Comparing the effectiveness of three scoring systems in predicting adult patient outcomes in the emergency department

Abstract

This study aimed to evaluate the performance of the rapid acute physiology score (RAPS), the rapid emergency medicine score (REMS), and the modified early warning score (MEWS) in predicting the outcomes of adult patients presenting to the emergency department (ED).A retrospective review was undertaken between February 2014 and February 2018 in an adult ED of a 3300-bed university hospital. The RAPS, REMS, and MEWS were calculated to assess their capability to predict hospital admission, length of hospital stay, and in-hospital mortality, using area under receiver operating characteristic analysis. Multivariate analysis was used to identify variables that were independent predictors of the outcomes.We included 39,977 patients who had presented to the ED during 48 consecutive months, of whom 4857 were admitted and 213 died in hospital. The predictabilities of REMS, RAPS, and MEWS for hospital admission were 0.76, 0.59, and 0.55, respectively; the predictability of REMS, RAPS, and MEWS for hospital mortality were 0.88, 0.72, and 0.73, respectively; and the predictability of REMS, RAPS, and MEWS for length of hospital stay were 0.76, 0.67, and 0.65, respectively. Multivariate analysis showed that the Glasgow coma scale (GCS) (odds ratio (OR), 1.61; P < .001), age (OR, 1.50; P < .001), and MAP (OR, 1.27; P < .001) were independent predictors for hospital admission; GCS (OR, 2.92; P < .001), respiratory rate (RR) (OR, 2.69; P < .001), peripheral oxygen saturation (OR, 2.67; P < .001), MAP (OR, 2.11; P < .001), age (OR, 1.75; P < .001), and pulse rate (PR) (OR, 1.73; P < .001) were independent predictors for in-hospital mortality; and RR (OR, 1.41; P < .001), temperature (OR, 1.05; P = .01), and PR (OR, 0.96; P = .04) were independent predictors for length of hospital stay.Our study evaluated and confirmed the REMS as a powerful predictor of ED adult patient outcomes, including hospital admission, length of hospital stay, and in-hospital mortality compared to RAPS and MEWS.

Figure 1

Receiver operating curves for predicting hospital admission according to REMS, RAPS, and MEWS. REMS (AUROC: 0.756, Hosmer-Lemeshow statistic P value < .001); MEWS (AUROC: 0.551, Hosmer-Lemeshow statistic P value < .001); RAPS (AUROC: 0.592, Hosmer-Lemeshow statistic P value < .001). MEWS = modified early warning score, PPV = positive predictive value, RAPS = rapid acute physiology score, REMS = rapid emergency medicine score.

Figure 2

Receiver operating curves for predicting mortality according to REMS, RAPS, and MEWS. REMS (AUROC: 0.886, Hosmer-Lemeshow statistic P value < .001); MEWS (AUROC: 0.728, Hosmer Lemeshow statistic P value < .001); RAPS (AUROC: 0.733, Hosmer Lemeshow statistic P value < .001). MEWS = modified early warning score, RAPS = rapid acute physiology score, REMS = rapid emergency medicine score.

Figure 3

Receiver operating curves for predicting length of hospital stay according to REMS, RAPS, and MEWS. REMS (AUROC: 0.762, Hosmer-Lemeshow statistic P value < .001); MEWS (AUROC: 0.645, Hosmer-Lemeshow statistic P value < .001); RAPS (AUROC: 0.668, Hosmer-Lemesh-ow statistic P value < .001). MEWS = modified early warning score, RAPS = rapid acute physiology score, REMS = rapid emergency medicine score.