• Quality Improvement in Health Care
• /
• v.27 no.2
• /
• pp.2-17
• /
• 2021

Purpose: The purpose of this study is to seek in-depth perspectives of stakeholders on the necessity and specific criteria for designating a specialized hospital for urologic diseases. Methods: Eight participants experts in urology medicine and specialized hospital system were divided into four groups. Following the semi-structured guidelines, an in-depth interview was conducted twice and a focus group discussion was conducted three times. All the interviews were transcribed verbatim and analyzed. Results: The majority of participants predicted that there would be demand for specialized hospitals for urologic diseases. The criteria of designating a specialized hospital, such as the number of hospital beds and quality of health care, have to be modified in consideration of the specificity of urology. The introduction of a specialized hospital would improve the healthcare delivery system, positively affecting hospitals and patients. Furthermore, government support is essential for the maintenance of specialized hospital systems as urology hospitals experience difficulties in generating profits. Conclusion: This study is expected to be used as base data for introducing and operating a specialized hospital for urologic diseases. In addition, it is expected that the methodology and results of this study would encourage follow-up studies on specialized hospitals and provide guidelines to evaluate the effectiveness of such hospitals in other medical fields.

• Journal of Trauma and Injury
• /
• v.34 no.4
• /
• pp.225-232
• /
• 2021

Purpose: Trauma is the top cause of death in people under 45 years of age. Deaths from severe trauma can have a negative economic impact due to the loss of people belonging to socio-economically active age groups. Therefore, efforts to reduce the mortality rate of trauma patients are essential. The purpose of this study was to investigate preventable mortality in trauma patients and to identify factors and healthcare-related challenges affecting mortality. Ultimately, these findings will help to improve the quality of trauma care. Methods: We analyzed the deaths of 411 severe trauma patients who presented to Gachon University Gil Hospital regional trauma center in South Korea from January 2015 to December 2017, using an expert panel review. Results: The preventable death rate of trauma patients treated at the Gachon University Gil Hospital regional trauma center was 8.0%. Of these, definitely preventable deaths comprised 0.5% and potentially preventable deaths 7.5%. The leading cause of death in trauma patients was traumatic brain injury. Treatment errors most commonly occurred in the intensive care unit (ICU). The most frequent management error was delayed treatment of bleeding. Conclusions: Most errors in the treatment of trauma patients occurred in early stages of the treatment process and in the ICU. By identifying the main causes of preventable death and errors during the course of treatment, our research will help to reduce the preventable death rate. Appropriate trauma care systems and ongoing education are also needed to reduce preventable deaths from trauma.

• Health Policy and Management
• /
• v.32 no.2
• /
• pp.173-179
• /
• 2022

Background: This study aimed to identify patterns of elderly patients who transferred from long-term care hospitals to emergency rooms and provide the evidence of emergency medical systems to prepare for a super-aged society. Methods: The data source was the National Emergency Department Information System database from January 2014 to December 2019 in Korea. We performed a cross-sectional study among elderly patients (≥65 years) who transferred from a long-term care hospital to an emergency room. Trend analysis was conducted by year. Results: We identified 225,765 elderly patients who were transferred from long-term care hospitals to emergency rooms between January 1, 2014 and December 31, 2019. The proportion of the study population and their mean age were recently increased (p<0.001, respectively). The proportion of elderly patients being re-transferred (p=0.049) and the patients re-transferred to long-term care hospitals is significantly increased (p=0.005). Conclusion: The establishment of efficient emergency medical services for an aging society is important. It is necessary to develop a healthcare network with the government, long-term care hospitals, and medical institutions in the community suitable for preventing disease deterioration.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.97-110
• /
• 2022

Federated learning is a learning method capable of performing model learning without transmitting learning data. The IoT or healthcare field is sensitive to information leakage as it deals with users' personal information, so a lot of attention should be paid to system design, but when using federated-learning, data does not move from devices where data is collected. Accordingly, many federated-learning implementations have been developed, but detailed research on system design for the development and operation of systems using federated learning is insufficient. This study shows that measures for the life cycle, code version management, model serving, and device monitoring of federated learning are needed to be applied to actual projects and distributed to IoT devices, and we propose a design for a development environment that complements these points. The system proposed in this paper considered uninterrupted model-serving and includes source code and model version management, device state monitoring, and server-client learning schedule management.

• Journal of the Korea Safety Management & Science
• /
• v.23 no.4
• /
• pp.31-42
• /
• 2021

Recently, virtual reality (VR) and augmented reality (AR) technologies are attracting attention as core technologies in the era of the 4th industrial revolution. These virtual and augmented reality technologies are being used in a variety of industries, including the construction industry, healthcare industry, and manufacturing industry, to innovate in communication and collaboration, education and simulation, customer service and reinvention of the customer experience. In this paper, VR-based experiential safety education was conducted for workers of shipbuilding companies in Ulsan city, and for them, the educational effectiveness such as immersion, site applicability, safety accident prevention, education satisfaction, overall performance, and safety behavior in VR-based safety experience education were measured. In addition, we examined whether the immersion of VR-based safety experience education affects site applicability, safety accident prevention, educational satisfaction, overall performance, and safety behavior. Furthermore, it was analyzed whether site applicability plays a mediating role in the relationship between immersion and safety accident prevention. As a result, it was found that the immersion of VR-based safety experience education affects site applicability, safety accident prevention effect, education satisfaction, overall performance, and safety behavior, and that site applicability mediates between immersion and safety accident prevention. Based on these results, we suggests a direction for the development of VR-based contents in the field of safety and health and the transformation of safety and health education in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.742-756
• /
• 2022

