A Machine Learning Challenge for Prognostic Modelling in Head and Neck Cancer Using Multi-modal Data

Abstract

Accurate prognosis for an individual patient is a key component of precision oncology. Recent advances in machine learning have enabled the development of models using a wider range of data, including imaging. Radiomics aims to extract quantitative predictive and prognostic biomarkers from routine medical imaging, but evidence for computed tomography radiomics for prognosis remains inconclusive. We have conducted an institutional machine learning challenge to develop an accurate model for overall survival prediction in head and neck cancer using clinical data etxracted from electronic medical records and pre-treatment radiological images, as well as to evaluate the true added benefit of radiomics for head and neck cancer prognosis. Using a large, retrospective dataset of 2,552 patients and a rigorous evaluation framework, we compared 12 different submissions using imaging and clinical data, separately or in combination. The winning approach used non-linear, multitask learning on clinical data and tumour volume, achieving high prognostic accuracy for 2-year and lifetime survival prediction and outperforming models relying on clinical data only, engineered radiomics and deep learning. Combining all submissions in an ensemble model resulted in improved accuracy, with the highest gain from a image-based deep learning model. Our results show the potential of machine learning and simple, informative prognostic factors in combination with large datasets as a tool to guide personalized cancer care.

SCARF: Auto-Segmentation Clinical Acceptability & Reproducibility Framework for Benchmarking Essential Radiation Therapy Targets in Head and Neck Cancer

“…As the associated clinical data has been collected prospectively as part of the PM Anthology of Outcomes 31 , the clinical endpoints associated with this imaging resource are of high quality and have been used to drive significant changes in the management of HNC 32 . This dataset has been previously used for radiomic prediction of survival in HNC 33 and in studies addressing dental artifact reduction 34 . At PM, all patient contours are required to conform to standard nomenclature for both OARs and targets.…”

Incidence and Clinical Risk Factors of Post-Operative Complications following Primary Total Hip Arthroplasty: A 10-Year Population-Based Cohort Study

“…Race was categorized as white, black, Hispanic, and other. The Elixhauser Comorbidity readmission score was derived from the HCUP Elixhauser Comorbidity v2023.1 software [16]. Even though the score was designed to predict 30-day readmissions, it was used here as a surrogate variable for a predictor of any complications.…”