ABSTRACT
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.
Subject(s)
Humans , Acute Coronary Syndrome/epidemiology , Bayes Theorem , Feasibility Studies , Risk Assessment/methods , Chest Pain/etiology , Myocardial Infarction/diagnosisABSTRACT
Objective:To analyze the effects of exercise-based cardiac rehabilitation (ER) on patients with acute coronary syndrome (ACS) after percutaneous coronary intervention (PCI), and to identify which type of ACS patients would benefit most in terms of cardiovascular functional capacity after ER. Methods:From December, 2017 to July, 2019, 31 ACS patients who discharged in a stable situation after PCI were studied. All patients were referred to a three-month ER program after discharge. They were divided into normal wall motion group (normal group, n = 14) and abnormal regional wall motion group (abnormal group, n = 17) according to baseline myocardial wall motion reported by echocardiography. The degree of wall motion abnormalities was quantified by the wall motion score index (WMSI). Echocardiography and cardiopulmonary exercise testing (CPET) were performed before and after ER. Results:Eight patients were dropped, and 23 patients completed the trial. WMSI decreased in the abnormal group (Z = -2.852, P = 0.004), and the left ventricular ejection fraction (LVEF) didn't change in both groups (P > 0.05) after ER. CPET showed that the heart rate at rest decreased in the normal group after ER (t = -2.268, P = 0.047); and the peak work rate, peak oxygen uptake, percentage of predicted value of peak oxygen uptake, peak minute ventilation and the third minute heart rate recovery increased in the abnormal group after ER (t > 2.739, P < 0.05). Conclusion:ER during recovery period could help more improve the cardiac function and exercise tolerance of ACS patients with abnormal WMSI after PCI. WMSI is an important indicator of cardiac function in ACS patients with preserved ejection fraction.
ABSTRACT
Objective:To create a prediction model that could be used to stratify the risk of cardiac rehabilitation in patients with stable coronary artery disease by using test data based on cardiopulmonary exercise testing (CPET) and general clinical data. Methods:A total of 114 patients with stable coronary artery disease were consecutively enrolled from the Cardiology Coronary Artery Disease Database of our hospital from December, 2014 to December, 2018, all the patients underwent CPET before coronary angiography. LASSO was used for feature selection. A nomogram was formulated based on the results of multivariate Logistic regression analysis using the RMS package of R. The predictive power was assessed with Receiver Operating Characteristic Curve. Results:Seven predictors were identified based on LASSO: coronary angiography results, the maximum value of ventilatory equivalent for carbon dioxide (EqCO2max), lymphocyte count, fasting blood glucose levels, cardiac muscle enzyme positivity, blood homocysteine and blood urea nitrogen levels. Combined with clinical experience and weighting analysis, the final four factors were included for Logistic regression modeling: coronary angiography results, EqCO2max, lymphocyte count and fasting blood glucose levels. The area under the curve was 0.875 for the model. Conclusion:EqCO2max and lymphocyte count are key predictors for stable coronary heart disease and can be used to identify patients at high risk for cardiac rehabilitation. A risk stratification model based on CPET and laboratory tests can be used to assess risk stratification for cardiac rehabilitation in patients with stable coronary artery disease.
ABSTRACT
Objective:To explore the time-dependent changes of blood pressure with the increase of exercise intensity and its clinical significance in Cardiopulmonary Exercise Test for female patients with hypertension. Methods:From August, 2018 to August, 2019, 64 patients (hypertension group) who did not take β-receptor blockers and dihydropyridine calcium antagonists were selected from grade 1 and grade 2 hypertension women excluding myocardial ischemia with Cardiopulmonary Exercise Test. And 86 healthy women (non-hypertension group) excluding myocardial ischemia from the same period of Cardiopulmonary Exercise Test were selected as the controls for retrospective analysis. The time-dependent changes of blood pressure with the increase of exercise intensity were compared between two groups. Results:The blood pressures at resting for three minutes, anaerobic threshold and peak were significantly higher in the hypertension group than in the non-hypertension group (Z > 3.306, P < 0.001). There was no significant difference in peak oxygen uptake between two groups (Z = 1.549, P > 0.05). Conclusion:The blood pressure of the patients with grade 1 and grade 2 hypertension is prone to over elevation, who should pay more attention on blood pressure in sports and rehabilitation.