• Journal of Biomedical Engineering Research
• /
• v.19 no.4
• /
• pp.351-360
• /
• 1998

Digital gamma camera has many advantages over analog gamma camera. These include convenient quality control, easy calibration and operation, and possible image quantitation which results in improving diagnostic accuracies. The digital data can also be utilized for telemedicine and picture archiving and communication system. However, many hospitals still operate analog cameras and have difficult situation to replace them with digital cameras. We have studied a feasibility of digitalizing an analog gamma camera into a digital camera using Gamma-PF interface board. The physical characteristics that we have measured are spatial resolution, sensitivity, uniformity, and image contrast. The patient's data obtained for both analog and digital camera showed very similar image quality. The results suggest that it may be feasible to upgrade an analog camera into a digital gamma camera in clinical environments.

• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.24-34
• /
• 2019

In this research, a practical deep learning framework to differentiate the lesions and nodules in breast acquired with ultrasound imaging has been proposed. 7408 ultrasound breast images of 5151 patient cases were collected. All cases were biopsy proven and lesions were semi-automatically segmented. To compensate for the shift caused in the segmentation, the boundaries of each lesion were drawn using Fully Convolutional Networks(FCN) segmentation method based on the radiologist's specified point. The data set consists of 4254 benign and 3154 malignant lesions. In 7408 ultrasound breast images, the number of training images is 6579, and the number of test images is 829. The margin between the boundary of each lesion and the boundary of the image itself varied for training image augmentation. The training images were augmented by varying the margin between the boundary of each lesion and the boundary of the image itself. The images were processed through histogram equalization, image cropping, and margin augmentation. The networks trained on the data with augmentation and the data without augmentation all had AUC over 0.95. The network exhibited about 90% accuracy, 0.86 sensitivity and 0.95 specificity. Although the proposed framework still requires to point to the location of the target ROI with the help of radiologists, the result of the suggested framework showed promising results. It supports human radiologist to give successful performance and helps to create a fluent diagnostic workflow that meets the fundamental purpose of CADx.

• Journal of the Korean Applied Science and Technology
• /
• v.39 no.5
• /
• pp.674-682
• /
• 2022

This study aims to examine the relationship between hyperuricemia and metabolic syndrome, which is a risk to health, and to analyze the effect of hyperuricemia on the body. The analysis data were downloaded and used for the 8th 2nd (2020) data of the National Health and Nutrition Survey, and in this study, 2,320 men and 2,893 women were finally analyzed. For the analysis of the data, Chi-square test and t-test were used for the difference values according to collected general characteristics and hyperuricemia, and the risk of eGFR rise was analyzed by regression analysis, and Pearson correlation was used to confirm the correlation with each variable. Through this study, it was found that hyperuricemia is significantly related to metabolic syndrome, and through this, preemptive management is needed to prevent metabolic syndrome from worsening into vascular diseases including kidney diseases. Therefore, it is proposed to develop a health program suitable for the patient's age through this study.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.69-76
• /
• 2022

This paper proposes a method of refining and processing time-series data using Medical Information Mart for Intensive Care (MIMIC-IV) v2.0 data. In addition, the significance of the processing method was validated through a machine learning-based pressure ulcer early warning system using a dataset processed based on the proposed method. The implemented system alerts medical staff in advance 12 and 24 hours before a lesion occurs. In conjunction with the Electronic Medical Record (EMR) system, it informs the medical staff of the risk of a patient's pressure ulcer development in real-time to support a clinical decision, and further, it enables the efficient allocation of medical resources. Among several machine learning models, the GRU model showed the best performance with AUROC of 0.831 for 12 hours and 0.822 for 24 hours.

• Journal of The Korean Society of Integrative Medicine
• /
• v.11 no.3
• /
• pp.69-78
• /
• 2023

Purpose : Establishing competency in person-centered care is crucial for providing high-quality nursing care in diverse clinical settings and adapting to changing roles in different situations. This study aimed to explore the level of transcultural self-efficacy, cultural empathy, and person-centered care competency among nursing students, as well as identify the factors influencing their person-centered care competency. The findings will serve as fundamental data to enhance person-centered care competency. Methods : A questionnaire consisting of items on general characteristics, person-centered care competency, transcultural self-efficacy, and cultural empathy was administered to 175 nursing students in G city. Data were collected from March 5, 2023, to March 20, 2023. The collected data were analyzed using the SPSS 23.0 program. Pearson's correlation coefficients were used to examine the correlation among transcultural self-efficacy, cultural empathy, and person-centered care competency. Multiple regression analysis was employed to determine the factors influencing person-centered care competency. Results : The person-centered care competency scores were above the average level and varied according to department satisfaction (F=13.79, p<.001), subjective well-being (t=3.34, p=.015), and interpersonal relations (F=5.74, p=.001). Person-centered care competency exhibited a significant positive correlation with cultural empathy (r=.51, p<.001) and transcultural self-efficacy (r=.49, p<.001). Regression analysis confirmed that cultural empathy (β=.39, p<.001) and transcultural self-efficacy (β=.22, p<.001) were influential factors for nursing students' person-centered care competency, with the model explaining 37 % of the variance. Conclusion : Cultural empathy and transcultural self-efficacy are significant factors influencing the person-centered care competency of nursing students. It is crucial to encourage nursing students to develop person-centered care competency by fostering cultural empathy and transcultural self-efficacy. Further research is needed to identify additional factors affecting person-centered care competency among nursing students. Additionally, the development of education programs aimed at enhancing person-centered care competency is necessary.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.141-147
• /
• 2022

In a broad sense, the definition of digital health care is an industrial area that manages personal health and diseases through the convergence of the health care industry and ICT. In a narrow sense, various medical technologies are used to manage medical services to improve patient health. This paper aims to provide design guidelines so that artificial intelligence technology can be applied stably and efficiently to more diverse digital health care fields in the future by introducing use cases of artificial intelligence and machine learning techniques applied in the digital health care field. For this purpose, in this thesis, the medical field and the daily life field are divided and examined. The two regions have different data characteristics. By further subdividing the two areas, we looked at the use cases of artificial intelligence algorithms according to data characteristics and problem definitions and characteristics. Through this, we will increase our understanding of artificial intelligence technologies used in the digital health care field and examine the possibility of using various artificial intelligence technologies.

• International Journal of Advanced Culture Technology
• /
• v.10 no.1
• /
• pp.187-195
• /
• 2022

Since most of the first witnesses of cardiac arrest in clinical settings are nurses, the ability to perform CPR is important. The purpose of this study is to provide basic data for developing education that strengthens CPR performance in the future by examining inactive nurses' CPR knowledge, attitude, performance confidence, device discomfort, continued use intention, and educational achievement. The final subjects of this study were 88 inactive nurses residing in B city. The study period was from June 23, 2020 to December 24, 2020. The collected data were analyzed by descriptive statistics and Pearson correlation using SPSS WIN 24.0 program. After obtaining the subject's consent for the study, an inactive nurse who understood the purpose of the study and voluntarily consented to the study participated. To investigate the perception of experience, the subjects watched 360-degree virtual reality contents about CPR in the hospital using HMD. The data of this study were analyzed using SPSS WIN 22.0.program. As a result of this 360-degree study on CPR in the hospital, the average score for the inactive nurses on CPR knowledge was 12.70±3.43, the average score for performance confidence was 6.04±2.45, and the average score for attitude was 4.63±0.80. As a result of experience recognition of 360-degree virtual reality contents for CPR in hospitals, the average score for device discomfort was 4.01±0.94, the average score for continued use intention was 2.07±0.85, and the average score for educational achievement was 2.11±0.79. As a result of correlation analysis, educational achievement and continued use intention were significantly positively correlated (r=.77, p<.001). Based on the results of this study, in order to strengthen the CPR performance capability of inactive nurses in emergency situations, it is necessary to increase CPR knowledge and confidence in performing CPR, and to cultivate a positive attitude toward performing CPR. In addition, it is necessary to implement CPR simulation education based on patient cases by applying content that considers educational achievement and continuous use intention.

