RESUMO
Introduction: Post-stroke dysphagia is common and associated with significant morbidity and mortality, rendering bedside screening of significant clinical importance. Using voice as a biomarker coupled with deep learning has the potential to improve patient access to screening and mitigate the subjectivity associated with detecting voice change, a component of several validated screening protocols. Methods: In this single-center study, we developed a proof-of-concept model for automated dysphagia screening and evaluated the performance of this model on training and testing cohorts. Patients were admitted to a comprehensive stroke center, where primary English speakers could follow commands without significant aphasia and participated on a rolling basis. The primary outcome was classification either as a pass or fail equivalent using a dysphagia screening test as a label. Voice data was recorded from patients who spoke a standardized set of vowels, words, and sentences from the National Institute of Health Stroke Scale. Seventy patients were recruited and 68 were included in the analysis, with 40 in training and 28 in testing cohorts, respectively. Speech from patients was segmented into 1,579 audio clips, from which 6,655 Mel-spectrogram images were computed and used as inputs for deep-learning models (DenseNet and ConvNext, separately and together). Clip-level and participant-level swallowing status predictions were obtained through a voting method. Results: The models demonstrated clip-level dysphagia screening sensitivity of 71% and specificity of 77% (F1 = 0.73, AUC = 0.80 [95% CI: 0.78-0.82]). At the participant level, the sensitivity and specificity were 89 and 79%, respectively (F1 = 0.81, AUC = 0.91 [95% CI: 0.77-1.05]). Discussion: This study is the first to demonstrate the feasibility of applying deep learning to classify vocalizations to detect post-stroke dysphagia. Our findings suggest potential for enhancing dysphagia screening in clinical settings. https://github.com/UofTNeurology/masa-open-source.
RESUMO
A new technique for 3-D imaging with a row-column array (RCA) configuration has been developed. The technique requires an electrostrictive piezoelectric for the active substrate. While the top set of electrodes is connected to RF transmit and receive channels for conventional diverging wave imaging (DWI), the orthogonal bottom set of electrodes is connected to independently controlled variable dc bias channels. By implementing modulated bias patterns compounded across multiple pulses, fine delay control across the bottom elements can be achieved simultaneously with imaging with the top set of electrodes. This resulted in a high-quality two-way focus in both azimuth and elevation. A 20-MHz electrostrictive composite substrate was fabricated, and 64 top ×64 bottom electrodes were patterned and connected to custom beamforming and biasing electronics. The point spread functions were generated in all dimensions, and the -6 dB resolution was measured to be 93 [Formula: see text] axially, [Formula: see text] in the azimuth, and 328 [Formula: see text] in the elevation dimension. This was in good agreement with the simulated resolutions of 80, 273, and 280 [Formula: see text], respectively.