Prognostic power of radiomics in head and neck cancers: Insights from a meta-analysis

Abstract

Background

Prognostic modeling in head and neck cancers (HNC) has advanced with the integration of clinical factors and radiomic data from CT and MRI scans. However, previous reviews have not systematically evaluated the predictive performance of these models across different oncological endpoints or assessed factors affecting their generalizability. This study aims to fill this gap by providing a comprehensive analysis of prognostic models in HNC.

Methods

Our systematic review and meta-analysis sourced data from PubMed, Embase, and Web of Science until August 30, 2023, shortlisting 16 studies. We concentrated on studies detailing HNC prognosis prediction through radiomics, which transparently tabulated performance metrics of c-index and utilized external validation sets. We excluded studies employing imaging techniques other than CT or MRI. Study quality was assessed using the QUIPS and RQS tools. Our meta-analysis comprised the radiomics prognosis model on all validation datasets, overall survival prediction with radiomics on all validation datasets, and overall survival prediction integrating clinical and radiomics data on external validation sets. All assessments adopted a random effects model. The research has been registered under CRD42023459049.

Results

When evaluating by distinct endpoints, marked differences were observed. Delving deeper into the complexities of overall survival prediction, variables such as incorporation of clinical features and an enlarged training set were identified as major enhancers of the model's performance. Evaluating exclusively on external validation cohorts, purely clinical models demonstrated a prognostic strength of pooled 0.69 c-index for overall survival, in contrast to the 0.68 pooled c-index achieved by models rooted in radiomics. Combining both approaches elevated the pooled c-index to 0.76. It was clear that a blend of an expanded training dataset and features selected, coupled with the diversity in CT and MRI equipment and model counts, are pivotal in fortifying the model's resilience.

Conclusion

This systematic review and meta-analysis demonstrate that combining clinical and radiomic features significantly improves the predictive performance of prognostic models for overall survival in HNC. By systematically evaluating various endpoints and identifying key factors influencing model generalizability, our study fills a critical gap in the literature. These findings provide valuable insights for developing more accurate and personalized prognostic tools in HNC, guiding future research and enhancing clinical decision-making.