Using electronic health record collected clinical variables to predict medical intensive care unit mortality

Abstract

BackgroundClinical decision support systems are used to help predict patient stability and mortality in the Intensive Care Unit (ICU). Accurate patient information can assist clinicians with patient management and in allocating finite resources. However, systems currently in common use have limited predictive value in the clinical setting. The increasing availability of Electronic Health Records (EHR) provides an opportunity to use medical information for more accurate patient stability and mortality prediction in the ICU.ObjectiveDevelop and evaluate an algorithm which more accurately predicts patient mortality in the ICU, using the correlations between widely available clinical variables from the EHR.MethodsWe have developed an algorithm, AutoTriage, which uses eight common clinical variables from the EHR to assign patient mortality risk scores. Each clinical variable produces a subscore, and combinations of two or three discretized clinical variables also produce subscores. A combination of weighted subscores produces the overall score. We validated the performance of this algorithm in a retrospective study on the MIMIC III medical ICU dataset.ResultsAutoTriage 12 h mortality prediction yields an Area Under Receiver Operating Characteristic value of 0.88 (95% confidence interval 0.86 to 0.88). At a sensitivity of 80%, AutoTriage maintains a specificity of 81% with a diagnostic odds ratio of 16.26.ConclusionsThrough the multidimensional analysis of the correlations between eight common clinical variables, AutoTriage provides an improvement in the specificity and sensitivity of patient mortality prediction over existing prediction methods.

Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach

“…10 after the first 24, 48 or 72 hours of ICU admission [3,4,5,6, 7,8, 9]. Even models, such as the one proposed by Calvert et al [10] attempts to predict mortality 12 hours before in-hospital death; this study shows strong predictive accuracy but we question the practical utility of the tool, which predicts at a point twelve hours from the sampling. It is not clear at what stage in the evolution of a critical care episode that this tool should be employed to best effect.…”

Learning to Predict in-hospital mortality risk in intensive care unit with attention-based Temporal convolution network

“…These models are all non-time series and based on statistical methods, the input data are static data or statistical data, such as comorbidities and the minimum of systolic pressure in the rst 24h, which make it impossible to predict the mortality risk in the rst 24h or to update data for predicting long-term mortality risk. Despite the AUCROCs of the score-based models were satis ed, either the sensitivity or the speci city was poor (23,24). It's not suprising that these models have been modi ed several times to improve their predictive performance since they rst being published (25).…”

“…It's not suprising that these models have been modi ed several times to improve their predictive performance since they rst being published (25). Recently, for the complex, non-linear relationship between clinical variables and the outcome, non-time series AI methods, such as Arti cal neural work (ANN), SVM, DT , RF, Naive Bayes, projective adaptive resonance theory (PART) and AutoTriage, were used to predict the mortality risk of patients in ICUs (5,11,24,26,27) with relatively satis ed model performance. However, due to the non-time series methods, all the variables are static or extracted from time series data, which makes it impossible to realize dynamic prediction.…”

Predicting hospital mortality for intensive care unit patients: Time-series analysis

“…Various studies have advocated the use of DM techniques for predicting ICU mortality, such as the one proposed by Calvert et al, 29 which attempts to predict mortality 12 h before in-hospital death. Although the work conducted shows strong predictive accuracy, however, we question the practical utility of the tool, which predicts at a point 12 h from the sampling.…”