Machine Learning for In-hospital Mortality Prediction in Critically Ill Patients With Acute Heart Failure: A Retrospective Analysis Based on the MIMIC-IV Database

Abstract

Background: The incidence, mortality, and readmission rates for acute heart failure (AHF) are high, and the in-hospital mortality for AHF patients in the intensive care unit (ICU) is higher. However, there is currently no method to accurately predict the mortality of AHF patients.

Methods: The Medical Information Mart for Intensive Care Ⅳ (MIMIC-Ⅳ) database was used to perform a retrospective study. Patients meeting the inclusion criteria were identified from the MIMIC-Ⅳ database and randomly divided into a training set (n = 3,580, 70%) and a validation set (n = 1,534, 30%). The variates collected include demographic data, vital signs, comorbidities, laboratory test results, and treatment information within 24 hours of ICU admission. By using the least absolute shrinkage and selection operator (LASSO) regression model in the training set, variates that affect the in-hospital mortality of AHF patients were screened. Subsequently, in the training set, five common machine learning (ML) algorithms were applied to construct models using variates selected by LASSO to predict the in-hospital mortality of AHF patients. The predictive ability of the models was evaluated for sensitivity, specificity, accuracy, the area under the curve of receiver operating characteristics, and clinical net benefit in the validation set. To obtain a model with the best predictive ability, the predictive ability of common scoring systems was compared with the best ML model.

Results: Among the 5,114 patients, in-hospital mortality was 12.5%. Comparing the area under the curve, the XGBoost model had the best predictive ability among all ML models, and the XGBoost model was chosen as the final model for its higher net benefit. Its predictive ability was superior to common scoring systems.

Conclusions: The XGBoost model can effectively predict the in-hospital mortality of AHF patients admitted to the ICU, which may assist clinicians in precise management and early intervention for patients with AHF to reduce mortality.

Keywords: MIMIC-IV database; acute heart failure; in-hospital mortality; intensive care unit; machine learning; prediction model.