Kinematic analysis of the hyoid bone in a videofluorosopic swallowing study (VFSS) is important for assessing dysphagia. However, calibrating the hyoid bone movement is time-consuming, and its reliability shows wide variation. Computer-assisted analysis has been studied to improve the efficiency and accuracy of hyoid bone identification and tracking, but its performance is limited. In this study, we aimed to design a robust network that can track hyoid bone movement automatically without human intervention. Using 69,389 frames from 197 VFSS files as the data set, a deep learning model for detection and trajectory prediction was constructed and trained by the BiFPN-U-Net(T) network. The present model showed improved performance when compared with the previous models: an area under the curve (AUC) of 0.998 for pixelwise accuracy, an accuracy of object detection of 99.5%, and a Dice similarity of 90.9%. The bounding box detection performance for the hyoid bone and reference objects was superior to that of other models, with a mean average precision of 95.9%. The estimation of the distance of hyoid bone movement also showed higher accuracy. The deep learning model proposed in this study could be used to detect and track the hyoid bone more efficiently and accurately in VFSS analysis.

Computer-assisted analysis is expected to improve the reliability of videofluoroscopic swallowing studies (VFSSs), but its usefulness is limited. Previously, we proposed a deep learning model that can detect laryngeal penetration or aspiration fully automatically in VFSS video images, but the evidence for its reliability was insufficient. This study aims to compare the intra- and inter-rater reliability of the computer model and human raters. The test dataset consisted of 173 video files from which the existence of laryngeal penetration or aspiration was judged by the computer and three physicians in two sessions separated by a one-month interval. Intra- and inter-rater reliability were calculated using Cohen’s kappa coefficient, the positive reliability ratio (PRR) and the negative reliability ratio (NRR). Intrarater reliability was almost perfect for the computer and two experienced physicians. Interrater reliability was moderate to substantial between the model and each human rater and between the human raters. The average PRR and NRR between the model and the human raters were similar to those between the human raters. The results demonstrate that the deep learning model can detect laryngeal penetration or aspiration from VFSS video as reliably as human examiners.

(1) Background: Pressure ulcers (PUs) substantially impact the quality of life of spinal cord injury (SCI) patients and require prompt intervention. This study used machine learning (ML) techniques to develop advanced predictive models for the occurrence of PUs in patients with SCI. (2) Methods: By analyzing the medical records of 539 patients with SCI, we observed a 35% incidence of PUs during hospitalization. Our analysis included 139 variables, including baseline characteristics, neurological status (International Standards for Neurological Classification of Spinal Cord Injury [ISNCSCI]), functional ability (Korean version of the Modified Barthel Index [K-MBI] and Functional Independence Measure [FIM]), and laboratory data. We used a variety of ML methods—a graph neural network (GNN), a deep neural network (DNN), a linear support vector machine (SVM_linear), a support vector machine with radial basis function kernel (SVM_RBF), K-nearest neighbors (KNN), a random forest (RF), and logistic regression (LR)—focusing on an integrative analysis of laboratory, neurological, and functional data. (3) Results: The SVM_linear algorithm using these composite data showed superior predictive ability (area under the receiver operating characteristic curve (AUC) = 0.904, accuracy = 0.944), as demonstrated by a 5-fold cross-validation. The critical discriminators of PU development were identified based on limb functional status and laboratory markers of inflammation. External validation highlighted the challenges of model generalization and provided a direction for future research. (4) Conclusions: Our study highlights the importance of a comprehensive, multidimensional data approach for the effective prediction of PUs in patients with SCI, especially in the acute and subacute phases. The proposed ML models show potential for the early detection and prevention of PUs, thus contributing substantially to improving patient care in clinical settings.

