This study enhances AI algorithms for extracting spinal regions from Whole Spine X-rays, aiming for higher accuracy while minimizing learning and detection times. Whole Spine X-rays, critical for diagnosing conditions such as scoliosis and kyphosis, necessitate precise differentiation of spinal contours. The conventional manual methodology encounters challenge due to the overlap of anatomical structures, prompting the integration of AI to overcome these limitations and enhance diagnostic precision. In this study, 1204 AP and 500 LAT Whole Spine X-ray images were meticulously labeled, spanning the third cervical to the fifth lumbar vertebrae. We based our efforts on the HR-Net algorithm, which exhibited the highest accuracy, and proceeded to simplify its network architecture and enhance the block structure for optimization. The optimized HR-Net algorithm demonstrates an improvement, increasing accuracy by 2.98% for the AP dataset and 1.59% for the LAT dataset compared to its original formulation. Additionally, the modification resulted in a substantial reduction in learning time by 70.06% for AP images and 68.43% for LAT images, along with a decrease in detection time by 47.18% for AP and 43.07% for LAT images. The time taken per image for detection was also reduced by 47.09% for AP and 43.07% for LAT images. We suggest that the application of the proposed HR-Net in this study can lead to more accurate and efficient extraction of spinal regions in Whole Spine X-ray images. This can become a crucial tool for medical professionals in the diagnosis and treatment of spinal-related conditions, and it will serve as a foundation for future research aimed at further improving the accuracy and speed of spinal region segmentation.

This study compares and analyzes domestic and international regulations on the application of software in In Vitro Diagnostic (IVD) medical devices, proposing improvements for South Korea. The research examines regulatory statuses in Europe, the United States, and Australia, identifying differences in regulatory approaches and definitions. Despite varying methods, all countries recognize the importance of software, though the regulatory scope differs. Considering the current domestic regulations, systematic improvements are essential for sustainable growth. This study suggests regulatory enhancements and draft guidelines, emphasizing the need for ongoing monitoring and stakeholder input to develop practical solutions.

To analyse the overall research trends in digital therapeutics, this study conducted a quantitative bibliometric analysis of articles published in the last 10 years from 2014 to 2023. We extracted bibliographic information of studies related to digital therapeutics from the Web of Science (WOS) database and performed publication status, citation analysis and keyword analysis using R (version 4.3.1) and VOSviewer (version 1.6.18) software. A total of 1,114 articles were included in the study, and the annual publication growth rate for digital therapeutics was 66.1%, a very rapid increase. "health" is the most used keyword based on Keyword Plus, and "cognitive-behavioral therapy", "depression", "healthcare", "mental-health", "meta-analysis" and "randomized controlled-trial" are the research keywords that have driven the development and impact of digital therapeutic devices over the long term. A total of five clusters were observed in the co-occurrence network analysis, with new research keywords such as "artificial intelligence", "machine learning" and "regulation" being observed in recent years. In our analysis of research trends in digital therapeutics, keywords related to mental health, such as depression, anxiety, and disorder, were the top keywords by occurrences and total link strength. While many studies have shown the positive effects of digital therapeutics, low engagement and high dropout rates remain a concern, and much research is being done to evaluate and improve them. Future studies should expand the search terms to ensure the representativeness of the results.

We present an improved biphasic electrical nerve stimulator designed to overcome limitations. Traditional electrical nerve stimulators lacking a microcontroller unit (MCU) have restrictions in terms of frequency, pulse duration, and amplitude control, making them insufficient for medical applications requiring a broader range of pulse specifications. To address this, we developed a stimulator with enhanced capabilities. By not using an MCU, the design reduces power consumption and the required area, simplifying the overall design and increasing efficiency. In addition, our approach optimizes oscillator parameters to achieve wide frequency and pulse duration ranges. Specifically, we expanded the frequency range of the stimulator up to from 1 mHz to 100 kHz and the pulse duration up to from 5 ㎲ to 500 s. Improved amplitude control mechanisms were implemented for adjustable and high biphasic amplitudes. Furthermore, we added a balancing circuit to ensure proper discharging for tissue safety when biphasic pulses do not occur. The improved stimulator demonstrated an increase in operational range compared to traditional MCU-less designs, producing consistent biphasic pulses with adjustable amplitude and duration. The balancing circuit effectively managed discharging, reducing the risk of tissue damage and ensuring safety and efficacy.

This paper investigates the impact of Riemannian Procrustes Analysis (RPA) on enhancing the classification performance of SPD-Net when applied to EEG signals across different sessions and subjects. EEG signals, known for their inherent individual variability, are initially transformed into Symmetric Positive Definite (SPD) matrices, which are naturally represented on a Riemannian manifold. To mitigate the variability between sessions and subjects, we employ RPA, a method that geometrically aligns the statistical distributions of these matrices on the manifold. This alignment is designed to reduce individual differences and improve the accuracy of EEG signal classification. SPD-Net, a deep learning architecture that maintains the Riemannian structure of the data, is then used for classification. We compare its performance with the Minimum Distance to Mean (MDM) classifier, a conventional method rooted in Riemannian geometry. The experimental results demonstrate that incorporating RPA as a preprocessing step enhances the classification accuracy of SPD-Net, validating that the alignment of statistical distributions on the Riemannian manifold is an effective strategy for improving EEG-based BCI systems. These findings suggest that RPA can play a role in addressing individual variability, thereby increasing the robustness and generalization capability of EEG signal classification in practical BCI applications.

In this study, text network analysis was performed using PMS(Post-Marketing Surveillance) data collected from the FDA's MAUDE(Manufacturer and User Facility Device Experience) database to evaluate the usability of the central monitoring system. Based on the data reported from January 1, 2021 to June 30, 2023, keywords related to the central monitoring system were extracted and visualized with a text network. By analyzing the eigenvector centrality of text network, we identified hazards and types of hazardous situations related to usability of the central monitoring system. Eigenvector centrality was chosen because it is relatively more accurate than other centralities. In addition, we derived an appropriate use scenario to evaluate the usability of the central monitoring system. The research results provide more realistic and valuable insights through data derived based on actual adverse event cases, and are expected to contribute to improving safety and reliability by identifying user requirements for improved usability and reducing use errors in the future.

Muscle disorders arise from genetic factors or other external environmental influences, leading to muscle loss and decreased strength. Muscle disease is closely related to age, and with the global progression of aging, there is increasing interest in the prevention and treatment of muscle diseases among the elderly population. Muscles release various substances during contraction and relaxation when exercising, and growth and differentiation are enhanced. Similar effects can be achieved by vibration stimulations of specific frequencies. To examine the response of muscle cells to vibration stimuli, an in vitro vibration device capable of setting various frequencies and amplitudes was developed for use with a 6-well plate. In vitro vibrational stimulation was applied to C2C12 myoblasts to quantify the growth and differentiation of myoblasts, as well as cell apoptosis. 10 Hz vibrational stimuli resulted in increases in ERK signaling and decreases in cell death. Moreover, an increase in the number of exposures to vibration promoted cellular differentiation. In conclusion, 10 Hz vibrational stimuli have the potential to increase muscle growth and differentiation and reduce apoptosis in C2C12 myoblasts.