RESUMO
Background: Early prediction and classification of prognosis is essential for patients in the coronary care unit (CCU). We applied a machine learning (ML) model using the eXtreme Gradient Boosting (XGBoost) algorithm to prognosticate CCU patients and compared XGBoost with traditional classification models. Methods: CCU patients' data were extracted from the MIMIC-III v1.4 clinical database, and divided into four groups based on the time to death: <30 days, 30 days-1 year, 1-5 years, and ≥5 years. Four classification models, including XGBoost, naïve Bayes (NB), logistic regression (LR), and support vector machine (SVM) were constructed using the Python software. These four models were tested and compared for accuracy, F1 score, Matthews correlation coefficient (MCC), and area under the curve (AUC) of the receiver operating characteristic curves. Subsequently, Local Interpretable Model-Agnostic Explanations method was performed to improve XGBoost model interpretability. We also constructed sub-models of each model based on the different categories of death time and compared the differences by decision curve analysis. The optimal model was further analyzed using a clinical impact curve. At last, feature ablation curves of the XGBoost model were conducted to obtain the simplified model. Results: Overall, 5360 CCU patients were included. Compared to NB, LR, and SVM, the XGBoost model showed better accuracy (0.663, 0.605, 0.632, and 0.622), micro-AUCs (0.873, 0.811, 0.841, and 0.818), and MCC (0.337, 0.317, 0.250, and 0.182). In subgroup analysis, the XGBoost model had a better predictive performance in acute myocardial infarction subgroup. The decision curve and clinical impact curve analyses verified the clinical utility of the XGBoost model for different categories of patients. Finally, we obtained a simplified model with thirty features. Conclusions: For CCU physicians, the ML technique by XGBoost is a potential predictive tool in patients with different conditions, and it may contribute to improvements in prognosis.
RESUMO
BACKGROUND: Considered as one of the major reasons of sudden cardiac death, hypertrophic cardiomyopathy (HCM) is a common inherited cardiovascular disease. However, effective treatment for HCM is still lacking. Identification of hub gene may be a powerful tool for discovering potential therapeutic targets and candidate biomarkers. METHODS: We analysed three gene expression datasets for HCM from the Gene Expression Omnibus. Two of them were merged by "sva" package. The merged dataset was used for analysis while the other dataset was used for validation. Following this, a weighted gene coexpression network analysis (WGCNA) was performed, and the key module most related to HCM was identified. Based on the intramodular connectivity, we identified the potential hub genes. Then, a receiver operating characteristic curve analysis was performed to verify the diagnostic values of hub genes. Finally, we validated changes of hub genes, for genetic transcription and protein expression levels, in datasets of HCM patients and myocardium of transverse aortic constriction (TAC) mice. RESULTS: In the merged dataset, a total of 455 differentially expressed genes (DEGs) were identified from normal and hypertrophic myocardium. In WGCNA, the blue module was identified as the key module and the genes in this module showed a high positive correlation with HCM. Functional enrichment analysis of DEGs and key module revealed that the extracellular matrix, fibrosis, and neurohormone pathways played important roles in HCM. FRZB, COL14A1, CRISPLD1, LUM, and sFRP4 were identified as hub genes in the key module. These genes showed a good predictive value for HCM and were significantly up-regulated in HCM patients and TAC mice. We also found protein expression of LUM and sFRP4 increased in myocardium of TAC mice. CONCLUSION: This study revealed that five hub genes are involved in the occurrence and development of HCM, and they are potentially to be used as therapeutic targets and biomarkers for HCM.