Purpose: This study aims to evaluate the physical activity of healthcare personnel and the affecting factors of physical activity (PA) in a hospital using an accelerometer device (Actigraph wGT3X-BT). Method: A total of 63 subjects (22 physicians, 19 nurses, and 23 supporting staff) participated and wore an accelerometer for seven days. Among the outputs, the mean counts for a minute, time spent for light, moderate, and vigorous intensity PA, and step count were extracted. As a secondary study, 16 subjects continued for one more week after feedback on their PA of the previous week and counseling to encourage PA. Result: Most of (62/63) the participants fulfilled the recommended amount of PA, which is more than 300 min of moderate to vigorous physical activity (MVPA). Physicians showed significantly less PA than nurses or supporting staffs: Mean counts per minute (210.4 vs. 476.0 and 441.8 respectively), time in MVPA per week (904.7 min vs. 1471.3 min and 1451.0 min), and step counts per week (69,029 vs. 87,119 and 84,700) (p < 0.001). Nurses and supporting staff were not statistically different. There was no significant difference in the PA of workers in the hospital regarding gender and marital status. However, the average calorie expenditure of the child raising group was significantly higher. There was no statistically significant difference in PA before and after counseling. No participants reported a vigorous degree of exercise intensity over the study period. Conclusion: Most of the healthcare personnel met the recommended PA, however, only 57% (36/63) recalled having engaged in MVPA during the study period. The group of physicians showed less PA compared to nurses or supporting staff. Single check-up and counseling were not found to increase PA.

Background: Speech sound disorders (SSDs) are common communication challenges in children, typically assessed by speech-language pathologists (SLPs) using standardized tools. However, traditional evaluation methods are time-intensive and prone to variability, raising concerns about reliability. Objective: This study aimed to compare the evaluation outcomes of SLPs and an automatic speech recognition (ASR) model using two standardized SSD assessments in South Korea, evaluating the ASR model’s performance. Methods: A fine-tuned wav2vec 2.0 XLS-R model, pretrained on 436,000 hours of adult voice data spanning 128 languages, was used. The model was further trained on 93.6 minutes of children’s voices with articulation errors to improve error detection. Participants included children referred to the Department of Rehabilitation Medicine at a general hospital in Incheon, South Korea, from August 19, 2022, to June 14, 2023. Two standardized assessments—the Assessment of Phonology and Articulation for Children (APAC) and the Urimal Test of Articulation and Phonology (U-TAP)—were used, with ASR transcriptions compared to SLP transcriptions. Results: This study included 30 children aged 3-7 years who were suspected of having SSDs. The phoneme error rates for the APAC and U-TAP were 8.42% (457/5430) and 8.91% (402/4514), respectively, indicating discrepancies between the ASR model and SLP transcriptions across all phonemes. Consonant error rates were 10.58% (327/3090) and 11.86% (331/2790) for the APAC and U-TAP, respectively. On average, there were 2.60 (SD 1.54) and 3.07 (SD 1.39) discrepancies per child for correctly produced phonemes, and 7.87 (SD 3.66) and 7.57 (SD 4.85) discrepancies per child for incorrectly produced phonemes, based on the APAC and U-TAP, respectively. The correlation between SLPs and the ASR model in terms of the percentage of consonants correct was excellent, with an intraclass correlation coefficient of 0.984 (95% CI 0.953-0.994) and 0.978 (95% CI 0.941-0.990) for the APAC and UTAP, respectively. The z scores between SLPs and ASR showed more pronounced differences with the APAC than the U-TAP, with 8 individuals showing discrepancies in the APAC compared to 2 in the U-TAP. Conclusions: The results demonstrate the potential of the ASR model in assessing children with SSDs. However, its performance varied based on phoneme or word characteristics, highlighting areas for refinement. Future research should include more diverse speech samples, clinical settings, and speech data to strengthen the model’s refinement and ensure broader clinical applicability.

We aimed to evaluate muscle mass changes after injection of botulinum toxin (BoNT) in children with spastic hemiplegic cerebral palsy (CP). Children aged between 2 and 12 years who were diagnosed with hemiplegic CP with spastic equinus foot were prospectively recruited and administered BoNT in the affected leg. Lean body mass (LBM) of both legs and total limbs was measured by dual-energy X-ray absorptiometry (DXA) preinjection and 4 and 12 weeks after injection. A total of 15 children were enrolled into the study. LBM of both legs and total limbs increased significantly over 12 weeks of growth. The ratio of LBM of the affected leg to total limbs and to the unaffected leg significantly reduced at 4 weeks after injection compared with preinjection but significantly increased at 12 weeks after injection compared with 4 weeks after injection. In conclusion, the muscle mass of the affected leg after BoNT injection in children with hemiplegic spastic CP decreased at 4 weeks after BoNT injection but significantly recovered after 12 weeks after injection.

Park S, et al. Brain Neurorehabil. 2022 May;15(2):e20. https://doi.org/10.12786/bn.2022.15.e20

This study presents a model of automatic speech recognition (ASR) that is designed to diagnose pronunciation issues in children with speech sound disorders (SSDs) to replace manual transcriptions in clinical procedures. Because ASR models trained for general purposes mainly predict input speech into standard spelling words, well-known high-performance ASR models are not suitable for evaluating pronunciation in children with SSDs. We fine-tuned the wav2vec2.0 XLS-R model to recognise words as they are pronounced by children, rather than converting the speech into their standard spelling words. The model was fine-tuned with a speech dataset of 137 children with SSDs pronouncing 73 Korean words that are selected for actual clinical diagnosis. The model's Phoneme Error Rate (PER) was only 10% when its predictions of children's pronunciations were compared to human annotations of pronunciations as heard. In contrast, despite its robust performance on general tasks, the state-of-the-art ASR model Whisper showed limitations in recognising the speech of children with SSDs, with a PER of approximately 50%. While the model still requires improvement in terms of the recognition of unclear pronunciation, this study demonstrates that ASR models can streamline complex pronunciation error diagnostic procedures in clinical fields.

Carpal tunnel syndrome (CTS) is a prevalent neuropathy resulting from median nerve compression, typically diagnosed through electrodiagnostic studies. Shear wave elastography (SWE) has emerged as an essential imaging technique, especially in evaluating tissue elasticity, which could enhance the diagnosis and severity assessment of CTS. This study aimed to examine the combined effect of the median nerve’s cross-sectional area (CSA) and elasticity assessed through SWE in diagnosing CTS and evaluating its severity. A total of 50 participants were involved in this prospective study, with 99 wrists analyzed (51 affected by CTS and 48 normal controls). Measurements of both CSA and elasticity were taken at the carpal tunnel inlet. The findings indicated that CSA and elasticity were considerably higher in CTS patients than in the controls. The combined parameter of CSA × elasticity outperformed other measures for differentiating between normal and CTS cases (Area Under the Curve 0.91, sensitivity 0.90, specificity 0.83, cutoff 753.7 kPa·mm²). This combined metric also showed potential for distinguishing CTS severity levels, particularly between mild and severe cases. Although CSA and elasticity alone had limitations in severity classification, their combined values illustrated significant distinctions across severity levels. Integrating SWE with CSA notably improves diagnostic accuracy for CTS and shows potential for severity grading. This approach offers a more detailed evaluation of the structural and mechanical changes in the median nerve, potentially enhancing both the diagnosis and management of CTS.