RT-HaND-C: A Multi-Source, Validated Real-World Head and Neck Cancer Dataset for Research

Real-world data (RWD) is essential in head and neck cancer (HNC) research, offering insights into outcomes among diverse, comorbid patients often underrepresented in clinical trials. We developed RT-HaND-C, a multi-source clinical dataset integrating structured EHR data, unstructured data extracted using an AI-driven NLP tool, and previously manually-curated datasets, with extensive demographic, disease, laboratory, treatment, outcome and radiotherapy dosimetry data for all HNC oncology patients seen at our centre (2010–2023). The dataset underwent rigorous evaluation for accuracy, completeness, consistency, and usability. The retrospective cohort comprises 2,895 HNC patients with over 1.8 million data points across over 2000 data categories. Accuracy assessments exceeded 98% for most variables. An example of usability testing showing rapid extraction and evaluation of longitudinal weight patterns post-radical radiotherapy is depicted. RT-HaND-C represents a novel, high-quality RWD resource and evaluation framework. The dataset is available for research and collaboration, with ongoing efforts to enhance completeness and support prospective updates.