Evaluation of the Overall Accuracy of the Combined Early Warning Scoring Systems in the Prediction of In-Hospital Mortality

Introduction Deterioration of clinical condition of in-hospital patients further leads to intensive care unit (ICU) transfer or death which can be reduced by the use of prediction tools. The early warning scoring (EWS) system is a prediction tool used in monitoring medical patients in hospitals, hospital staying length, and inpatient mortality. The present study evaluated four different EWS systems for the prediction of patient survival. Method The present prospective observational study has analyzed 217 patients visiting the emergency department from November 2016 to November 2018, followed by demographic and clinical data collection. Modified Early Warning Score (MEWS), Triage Early Warning Score (TEWS), Leed's Early Warning Score (LEWS), and patient-at-risk scores (PARS) were assigned based upon body temperature, consciousness level, heart rate, blood pressure, respiratory rate, mobility, etc. Data was analyzed with the help of R 4.0.4 (R Foundation, Vienna, Austria) and Microsoft Excel (Microsoft, Redmond, Washington). Results Out of these 217 patients, 205 got shifted to a ward, and 12 died, amongst which the majority belonged to the 31-40 age group. Among patients admitted to ICU had a MEWS greater than 3, TEWS within the range 0 to 2 and 3 to 5, LEWS greater than 7, and PARS greater than 5 on the initial days of admission. The patients who died and those who were shifted to the ward showed significant differences in EWS. A significant association was observed between all the EWS and patient outcomes (p<0.001). Conclusion MEWS, TEWS, LEWS, and PARS were effective in the prediction of inpatient mortality as well as admission to the ICU. With the increase in the EWS, there was an increase in the duration of ICU stay and a decrease in chances of survival.