Magnetocardiography-Based Ischemic Heart Disease Detection and Localization Using Machine Learning Methods.

OBJECTIVE: This study focused on developing a fast and accurate automatic ischemic heart disease detection/localization methodology. METHODS: T wave was segmented from averaged Magnetocardiography (MCG) recordings and 164 features were subsequently extracted. These features were categorized into three groups: time domain features, frequency domain features, and information theory features. Next, we compared different machine learning classifiers including: k-nearest neighbor, decision tree, support vector machine (SVM), and XGBoost. To identify ischemia heart disease (IHD) case, we selected three classifiers with best performance and applied model ensemble to average results. All 164 features were used in this stage. To localize ischemia, we classified IHD group according to stenosis locations, including left anterior descending (LAD), left circumflex artery (LCX), and right coronary artery (RCA). For this task, we used XGBoost classifier and 18 time domain features. RESULTS: For IHD detection, the SVM-XGBoost model achieved best results with accuracy = 94.03%, precision = 86.56%, recall = 97.78%, F-score = 92.79%, AUC = 0.98, and average precision = 0.98. For ischemia localization, XGBoost model achieved accuracy = 0.74, 0.68, and 0.65, for LAD, LCX, and RCA, respectively. CONCLUSION: we have developed an automatic IHD detection and localization system. We find that 1. T wave repolarization synchronicity is an important factor to distinguish IHD from normal subjects 2. Magnetic field pattern is associated with stenosis location. SIGNIFICANCE: The proposed machine learning method provides the clinicians a fast and accurate diagnosis tool to interpret MCG data, boosting its acceptance into clinics. Furthermore, the magnetic pole characteristics revealed by the method shows to be related to ischemia location, presenting the opportunity to noninvasively locate ischemia.

Platelet Inhibition Ratio by Thromboelastography in Patients Undergoing Percutaneous Coronary Intervention / 中国康复理论与实践

@#ObjectiveTo investigate the platelet inhibition ratio by thromboelastography (TEG) and its clinical impact in patients undergoing percutaneous coronary intervention (PCI). Methods118 PCI patients were divided into ischemic events group (22 cases) and nonischemic events group (96 cases) according to their clinical follow-up of 6 months. Platelet inhibition ratio was measured by TEG. ResultsADP-induced platelet inhibition ratio of ischemic events group decreased significantly compared with nonischemic events group (P<0.01). And there were no significant differences in AA-induced platelet inhibition ratio between two groups (P＞0.05). ConclusionThere may be some relationship between the ischemic events of PCI patients and their drug resistance to clopidogrel.

Variance of Brain Natriuretic Peptide in Aged Patients after Noncardiac Surgery and Its Significance / 中国康复理论与实践

@#Objective To explore the variance of plasma brain natriuretic peptide (BNP) concentrations in the aged patients after noncardiac surgery and its significance. Methods 101 patients undergoing elective noncardiac surgery were divided into two groups based on the BNP concentrations before surgery: group A: BNP≤100 ng/L，n=61; group B: BNP>100 ng/L，n=40. The BNP concentrations before and after noncardiac surgery and the incidence of cardiac events in both groups were compared. Results There was no significant difference （P>0.05） of BNP concentrations before and after noncardiac surgery in group A, which were (58.2±28.7) ng/L and (53.7±25.9) ng/L respectively, but was significant difference （P<0.05） in group B, which were (147.3±72.1) ng/L and (341.5±92.4) ng/L respectively. There was significant difference （P<0.05） between group A, in which no patient happened cardiac event, and group B, in which 14 patients happened. Conclusion The plasma BNP concentration would be increased significantly in the aged patients with a BNP concentration>100 ng/L before surgery, which may cause more cardiac events.

Prediction of B-type Natriuretic Peptide for Cardiac Events after Noncardiac Surgery in Aged Patients / 中国康复理论与实践

@# Objective To explore the value of B-type natriuretic peptide (BNP) predicting cardiac events after noncardiac surgery in the aged patients. Methods The level of BNP， the score of Goldman analysis and the cardiac risk grade of ACC/AHA guideline were analyzed in 274 aged patients for cardiac outcome after noncardiac surgery. Results Preoperative BNP concentration>100 pg/ml，score of Goldman≥13，and the high or moderate risk grade by ACC/AHA guideline were related with cardiac events. There was no significant difference in the index such as sensitivity，specificity, accuracy，positive predictive value and negative predictive value for cardiac events between BNP level and cardiac risk grade. Compared with the score of Goldman, BNP was more sensitive （100% vs 55.6%）and negatively predictive （100% vs 96.3%） for cardiac events. Conclusion The risk of cardiac events after noncardiac surgery could be predicted with the level of BNP before operation in the aged patient.