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.

Unhealthy lifestyle behaviors such as smoking, alcohol consumption, and physical inactivity (multiple risks) often lead to serious health consequence and impaired health status. The purpose of this study was to investigate the trend in health-related behavioral factors over time among adults in South Korea (hereafter Korea). The data of 1,595,842 Koreans older than 19 years who participated in the 2008-2014 Korea Community Health Survey were analyzed to assess the trend in the prevalence of behavioral risk factors. Individual or clustering health-related behaviors were assessed according to sex, age, and region among 228,712 adults who participated in the 2014 survey. From 2008 to 2014, the age-adjusted prevalence of obesity and high-risk alcohol use increased the prevalence of male current smoking and marginally decreased walking ability. Over 7 years, the percentage of adults who reported having all three healthy behaviors (i.e., currently not smoking, not consuming alcohol or having high-risk alcohol use, and engaging in walking) decreased from 35.2% in 2008 to 29.6% in 2014. Increased efforts to emphasize multiple health-related behavioral risk factors, including reducing alcohol use and smoking, and to encourage walking are needed in the thirties and forties age groups in Korea.
Adult* ; Alcohol Drinking ; Health Surveys* ; Humans ; Korea ; Life Style ; Male ; Obesity ; Prevalence ; Risk Factors ; Smoke ; Smoking ; Walking

In 2008, Korea Centers for Disease Control and Prevention initiated the first nationwide survey, Korea Community Health Survey (KCHS), to provide data that could be used to plan, implement, monitor, and evaluate community health promotion and disease prevention programs. This community-based cross-sectional survey has been conducted by 253 community health centers, 35 community universities, and 1500 interviewers. The KCHS standardized questionnaire was developed jointly by the Korea Centers for Disease Control and Prevention staff, a working group of health indicators standardization subcommittee, and 16 metropolitan cities and provinces with 253 regional sites. The questionnaire covers a variety of topics related to health behaviors and prevention, which is used to assess the prevalence of personal health practices and behaviors related to the leading causes of disease, including smoking, alcohol use, drinking and driving, high blood pressure control, physical activity, weight control, quality of life (European Quality of Life-5 Dimensions, European Quality of Life-Visual Analogue Scale, Korean Instrumental Activities of Daily Living ), medical service, accident, injury, etc. The KCHS was administered by trained interviewers, and the quality control of the KCHS was improved by the introduction of a computer-assisted personal interview in 2010. The KCHS data allow a direct comparison of the differences of health issues among provinces. Furthermore, the provinces can use these data for their own cost-effective health interventions to improve health promotion and disease prevention. For users and researchers throughout the world, microdata (in the form of SAS files) and analytic guidelines can be downloaded from the KCHS website (http://KCHS.cdc.go.kr/) in Korean.