Background: With the advances in modern radiotherapy (RT), many patients with head and neck cancer (HNC) can be effectively cured, and their health-related quality of life (HR-QoL) has become an important issue. In this study, we evaluated the prognosticators of HR-QoL in a large cohort of HNC patients, with a focus on the result from technological advances in RT. Methods: A cross-sectional investigation was conducted to assess the HR-QoL of 640 HNC patients with cancer-free survival of more than 2 years. Among them, 371 patients were treated by two-dimensional RT (2DRT), 127 by three-dimensional conformal RT (3DCRT), and 142 by intensity-modulated RT (IMRT). The EORTC QLQ-C30 questionnaire and QLQ-H&N35 module were used. A general linear model multivariate analysis of variance was used to analyze the prognosticators of HR-QoL. Results: By multivariate analysis, the variables of gender, annual family income, tumor site, AJCC stage, treatment methods, and RT technique were prognosticators for QLQ-C30 results, so were tumor site and RT technique for H&N35. Significant difference (p < 0.05) of HR-QoL outcome by different RT techniques was observed at 2 of the 15 scales in QLQ-C30 and 10 of the 13 scales in H&N35. Compared with 2DRT, IMRT had significant better outcome in the scales of global QoL, physical functioning, swallowing, senses (taste/smell), speech, social eating, social contact, teeth, opening mouth, dry mouth, sticky saliva, and feeling ill. Conclusions: The technological advance of RT substantially improves the head-and-neck related symptoms and broad aspects of HR-QoL for HNC survivors.

Radiation-induced tinnitus is a side effect of radiotherapy in the inner ear for cancers of the head and neck. Effective dose constraints for protecting the cochlea are under-reported. The aim of this study is to determine the cochlea dose limitation to avoid causing tinnitus after head-and-neck cancer (HNC) intensity-modulated radiation therapy (IMRT). In total 211 patients with HNC were included; the side effects of radiotherapy were investigated for 422 inner ears in the cohort. Forty-nine of the four hundred and twenty-two samples (11.6 %) developed grade 2+ tinnitus symptoms after IMRT, as diagnosed by a clinician. The Late Effects of Normal Tissues–Subjective, Objective, Management, Analytic (LENT-SOMA) criteria were used for tinnitus evaluation. The logistic and Lyman-Kutcher-Burman (LKB) normal tissue complication probability (NTCP) models were used for the analyses. The NTCP-fitted parameters were TD 50 = 46.31 Gy (95 % CI, 41.46–52.50), γ 50 = 1.27 (95 % CI, 1.02–1.55), and TD 50 = 46.52 Gy (95 % CI, 41.91–53.43), m = 0.35 (95 % CI, 0.30–0.42) for the logistic and LKB models, respectively. The suggested guideline TD 20 for the tolerance dose to produce a 20 % complication rate within a specific period of time was TD 20 = 33.62 Gy (95 % CI, 30.15–38.27) (logistic) and TD 20 = 32.82 Gy (95 % CI, 29.58–37.69) (LKB). To maintain the incidence of grade 2+ tinnitus toxicity <20 % in IMRT, we suggest that the mean dose to the cochlea should be <32 Gy. However, models should not be extrapolated to other patient populations without further verification and should first be confirmed before clinical implementation.

