Background: Acute deterioration of patients in general wards often leads to major adverse events (MAEs), including unplanned intensive care unit transfers, cardiac arrest, or death. Traditional early warning scores (EWSs) have shown limited predictive accuracy, with frequent false positives. We conducted a prospective observational external validation study of an artificial intelligence (AI)-based EWS, the VitalCare - Major Adverse Event Score (VC-MAES), at a tertiary medical center in the Republic of Korea. Methods: Adult patients from general wards, including internal medicine (IM) and obstetrics and gynecology (OBGYN)—the latter were rarely investigated in prior AI-based EWS studies—were included. The VC-MAES predictions were compared with National Early Warning Score (NEWS) and Modified Early Warning Score (MEWS) predictions using the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and logistic regression for baseline EWS values. False-positives per true positive (FPpTP) were assessed based on the power threshold. Results: Of 6,039 encounters, 217 (3.6%) had MAEs (IM: 9.5%, OBGYN: 0.26%). Six hours prior to MAEs, the VC-MAES achieved an AUROC of 0.918 and an AUPRC of 0.352, including the OBGYN subgroup (AUROC, 0.964; AUPRC, 0.388), outperforming the NEWS (0.797 and 0.124) and MEWS (0.722 and 0.079). The FPpTP was reduced by up to 71%. Baseline VC-MAES was strongly associated with MAEs (P<0.001). Conclusions The VC-MAES significantly outperformed traditional EWSs in predicting adverse events in general ward patients. The robust performance and lower FPpTP suggest that broader adoption of the VC-MAES may improve clinical efficiency and resource allocation in general wards.

OBJECTIVES: Stroke remains the second leading cause of death in Korea. This study was designed to estimate the crude, age-adjusted and age-specific incidence rates, as well as the case fatality rate of stroke, in Korea from 2011 to 2020. METHODS: We utilized data from the National Health Insurance Services from January 1, 2002 to December 31, 2020, to calculate incidence rates and 30-day and 1-year case fatality rates of stroke. Additionally, we determined sex and age-specific incidence rates and computed age-standardized incidence rates by direct standardization to the 2005 population. RESULTS: The crude incidence rate of stroke hovered around 200 (per 100,000 person-years) from 2011 to 2015, then surged to 218.4 in 2019, before marginally declining to 208.0 in 2020. Conversely, the age-standardized incidence rate consistently decreased by 25% between 2011 and 2020. When stratified by sex, the crude incidence rate increased between 2011 and 2019 for both sexes, followed by a decrease in 2020. Age-standardized incidence rates displayed a downward trend throughout the study period for both sexes. Across all age groups, the 30-day and 1-year case fatality rates of stroke consistently decreased from 2011 to 2019, only to increase in 2020. CONCLUSIONS Despite a decrease in the age-standardized incidence rate, the total number of stroke events in Korea continues to rise due to the rapidly aging population. Moreover, 2020 witnessed a decrease in incidence but an increase in case fatality rates.

A 35-year-old male presented with atypical aphasia following left anterior choroidal artery infarction associated with distal internal carotid artery dissection. He presented with 1) lexical-semantic deficit without semantic impairment, 2) frequent surface errors (both surface dyslexia and dysgraphia), and 3) intact non-word reading/repetition (preserved sub-lexical route), suggesting deficit in the phonological output lexicon. Diffusion-tensor tractography analysis revealed disruption in the inferior fronto-occipital fasciculus and inferior longitudinal fasciculus, which might serve as potential subcortical neural correlates for phonological output lexicon.