Swallowing accelerometry may provide a portable and cost-effective bedside alternative to currently available instrumentation. In this study, dual-axis accelerometry signals were collected simultaneous to videofluoroscopic records from 29 pediatric participants (age 6.8 $\pm$ 4.8 years; 20 males) previously diagnosed with neurogenic dysphagia. Videofluoroscopic records were reviewed by a clinical expert to extract swallow timings and ratings. The dual-axis accelerometry signals corresponding to each identified swallow were pre-processed, segmented and trimmed prior to feature extraction from time, frequency, time-frequency and information theoretic domains. Feature space dimensionality was reduced via principal components. Using 8-fold cross-validation, 16-18 dimensions and a support vector machine classifier with an RBF kernel, an adjusted accuracy of 89.6\% $\pm$ 0.9 was achieved for the discrimination between swallows with and without airway entry. Our results suggest that dual-axis accelerometry has merit in the non-invasive detection of unsafe swallows in children and deserves further consideration as a pediatric medical device.
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:OTU.1807/33763 |
| Date | 04 December 2012 |
| Creators | Mérey, Céleste |
| Contributors | Chau, Tom, Berall, Glenn |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | en_ca |
| Detected Language | English |
| Type | Thesis |
Page generated in 0.0015 seconds