The ability of the National Early Warning Score (NEWS) to discriminate patients at risk of early cardiac arrest, unanticipated intensive care unit admission, and death.

By Gary B. Smith, D. Prytherch, P. Meredith, P. Schmidt, P. Featherstone. 2013

1,004 citations recorded by the source corpus.

Subfields: Epidemiology, Public Health, Environmental and Occupational Health, Surgery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Epidemiology

In Surgery

Citations in the corpus

AutoScore: A Machine Learning–Based Automatic Clinical Score Generator and Its Application to Mortality Prediction Using Electronic Health Records (2020, background): “Accurate identification of patients at risk can be useful for appropriate allocations of medical resources [2-4].”
Scalable and accurate deep learning with electronic health records (2018, methodology): “For mortality, we used a logistic model with variables inspired by NEWS [50] score but added additional variables to make it more accurate, including the most recent systolic blood pressure, heart rate, respiratory rate, temperature, and we used 24 common lab tests, like the white-blood cell count, ”
Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier (2017, methodology): “, 2006) and NEWS score (Smith et al., 2013) are two of the more common scores used to assess overall clinical deterioration.”
What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use (2019, methodology): “The uptake and sustained use of ML in healthcare has been more challenging than anticipated, as observed through piloting models for cardiac arrest (Smith et al., 2013) and sepsis (Masino et al., 2019; Elish, 2018).”
The Importance of Respiratory Rate Monitoring: From Healthcare to Sport and Exercise (2020, background): “The NEWS assigns a score to f R values outside of the 12–20 breaths/min range, with the highest score attributed to f R values≤8 and ≥25 breaths/min [112], while the highest score for MEWS is attributed to f R values≥30 breaths/min [113].”
Development, Implementation, and Evaluation of an In-Hospital Optimized Early Warning Score for Patient Deterioration (2020, methodology): “We compared this to the performance of the NEWS.1 We used the bootstrap to construct 95% confidence intervals (CIs) and compare model performance14 using the pROC15 package in R.”
Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards (2016, methodology): “…a probability threshold versus the percentage of observations detected that were followed by an outcome (i.e. sensitivity), previously described as an “early warning score efficiency curve,” was created for the logistic regression models, MEWS, and the most accurate machine learning method (14).”
An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest (2018, background): “5 to 24 hours before the outcomes.(28,29) It is important to note that the prediction unit was not the patient but the input vector.”
Predicting in-hospital mortality and unanticipated admissions to the intensive care unit using routinely collected blood tests and vital signs: Development and validation of a multivariable model (2018, methodology): “To be comparable to the original NEWS and LDT-EWS publications [3,14] and increase case-mix homogeneity in hospital, we validate the risk index using emergency medical admissions.”
Barriers and facilitators related to the implementation of a physiological track and trigger system: A systematic review of the qualitative evidence (2017, methodology): “A single composite score is generated and can be used by the medical team to determine the stability of the patient’s condition and to inform decisions regarding any changes in care [11, 12].”
Coarse race data conceals disparities in clinical risk score performance (2023, methodology): “For existing clinical scores, we study two measures for patient triage: the National Early Warning Score (NEWS; Smith et al. (2013)) and the more-specialized Cardiac Arrest Risk Triage (CART; Churpek et al. (2012)).”