Paper Overview
Field: Machine Learning Authors: Siyuan Zhao, Eric Ababio Anyimadu, Zachary G. Brumm, Yue Ma, Clifton David Fuller, Xinhua Zhang, G. Elisabeta Marai, Guadalupe Canahuate Published: 2026-07-24 arXiv: 2607.22514
Background
Dysphagia is a debilitating late effect of head and neck cancer (HNC) treatment, yet timely identification of at-risk patients remains challenging in survivorship care. Definitive assessment relies on videofluoroscopic imaging, as captured by the Dynamic Imaging Grade of Swallowing Toxicity (CTCAE-DIGEST). While validated, this approach requires specialized equipment, trained personnel, and significant patient burden, limiting its routine use in surveillance.
Approach
Patient-reported outcomes (PROs) are low-cost, scalable, and easily collected at any clinical encounter, making them an attractive alternative signal for identifying patients who may warrant further evaluation. However, a clear clinical framework for translating PRO responses into actionable interventions is still evolving — in particular, when a patient's self-reported symptom burden should prompt escalated care remains uncertain.
The authors address this gap by constructing a single-visit PRO-clinical prediction framework and introducing a clinically interpretable two-stage stacked model that uses PRO responses and structured clinical variables to predict swallowing injury risk — without videofluoroscopic imaging. The framework quantifies the independent contributions of patient-reported symptoms and clinical factors within a unified, interpretable risk assessment model.
Key Findings
- Individual MDADI responses contain predictive information beyond what composite or global summary scores capture.
- Interpretability analysis reveals symptom patterns and clinical risk factors associated with swallowing injury.
- Together, these results support structured PRO-clinical integration as a practical, imaging-free dysphagia risk stratification approach for HNC survivorship care.
- arXiv: https://arxiv.org/abs/2607.22514