Browsing by Subject "Emergency care systems"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Open Access
    Harnessing inter-disciplinary collaboration to improve emergency care in low- and middle-income countries (LMICs): results of research prioritisation setting exercise
    (2020-08-31) Lecky, Fiona E; Reynolds, Teri; Otesile, Olubukola; Hollis, Sara; Turner, Janette; Fuller, Gordon; Sammy, Ian; Williams-Johnson, Jean; Geduld, Heike; Tenner, Andrea G; French, Simone; Govia, Ishtar; Balen, Julie; Goodacre, Steve; Marahatta, Sujan B; DeVries, Shaheem; Sawe, Hendry R; El-Shinawi, Mohamed; Mfinanga, Juma; Rubiano, Andrés M; Chebbi, Henda; Do Shin, Sang; Ferrer, Jose M E; Haddadi, Mashyaneh; Firew, Tsion; Taubert, Kathryn; Lee, Andrew; Convocar, Pauline; Jamaluddin, Sabariah; Kotecha, Shahzmah; Yaqeen, Emad A; Wells, Katie; Wallis, Lee
    Abstract Background More than half of deaths in low- and middle-income countries (LMICs) result from conditions that could be treated with emergency care - an integral component of universal health coverage (UHC) - through timely access to lifesaving interventions. Methods The World Health Organization (WHO) aims to extend UHC to a further 1 billion people by 2023, yet evidence supporting improved emergency care coverage is lacking. In this article, we explore four phases of a research prioritisation setting (RPS) exercise conducted by researchers and stakeholders from South Africa, Egypt, Nepal, Jamaica, Tanzania, Trinidad and Tobago, Tunisia, Colombia, Ethiopia, Iran, Jordan, Malaysia, South Korea and Phillipines, USA and UK as a key step in gathering evidence required by policy makers and practitioners for the strengthening of emergency care systems in limited-resource settings. Results The RPS proposed seven priority research questions addressing: identification of context-relevant emergency care indicators, barriers to effective emergency care; accuracy and impact of triage tools; potential quality improvement via registries; characteristics of people seeking emergency care; best practices for staff training and retention; and cost effectiveness of critical care – all within LMICs. Conclusions Convened by WHO and facilitated by the University of Sheffield, the Global Emergency Care Research Network project (GEM-CARN) brought together a coalition of 16 countries to identify research priorities for strengthening emergency care in LMICs. Our article further assesses the quality of the RPS exercise and reviews the current evidence supporting the identified priorities.
  • Thumbnail Image
    Item
    Open Access
    Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning
    (2021-07-12) Karlsson, Adam; Stassen, Willem; Loutfi, Amy; Wallgren, Ulrika; Larsson, Eric; Kurland, Lisa
    Background Sepsis is a life-threatening condition, causing almost one fifth of all deaths worldwide. The aim of the current study was to identify variables predictive of 7- and 30-day mortality among variables reflective of the presentation of septic patients arriving to the emergency department (ED) using machine learning. Methods Retrospective cross-sectional design, including all patients arriving to the ED at Södersjukhuset in Sweden during 2013 and discharged with an International Classification of Diseases (ICD)-10 code corresponding to sepsis. All predictions were made using a Balanced Random Forest Classifier and 91 variables reflecting ED presentation. An exhaustive search was used to remove unnecessary variables in the final model. A 10-fold cross validation was performed and the accuracy was described using the mean value of the following: AUC, sensitivity, specificity, PPV, NPV, positive LR and negative LR. Results The study population included 445 septic patients, randomised to a training (n = 356, 80%) and a validation set (n = 89, 20%). The six most important variables for predicting 7-day mortality were: “fever”, “abnormal verbal response”, “low saturation”, “arrival by emergency medical services (EMS)”, “abnormal behaviour or level of consciousness” and “chills”. The model including these variables had an AUC of 0.83 (95% CI: 0.80–0.86). The final model predicting 30-day mortality used similar six variables, however, including “breathing difficulties” instead of “abnormal behaviour or level of consciousness”. This model achieved an AUC = 0.80 (CI 95%, 0.78–0.82). Conclusions The results suggest that six specific variables were predictive of 7- and 30-day mortality with good accuracy which suggests that these symptoms, observations and mode of arrival may be important components to include along with vital signs in a future prediction tool of mortality among septic patients presenting to the ED. In addition, the Random Forests appears to be a suitable machine learning method on which to build future studies.