• Journal of Trauma and Injury
• /
• v.36 no.3
• /
• pp.172-179
• /
• 2023

Purpose: Out-of-hospital traumatic cardiac arrest (TCA) often has a poor prognosis despite rescue efforts. Although the incidence and mortality of out-of-hospital cardiac arrest have increased, bystander cardiopulmonary resuscitation (CPR) has decreased in some countries during the COVID-19 pandemic. In the prehospital setting, immediate treatment of cardiac arrest is required without knowing the patient's COVID-19 status. Because COVID-19 is usually transmitted through the respiratory tract, airway management can put medical personnel at risk for infection. This study explored whether on-scene treatments involving CPR for TCA patients changed during the COVID-19 pandemic in Korea. Methods: This retrospective study used data from emergency medical services (EMS) run sheets in Gangwon Province from January 2019 to December 2021. Patients whose initial problem was cardiac arrest and who received CPR were included. Data in 2019 were classified as pre-COVID-19 and all subsequent data (from 2020 and 2021) as post-COVID-19. Age, sex, possible cause of cardiac arrest, and treatments including airway maneuvers, oropharyngeal airway (OPA) or i-gel insertion, endotracheal intubation (ETI), bag-valve mask (BVM) ventilation, intravenous (IV) line establishment, neck collar application, and wound dressing with hemostasis were investigated. Results: During the study period, 2,007 patients received CPR, of whom 596 patients had TCA and 367 had disease-origin cardiac arrest (DCA). Among the patients with TCA, 192 (32.2%) were pre-COVID-19 and 404 (67.8%) were post-COVID-19. In the TCA group, prehospital treatments did not decrease. The average frequencies were 59.7% for airway maneuvers, 47.5% for OPA, 57.4% for BVM, and 51.3% for neck collar application. The rates of ETI, i-gel insertion, and IV-line establishment increased. The treatment rate for TCA was significantly higher than that for DCA. Conclusions: Prehospital treatments by EMS workers for patients with TCA did not decrease during the COVID-19 pandemic. Instead, the rates of ETI, i-gel insertion, and IV-line establishment increased.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.32-38
• /
• 2023

This study investigates the influence of particulate matter concentrations on the incidence of asthma, focusing on the delayed onset of symptoms and subsequent medical consultations. Analysis incorporates a four-day lag from the initiation of fine dust exposure and compares asthma patterns before and after the World Health Organization's (WHO) classification of fine dust as a Group 1 carcinogen in November 2013. Utilizing daily PM10 data and asthma-related medical visit counts in Seoul from 2008 to 2016, the study additionally incorporates Google search frequencies and newspaper article counts on fine dust to assess public awareness. Results reveal a surge in search frequencies and article publications after WHO announcement, indicating heightened public interest. To standardize the long-term asthma occurrence trend, the daily asthma patient numbers are ratio-adjusted based on annual averages. The analysis uncovers an increase in asthma medical visits 2 to 3 days after fine dust events. Additionally, greater public awareness of fine dust hazards correlates with a significant reduction in asthma occurrence after such events, even within 'normal' fine dust concentrations. Notably, behavioral changes, like limiting outdoor activities, contribute to this decrease. This study highlights the importance of analyzing accumulated medical data over an extended period to identify general public behavioral patterns, deviating from conventional survey methods in social sciences. Future research aims to extend data collection beyond 2016, exploring recent trends and considering the potential impact of decreased fine dust awareness amid the COVID-19 pandemic.

• Tuberculosis and Respiratory Diseases
• /
• v.52 no.2
• /
• pp.179-185
• /
• 2002

A bronchus-associated lymphoid tissue(BALT) lymphoma of the lung is a rare disorder of patients with Sj$\ddot{o}$gren's syndrome. A 49-year-old woman was admitted for an evaluation of exertional dyspnea and general weakness which had persisted for two years. The patient had suffered from dry mouth and dry eyes for five years. The physical examinations showed a coarse breath sound with inspiratory crackles on the whole lung field, particularly on the both basal lungs. The laboratory data disclosed high titers of anti-nuclear antibodies, and anti-SSA (Ro), and anti-SSB (La) antibodies. Chest radiographs demonstrated the presence of bilateral, diffuse, reticulonodular densities in both lungs. Thin-section CT scans showed diffusely distributed mosaic pattern of an inhomogeneous attenuation extending over the entire lung zone. The histological findings from an open-lung biopsy specimen revealed an accumulation of lymphoid cells around the bronchioles and an extension of malignant lymphoma cells from the bronchiolar epithelium toward the alveolar space. Immunohistochemically, the neoplastic cells reacted positively to the CD 20 antigen and were focally positive for the UCHL 1 antigen. The histological diagnosis was consistent with a low grade marginal zone B-cell lymphoma originating in the BALT. Here, we present a case of a histologically proven BALT lymphoma of the lung in a patient with primary Sj$\ddot{o}$gren's Syndrome.