Key result
SME-XGBoost machine learning model predicts adverse in-hospital heart failure outcomes with an AUC of ~0.80.
Why the study?
The study sought to develop models with good identification for adverse outcomes in patients with heart failure and identify strong factors that affect prognosis.
Does a machine learning model using SMOTE+ENN and XGBoost improve risk identification of adverse outcomes in hospitalized patients with heart failure?
Observational (n=5,004)
Yes
Does a machine learning model using SMOTE+ENN and XGBoost improve risk identification of adverse outcomes in hospitalized patients with heart failure?
Effect estimate: AUC 0.8010 (95% CI 0.7974-0.8046)
p-value: p=<0.001
The combination of SMOTE+ENN preprocessing and XGBoost machine learning accurately stratifies the risk of in-hospital adverse outcomes in patients with heart failure, addressing the challenge of imbalanced medical data.
May support ML risk stratification in hospitalized HF; hypothesis-generating and requires prospective validation before clinical use.
PURPOSE: This study sought to develop models with good identification for adverse outcomes in patients with heart failure (HF) and find strong factors that affect prognosis. PATIENTS AND METHODS: A total of 5004 qualifying cases were selected, among which 498 cases had adverse outcomes and 4506 cases were discharged after improvement. The study subjects were hospitalized patients diagnosed with HF from a regional cardiovascular hospital and the cardiology department of a medical university hospital in Shanxi Province of China between January 2014 and June 2019. Synthesizing minority oversampling technology combined with edited nearest neighbors (SMOTE+ENN) was used to pre-process unbalanced data. Traditional logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost) were used to build risk identification models, and each model was repeated 100 times. Model discrimination and calibration were estimated using F1-score, the area under the receiver-operating characteristic curve (AUROC), and Brier score. The best performing of the five models was used to identify the risk of adverse outcomes and evaluate the influencing factors. RESULTS: The SME-XGBoost was the best performing model with means of F1-score (0.3673, 95% confidence interval [CI]: 0.3633-0.3712), AUC (0.8010, CI: 0.7974-0.8046), and Brier score (0.1769, CI: 0.1748-0.1789). Age, N-terminal pronatriuretic peptide, pulmonary disease, etc. were the most significant factors of adverse outcomes in patients with HF. CONCLUSION: The combination of SMOTE+ENN and advanced machine learning methods effectively improved the discrimination efficacy of adverse outcomes in HF patients, accurately stratified patients at risk of adverse outcomes, and found the top factors of adverse outcomes. These models and factors emphasize the importance of health status data in determining adverse outcomes in patients with HF.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2021) conducted an observational in Chronic Heart Failure (n=5,004). SME-XGBoost machine learning model vs. Traditional logistic regression and other machine learning models (KNN, SVM, RF) was evaluated on Model discrimination for adverse outcomes (Area Under the Curve) (AUC 0.8010, 95% CI 0.7974-0.8046, p=<0.001). The SME-XGBoost machine learning model effectively identified the risk of adverse outcomes in patients with heart failure, achieving an AUC of 0.8010.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: