Improving Risk Identification of Adverse Outcomes in Chronic Heart Failure Using SMOTE+ENN and Machine Learning

Abstract

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 receiveroperating 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.

Machine learning-based warning model for chronic kidney disease in individuals over 40 years old in underprivileged areas, Shanxi Province

“…The Synthetic Minority Over-Sampling Technique (SMOTE) is an oversampling technique that is an effective algorithm for handling imbalances between data classes ( 16 ). It uses k-neighbour synthesis to amplify minority classes to obtain a balanced data set ( 17 ) that exhibits good performance in areas such as network intrusion detection systems and disease detection. In this study, there is a serious imbalance in the response variables, ACR outcomes and MCR outcomes ( Figures 2A , B ).…”

Using random forest algorithm for glomerular and tubular injury diagnosis

“…The Synthetic Minority Over-Sampling Technique (SMOTE) is an oversampling technique that is an effective algorithm for dealing with imbalances between data classes ( 21 ). It’s employed to synthetically enlarge the minority class using K-nearest neighors to obtain a balanced data set ( 22 ) and has been shown good performance in such fields as network intrusion detection systems and disease detection. In this study, there is a serious imbalance in the response variables, GI and TI ( Figures 1A,B ).…”

Machine learning models to detect social distress, spiritual pain, and severe physical psychological symptoms in terminally ill patients with cancer from unstructured text data in electronic medical records

“…To address imbalances among classes within a dataset, we also employed a combination of both undersampling and oversampling, SMOTEENN (Supplemental Appendix 5). 24 Since an imbalance in classes can have a considerable impact on the performance of a classifier, 25 the training set should be balanced. 26 We applied SMOTEENN to 80% of the records used for training.…”