, 2020 for NSCLC, SCLC, mesothelioma, and thymic epithelial tumor. Clinical trials were indexed according to monotherapy versus combination approaches, PD-(L)1 agents under investigation, clinical settings, trial start date, and partner drug(s). We assessed redundancy among the clinical trials.ResultsWe found 686 clinical trials investigating anti-PD-(L)1 agents for intrathoracic tumors (540 trials in NSCLC, 96 in SCLC, 38 in mesothelioma, and 12 in thymic epithelial tumor). A total of 23 PD-(L)1 inhibitors are undergoing clinical development. A total of 81% of trials assess combination treatment. The number of clinical trials has been growing exponentially in the past decade. PD-(L)1 blockade was frequently combined with chemotherapy or immunomodulatory therapy. Various strategies are in development to overcome resistance to PD-(L)1 blockade in metastatic NSCLC. PD-(L)1 blockade is also increasingly evaluated in neoadjuvant and adjuvant settings. After the U.S. Food and Drug Administration's approval of an anti-PD-(L)1 agent for a specific indication, 14 trials were launched thereafter, which continued to randomize patients to treatments that were inferior to the best available therapy.ConclusionsThe number of clinical trials investigating anti-PD-(L)1 agents in intrathoracic tumors has experienced a steep increase over the past decade with a notable upward trend for combination trials. To reduce duplicative research efforts and accelerate the development of effective immunotherapeutics, improved coordination among key stakeholders and the adoption of innovative trial designs will be vital.

Project description:ImportanceTherapies to inhibit programmed cell death 1 and its ligand (anti-PD-1/PD-L1) provide significant survival benefits in many cancers, but the efficacy of these treatments varies considerably across different cancer types. Identifying the underlying variables associated with this cancer type-specific response remains an important open research challenge.ObjectiveTo evaluate systematically a multitude of neoantigen-, checkpoint-, and immune response-related variables to determine the key variables that accurately predict the response to anti-PD-1/PD-L1 therapy across different cancer types.Design, setting, and participantsThis analysis of a broad range of data used whole-exome and RNA sequencing of 7187 patients from the publicly available Cancer Genome Atlas and the objective response rate (ORR) data of 21 cancer types obtained from a collection of clinical trials. Thirty-six variables of 3 distinct classes considered were associated with (1) tumor neoantigens, (2) tumor microenvironment and inflammation, and (3) the checkpoint targets. The performance of each class of variables and their combinations in predicting the ORR to anti-PD-1/PD-L1 therapy was evaluated. Accuracy of predictions was quantified with Spearman correlation measured using a standard leave-one-out cross-validation, a statistical method of evaluating a statistical model by dividing data into 2 segments: one to train the model and the other to validate the model. Data were collected from October 19 through 31, 2018, and were analyzed from November 1 through December 14, 2018.Main outcomes and measuresResponse to anti-PD-1/PD-1 therapy.ResultsAmong the 36 variables, estimated CD8+ T-cell abundance was the most predictive of the response to anti-PD-1/PD-L1 therapy across cancer types (Spearman R = 0.72; P < 2.3 × 10-4), followed by the tumor mutational burden (Spearman R = 0.68; P < 6.2 × 10-4), and the fraction of samples with high PD1 gene expression (Spearman R = 0.68; P < 6.9 × 10-4). Notably these top 3 variables cover the 3 classes considered, and their combination is highly correlated with response (Spearman R = 0.90; P < 4.1 × 10-8), explaining more than 80% of the ORR variance observed across different tumor types.Conclusions and relevanceThat we know of, this is the first systematic evaluation of the different variables associated with anti-PD-1/PD-L1 therapy response across different tumor types. The findings suggest that the 3 key variables can explain most of the observed cross-cancer response variability, but their relative explanatory roles may vary in specific cancer types.

Dataset Information

Radiomics-Based Machine Learning for Outcome Prediction in a Multicenter Phase II Study of Programmed Death-Ligand 1 Inhibition Immunotherapy for Glioblastoma.

Background and purpose

Materials and methods

Results

Conclusions

Publications

Radiomics-Based Machine Learning for Outcome Prediction in a Multicenter Phase II Study of Programmed Death-Ligand 1 Inhibition Immunotherapy for Glioblastoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets