Precision toxicity correlates of tumor spatial proximity to organs at risk in cancer patients receiving intensity-modulated radiotherapy

• Published in: Radiotherapy and oncology Vol. 148; pp. 245 - 251
• Main Authors: Wentzel, Andrew, Hanula, Peter, van Dijk, Lisanne V., Elgohari, Baher, Mohamed, Abdallah S.R., Cardenas, Carlos E., Fuller, Clifton D., Vock, David M., Canahuate, Guadalupe, Marai, G.E.
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.07.2020
• Subjects: Data Interpretation; Deglutition Disorders; Dysphagia; Head and Neck cancer; Head and Neck Neoplasms - radiotherapy; Humans; Intensity-modulated radiotherapy; Medical Informatics; Organs at Risk; Radiation therapy; Radiotherapy Dosage; Radiotherapy Planning, Computer-Assisted; Radiotherapy, Intensity-Modulated - adverse effects; Statistical; Head and Neck cancer; Medical Informatics; Data Interpretation; Statistical; Intensity-modulated radiotherapy; Dysphagia; Radiation therapy
• ISSN: 0167-8140; 1879-0887
• DOI: 10.1016/j.radonc.2020.05.023

•200 H&N cancer patients under radiation treatment were analyzed.•We aim to predict post-treatment dysphagia.•Patient similarity was defined in terms of tumor location with respect to organs at risk.•Tumor location and predicted doses were used to stratify the cohort into 4 groups.•Patient groups were significantly correlated with dysphagia 6 months post treatment. Using a 200 Head and Neck cancer (HNC) patient cohort, we employ patient similarity based on tumor location, volume, and proximity to organs at risk to predict radiation-associated dysphagia (RAD) in a new patient receiving intensity modulated radiation therapy (IMRT). All patients were treated using curative-intent IMRT. Anatomical features were extracted from contrast-enhanced tomography scans acquired pre-treatment. Patient similarity was computed using a topological similarity measure, which allowed for the prediction of normal tissues’ mean doses. We performed feature selection and clustering, and used the resulting groups of patients to forecast RAD. We used Logistic Regression (LG) cross-validation to assess the potential toxicity risk of these groupings. Out of 200 patients, 34 patients were recorded as having RAD. Patient clusters were significantly correlated with RAD (p < .0001). The area under the receiver-operator curve (AUC) using pre-established, baseline features gave a predictive accuracy of 0.79, while the addition of our cluster labels improved accuracy to 0.84. Our results show that spatial information available pre-treatment can be used to robustly identify groups of RAD high-risk patients. We identify feature sets that considerably improve toxicity risk prediction beyond what is possible using baseline features. Our results also suggest that similarity-based predicted mean doses to organs can be used as valid predictors of risk to organs.