Deep-learning model for screening sepsis using electrocardiography.

BACKGROUND: Sepsis is a life-threatening organ dysfunction and a major healthcare burden worldwide. Although sepsis is a medical emergency that requires immediate management, screening for the occurrence of sepsis is difficult. Herein, we propose a deep learning-based model (DLM) for screening sepsis using electrocardiography (ECG). METHODS: This retrospective cohort study included 46,017 patients who were admitted to two hospitals. A total of 1,548 and 639 patients had sepsis and septic shock, respectively. The DLM was developed using 73,727 ECGs from 18,142 patients, and internal validation was conducted using 7774 ECGs from 7,774 patients. Furthermore, we conducted an external validation with 20,101 ECGs from 20,101 patients from another hospital to verify the applicability of the DLM across centers. RESULTS: During the internal and external validations, the area under the receiver operating characteristic curve (AUC) of the DLM using 12-lead ECG was 0.901 (95% confidence interval, 0.882-0.920) and 0.863 (0.846-0.879), respectively, for screening sepsis and 0.906 (95% confidence interval (CI), 0.877-0.936) and 0.899 (95% CI, 0.872-0.925), respectively, for detecting septic shock. The AUC of the DLM for detecting sepsis using 6-lead and single-lead ECGs was 0.845-0.882. A sensitivity map revealed that the QRS complex and T waves were associated with sepsis. Subgroup analysis was conducted using ECGs from 4,609 patients who were admitted with an infectious disease, and the AUC of the DLM for predicting in-hospital mortality was 0.817 (0.793-0.840). There was a significant difference in the prediction score of DLM using ECG according to the presence of infection in the validation dataset (0.277 vs. 0.574, p < 0.001), including severe acute respiratory syndrome coronavirus 2 (0.260 vs. 0.725, p = 0.018). CONCLUSIONS: The DLM delivered reasonable performance for sepsis screening using 12-, 6-, and single-lead ECGs. The results suggest that sepsis can be screened using not only conventional ECG devices but also diverse life-type ECG machines employing the DLM, thereby preventing irreversible disease progression and mortality.

Nurses' duty to care during the COVID-19 pandemic: a cross-sectional survey.

BACKGROUND: Despite the increased demand for nurses worldwide, discussion of nurses' duty to care is lacking. This study aimed to examine nurses' duty to care during the coronavirus disease 2019 (COVID-19) pandemic and to identify the influencing factors. METHODS: This was a cross-sectional descriptive research study that used a structured online questionnaire. Registered Korean nurses answered a demographic questionnaire and the Nash Duty to Care Scale. RESULTS: Age and employment at tertiary hospitals increased nurses' duty to care. Male sex, a highly educated status, and employment at tertiary hospitals increased the perceived risk. Male sex and employment at tertiary or general hospitals increased confidence in the employer, while a high level of education and a longer total clinical career decreased the same. Age and a higher monthly wage increased perceived obligation. Age, lack of religious beliefs, and clinical experience of 3-7 years increased professional preparedness. CONCLUSION: Without enough nursing manpower, the disaster response system could prove to be inefficient. Considering that adequate nurse staffing is essential in disaster management, it is crucial to ensure that nurses have a will to provide care in the case of disaster. In the future, a more active discussion on nurses' duty to care and additional research on factors that may hinder and facilitate the same are needed.

The Differential Consequences of Fear, Anger, and Depression in Response to COVID-19 in South Korea.

Studies on previous outbreaks of contagious diseases suggest that the impact of the emotions associated with an epidemic can be greater than that of the epidemic in terms of the number of people affected. This study explores the relationships between the three most commonly expressed emotional responses to the COVID-19 pandemic (fear, anger, and depression) and two outcome variables (compliance with the social-distancing policy and the stigmatization of those infected by COVID-19). A large online, public opinion survey was conducted in South Korea (n = 1000) between 4 and 11 June 2020, which was between the first and the second waves of COVID-19. A series of regression analyses suggest that the emotional response was accompanied by differential behavioral and perceptual consequences. Fear was consistently positively related to all indicators of compliance with social-distancing policies (the voluntary practice of social distancing, support for the "routine-life-distancing" policy, and support for stronger social-distancing policies). Anger was positively related to both stigmatization indicators (responsibility attribution and stigmatizing attitude toward people infected with COVID-19). Finally, depression showed negative relationships with support for the "routine-life-distancing" policy and for stronger social-distancing policies but a positive relationship with the voluntary practice of social distancing. By examining whether and how certain types of emotional responses are more or less related to compliance with social distancing and stigmatization, the present study provides practical implications for effective public communication during an epidemic such as COVID-19.

Determinants of adherence to personal preventive behaviours based on the health belief model: a cross-sectional study in South Korea during the initial stage of the COVID-19 pandemic.

BACKGROUND: Along with the rapid transmission of COVID-19, adherence to preventive behaviours plays a crucial role with respect to the control of COVID-19. However, different individuals' psychological characteristics and risk perception result in various forms of response to preventive behaviours. Based on the Health Belief Model, this study identifies the factors associated with preventive behaviours towards COVID-19 in South Korea during the initial stage of the COVID-19 pandemic. METHODS: A cross-sectional study was conducted in April 2020 through an anonymous online survey. A total of 1207 people in the age bracket of 20-59 years participated in the survey. Single and multiple linear regression analyses were conducted to identify the determinants of preventive behaviours against COVID-19. RESULTS: The following factors were associated with preventive behaviours towards COVID-19: female gender (ß = .124, p < 0.001), has a master's degree or above (ß = 0.065, p = 0.010), perceived susceptibility (ß = .197, p < 0.001), self-efficacy (ß = .404, p < 0.001), trust in radio (ß = -.080, p = .006), trust in official government website (ß = .057, p = .045), trust in social networks (ß = .054, p = .033), and trust in family and friends (ß = .068, p = .009), with an explanatory power of 41.5% (R2 = 0.415). CONCLUSIONS: To flatten the epidemic curve, it is important to understand the public's risk perception and the motivation behind behavioural responses that aim to promote preventive behaviours among the public. Thus, this study calls for the provision of accessible and credible information sources and demonstrates a public health campaign that encourages the public's engagement in preventive behaviours towards COVID-19.