Preserving Informative Presence: How Missing Data and Imputation Strategies Affect the Performance of an AI-Based Early Warning Score

Abstract

Background/Objectives: Data availability can affect the performance of AI-based early warning scores (EWSs). This study evaluated how the extent of missing data and imputation strategies influence the predictive performance of the VitalCare-Major Adverse Event Score (VC-MAES), an AI-based EWS that uses last observation carried forward and normal-value imputation for missing values, to forecast clinical deterioration events, including unplanned ICU transfers, cardiac arrests, or death, up to 6 h in advance. Methods: We analyzed real-world data from 6039 patient encounters at Keimyung University Dongsan Hospital, Republic of Korea. Performance was evaluated under three scenarios: (1) using only vital signs and age, treating all other variables as missing; (2) reintroducing a full set of real-world clinical variables; and (3) imputing missing values drawn from a distribution within one standard deviation of the observed mean or using Multiple Imputation by Chained Equations (MICE). Results: VC-MAES achieved the area under the receiver operating characteristic curve (AUROC) of 0.896 using only vital signs and age, outperforming traditional EWSs, including the National Early Warning Score (0.797) and the Modified Early Warning Score (0.722). Reintroducing full clinical variables improved the AUROC to 0.918, whereas mean-based imputation or MICE decreased the performance to 0.885 and 0.827, respectively. Conclusions: VC-MAES demonstrates robust predictive performance with limited inputs, outperforming traditional EWSs. Incorporating actual clinical data significantly improved accuracy. In contrast, mean-based or MICE imputation yielded poorer results than the default normal-value imputation, potentially due to disregarding the "informative presence" embedded in missing data patterns. These findings underscore the importance of understanding missingness patterns and employing imputation strategies that consider the decision-making context behind data availability to enhance model reliability.

Keywords: artificial intelligence; early warning score; imputation; modified early warning score; national early warning score.

Figure 1

Receiver Operating Characteristic Curves (a) and Precision–Recall Curves (b) comparing predictive performance among models using vital signs only, vital signs + laboratory data, Modified Early Warning Score (MEWS), and National Early Warning Score (NEWS).

Figure 2

Receiver Operating Characteristic Curves (a) and Precision–Recall Curves (b) comparing predictive performance among models using vital signs + laboratory data and forced lab imputation.