A flood of information has occurred with the rise of the internet and digital devices in the fourth industrial revolution era. Every millisecond, massive amounts of structured and unstructured data are generated; smartphones, wearable devices, sensors, and self-driving cars are just a few examples of devices that currently generate massive amounts of data in our daily. Machine learning has been considered an approach to support and recognize patterns in data in many areas to provide a convenient way to other sectors, including the healthcare sector, government sector, banks, military sector, and more. However, the conventional machine learning model requires the data owner to upload their information to train the model in one central location to perform the model training. This classical model has caused data owners to worry about the risks of transferring private information because traditional machine learning is required to push their data to the cloud to process the model training. Furthermore, the training of machine learning and deep learning models requires massive computing resources. Thus, many researchers have jumped to a new model known as "Federated Learning". Federated learning is emerging to train Artificial Intelligence models over distributed clients, and it provides secure privacy information to the data owner. Hence, this paper implements Federated Averaging with a Deep Neural Network to classify the handwriting image and protect the sensitive data. Moreover, we compare the centralized machine learning model with federated averaging. The result shows the centralized machine learning model outperforms federated learning in terms of accuracy, but this classical model produces another risk, like privacy concern, due to the data being stored in the data center. The MNIST dataset was used in this experiment.

• Research in Community and Public Health Nursing
• /
• v.33 no.3
• /
• pp.269-278
• /
• 2022

Purpose: This study analyzed the retention factors of Korean community health practitioners who sustained over 20 years based on a multi-dimensional framework. This study suggests global implications for nurses working in rural or remote areas, even during a worldwide pandemic. Methods: The participants were 16 Korean community health practitioners who worked in rural or remote locations for over 20 years. This study identified nurses' key retention factors contributing to long service in rural and remote areas. This is a qualitative study based on the narrative method and analysis was conducted using grounded theory. A semi-structured questionnaire was conducted based on the following: the life flow of the participants' first experience, episodes during the work experience, and reflections on the past 20 years. Results: First, personal 'financial needs' and 'callings' were motivation-related causal conditions. The adaptation of environment-work-community was the contextual condition leading to intervening conditions, building coping strategies by encountering a lifetime crisis. The consequences of 'transition' and 'maturation' naturally occurred with chronological changes. The unique factors were related to the 'external changes' in the Korean primary health system, which improved the participants' social status and welfare. Conclusion: Considering multi-dimensional retention factors was critical, including chronological (i.e., historical changes) and external factors (i.e., healthcare systems), to be supportive synchronously for rural nurses. Without this, the individuals working in the rural areas could be victimized by insecurity and self-commitment. Furthermore, considering the global pandemic, the retention of nurses is crucial to prevent the severity of isolation in rural and remote areas.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.359-373
• /
• 2022

The new crown pneumonia (COVID-19) has become a global epidemic. The disease has spread to most countries and poses a challenge to the healthcare system. Contact tracing technology is an effective way for public health to deal with diseases. Many experts have studied traditional contact tracing and developed digital contact tracking. In order to better understand the field of contact tracking, it is necessary to analyze the development of contact tracking in the field of computer science by bibliometrics. The purpose of this research is to use literature statistics and topic analysis to characterize the research literature of contact tracking in the field of computer science, to gain an in-depth understanding of the literature development status of contact tracking and the trend of hot topics over the past decade. In order to achieve the aforementioned goals, we conducted a bibliometric study in this paper. The study uses data collected from the Scopus database. Which contains more than 10,000 articles, including more than 2,000 in the field of computer science. For popular trends, we use VOSviewer for visual analysis. The number of contact tracking documents published annually in the computer field is increasing. At present, there are 200 to 300 papers published in the field of computer science each year, and the number of uncited papers is relatively small. Through the visual analysis of the paper, we found that the hot topic of contact tracking has changed from the past "mathematical model," "biological model," and "algorithm" to the current "digital contact tracking," "privacy," and "mobile application" and other topics. Contact tracking is currently a hot research topic. By selecting the most cited papers, we can display high-quality literature in contact tracking and characterize the development trend of the entire field through topic analysis. This is useful for students and researchers new to field of contact tracking ai well as for presenting our results to other subjects. Especially when comprehensive research cannot be conducted due to time constraints or lack of precise research questions, our research analysis can provide value for it.

• Fashion & Textile Research Journal
• /
• v.24 no.6
• /
• pp.694-706
• /
• 2022

This study focusses on the development of a motion-sensing smart leggings prototype with the help of a module that monitors motion using a fiber-type stretch sensor. Additionally, it acquires data on Electrocardiogram (ECG), respiration, and body temperature signals, for the development of smart clothing used in online exercise coaching and customized healthcare systems. The research process was conducted in the following order: 1) Fabrication of a fiber-type elastic strain sensor for motion monitoring, 2) Positioning and attaching the sensor, 3) Pattern development and three-dimensional (3D) design, 4) Prototyping 5) Wearability test, and 6) Expert evaluation. The 3D design method was used to develop an aesthetic design, and for sensing accurate signal acquisition functions, wearability tests, and expert evaluation. As a result, first, the selection or manufacturing of an appropriate sensor for the function is of utmost importance. Second, the selection and attachment method of a location that can maximize the function of the sensor without interfering with any activity should be studied. Third, the signal line selection and connection method should be considered, and fourth, the aesthetic design should be reflected along with functional verification. In addition, the selection of an appropriate material is important, and tests for washability and durability must be made. This study presented a manufacturing method to improve the functionality and design of smart clothing, through the process of developing a prototype of motion-sensing smart leggings.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.59-67
• /
• 2023

Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.