Development of a questionnaire for measuring health-related quality of life among children and adolescents with mouth breathing

Explainable artificial intelligence to quantify adenoid hypertrophy-related upper airway obstruction using 3D Shape Analysis

OBJECTIVES

To develop and validate an explainable Artificial Intelligence (AI) model for classifying and quantifying upper airway obstruction related to adenoid hypertrophy using three-dimensional (3D) shape analysis of cone-beam computed tomography (CBCT) scans.

METHODS

400 CBCT scans of patients aged 5-18 years were analyzed. Nasopharyngeal airway obstruction (NAO) ratio was calculated to label scans into four grades of obstruction severity, used as the ground truth. Upper airway surface meshes were used to train a deep learning model combining multiview and point-cloud approaches for 3D shape analysis and obstruction severity classification and quantification. Surface Gradient-weighted Class Activation Mapping (SurfGradCAM) generated explainability heatmaps. Performance was evaluated using area under the curve (AUC), precision, recall, F1-score, mean absolute error, root mean squared error, and correlation coefficients.

RESULTS

The explainable AI model demonstrated strong performance in both classification and quantification tasks. The AUC values for the classification task ranged from 0.77 to 0.94, with the highest values of 0.88 and 0.94 for Grades 3 and 4, respectively, indicating excellent discriminative ability for identifying more severe cases of obstruction. The SurfGradCAM-generated heatmaps consistently highlighted the most relevant regions of the upper airway influencing the AI's decision-making process. In the quantification task, the regression model successfully predicted the NAO ratio, with a strong correlation coefficient of 0.854 (p < 0.001) and R2= 0.728, explaining a substantial proportion of the variance in NAO ratios.

CONCLUSIONS

The proposed explainable AI model, using 3D shape analysis, demonstrated strong performance in classifying and quantifying adenoid hypertrophy-related upper airway obstruction in CBCT scans.

CLINICAL SIGNIFICANCE

This AI model provides clinicians with a reliable, automated tool for standardized adenoid hypertrophy assessment. The model's explainable nature enhances clinical confidence and patient communication, potentially improving diagnostic workflow and treatment planning.

Mouth breathing – A predictor for patient satisfaction after nasal septoplasty?

Background: No reliable marker exists to predict septoplasty outcome. Most patients suffering from nasal airway obstruction (NAO) caused by a deviation of the nasal septum report a bothersome mouth breathing and dryness. In this study our aim was to assess, whether mouth breathing could be objectified in these patients and whether mouth breathing could predict septoplasty outcome. Methods: A monocentric, prospective case-control study of 21 patients was conducted. The proportion of mouth breathing was measured in a blinded manner. As a measurement of patient satisfaction, subjective symptoms pre- and postoperatively, were assessed by using VAS, NOSE and SNOT-20 score. In the patient group an additional acoustic rhinometry and a clinical examination of the nose were performed. Results: With a mean of 25% (SD = 20%) the proportion of mouth breathing in patients with NAO did not differ significantly from the proportion in controls without NAO, with a mean of 27% (SD = 23%). Analysis of subjective scores revealed a significant reduction of subjective symptoms after septoplasty. A higher preoperative proportion of mouth breathing correlated with more remaining postoperative NAO. Conclusions: The percentage of mouth breathing is no different in patients with symptomatic septal deviation than in control patients. Mouth breathing in patients with NAO, evaluated for septoplasty, could be a negative predictive factor for patient satisfaction after nasal septoplasty. Mouth breathing in these patients should be observed carefully because more preoperative mouth breathing should make one more hesitant to consider septoplasty.

Impact of Breathing Patterns on the Quality of Life of 9- to 10-year-old Schoolchildren

Background

Mouth breathing can cause a set of changes in craniofacial growth and development, with esthetic, functional, and psychological repercussions.

Objective

To determine the impact of mouth breathing on the quality of life of schoolchildren.

Methods

A school-based, cross-sectional study was conducted with 1911 children ages 9 and 10 years in the city of Recife, Brazil. The children answered the Mouth Breather Quality of Life questionnaire and a questionnaire that addressed sociodemographic data and health-related aspects. Clinical examinations were performed by an examiner who had undergone a training and calibration process for the diagnosis of mouth breathing (kappa = 0.90). Descriptive statistics were conducted to characterize the sample. Statistical analysis involved the Student's t-test and the F test (analysis of variance) (alpha = 5%).

Results

The prevalence of mouth breathing was 54.81%. Children with oral breathing demonstrated a poorer quality of life in comparison with children with nasal breathing (p < 0.001). The following variables were significantly associated with a poorer quality of life among the children with mouth breathing: a younger age (p < 0.001) and the use of medication (p = 0.002).

Conclusion

Based on the present findings, children with the mouth-breathing pattern experience a greater negative impact on quality of life in comparison with those with the nose-breathing pattern. Thus, the early diagnosis and treatment of this clinical condition are fundamental to minimizing the consequences of mouth breathing on the quality of life of schoolchildren with respiration disorders.