Individualized prediction of late-onset dysphagia in head and neck cancer survivors

Radiation-induced long-term dysphagia in survivors of head and neck cancer and association with dose-volume parameters

BACKGROUND

Although dysphagia is a common side effect after radiotherapy (RT) of head and neck cancer (HNC), data on long-term dysphagia is scarce. We aimed to 1) compare radiation dose parameters in HNC survivors with and without dysphagia, 2) investigate factors associated with long-term dysphagia and its possible impact on health-related quality of life (HRQoL), and 3) investigate how our data agree with existing NTCP models.

METHODS

This cross-sectional study conducted in 2018-2020, included HNC survivors treated in 2007-2013. Participants attended a one-day examination in hospital and filled in patient questionnaires. Dysphagia was measured with the EORTC QLQ-H&N35 swallowing scale. Toxicity was scored with CTCAE v.4. We contoured swallowing organs at risk (SWOAR) on RT plans, calculated dose-volume histograms (DVHs), performed logistic regression analyses and tested our data in established NTCP models.

RESULTS

Of the 239 participants, 75 (31%) reported dysphagia. Compared to survivors without dysphagia, this group had reduced HRQoL and the DVHs for infrahyoid SWOAR were significantly shifted to the right. Long-term dysphagia was associated with age (OR 1.07, 95% CI 1.03-1.10), female sex (OR 2.75, 95% CI 1.45-5.21), and mean dose to middle pharyngeal constrictor muscle (MD-MPCM) (OR 1.06, 95% CI 1.03-1.09). NTCP models overall underestimated the risk of long-term dysphagia.

CONCLUSIONS

Long-term dysphagia was associated with higher age, being female, and high MD-MPCM. Doses to distally located SWOAR seemed to be risk factors. Existing NTCP models do not sufficiently predict long-term dysphagia. Further efforts are needed to reduce the prevalence and consequences of this late effect.

Expert Consensus Statement: Management of Dysphagia in Head and Neck Cancer Patients

OBJECTIVE

To develop an expert consensus statement (ECS) on the management of dysphagia in head and neck cancer (HNC) patients to address controversies and offer opportunities for quality improvement. Dysphagia in HNC was defined as swallowing impairment in patients with cancers of the nasal cavity, paranasal sinuses, nasopharynx, oral cavity, oropharynx, larynx, or hypopharynx.

METHODS

Development group members with expertise in dysphagia followed established guidelines for developing ECS. A professional search strategist systematically reviewed the literature, and the best available evidence was used to compose consensus statements targeted at providers managing dysphagia in adult HNC populations. The development group prioritized topics where there was significant practice variation and topics that would improve the quality of HNC patient care if consensus were possible.

RESULTS

The development group identified 60 candidate consensus statements, based on 75 initial proposed topics and questions, that focused on addressing the following high yield topics: (1) risk factors, (2) screening, (3) evaluation, (4) prevention, (5) interventions, and (6) surveillance. After 2 iterations of the Delphi survey and the removal of duplicative statements, 48 statements met the standardized definition for consensus; 12 statements were designated as no consensus.

CONCLUSION

Expert consensus was achieved for 48 statements pertaining to risk factors, screening, evaluation, prevention, intervention, and surveillance for dysphagia in HNC patients. Clinicians can use these statements to improve quality of care, inform policy and protocols, and appreciate areas where there is no consensus. Future research, ideally randomized controlled trials, is warranted to address additional controversies related to dysphagia in HNC patients.

Evaluation of Objective and Subjective Swallowing Outcomes in Patients with Dysphagia Treated for Head and Neck Cancer

We evaluated objective and subjective swallowing function outcomes in patients with dysphagia treated for head and neck cancer (HNC) and identified risk factors for poor swallowing outcomes. Patients undergoing videofluoroscopic swallowing studies (VFSS) between January 2016 and March 2021 were divided into four groups according to primary tumor sites; post-treatment dysphagia was assessed. The penetration–aspiration scale (PAS) and bolus residue scale (BRS) were used to objectively assess swallowing function through VFSS. The Functional Oral Intake Scale (FOIS) was used for subjective analyses of swallowing statuses. To account for potential confounding, important covariates were adjusted for in logistic regression models. Oropharyngeal tumors were significantly more likely to have poor PAS and BRS scores than oral cavity tumors, and the patients with nasopharyngeal tumors were significantly less likely to have poor FOIS scores. Old age, having multiple HNCs, and a history of radiotherapy were associated with an increased odds of poor PAS scores (for all types of swallows), poor BRS scores (for semiliquid and solid swallows), and poor FOIS scores, respectively. This indicates using only subjective assessments may not allow for accurate evaluations of swallowing function in patients treated for HNC. Using both objective and subjective assessments may allow for comprehensive evaluations.

Convolutional Neural Network Classifies Pathological Voice Change in Laryngeal Cancer with High Accuracy

Voice changes may be the earliest signs in laryngeal cancer. We investigated whether automated voice signal analysis can be used to distinguish patients with laryngeal cancer from healthy subjects. We extracted features using the software package for speech analysis in phonetics (PRAAT) and calculated the Mel-frequency cepstral coefficients (MFCCs) from voice samples of a vowel sound of /a:/. The proposed method was tested with six algorithms: support vector machine (SVM), extreme gradient boosting (XGBoost), light gradient boosted machine (LGBM), artificial neural network (ANN), one-dimensional convolutional neural network (1D-CNN) and two-dimensional convolutional neural network (2D-CNN). Their performances were evaluated in terms of accuracy, sensitivity, and specificity. The result was compared with human performance. A total of four volunteers, two of whom were trained laryngologists, rated the same files. The 1D-CNN showed the highest accuracy of 85% and sensitivity and sensitivity and specificity levels of 78% and 93%. The two laryngologists achieved accuracy of 69.9% but sensitivity levels of 44%. Automated analysis of voice signals could differentiate subjects with laryngeal cancer from those of healthy subjects with higher diagnostic properties than those performed by the four volunteers.