Risk model and nomogram for dysphagia and xerostomia prediction in head and neck cancer patients treated by radiotherapy and/or chemotherapy

Integrated radiomics, dose-volume histogram criteria and clinical features for early prediction of saliva amount reduction after radiotherapy in nasopharyngeal cancer patients

PURPOSE

Previously, the evaluation of xerostomia depended on subjective grading systems, rather than the accurate saliva amount reduction. Our aim was to quantify acute xerostomia with reduced saliva amount, and apply radiomics, dose-volume histogram (DVH) criteria and clinical features to predict saliva amount reduction by machine learning techniques.

MATERIAL AND METHODS

Computed tomography (CT) of parotid glands, DVH, and clinical data of 52 patients were collected to extract radiomics, DVH criteria and clinical features, respectively. Firstly, radiomics, DVH criteria and clinical features were divided into 3 groups for feature selection, in order to alleviate the masking effect of the number of features in different groups. Secondly, the top features in the 3 groups composed integrated features, and features selection was performed again for integrated features. In this study, feature selection was used as a combination of eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) to alleviate multicollinearity. Finally, 6 machine learning techniques were used for predicting saliva amount reduction. Meanwhile, top radiomics features were modeled using the same machine learning techniques for comparison.

RESULT

17 integrated features (10 radiomics, 4 clinical, 3 DVH criteria) were selected to predict saliva amount reduction, with a mean square error (MSE) of 0.6994 and a R² score of 0.9815. Top 17 and 10 selected radiomics features predicted saliva amount reduction, with MSE of 0.7376, 0.7519, and R² score of 0.9805, 0.9801, respectively.

CONCLUSION

With the same number of features, integrated features (radiomics + DVH criteria + clinical) performed better than radiomics features alone. The important DVH criteria and clinical features mainly included, white blood cells (WBC), parotid_glands_Dmax, Age, parotid_glands_V15, hemoglobin (Hb), BMI and parotid_glands_V45.

Contouring the accessory parotid gland and major parotid glands as a single organ at risk during nasopharyngeal carcinoma radiotherapy

Background and purpose

No research currently exists on the role of the accessory parotid gland (APG) in nasopharyngeal carcinoma (NPC). We thereby aimed to assess the effects of APG on the dosimetry of the parotid glands (PGs) during NPC radiotherapy and evaluate its predictive value for late xerostomia.

Material and methods

The clinical data of 32 NPC patients with radiological evidence of the APG treated at Sun Yat-sen Memorial Hospital between November 2020 and February 2021 were retrospectively reviewed. Clinically approved treatment plans consisted of only the PGs as an organ at risk (OAR) (Plan1), while Plan2 was designed by considering the APG as a single organ at risk (OAR). The APG on Plan1 was delineated, and dose–volume parameters of the PGs alone (PG-only) and of the combined structure (PG+APG) were analyzed in both plans. The association of such dosimetric parameters in Plan1 with xerostomia at 6–9 months post-radiotherapy was further explored.

Results

Fifty APGs were found, with a mean volume of 3.3 ± 0.2 ml. Significant differences were found in all dosimetric parameters between Plan1 and Plan2. The mean dose and percentage of OAR volumes receiving more than 30 Gy significantly reduced in Plan1 itself (PG-only vs. PG+APG, 39.55 ± 0.83 Gy vs. 37.71 ± 0.75 Gy, and 62.00 ± 2.00% vs. 57.41 ± 1.56%, respectively; p < 001) and reduced further in Plan2 (PG+APG, 36.40 ± 0.74 Gy, and 55.54 ± 1.61%, respectively; p < 0.001). Three additional patients met the dose constraint in Plan1, which increased to seven in Plan2. With APG included, the predictive power of the dosimetric parameters for xerostomia tended to improve, although no significant differences were observed.

Conclusion

APG is anatomically similar to the PGs. Our findings suggest the potential benefits of treating the APG and PGs as a single OAR during radiotherapy (RT) of NPC by improving PG sparing.

Risk Score for Predicting Dysphagia in Patients After Neurosurgery: A Prospective Observational Trial

Background: Acquired dysphagia is common in patients with tracheal intubation and neurological disease, leading to increased mortality. This study aimed to ascertain the risk factors and develop a prediction model for acquired dysphagia in patients after neurosurgery.

Methods: A multicenter prospective observational study was performed on 293 patients who underwent neurosurgery. A standardized swallowing assessment was performed bedside within 24 h of extubation, and logistic regression analysis with a best subset selection strategy was performed to select predictors. A nomogram model was then established and verified.

Results: The incidence of acquired dysphagia in our study was 23.2% (68/293). Among the variables, days of neurointensive care unit (NICU) stay [odds ratio (OR), 1.433; 95% confidence interval (CI), 1.141–1.882; P = 0.005], tracheal intubation duration (OR, 1.021; CI, 1.001–1.062; P = 0.175), use of a nasogastric feeding tube (OR, 9.131; CI, 1.364–62.289; P = 0.021), and Acute Physiology and Chronic Health Evaluation (APACHE)-II C score (OR, 1.709; CI, 1.421–2.148; P < 0.001) were selected as risk predictors for dysphagia and included in the nomogram model. The area under the receiver operating characteristic curve was 0.980 (CI, 0.965–0.996) in the training set and 0.971 (0.937–1) in the validation set, with Brier scores of 0.045 and 0.056, respectively.

Conclusion: Patients who stay longer in the NICU, have a longer duration of tracheal intubation, require a nasogastric feeding tube, and have higher APACHE-II C scores after neurosurgery are likely to develop dysphagia. This developed model is a convenient and efficient tool for predicting the development of dysphagia.

Clinical study on swallowing function of brainstem stroke by tDCS

OBJECTIVE

To investigate the effect of transcranial direct current stimulation (tDCS) combined with conventional comprehensive rehabilitation on dysphagia after brainstem stroke.

MATERIALS AND METHODS

Forty brainstem stroke patients were randomly divided into tDCS group and conventional comprehensive treatment group, including 20 patients in each group. Both groups were given routine swallowing function training, and tDCS group added transcranial direct current stimulation (tDCS). The Dysphagia Outcome and Severity Scale (DOSS) and Functional Dysphagia Scale (FDS) were evaluated respectively before and after 8 weeks of continuous treatment with VFSS. The white blood cell (WBC), c-reactive protein, prealbumin (PAB), albumin (Alb), and hemoglobin (Hb) were also compared between the two groups before and after 8 weeks of continuous treatment.

RESULTS

After 8 consecutive weeks of treatment, the score of DOSS scale and FDS scale in both groups was improved (P < 0.05), WBC and CRP were decreased (P < 0.05), and Alb and Hb were improved (P < 0.05), and PAB had no differences (P=0.474). The tDCS group was superior to conventional comprehensive group in improving the swallowing function and nutritional indexes (P < 0.05).

CONCLUSIONS

tDCS therapy combined with routine training can improve the swallowing function and nutritional status of patients, and reduce infection.

Predictors of Patient-Reported Dysphagia Following IMRT Plus Chemotherapy in Oropharyngeal Cancer

The aim of this cross-sectional study is to evaluate the factors associated with patient-reported dysphagia in patients affected by locally advanced oropharyngeal cancer (OPC) treated with definitive intensity-modulated radiation therapy (IMRT) and concurrent chemotherapy (CHT), with or without induction CHT. We evaluated 148 OPC patients treated with IMRT and concurrent CHT, without evidence of disease and who had completed their treatment since at least 6 months. At their planned follow-up visit, patients underwent clinical evaluation and completed the M.D. Anderson dysphagia inventory (MDADI) questionnaire. The association between questionnaire composite score (MDADI-CS) and different patients' and tumor's characteristics and treatments (covariates) was investigated by univariable and multivariable analyses, the latter including only covariates significant at univariable analysis. With a median time from treatment end of 30 months [range 6-74 months, interquartile range (IQR) 16-50 months], the median (IQR) MDADI-CS was 72 (63-84). The majority of patients (82.4%) had a MDADI-CS ≥ 60. At multivariable analysis, female gender, human papilloma virus (HPV)-negative status, and moderate and severe clinician-rated xerostomia were significantly associated with lower MDADI-CS. Patient-perceived dysphagia was satisfactory or acceptable in the majority of patients. HPV status and xerostomia were confirmed as important predictive factors for swallowing dysfunction after radiochemotherapy. Data regarding female gender are new and deserve further investigation.

Treatment de-intensification strategies for head and neck cancer

Increasingly, squamous cell carcinoma of the oropharynx (OPSCC) is attributable to transformation resulting from high-risk human papillomavirus (HPV) infection. Such cancers are significantly more responsive to treatment than traditional tobacco- and alcohol-associated squamous cell cancers of the head and neck. Conventional management with definitive chemoradiation, surgery and adjuvant radiation, or radiation given with altered fractionation schemes, while effective, incurs long-term morbidity that escalates with treatment intensity and significantly impairs quality of life. Recent trials have suggested that less intensive treatment regimens may achieve similar efficacy with decreased toxicity. In this article, we review the primary strategies used for de-escalation of treatment, which include the reduction of radiation dose, substitution and/or elimination of concurrent radiosensitising chemotherapy, and the use of minimally invasive surgery. We discuss the rationale behind these approaches and the preliminary data demonstrating the success of de-escalation, as well as potential considerations raised by treatment de-intensification in HPV-associated OPSCC.