What is the clinical evidence from this study?

Study design: Observational. Population: Acute heart failure (AHF) (n=5114). Intervention: XGBoost machine learning model vs. Common scoring systems (LODS, SAPSII, SOFA). Primary outcome: Area under the curve (AUC) for in-hospital mortality prediction.

What does this research mean for the field?

The XGBoost machine learning model demonstrates superior predictive ability for in-hospital mortality in ICU patients with acute heart failure compared to common clinical scoring systems like LODS. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

January 8, 2024Open Access

Machine learning for in-hospital mortality prediction in critically ill patients with acute heart failure: A retrospective analysis based on MIMIC -Ⅳ databases

Key Result

The XGBoost machine learning model demonstrated superior predictive ability for in-hospital mortality in ICU patients with acute heart failure, achieving an AUC of 0.8215 compared to 0.7779 for LODS.

Study Design

Type

Observational (n=5,114)

Multicenter

Structured PICO

Does the XGBoost machine learning model accurately predict in-hospital mortality in critically ill patients with acute heart failure?

Population

5,114 adult patients (≥18 years) with acute heart failure admitted to the ICU, extracted from the MIMIC-IV database (2008-2019).

Intervention

XGBoost machine learning model using 18 clinical variables selected by LASSO regression

Comparator

Other machine learning models (logistic regression, k-Nearest Neighbor, decision tree, random forest) and common ICU scoring systems (SOFA, LODS, SAPSII)

Outcome

In-hospital mortalityhard clinical

The XGBoost machine learning model effectively predicts in-hospital mortality in ICU patients with acute heart failure, outperforming traditional scoring systems like SOFA and SAPSII.

Main Result

Absolute Event Rate: 0.8215% vs 0.7779%

Limitations

Retrospective study design may lead to inevitable selection bias.
Data derived solely from the single-center MIMIC-IV database, potentially limiting generalizability to other populations.
Use of multiple imputation methods to fill in missing data may lead to deviations from true values.

Abstract

Abstract Background The incidence rate, mortality rate and readmission rate of acute heart failure (AHF) are high, and the in-hospital mortality of AHF patients in ICU is higher. However, there is no method to accurately predict the mortality of AHF patients at present. 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 training set (n = 3580, 70%) and validation set (n = 1534, 30%). The variates we 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, we screened variates that affect the in-hospital mortality of AHF patients. 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. We evaluated the predictive ability of the models by sensitivity, specificity, accuracy, the area under the curve (AUC) of receiver operating characteristics (ROC), and clinical net benefit in the validation set. In order to obtain a model with the best predictive ability, we compared the predictive ability of common scoring systems with the best ML model. Results Among the 5114 patients, in-hospital mortality was 12.5%. By comparing AUC, the XGBoost model had the best predictive ability among all ML models, and the XGBoost model was chosen as our final model for its higher net benefit. Meanwhile, its predictive ability is 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 of patients with AHF to reduce mortality.

Ask AI

Mark Helpful

Bookmark

Relay

View Full Paper