Background/Objectives: Shear wave elastography (SWE) has emerged as a quantitative imaging technique for assessing muscle mechanical properties and has been increasingly applied to post-stroke spasticity. However, the clinical validity of SWE relative to established clinical spasticity scales and the influence of assessment protocols remain incompletely understood. This systematic review and meta-analysis aimed to evaluate the clinical validity of SWE for post-stroke spasticity and to identify clinically relevant methodological moderators. Methods: A systematic literature search was conducted in PubMed, Cochrane Library, CINAHL, and Web of Science to identify studies reporting correlations between SWE measures and clinical spasticity scales in individuals with stroke. Random-effects meta-analyses were performed using robust variance estimation to account for dependent effect sizes within studies. Prespecified subgroup and meta-regression analyses examined potential moderators, including clinical scale, muscle position during assessment, output metric, limb segment, and stroke chronicity. Results: Ten studies involving 303 participants contributed 38 correlation estimates. The pooled correlation between SWE and clinical spasticity scales was moderate (r = 0.42, 95% CI 0.34–0.49). SWE demonstrated significantly stronger correlations with the Modified Tardieu Scale than with the Modified Ashworth Scale. Measurements obtained in stretched muscle positions showed higher validity than those obtained at rest. Other examined moderators were not statistically significant. No evidence of publication bias was detected. Conclusions: SWE shows a moderate association with clinician-rated spasticity scales and appears to reflect the mechanical consequences of post-stroke spasticity. Associations were influenced by scale selection and measurement position. These findings support protocol-informed integration of SWE as a quantitative adjunct for assessing passive muscle stiffness rather than as a replacement for established clinical scales.

Objectives: This paper’s objective was to identify clinical predictors, especially modifiable ones, associated with postoperative gait recovery in total hip arthroplasty (THA) patients, utilizing propensity score weighting (PSW) to control confounding factors. Methods: This retrospective cohort study included 221 patients who underwent primary unilateral THA. We used PSW analysis to balance patient characteristics. Univariate and multivariate logistic regression analyses were applied to determine predictors of improved gait recovery, assessing variables such as age, gender, and postoperative muscle strength. Results: Independent predictors of favorable gait recovery were male gender (Odds Ratio [OR]: 1.382; 95% Confidence Interval [CI]: 1.225–1.560; p < 0.001), younger age (OR: 0.990 per year; 95% CI: 0.985–0.995; p < 0.001), and postoperative hip flexor muscle strength greater than grade 3 (OR: 1.516; 95% CI: 1.177–1.953; p = 0.002). Muscle strength emerged as a modifiable factor, suggesting that targeted rehabilitation may enhance functional outcomes. Conclusions: Enhancing hip flexor strength postoperatively could significantly improve gait recovery in THA patients. These findings support developing individualized rehabilitation strategies to optimize functional outcomes.

Background: Early stroke recurrence is a significant risk for survivors of ischemic stroke. Although admission severity is commonly used in prognosis, the predictive value of residual neurological deficits at discharge remains underexplored. We aimed to determine whether discharge National Institutes of Health Stroke Scale (NIHSS) score predicts 1‐year ischemic stroke recurrence, using a large multicenter registry and propensity score matching. Methods: We analyzed 39 947 patients with first‐ever ischemic stroke from the KRS (Korean Registry of Regional Cardiocerebrovascular Center for Stroke) (2014–2022). NIHSS scores were recorded at admission (baseline) and at discharge. Patients were dichotomized by discharge NIHSS score (<5 versus ≥5); supplementary cutoffs of 16 and 21 were explored. Propensity score matching (1:1 nearest neighbor) was used to adjust baseline covariates. The primary outcome was stroke recurrence within 1 year, defined as a new neurological deficit confirmed by imaging. Kaplan–Meier survival and Cox regression were used to evaluate predictors. Results: After propensity score matching, discharge NIHSS score was a significant predictor of recurrence (hazard ratio per point, 1.03 [95% CI, 1.00–1.05]; P =0.028). Higher discharge mRS score and hypertension were also significantly associated with recurrence. Patients with NIHSS score ≥5 had 20% to 30% higher recurrence rates across analyses. Stroke subtype analysis showed that small artery occlusion conferred lower recurrence risk. Conclusions: Discharge NIHSS score significantly reflects risk of early recurrence compared with initial stroke severity. These findings support incorporating discharge neurological status into poststroke risk stratification and follow‐up planning.