• International Journal of Oral Biology
• /
• v.46 no.1
• /
• pp.1-6
• /
• 2021

Since the outbreak of coronavirus disease 2019 (COVID-2019), the infection has spread worldwide due to the highly contagious nature of severe acute syndrome coronavirus (SARS-CoV-2). To manage SARS-CoV-2, the development of diagnostic assays that can quickly and accurately identify the disease in patients is necessary. Currently, nucleic acid-based testing and serology-based testing are two widely used approaches. Of these, nucleic acid-based testing with quantitative reverse transcription-PCR (RT-qPCR) using nasopharyngeal (NP) and/or oropharyngeal (OP) swabs is considered to be the gold standard. Recently, the use of saliva samples has been considered as an alternative method of sample collection. Compared to the NP and OP swab methods, saliva specimens have several advantages. Saliva specimens are easier to collect. Self-collection of saliva specimens can reduce the risk of infection to healthcare providers and reduce sample collection time and cost. Until recently, the sensitivity and accuracy of the data obtained using saliva specimens for SARS-CoV-2 detection was controversial. However, recent clinical research has found that sensitive and reliable data can be obtained from saliva specimens using RT-qPCR, with approximately 81% to 95% correspondence with the data obtained from NP and OP swabs. These data suggest that self-collected saliva is an alternative option for the diagnosis of COVID-19.

• Korean Journal of Clinical Laboratory Science
• /
• v.52 no.4
• /
• pp.297-309
• /
• 2020

Coronaviruses were originally discovered as enzootic infections that limited to their natural animal hosts, but some strains have since crossed the animal-human species barrier and progressed to establish zoonotic diseases. Accordingly, cross-species barrier jumps resulted in the appearance of SARS-CoV, MERS-CoV, and SARS-CoV-2 that manifest as virulent human viruses. Coronaviruses contain four main structural proteins: spike, membrane, envelope, and nucleocapsid protein. The replication cycle is as follows: cell entry, genome translation, replication, assembly, and release. They were not considered highly pathogenic to humans until the outbreaks of SARS-CoV in 2002 in Guangdong province, China. The consequent outbreak of SARS in 2002 led to an epidemic with 8,422 cases, and a reported worldwide mortality rate of 11%. MERS-CoVs is highly related to camel CoVs. In 2019, a cluster of patients infected with 2019-nCoV was identified in an outbreak in Wuhan, China, and soon spread worldwide. 2019-nCoV is transmitted through the respiratory tract and then induced pneumonia. Molecular diagnosis based on upper respiratory region swabs is used for confirmation of this virus. This review examines the structure and genomic makeup of the viruses as well as the life cycle, diagnosis, and potential therapy.

• Journal of Platform Technology
• /
• v.10 no.1
• /
• pp.29-34
• /
• 2022

The emergence of new diseases such as the Covid 19 pandemic that occurs in the 21st century and the occurrence of health abnormalities according to the busy daily life of modern people are increasing. Accordingly, the importance of health care management and data-based health management is being highlighted, and in particular, interest in personal health management data based on personal health care data of patients is rapidly increasing. In this study, to solve the difficult problems of personal health management, we developed a personal health care platform incorporating IT for self-diagnosis and solution and developed an application that measures bio-signals generated in the human body and transmits them to the platform. A health management system was established. Through this, not only the health care of modern people, but also the psychological and emotional care support needs through psychological and emotional monitoring of the developmentally disabled and the vulnerable who have difficulty in expressing their opinions are to be addressed. In addition, the overall health and living environment data of the individual was integrated to develop an optimized medical and health management service for the individual.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.27-40
• /
• 2022

Medical AI, which has lately made significant advances, is playing a vital role, such as assisting clinicians with diagnosis and decision-making. The field of chest X-rays, in particular, is attracting a lot of attention since it is important for accessibility and identification of chest diseases, as well as the current COVID-19 pandemic. However, despite the vast amount of data, there remains a limit to developing an effective AI model due to a lack of labeled data. A research that used federated learning on chest X-ray data to lessen this difficulty has emerged, although it still has the following limitations. 1) It does not consider the problems that may occur in the Non-IID environment. 2) Even in the federated learning environment, there is still a shortage of labeled data of clients. We propose a method to solve the above problems by using the self-supervised learning model as a global model of federated learning. To that aim, we investigate a self-supervised learning methods suited for federated learning using chest X-ray data and demonstrate the benefits of adopting the self-supervised learning model for federated learning.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.49-59
• /
• 2023

Recently, attention to the pandemic situation represented by COVID-19 emerged problems caused by unexpected shortage of medical personnel. In this paper, we present a method for diagnosing the presence or absence of lesional sign on PA chest X-ray images as computer vision solution to support diagnosis tasks. Method for visual anomaly detection based on feature modeling can be also applied to X-ray images. With extracting feature vectors from PA chest X-ray images and divide to patch unit, region-specific abnormality can be detected. As preliminary experiment, we created simulation data set containing multiple objects and present results of the comparative experiments in this paper. We present method to improve both efficiency and performance of the process through hard masking of patch features to aligned images. By summing up regional specificity and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to previous studies. By aggregating region-specific and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to our last study.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.25 no.4
• /
• pp.327-336
• /
• 2021

In this paper, we will introduce the image processing methods for the remote pupillary light reflex measurement using the video taken by a general smartphone camera without a special device such as an infrared camera. We propose an algorithm for estimate the size of the pupil that changes with light using image data analysis without a learning process. In addition, we will introduce the results of visualizing the change in the pupil size by removing noise from the recorded data of the pupil size measured for each frame of the video. We expect that this study will contribute to the construction of an objective indicator for remote pupillary light reflex measurement in the situation where non-face-to-face communication has become common due to COVID-19 and the demand for remote diagnosis is increasing.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.463-468
• /
• 2022

The prolonged of the Post Corona made many industry's paradigm. It's become very important In the industries products that customers directly touch and use. To cope with this situation, The Cosmetics industry has recently introduced various untact services. many customers would like to try these new services. Typically, online survey services recommend personalized products. but these services reached its limit later. This paper research how to recommend products and define skine type with AI Image diagnosis module combine with legacy survey system.

• Pediatric Infection and Vaccine
• /
• v.30 no.1
• /
• pp.20-32
• /
• 2023

Purpose: This study aimed to identify the etiology and risk factors of community-acquired pneumonia (CAP) requiring hospitalization in Korean children during the coronavirus disease 2019 (COVID-19) pandemic. Methods: Clinical information of children admitted with CAP to Seoul National University Children's Hospital (SNUCH) between January 1, 2021, and February 28, 2022, was retrospectively collected and analyzed. In addition, the etiologic diagnosis and demographic data of children with CAP who were discharged at the other seven hospitals between January and February 2022 were collected. Pneumonia was diagnosed using strict criteria comprising clinical symptoms, physical examination findings, and chest radiographic findings. Results: Among 91 children hospitalized with CAP at SNUCH during the 14-month period, 68.4% were aged <5 years and 79.1% had underlying diseases. Among the 95 CAP cases, respiratory assistance was required in 70.5%, and the use of a ventilator was required in 20.0%. A total of five patients expired, all of whom were either immunocompromised or had underlying neurological diseases. Neurological diseases and immunosuppression were significantly correlated with respiratory assistance (P=0.003) and death (P=0.014). A total of 55% of the detected respiratory pathogens were viruses, the most common of which was rhinovirus at 35.9%. Among the 169 children hospitalized for CAP at the eight institutions, ≥1 respiratory virus was detected in 92.3%, among which respiratory syncytial virus (79.8%) was the most prevalent. Conclusions: Even during the COVID-19 pandemic, Korean children were hospitalized with CAP caused by seasonal respiratory viral pathogens. Although atypical and pyogenic bacteria were not detected, continuous clinical monitoring and further prospective studies should be conducted.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• Journal of Korean Society on Water Environment
• /
• v.40 no.1
• /
• pp.19-35
• /
• 2024

The global pandemic, coronavirus disease caused by Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has led to the implementation of wastewater surveillance as a means to monitor the spread of SARS-CoV-2 prevalence in the community. The challenging aspect of establishing wastewater surveillance requires a well-equipped laboratory for wastewater sample analysis. According to previous studies, RT-PCR-based molecular tests are the most widely used and popular detection method worldwide. However, this approach for the detection or quantification of SARS-CoV-2 from wastewater demands a specialized laboratory, skilled personnel, expensive instruments, and a workflow that typically takes 6 to 8 hours to provide results for a few samples. Rapid and reliable alternative detection methods are needed to enable less-well-qualified practitioners to set up and provide sensitive detection of SARS-CoV-2 within wastewater at regional laboratories. In some cases, the structural and molecular characteristics of SARS-CoV-2 are unknown, and various strategies for the correct diagnosis of COVID-19 have been proposed by research laboratories. The ongoing research and development of alternative and rapid technologies, namely RT-LAMP, ELISA, Biosensors, and GeneXpert, offer a wide range of potential options not only for SARS-CoV-2 detection but also for other viruses. This study aims to discuss the effective regional rapid detection and quantification methods in community wastewater.