Abstract
BackgroundPrognostication is an essential tool for risk adjustment and decision making in the intensive care units (ICUs). In order to improve patient outcomes, we have been trying to develop a more effective model than Acute Physiology and Chronic Health Evaluation (APACHE) II to measure the severity of the patients in ICUs. The aim of the present study was to provide a mortality prediction model for ICUs patients, and to assess its performance relative to prediction based on the APACHE II scoring system.MethodsWe used the Medical Information Mart for Intensive Care version III (MIMIC-III) database to build our model. After comparing the APACHE II with 6 typical machine learning (ML) methods, the best performing model was screened for external validation on anther independent dataset. Performance measures were calculated using cross-validation to avoid making biased assessments. The primary outcome was hospital mortality. Finally, we used TreeSHAP algorithm to explain the variable relationships in the extreme gradient boosting algorithm (XGBoost) model.ResultsWe picked out 14 variables with 24,777 cases to form our basic data set. When the variables were the same as those contained in the APACHE II, the accuracy of XGBoost (accuracy: 0.858) was higher than that of APACHE II (accuracy: 0.742) and other algorithms. In addition, it exhibited better calibration properties than other methods, the result in the area under the ROC curve (AUC: 0.76). we then expand the variable set by adding five new variables to improve the performance of our model. The accuracy, precision, recall, F1, and AUC of the XGBoost model increased, and were still higher than other models (0.866, 0.853, 0.870, 0.845, and 0.81, respectively). On the external validation dataset, the AUC was 0.79 and calibration properties were good.ConclusionsAs compared to conventional severity scores APACHE II, our XGBoost proposal offers improved performance for predicting hospital mortality in ICUs patients. Furthermore, the TreeSHAP can help to enhance the understanding of our model by providing detailed insights into the impact of different features on the disease risk. In sum, our model could help clinicians determine prognosis and improve patient outcomes.
Highlights
Prognostication is an essential tool for risk adjustment and decision making in the intensive care units (ICUs)
We focused on machine learning (ML) algorithm selection and tuning to improve the performance of the Acute Physiology and Chronic Health Evaluation (APACHE) II scoring system, by using two large data sets for modeling and validation, respectively
We aim to construct several machine learning models to predict the mortality of ICUs patients and compare their predicting performance, and get a prediction model that is better than the Apache II traditional scoring scale
Summary
Prognostication is an essential tool for risk adjustment and decision making in the intensive care units (ICUs). According to data from World Population Prospects: the 2019 Revision, there will be more than twice as many persons above 65 as children under five by 2050 [1] Those increasing numbers of elderly patients and the emphasis on the long-term quality of life in patients with critically ill have led to a growing demand for intensive care units (ICUs). Luo et al BMC Med Inform Decis Mak (2021) 21:237 from 7% [2] to 52.3% [3] It is because critical care is fastpaced, complex, and commonly requires urgent high-risk decision-making, and the outcome of ICUs treatment is highly related to numerous factors, such as the site, cause of admission, age, prior comorbidities, acute physiological changes at admission and during the first several hours of treatment, etc. Rothschild et al [6] studied 391 patients with 420 unit admissions during 1490 patient-days and found that the rates per 1000 patient-days for adverse events and serious errors which had life-threatening were 13% and 11%, respectively
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
