Sudden out-of-hospital cardiac arrest is the most time-critical medical emergency. In the second paper of this Series on out-of-hospital cardiac arrest, we considered important issues in the prehospital management of cardiac arrest. Successful resuscitation relies on a strong chain of survival with the community, dispatch centre, ambulance, and hospital working together. Early cardiopulmonary resuscitation and defibrillation has the greatest impact on survival. If the community response does not restart the heart, resuscitation is continued by emergency medical services' staff. However, the best approaches for airway management and the effectiveness of currently used drug treatments are uncertain. Prognostic factors and rules for termination of resuscitation could guide the duration of a resuscitation attempt and decision to transport to hospital. If return of spontaneous circulation is achieved, the focus of treatment shifts to stabilisation, restoration of normal physiological parameters, and transportation to hospital for ongoing care.

Aim: The long-term stress, anxiety and job burnout experienced by healthcare workers (HCWs) are important to consider as the novel coronavirus disease (COVID-19) pandemic stresses healthcare systems globally. The primary objective was to examine the changes in the proportion of HCWs reporting stress, anxiety, and job burnout over six months during the peak of the pandemic in Singapore. The secondary objective was to examine the extent that objective job characteristics, HCW-perceived job factors, and HCW personal resources were associated with stress, anxiety, and job burnout. Method: A sample of HCWs (doctors, nurses, allied health professionals, administrative and operations staff; N = 2744) was recruited via invitation to participate in an online survey from four tertiary hospitals. Data were gathered between March-August 2020, which included a 2-month lockdown period. HCWs completed monthly web-based self-reported assessments of stress (Perceived Stress Scale-4), anxiety (Generalized Anxiety Disorder-7), and job burnout (Physician Work Life Scale). Results: The majority of the sample consisted of female HCWs (81%) and nurses (60%). Using random-intercept logistic regression models, elevated perceived stress, anxiety and job burnout were reported by 33%, 13%, and 24% of the overall sample at baseline respectively. The proportion of HCWs reporting stress and job burnout increased by approximately 1·0% and 1·2% respectively per month. Anxiety did not significantly increase. Working long hours was associated with higher odds, while teamwork and feeling appreciated at work were associated with lower odds, of stress, anxiety, and job burnout. Conclusions: Perceived stress and job burnout showed a mild increase over six months, even after exiting the lockdown. Teamwork and feeling appreciated at work were protective and are targets for developing organizational interventions to mitigate expected poor outcomes among frontline HCWs.

ACADEMIC EMERGENCY MEDICINE 2011; 18:890–897 © 2011 by the Society for Academic Emergency Medicine Abstract Disease-based registries can form the basis of comparative research to improve and inform policy for optimizing outcomes, for example, in out-of-hospital cardiac arrest (OHCA). Such registries are often lacking in resource-limited countries and settings. Anecdotally, survival rates for OHCA in Asia are low compared to those in North America or Europe, and a regional registry is needed. The Pan-Asian Resuscitation Outcomes Study (PAROS) network of hospitals was established in 2009 as an international, multicenter, prospective registry of OHCA across the Asia-Pacific region, to date representing a population base of 89 million in nine countries. The network’s goal is to provide benchmarking against established registries and to generate best practice protocols for Asian emergency medical services (EMS) systems, to impact community awareness of prehospital emergency care, and ultimately to improve OHCA survival. Data are collected from emergency dispatch, ambulance providers, emergency departments, and in-hospital collaborators using standard protocols. To date (March 2011), there are a total of 9,302 patients in the database. The authors expect to achieve a sample size of 13,500 cases over the next 2 years of data collection. The PAROS network is an example of a low-cost, self-funded model of an Asia-Pacific collaborative research network with potential for international comparisons to inform OHCA policies and practices. The model can be applied across similar resource-limited settings.

Background: Risk scores can be useful in clinical risk stratification and accurate allocations of medical resources, helping health providers improve patient care. Point-based scores are more understandable and explainable than other complex models and are now widely used in clinical decision making. However, the development of the risk scoring model is nontrivial and has not yet been systematically presented, with few studies investigating methods of clinical score generation using electronic health records. Objective: This study aims to propose AutoScore, a machine learning–based automatic clinical score generator consisting of 6 modules for developing interpretable point-based scores. Future users can employ the AutoScore framework to create clinical scores effortlessly in various clinical applications. Methods: We proposed the AutoScore framework comprising 6 modules that included variable ranking, variable transformation, score derivation, model selection, score fine-tuning, and model evaluation. To demonstrate the performance of AutoScore, we used data from the Beth Israel Deaconess Medical Center to build a scoring model for mortality prediction and then compared the data with other baseline models using the receiver operating characteristic analysis. A software package in R 3.5.3 (R Foundation) was also developed to demonstrate the implementation of AutoScore. Results: Implemented on the data set with 44,918 individual admission episodes of intensive care, the AutoScore-created scoring models performed comparably well as other standard methods (ie, logistic regression, stepwise regression, least absolute shrinkage and selection operator, and random forest) in terms of predictive accuracy and model calibration but required fewer predictors and presented high interpretability and accessibility. The nine-variable, AutoScore-created, point-based scoring model achieved an area under the curve (AUC) of 0.780 (95% CI 0.764-0.798), whereas the model of logistic regression with 24 variables had an AUC of 0.778 (95% CI 0.760-0.795). Moreover, the AutoScore framework also drives the clinical research continuum and automation with its integration of all necessary modules. Conclusions: We developed an easy-to-use, machine learning–based automatic clinical score generator, AutoScore; systematically presented its structure; and demonstrated its superiority (predictive performance and interpretability) over other conventional methods using a benchmark database. AutoScore will emerge as a potential scoring tool in various medical applications.