Dataset Information

Institutional clinical trial accrual volume and survival of patients with head and neck cancer.

ABSTRACT:

Purpose

National Comprehensive Cancer Network guidelines recommend patients with head and neck cancer (HNC) receive treatment at centers with expertise, but whether provider experience affects survival is unknown.

Patients and methods

The effect of institutional experience on overall survival (OS) in patients with stage III or IV HNC was investigated within a randomized trial of the Radiation Therapy Oncology Group (RTOG 0129), which compared cisplatin concurrent with standard versus accelerated fractionation radiotherapy. As a surrogate for experience, institutions were classified as historically low- (HLACs) or high-accruing centers (HHACs) based on accrual to 21 RTOG HNC trials (1997 to 2002). The effect of accrual volume on OS was estimated by Cox proportional hazards models.

Results

Median RTOG accrual (1997 to 2002) at HLACs was four versus 65 patients at HHACs. Analysis included 471 patients in RTOG 0129 (2002 to 2005) with known human papillomavirus and smoking status. Patients at HLACs versus HHACs had better performance status (0: 62% v 52%; P = .04) and lower T stage (T4: 26.5% v 35.3%; P = .002) but were otherwise similar. Radiotherapy protocol deviations were higher at HLACs versus HHACs (18% v 6%; P < .001). When compared with HHACs, patients at HLACs had worse OS (5 years: 51.0% v 69.1%; P = .002). Treatment at HLACs was associated with increased death risk of 91% (hazard ratio [HR], 1.91; 95% CI, 1.37 to 2.65) after adjustment for prognostic factors and 72% (HR, 1.72; 95% CI, 1.23 to 2.40) after radiotherapy compliance adjustment.

Conclusion

OS is worse for patients with HNC treated at HLACs versus HHACs to cooperative group trials after accounting for radiotherapy protocol deviations. Institutional experience substantially influences survival in locally advanced HNC.

SUBMITTER: Wuthrick EJ

PROVIDER: S-EPMC4279235 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:In radiation oncology, predicting patient risk stratification allows specialization of therapy intensification as well as selecting between systemic and regional treatments, all of which helps to improve patient outcome and quality of life. Deep learning offers an advantage over traditional radiomics for medical image processing by learning salient features from training data originating from multiple datasets. However, while their large capacity allows to combine high-level medical imaging data for outcome prediction, they lack generalization to be used across institutions. In this work, a pseudo-volumetric convolutional neural network with a deep preprocessor module and self-attention (PreSANet) is proposed for the prediction of distant metastasis, locoregional recurrence, and overall survival occurrence probabilities within the 10 year follow-up time frame for head and neck cancer patients with squamous cell carcinoma. The model is capable of processing multi-modal inputs of variable scan length, as well as integrating patient data in the prediction model. These proposed architectural features and additional modalities all serve to extract additional information from the available data when availability to additional samples is limited. This model was trained on the public Cancer Imaging Archive Head-Neck-PET-CT dataset consisting of 298 patients undergoing curative radio/chemo-radiotherapy and acquired from 4 different institutions. The model was further validated on an internal retrospective dataset with 371 patients acquired from one of the institutions in the training dataset. An extensive set of ablation experiments were performed to test the utility of the proposed model characteristics, achieving an AUROC of [Formula: see text], [Formula: see text] and [Formula: see text] for DM, LR and OS respectively on the public TCIA Head-Neck-PET-CT dataset. External validation was performed on a retrospective dataset with 371 patients, achieving [Formula: see text] AUROC in all outcomes. To test for model generalization across sites, a validation scheme consisting of single site-holdout and cross-validation combining both datasets was used. The mean accuracy across 4 institutions obtained was [Formula: see text], [Formula: see text] and [Formula: see text] for DM, LR and OS respectively. The proposed model demonstrates an effective method for tumor outcome prediction for multi-site, multi-modal combining both volumetric data and structured patient clinical data.