Modified National Early Warning Score (MNEWS) in predicting the mortality of intensive care unit patients

Area of Science:

• Critical Care Medicine
• Health Informatics
• Biostatistics

Background:

• The National Early Warning Score (NEWS) is widely used but may require refinement for specific patient populations.
• Predicting mortality in intensive care unit (ICU) patients is crucial for resource allocation and treatment planning.
• Existing scoring systems like APACHE II can be complex and may not fully capture patient acuity.

Purpose of the Study:

• To develop a simplified and accurate scoring system, the Modified National Early Warning Score (MNEWS), based on NEWS.
• To enhance the prediction of mortality for intensive care unit (ICU) patients.
• To compare the predictive performance of MNEWS against NEWS and APACHE II.

Main Methods:

• Utilized data from the Medical Information Mart for Intensive Care (MIMIC)-III and -IV databases for derivation and a separate cohort for validation.
• Calculated the Modified National Early Warning Score (MNEWS) for all included patients.
• Employed Area Under the Receiver Operating Characteristic (AUROC) analysis to evaluate discrimination and the Hosmer-Lemeshow test for calibration.

Main Results:

• The MNEWS demonstrated superior performance in predicting hospital and 90-day mortality compared to NEWS and APACHE II.
• An optimal MNEWS cutoff of 11 was identified, with scores ≥11 indicating significantly shorter survival.
• MNEWS exhibited high calibration ability in predicting hospital mortality, validated across different patient cohorts.

Conclusions:

• The Modified National Early Warning Score (MNEWS) is a simple yet accurate tool for assessing the severity of ICU patients.
• MNEWS provides reliable prediction of patient outcomes, including mortality.
• This scoring system can aid clinicians in better evaluating and managing critically ill patients.