Related Experiment Video
Updated: Jul 10, 2026
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
A radial basis function classifier for pediatric aspiration detection
Joon Lee1, Stefanie Blain, Mike Casas
1Toronto Univ., ON, Canada.
Insights
A new method uses cervical accelerometry to detect silent aspiration in children with dysphagia. This non-invasive technique shows promise for a portable device to identify aspiration risks at home.
Area of Science:
- Biomedical Engineering
- Pediatric Medicine
- Signal Processing
Background:
- Silent aspiration is a significant health concern for children with dysphagia.
- Current methods for detecting aspiration are often invasive or not suitable for home use.
Purpose of the Study:
- To develop a non-invasive, portable, and user-friendly device for detecting aspiration in children.
- To investigate the efficacy of radial basis functions applied to cervical accelerometry signals for aspiration detection.
Main Methods:
- Cervical accelerometry signals were collected from over 100 children with dysphagia during swallowing events.
- Vibration signals corresponding to safe swallows and aspirations (verified by videofluoroscopy) were analyzed.
- Three time-domain features (dispersion ratio, normality) were extracted and used to train radial basis function classifiers.
Main Results:
- The radial basis function classifier using dispersion ratio and normality achieved 81.03% accuracy.
- The classifier demonstrated a false negative rate of 9.06% and a false positive rate of 9.91% for aspiration detection.
- The developed method shows potential for implementation in a handheld device.
Conclusions:
- Radial basis functions based on cervical accelerometry provide a promising approach for detecting aspiration in pediatric dysphagia.
- The proposed method offers a reliable, non-invasive, and potentially portable solution for aspiration monitoring.
- Further development could lead to a practical device for home and community use.
Abstract:
Silent aspiration presents a serious health issue for children with dysphagia. To date, there is no satisfactory means of detecting aspiration in the home or community. In an effort to design a practical device that could offer reliability, non-invasiveness, portability, and easy usability, radial basis functions based on cervical accelerometry signals were investigated. Vibration signals associated with safe swallows and aspirations, both identified via videofluoroscopy, were collected from over 100 children with neurologically-based dysphagia using a single-axis accelerometer. Three time-domain discriminatory mathematical features were extracted from the accelerometry signals. An exhaustive set of all possible combinations of the features was investigated in the design of radial basis function classifiers. The feature pairing of dispersion ratio and normality achieved an accuracy of 81.03 +/- 5.78%, a false negative rate of 9.06 +/- 4.84%, and a false positive rate of 9.91 +/- 5.03% for aspiration detection. The proposed classifier can be easily implemented in a hand-held device.
