Dynamic individual vital sign trajectory early warning score (DyniEWS) versus snapshot national early warning score (NEWS) for predicting postoperative deterioration

Abstract

Aims: International early warning scores (EWS) including the additive National Early Warning Score (NEWS) and logistic EWS currently utilise physiological snapshots to predict clinical deterioration. We hypothesised that a dynamic score including vital sign trajectory would improve discriminatory power. Methods: Multicentre retrospective analysis of electronic health record data from postoperative patients admitted to cardiac surgical wards in four UK hospitals. Least absolute shrinkage and selection operator-type regression (LASSO) was used to develop a dynamic model (DyniEWS) to predict a composite adverse event of cardiac arrest, unplanned intensive care re-admission or in-hospital death within 24 h. Results: A total of 13,319 postoperative adult cardiac patients contributed 442,461 observations of which 4234 (0.96%) adverse events in 24 h were recorded. The new dynamic model (AUC = 0.80 [95% CI 0.78À0.83], AUPRC = 0.12 [0.10À0.14]) outperforms both an updated snapshot logistic model (AUC = 0.76 [0.73À0.79], AUPRC = 0.08 [0.60À0.10]) and the additive National Early Warning Score (AUC = 0.73 [0.70À0.76], AUPRC = 0.05 [0.02 À0.08]). Controlling for the false alarm rates to be at current levels using NEWS cutoffs of 5 and 7, DyniEWS delivers a 7% improvement in balanced accuracy and increased sensitivities from 41% to 54% at NEWS 5 and 18%À30% at NEWS 7. Conclusions: Using an advanced statistical approach, we created a model that can detect dynamic changes in risk of unplanned readmission to intensive care, cardiac arrest or in-hospital mortality and can be used in real time to risk-prioritise clinical workload.

Trajectories of vital signs in patients with Covid-19

“… 1 Given the paucity of published research in vital sign trends to predict clinical deterioration, this is an opportune addition to the literature. 2 , 3 Our recent multicentre paper also highlights the potential added value of inclusion of dynamic trajectory and inspired FiO 2 in a postoperative population 3 .…”

“…The binary weighting of oxygen therapy and consequent failure to detect increasing oxygen requirements has been of longstanding concern to cardiothoracic centres since NEWS was conceived in 2012. 4 We totally endorse the clear take home message that ‘early warning scores (EWS) could be enhanced by accounting for the degree of oxygen usage.’ 1 , 3 , 4 …”

“…In conclusion, the Oxford Covid-19 and cardiac surgical papers collectively make a powerful case for subdividing oxygen therapy based on inspired FiO2. 1 , 3 , 4 Current snapshot approaches do not reflect best use of existing data. Finally, the absence of major changes in heart rate, blood pressure and temperature in Covid-19 appears to challenge the basic premise of NEWS2 that one standard scoring system is suitable for all adult in-patients without type 2 respiratory failure.…”

Finally good NEWS: Something simple is working in COVID-19!

“…The National Early Warning Score (NEWS) is now over 15 years old and has been validated across a number of conditions and in different healthcare settings: NEWS has been used to predict outcomes with COPD 1 , after surgery 2 , in frail elderly patients 3 , pancreatitis 4 and many other conditions often by adapting it or comparing it to other scoring systems.…”

Reply to: Performance of the National Early Warning Score in hospitalised patients infected by Covid-19

“…We did not undertake a separate analysis of failed escalations resulting from any theoretical impact that the binary weighting of NEWS2 may have on model performance but did suggest that future research could investigate this hypothesis and cited the RCP guidance as the appropriate reference. We had no reason to cite or discuss the work of the Cambridge group into the impact of estimated F i O 2 on NEWS/NEWS2 values 4 , 5 in our publication, as its studies were conducted in patients following cardiac surgery and their findings may not be transferrable to patients with COVID-19 infections.…”