This study explores integrating clinical features with radiomic and dosiomic characteristics into AI models to enhance the prediction accuracy of radiation dermatitis (RD) in breast cancer patients undergoing volumetric modulated arc therapy (VMAT). This study involved a retrospective analysis of 120 breast cancer patients treated with VMAT at Kaohsiung Veterans General Hospital from 2018 to 2023. Patient data included CT images, radiation doses, Dose-Volume Histogram (DVH) data, and clinical information. Using a Treatment Planning System (TPS), we segmented CT images into Regions of Interest (ROIs) to extract radiomic and dosiomic features, focusing on intensity, shape, texture, and dose distribution characteristics. Features significantly associated with the development of RD were identified using ANOVA and LASSO regression (p-value < 0.05). These features were then employed to train and evaluate Logistic Regression (LR) and Random Forest (RF) models, using tenfold cross-validation to ensure robust assessment of model efficacy. In this study, 102 out of 120 VMAT-treated breast cancer patients were included in the detailed analysis. Thirty-two percent of these patients developed Grade 2+ RD. Age and BMI were identified as significant clinical predictors. Through feature selection, we narrowed down the vast pool of radiomic and dosiomic data to 689 features, distributed across 10 feature subsets for model construction. In the LR model, the J subset, comprising DVH, Radiomics, and Dosiomics features, demonstrated the highest predictive performance with an AUC of 0.82. The RF model showed that subset I, which includes clinical, radiomic, and dosiomic features, achieved the best predictive accuracy with an AUC of 0.83. These results emphasize that integrating radiomic and dosiomic features significantly enhances the prediction of Grade 2+ RD. Integrating clinical, radiomic, and dosiomic characteristics into AI models significantly improves the prediction of Grade 2+ RD risk in breast cancer patients post-VMAT. The RF model analysis demonstrates that a comprehensive feature set maximizes predictive efficacy, marking a promising step towards utilizing AI in radiation therapy risk assessment and enhancing patient care outcomes.

We investigated the incidence of moderate to severe patient-reported xerostomia among nasopharyngeal carcinoma (NPC) patients treated with helical tomotherapy (HT) and identified patient- and therapy-related factors associated with acute and chronic xerostomia toxicity. The least absolute shrinkage and selection operator (LASSO) normal tissue complication probability (NTCP) models were developed using quality-of-life questionnaire datasets from 67 patients with NPC. For acute toxicity, the dosimetric factors of the mean doses to the ipsilateral submandibular gland (Dis) and the contralateral submandibular gland (Dcs) were selected as the first two significant predictors. For chronic toxicity, four predictive factors were selected: age, mean dose to the oral cavity (Doc), education and T stage. The substantial sparing data can be used to avoid xerostomia toxicity. We suggest that the tolerance values corresponded to a 20% incidence of complications (TD₂₀) for Dis = 39.0 Gy, Dcs = 38.4 Gy and Doc = 32.5 Gy, respectively, when mean doses to the parotid glands met the QUANTEC 25 Gy sparing guidelines. To avoid patient-reported xerostomia toxicity, the mean doses to the parotid gland, submandibular gland and oral cavity have to meet the sparing tolerance, although there is also a need to take inherent patient characteristics into consideration.

With advances in modern radiotherapy (RT), many patients with head and neck (HN) cancer can be effectively cured. However, xerostomia is a common complication in patients after RT for HN cancer. The purpose of this study was to use the Lyman–Kutcher–Burman (LKB) model to derive parameters for the normal tissue complication probability (NTCP) for xerostomia based on scintigraphy assessments and quality of life (QoL) questionnaires. We performed validation tests of the Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC) guidelines against prospectively collected QoL and salivary scintigraphic data.

Purpose: This study aims to develop an ensemble machine learning-based (EML-based) risk prediction model for radiation dermatitis (RD) in patients with head and neck cancer undergoing proton radiotherapy, with the goal of achieving superior predictive performance compared to traditional models. Materials and methods: Data from 57 head and neck cancer patients treated with intensity-modulated proton therapy at Kaohsiung Chang Gung Memorial Hospital were analyzed. The study incorporated 11 clinical and 9 dosimetric parameters. Pearson’s correlation was used to eliminate highly correlated variables, followed by feature selection via LASSO to focus on potential RD predictors. Model training involved traditional logistic regression (LR) and advanced ensemble methods such as Random Forest and XGBoost, which were optimized through hyperparameter tuning. Results: Feature selection identified six key predictors, including smoking history and specific dosimetric parameters. Ensemble machine learning models, particularly XGBoost, demonstrated superior performance, achieving the highest AUC of 0.890. Feature importance was assessed using SHAP (SHapley Additive exPlanations) values, which underscored the relevance of various clinical and dosimetric factors in predicting RD. Conclusion: The study confirms that EML methods, especially XGBoost with its boosting algorithm, provide superior predictive accuracy, enhanced feature selection, and improved data handling compared to traditional LR. While LR offers greater interpretability, the precision and broader applicability of EML make it more suitable for complex medical prediction tasks, such as predicting radiation dermatitis. Given these advantages, EML is highly recommended for further research and application in clinical settings.