ABSTRACT
Background: During the coronavirus disease 2019 (COVID-19) pandemic, large-scale vaccinations have been performed worldwide without sufficient verification of safety profiles. So far, little is known about skin manifestations following COVID-19 vaccination in Korean patients. Objective: We investigated the epidemiological and clinical characteristics of patients who had skin manifestations following COVID-19 vaccination in Korea. Methods: We retrospectively reviewed me data of 123 patients that presented with skin manifestations within 1 month after COVID-19 vaccination from two tertiary referral hospitals in Korea. The types of COVID-19 vaccinations administered to the patients, demographics, comorbidities, and clinical course of the patients were obtained from the data. Statistical analyses of the extracted data were performed using Microsoft Excel. Results: Skin manifestations following COVID-19 vaccination were mostly observed in patients in their 40s (23.6%), according to our data. Urticarial eruption was the most common manifestation, followed by macular rash (17.1%) and papulosquamous eruption (17.1%). Notably, 70% of the patients showed delayed reactions. More than half of the patients showed a good prognosis, and their symptoms were relieved with conservative treatment, including corti-costeroids and antihistamines, even after additional vaccination. Conclusion: We statistically analyzed the prevalence and characteristics of skin manifestations after COVID-19 vaccination. Urticarial eruptions are the most common skin manifestations associated with the COVID-19 vacci¬nation. We believe that this real-world retrospective study will provide valuable information for doctors who treat patients with skin manifestations after COVID-19 vaccination by providing real-world experience in Korea. (Korean J Dermatol 2022;60(9):576~584). © 2022 Korean Dermatological Association. All rights reserved.
ABSTRACT
With the advancement of Artificial Intelligence technology, the development of various applied software and studies are actively conducted on detection, classification, and prediction through interdisciplinary convergence and integration. Among them, medical AI has been drawing huge interest and popularity in Computer-Aided Diagnosis, which collects human body signals to predict abnormal symptoms of health, and diagnoses diseases through medical images such as X-ray and CT. Since X-ray and CT in medicine use high-resolution images, they require high specification equipment and huge energy consumption due to high computation in learning and recognition, incurring huge costs to create an environment for operation. Thus, this paper proposes a chest X-ray outlier detection model using dimension reduction and edge detection to solve these issues. The proposed method scans an X-ray image using a window of a certain size, conducts difference imaging of adjacent segment-images, and extracts the edge information in a binary format through the AND operation. To convert the extracted edge, which is visual information, into a series of lines, it is computed in convolution with the detection filter that has a coefficient of 2n and the lines are divided into 16 types. By counting the converted data, a one-dimensional 16-size array per one segment-image is produced, and this reduced data is used as an input to the RNN-based learning model. In addition, the study conducted various experiments based on the COVID-chest X-ray dataset to evaluate the performance of the proposed model. According to the experiment results, the LFA-RNN showed the highest accuracy at 97.5% in the learning calculated through learning, followed by CRNN 96.1%, VGG 96.6%, AlexNet 94.1%, Conv1D 79.4%, and DNN 78.9%. In addition, LFA-RNN showed the lowest loss at about 0.0357. CCBY