Dataset Information

The performance of acute versus antecedent patient characteristics for 1-year mortality prediction during intensive care unit admission: a national cohort study.

ABSTRACT:

Background

Multiple factors contribute to mortality after ICU, but it is unclear how the predictive value of these factors changes during ICU admission. We aimed to compare the changing performance over time of the acute illness component, antecedent patient characteristics, and ICU length of stay (LOS) in predicting 1-year mortality.

Methods

In this retrospective observational cohort study, the discriminative value of four generalized mixed-effects models was compared for 1-year and hospital mortality. Among patients with increasing ICU LOS, the models included (a) acute illness factors and antecedent patient characteristics combined, (b) acute component only, (c) antecedent patient characteristics only, and (d) ICU LOS. For each analysis, discrimination was measured by area under the receiver operating characteristics curve (AUC), calculated using the bootstrap method. Statistical significance between the models was assessed using the DeLong method (p value ResultsIn 400,248 ICU patients observed, hospital mortality was 11.8% and 1-year mortality 21.8%. At ICU admission, the combined model predicted 1-year mortality with an AUC of 0.84 (95% CI 0.84-0.84). When analyzed separately, the acute component progressively lost predictive power. From an ICU admission of at least 3 days, antecedent characteristics significantly exceeded the predictive value of the acute component for 1-year mortality, AUC 0.68 (95% CI 0.68-0.69) versus 0.67 (95% CI 0.67-0.68) (p value ConclusionsComparing the predictive value of factors influencing 1-year mortality for patients with increasing ICU LOS, antecedent patient characteristics are more predictive than the acute component for patients with an ICU LOS of at least 3 days. For hospital mortality, antecedent patient characteristics outperform the acute component for patients with an ICU LOS of at least 7 days. After the first week of ICU admission, LOS itself is not predictive of hospital nor 1-year mortality.

SUBMITTER: Kerckhoffs MC

PROVIDER: S-EPMC7291572 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The performance of acute versus antecedent patient characteristics for 1-year mortality prediction during intensive care unit admission: a national cohort study.

Kerckhoffs Monika C MC Brinkman Sylvia S de Keizer Nicolet N Soliman Ivo W IW de Lange Dylan W DW van Delden Johannes J M JJM van Dijk Diederik D

Critical care (London, England) 20200611 1

<h4>Background</h4>Multiple factors contribute to mortality after ICU, but it is unclear how the predictive value of these factors changes during ICU admission. We aimed to compare the changing performance over time of the acute illness component, antecedent patient characteristics, and ICU length of stay (LOS) in predicting 1-year mortality.<h4>Methods</h4>In this retrospective observational cohort study, the discriminative value of four generalized mixed-effects models was compared for 1-year ...[more]

PMID: 32527298

Similar Datasets

Project description:ObjectiveTo compare the performance of machine learning models against the traditionally derived Combined Assessment of Risk Encountered in Surgery (CARES) model and the American Society of Anaesthesiologists-Physical Status (ASA-PS) in the prediction of 30-day postsurgical mortality and need for intensive care unit (ICU) stay >24 hours.BackgroundPrediction of surgical risk preoperatively is important for clinical shared decision-making and planning of health resources such as ICU beds. The current growth of electronic medical records coupled with machine learning presents an opportunity to improve the performance of established risk models.MethodsAll patients aged 18 years and above who underwent noncardiac and nonneurological surgery at Singapore General Hospital (SGH) between 1 January 2012 and 31 October 2016 were included. Patient demographics, comorbidities, preoperative laboratory results, and surgery details were obtained from their electronic medical records. Seventy percent of the observations were randomly selected for training, leaving 30% for testing. Baseline models were CARES and ASA-PS. Candidate models were trained using random forest, adaptive boosting, gradient boosting, and support vector machine. Models were evaluated on area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC).ResultsA total of 90,785 patients were included, of whom 539 (0.6%) died within 30 days and 1264 (1.4%) required ICU admission >24 hours postoperatively. Baseline models achieved high AUROCs despite poor sensitivities by predicting all negative in a predominantly negative dataset. Gradient boosting was the best performing model with AUPRCs of 0.23 and 0.38 for mortality and ICU admission outcomes respectively.ConclusionsMachine learning can be used to improve surgical risk prediction compared to traditional risk calculators. AUPRC should be used to evaluate model predictive performance instead of AUROC when the dataset is imbalanced.

Project description:BackgroundTo develop a highly discriminative machine learning model for the prediction of intensive care unit admission (>24h) using the easily available preoperative information from electronic health records. An accurate prediction model for ICU admission after surgery is of great importance for surgical risk assessment and appropriate utilization of ICU resources.MethodData were collected retrospectively from a large hospital, comprising 135,442 adult patients who underwent surgery except for cardiac surgery between 1 January 2014, and 31 July 2018 in China. Multiple existing predictive machine learning algorithms were explored to construct the prediction model, including logistic regression, random forest, adaptive boosting, and gradient boosting machine. Four secondary analyses were conducted to improve the interpretability of the results.ResultsA total of 2702 (2.0%) patients were admitted to the intensive care unit postoperatively. The gradient boosting machine model attained the highest area under the receiver operating characteristic curve of 0.90. The machine learning models predicted intensive care unit admission better than the American Society of Anesthesiologists Physical Status (area under the receiver operating characteristic curve: 0.68). The gradient boosting machine recognized several features as highly significant predictors for postoperatively intensive care unit admission. By applying subgroup analysis and secondary analysis, we found that patients with operations on the digestive, respiratory, and vascular systems had higher probabilities for intensive care unit admission.ConclusionCompared with conventional American Society of Anesthesiologists Physical Status and logistic regression model, the gradient boosting machine could improve the performance in the prediction of intensive care unit admission. Machine learning models could be used to improve the discrimination and identify the need for intensive care unit admission after surgery in elective noncardiac surgical patients, which could help manage the surgical risk.

Dataset Information

The performance of acute versus antecedent patient characteristics for 1-year mortality prediction during intensive care unit admission: a national cohort study.

Background

Methods

Publications

The performance of acute versus antecedent patient characteristics for 1-year mortality prediction during intensive care unit admission: a national cohort study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure