Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure

Abstract

ObjectiveRisk stratification of patients with congestive heart failure (HF) is vital in clinical practice. The aim of this study was to construct a machine learning model to predict the in-hospital all-cause mortality for intensive care unit (ICU) patients with HF.MethodseXtreme Gradient Boosting algorithm (XGBoost) was used to construct a new prediction model (XGBoost model) from the Medical Information Mart for Intensive Care IV database (MIMIC-IV) (training set). The eICU Collaborative Research Database dataset (eICU-CRD) was used for the external validation (test set). The XGBoost model performance was compared with a logistic regression model and an existing model (Get with the guideline-Heart Failure model) for mortality in the test set. Area under the receiver operating characteristic cure and Brier score were employed to evaluate the discrimination and the calibration of the three models. The SHapley Additive exPlanations (SHAP) value was applied to explain XGBoost model and calculate the importance of its features.ResultsThe total of 11,156 and 9,837 patients with congestive HF from the training set and test set, respectively, were included in the study. In-hospital all-cause mortality occurred in 13.3% (1,484/11,156) and 13.4% (1,319/9,837) of patients, respectively. In the training set, of 17 features with the highest predictive value were selected into the models with LASSO regression. Acute Physiology Score III (APS III), age and Sequential Organ Failure Assessment (SOFA) were strongest predictors in SHAP. In the external validation, the XGBoost model performance was superior to that of conventional risk predictive methods, with an area under the curve of 0.771 (95% confidence interval, 0.757–0.784) and a Brier score of 0.100. In the evaluation of clinical effectiveness, the machine learning model brought a positive net benefit in the threshold probability of 0%–90%, prompting evident competitiveness compare to the other two models. This model has been translated into an online calculator which is accessible freely to the public (https://nkuwangkai-app-for-mortality-prediction-app-a8mhkf.streamlit.app).ConclusionThis study developed a valuable machine learning risk stratification tool to accurately assess and stratify the risk of in-hospital all-cause mortality in ICU patients with congestive HF. This model was translated into a web-based calculator which access freely.

Machine learning in heart failure diagnosis, prediction, and prognosis: review

“…Both SVM and LR models identified various clinical factors as predictors, including medications (such as furosemide, beta-blockers, and spironolactone), physical examination findings (such as early diastolic murmur and parasternal heave), and comorbidities (such as coronary artery disease and ischemic cardiomyopathy). These predictors align with previous studies that have reported similar associations between clinical parameters and mortality in HF 31 . The study emphasized the significance of data quality and outlined plans to enhance the sample size by collecting data from multiple cardiac centers in sub-Saharan Africa, aiming to improve model performance 31 .…”

“…These predictors align with previous studies that have reported similar associations between clinical parameters and mortality in HF 31 . The study emphasized the significance of data quality and outlined plans to enhance the sample size by collecting data from multiple cardiac centers in sub-Saharan Africa, aiming to improve model performance 31 .…”

“…The performance of different algorithms was compared, revealing that support vector machines (SVM) exhibited desirable performance, achieving an area under the receiver operating characteristic (AUROC) curve of 0.77 and high accuracy during training and testing. ML algorithms and conventional statistical LR models identified similar predictors of all-cause mortality in HF, as revealed by the study 31 . The SVM is a valuable tool for predicting outcomes in HF patients.…”

“…In another study, an interpretable ML-based risk stratification tool for in-hospital all-cause mortality in ICU patients with HF was developed and validated by Chen et al . 31 . The authors compared their ML model with traditional risk prediction methods and highlighted the clinical implications of accurate prognostic evaluation in ICU patients with HF.…”

“…Chen et al . 31 utilized the XGBoost algorithm to develop a novel model that considered clinical features, comorbidities, and medication information. The model exhibited improved prediction performance compared to the Logistic model and the Get With The Guidelines-Heart Failure (GWTG-HF) model for all-cause mortality risk in ICU patients with HF.…”