Publications by authors named "Weon Jung"
Temporary Telemedicine Policy and Chronic Disease Management in South Korea: Retrospective Analysis Using National Claims Data.
JMIR Public Health Surveill
November 2024
Article Synopsis
- The study analyzed the effectiveness and safety of telemedicine for chronic diseases in South Korea during the COVID-19 pandemic, focusing on a temporary telemedicine policy.
- It utilized national health insurance claims data from before and after the policy's implementation, comparing patients who used telemedicine with those who did not across four chronic diseases.
- Results indicated that telemedicine improved medication adherence for hypertension and diabetes without increasing hospital admissions, while those who did not use telemedicine faced higher admission rates.
Article Synopsis
- A study developed a machine learning prediction model for post-donation kidney function in living donors, using data from 823 individuals to improve donor selection.
- The best-performing model, XGBoost, demonstrated strong accuracy in estimating eGFR, showing the importance of various health metrics in predicting kidney function post-donation.
- A user-friendly web application called Kidney Donation with Nephrologic Intelligence (KDNI) was created to facilitate the use of this prediction model in clinical settings.
A knowledgebase (KB) transition of a clinical decision support (CDS) system occurred at the study site. The transition was made from one commercial database to another, provided by a different vendor. The change was applied to all medications in the institute.
View Article and Find Full Text PDFArticle Synopsis
- To improve resuscitation outcomes during cardiac emergencies, the PReCAP model was created to predict the likelihood of return of spontaneous circulation (ROSC) at the scene of an out-of-hospital cardiac arrest (OHCA).
- This model analyzes various prehospital data from the Pan-Asian Resuscitation Outcome Study (PAROS) database, which includes a significant number of patients, to provide real-time predictions on key survival metrics.
- The PReCAP model shows strong predictive capabilities with AUROC scores ranging from 0.80 to 0.93 for different outcomes, indicating its potential use across diverse populations and locations.
Article Synopsis
- The study aims to predict latent shock in patients by analyzing sequential changes in vital signs during emergency department visits.
- Researchers used a large dataset of over 93,000 ED visits and applied various machine learning models, including logistic regression and neural networks, to create and validate their prediction model.
- The model showed promising results, with AUROC values indicating strong predictive capability, outperforming traditional methods like the shock index in forecasting latent shock up to three hours in advance.
Article Synopsis
- Post-donation kidney health is a significant concern for living kidney donors, particularly due to varying risks based on age and health conditions.
- A prediction model, developed using machine learning and including data from 823 donors, assesses expected kidney function after donation.
- The model demonstrated strong predictive accuracy, aiding clinical decisions through an accessible web-based tool for evaluating renal adaptation post-donation.
Background: In South Korea, after the spread of the Middle East Respiratory Syndrome epidemic was aggravated by long stays in crowded emergency departments (EDs), a 24-hour target policy for EDs was introduced to prevent crowding and reduce patients' length of stay (LOS). The policy requires at least 95% of all patients to be admitted, discharged or transferred from an ED within 24 hours of arrival. This study analyzes the effects of the 24-hour target policy on ED LOS and compliance rates and describes the consequences of the policy.
View Article and Find Full Text PDFBackground: Alert fatigue is unavoidable when many irrelevant alerts are generated in response to a small number of useful alerts. It is necessary to increase the effectiveness of the clinical decision support system (CDSS) by understanding physicians' responses.
Objective: This study aimed to understand the CDSS and physicians' behavior by evaluating the clinical appropriateness of alerts and the corresponding physicians' responses in a medication-related passive alert system.
The study aims to measure the effectiveness of an AI-based traumatic intracranial hemorrhage prediction model in the decisions of emergency physicians regarding ordering head computed tomography (CT) scans. We developed a deep-learning model for predicting traumatic intracranial hemorrhages (DEEPTICH) using a national trauma registry with 1.8 million cases.
View Article and Find Full Text PDFArticle Synopsis
- The study investigates how COVID-19 changed emergency department isolation protocols, leading to higher rates of patients leaving without being seen (LWBS), particularly among those with fever or respiratory symptoms.
- Researchers compared emergency department visits before and after the pandemic, finding that the proportion of patients with fever or respiratory symptoms decreased and the LWBS rate for these patients surged from 2.8% to 19.2%.
- Results showed a significant link between having fever/respiratory symptoms, the impact of the COVID-19 pandemic, and increased LWBS rates, highlighting concerns for healthcare access in this patient group.
: The aim of this study is to describe the temporal change in alert override with a minimally interruptive clinical decision support (CDS) on a Next-Generation electronic medical record (EMR) and analyze factors associated with the change. : The minimally interruptive CDS used in this study was implemented in the hospital in 2016, which was a part of the new next-generation EMR, Data Analytics and Research Window for Integrated kNowledge (DARWIN), which does not generate modals, 'pop-ups' but show messages as in-line information. The prescription (medication order) and alerts data from July 2016 to December 2017 were extracted.
View Article and Find Full Text PDFThe expression of the CD3zeta subunit was investigated in fresh (uncultured) tumor-infiltrating lymphocytes (TILs) isolated from either solid tumor (ST) specimens or ascites (ASC) from patients with epithelial ovarian carcinoma (EOC). Western blot analysis of CD3zeta immunoprecipitates using anti-CD3zeta rabbit serum revealed that in 6 out of 6 patients with EOC, the CD3zeta protein was absent from ST-TILs. Immunoprecipitation with anti-phosphotyrosine monoclonal antibody (anti-PY20) from ST-TILs from one patient revealed bands co-migrating with the phosphorylated CD3zeta.
View Article and Find Full Text PDF