Dataset Information

Spontaneous Swallowing Frequency in Post-Stroke Patients with and Without Oropharyngeal Dysphagia: An Observational Study.

ABSTRACT: Oropharyngeal dysphagia (OD) is a frequent complication after stroke (PSOD) that increases morbidity and mortality. Early detection of PSOD is essential to reduce morbidity and mortality in patients with acute stroke. In recent years, an association between reduced spontaneous swallowing frequency (SSF) and OD has been described. Likewise, the reduction of saliva substance P (SP) concentration has been associated with an increased risk of aspiration and a decrease in SSF. In this study we aimed to compare SSF, salivary SP concentration, hydration and nutritional status in post-stroke (PS) patients with and without OD. We included 45 acute PS patients (4.98 ± 2.80 days from stroke onset, 62.22% men, 71.78 ± 13.46 year). The Volume-Viscosity Swallowing Test (V-VST) was performed for clinical diagnosis of OD. SSF/minute was assessed through 10-min neurophysiological surface recordings including suprahyoid-electromyography and cricothyroid-accelerometry. Saliva samples were collected with a Salivette® to determine SP by ELISA. Hydration status was assessed by bioimpedance. Nutritional status was evaluated by Mini Nutritional Assessment Short Form (MNA-sf) and blood analysis. Twenty-seven PS patients (60%) had OD; 19 (40%), impaired safety of swallow. SSF was significantly reduced in PSOD, 0.23 ± 0.18 and PSOD with impaired safety, 0.22 ± 0.18 vs 0.48 ± 0.29 swallows/minute in PS without OD (PSnOD); (both p < 0.005). Nutritional risk was observed in 62.92% PSOD vs 11.11% PSnOD (p = 0.007) and visceral protein markers were also significantly reduced in PSOD (p < 0.05). Bioimpedance showed intracellular dehydration in 37.50% PSOD vs none in PSnOD. There were no differences for saliva SP concentrations. SSF is significantly reduced in PSOD in comparison with PSnOD. Acute PSOD patients present poor nutritional status, hydropenia, and high risk for respiratory complications.

SUBMITTER: Alvarez-Larruy M

PROVIDER: S-EPMC9034075 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:IntroductionPost-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.MethodsIn 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.ResultsThe 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]).DiscussionThis 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.

Dataset Information

Spontaneous Swallowing Frequency in Post-Stroke Patients with and Without Oropharyngeal Dysphagia: An Observational Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets