A Ventricular Fibrillation Recognition Method Based on Random Forest and BP Neural Network / 中国医疗器械杂志

Ventricular fibrillation is the most common pathophysiological mechanism leading to cardiac arrest. If cardiac arrest can be rescued in time, the survival rate of patients can be greatly improved. Therefore, rapid and accurate identification of ventricular fibrillation is extremely important. This paper proposes an automatic detection algorithm for ventricular fibrillation based on random forest and BP (back propagation) neural network. Pass the ECG signal through a 6 s moving window, calculate 6 kinds of characteristic parameters according to the time-frequency domain information of the signal, use these 6 kinds of characteristic parameters as the input of the classifier, carry out classification and test, and give the authoritative experts in the database. A total of 44 cases of related data were used to evaluate the method. The results show that using the ten-fold cross-validation method, the accuracy of classification of ventricular fibrillation in the CU database (Creighton University Ventricular Tachyarrhythmia Database) and the AHA database (the American Heart Association Database) has reached 96.38% and 99.45%, which has certain applicability.

Study on the distinction of glycemic variability among different glucose regulation populations by phase space reconstruction of time series / 中华内分泌代谢杂志

Sixty-six volunteers,including 24 subjects with normal glucose tolerance(NGT),18 patients with impaired glucose regulation (IGR),and 24 patients with type 2 diabetes mellitus ( T2DM ),underwent a test of continuous glucose monitoring.The data of continuous glucose monitoring were embedded into two-dimension Euclid space by Takens' embedding theory.Glycemic phase diagram was drawn by MATLAB.The area and center distance of glycemic phase diagram were calculated by computer.The distinction of glycemic variability and average glycemic level among different glucose regulation populations were analyzed.The results showed that there existed significant differences in body mass index,systolic blood pressure,diastolic blood pressure,low density lipoprotein-cholesterol,high density lipoprotein-cholesterol,triglyceride,total cholesterol,creatinine,and alanine aminotransferase among three groups( all P＜0.05 ).The levels of HbAIC,fasting plasma glucose( FPG ),postprandial 2 h plasma glucse (2hPG),area and center distance of glycemic phase diagram in T2DM group were higher than those in NGT and IGR groups( P＜0.01 ),and the levels of FPG,2hPG,area and center distance of glycemic phase diagram in IGR group were higher than those in NGT group( P＜0.01 ).The levels of FPG and 2hPG were correlated with area and center distance of glycemic phase diagram ( all P＜0.01 ).These results suggest that measuring the area and center distance of glycemic phase diagram is a good method to assess glycemic variability and average glycemic level during continuous glucose monitoring.