Exploring the Feasibility of Machine Learning to Predict Risk Stratification Within 3 Months in Chest Pain Patients with Suspected NSTE-ACS / 生物医学与环境科学（英文）

OBJECTIVE@#We aimed to assess the feasibility and superiority of machine learning (ML) methods to predict the risk of Major Adverse Cardiovascular Events (MACEs) in chest pain patients with NSTE-ACS.@*METHODS@#Enrolled chest pain patients were from two centers, Beijing Anzhen Emergency Chest Pain Center Beijing Bo'ai Hospital, China Rehabilitation Research Center. Five classifiers were used to develop ML models. Accuracy, Precision, Recall, F-Measure and AUC were used to assess the model performance and prediction effect compared with HEART risk scoring system. Ultimately, ML model constructed by Naïve Bayes was employed to predict the occurrence of MACEs.@*RESULTS@#According to learning metrics, ML models constructed by different classifiers were superior over HEART (History, ECG, Age, Risk factors, & Troponin) scoring system when predicting acute myocardial infarction (AMI) and all-cause death. However, according to ROC curves and AUC, ML model constructed by different classifiers performed better than HEART scoring system only in prediction for AMI. Among the five ML algorithms, Linear support vector machine (SVC), Naïve Bayes and Logistic regression classifiers stood out with all Accuracy, Precision, Recall and F-Measure from 0.8 to 1.0 for predicting any event, AMI, revascularization and all-cause death ( vs. HEART ≤ 0.78), with AUC from 0.88 to 0.98 for predicting any event, AMI and revascularization ( vs. HEART ≤ 0.85). ML model developed by Naïve Bayes predicted that suspected acute coronary syndrome (ACS), abnormal electrocardiogram (ECG), elevated hs-cTn I, sex and smoking were risk factors of MACEs.@*CONCLUSION@#Compared with HEART risk scoring system, the superiority of ML method was demonstrated when employing Linear SVC classifier, Naïve Bayes and Logistic. ML method could be a promising method to predict MACEs in chest pain patients with NSTE-ACS.

Association of in-stent restenosis with serum Gal-3 and MMP-9 levels / 西安交通大学学报(医学版)

Objective To investigate the relationship of galectin-3 (Gal-3)and matrix metalloproteinase-9 (MMP-9)with in-stent restenosis (ISR).Methods We consecutively recruited 434 patients who had undergone successful drug eluting stent (DES)implantation.Then we divided them into ISR group (n=41)and NO-ISR group (n=393)according to the results of coronary angiography review.Independent risk factors for ISR were found out by multivariate analysis and the two groups were matched for these factors except for Gal-3 and MMP-9 .After elim-ination of the influence of confounders,serum Gal-3 and MMP-9 were compared between the groups and their rela-tions with the severity of ISR were analyzed.Patients were grouped based on Gal-3 and MMP-9 concentrations and major adverse cardiac events (MACEs)were compared between the two groups.Results After elimination of the influence of confounders,the results showed that serum levels of Gal-3 and MMP-9 were significantly higher in ISR group than in NO-ISR group (P＜0.001).Serum levels of Gal-3 and MMP-9 increased with the increased grade of classification.Serum levels of Gal-3 and MMP-9 were obviously higher in classes Ⅲ and Ⅳ ISR than in class Ⅰ (P＜0.05).Patients with higher levels of Gal-3 and MMP-9 had a higher incidence of MACEs (P＜0.01).ISR group had a higher incidence of MACEs than NO-ISR group (P＜0.05).Conclusion Serum levels of Gal-3 and MMP-9 are correlated with ISR and its severity,and they are independent risk factors for ISR.The rate of MACEs during follow-up period was increased with the increased levels of Gal-3 and MMP-9 .