Related Experiment Video
Updated: Sep 26, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
1.0K
A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI)-Part 1:
Yukiko Matsuda1, Emi Ito1, Migiwa Kuroda1
1Division of Radiology, Department of Oral Diagnostic Sciences, Showa University School of Dentistry, 2-1-1 Kitasenzoku, Ohta-ku, Tokyo 145-8515, Japan.
Summary
Panoramic radiographs can help detect dysphagia risk. A lower hyoid bone position on these X-rays indicates a higher risk of swallowing difficulties, aiding in early diagnosis.
Area of Science:
- Oral and Maxillofacial Radiology
- Swallowing Disorders
- Artificial Intelligence in Healthcare
Background:
- Dysphagia significantly impacts patient quality of life and complicates dental treatment.
- Identifying dysphagia early is crucial for managing its associated challenges.
Purpose of the Study:
- To investigate the potential of panoramic radiography combined with AI for detecting radiographic signs of dysphagia.
- To establish a reliable method for identifying dysphagia risk using dental imaging.
Main Methods:
- Analysis of 77 patients with panoramic radiographs and videofluorographic swallowing studies.
- Evaluation of factors including hyoid bone position, tongue dimensions, and remaining teeth.
- Application of logistic regression and ROC curve analysis to determine significant predictors.
Main Results:
- Vertical hyoid bone position was the sole significant predictor of dysphagia (AUC=0.72).
- A hyoid bone position below the mandibular border line was identified as a key indicator.
- The study established a specific cutoff level for the vertical hyoid bone position.
Conclusions:
- A lower hyoid bone position on panoramic radiographs suggests a high risk of dysphagia.
- This finding supports the development of AI models using vertical hyoid bone assessment for dysphagia risk detection.
