In recent years, cardiovascular disease has become a common disease. With the development of machine learning and big data technologies, the processing ability of electrocardiogram (ECG) signals has been greatly enhanced through new computer technologies, enabling the auxiliary diagnosis technology for cardiovascular disease (CVD) to achieve new improvements. This article discusses the application of machine learning in ECG processing, especially in the auxiliary diagnosis of diseases. Firstly, the conventional signal preprocessing methods are introduced, and then the EEG signal processing methods based on feature extraction and fuzzy classification are explored. Secondly, the application of auxiliary diagnosis in CVD is further summarized. Finally, the advantages and disadvantages of the two methods are analyzed, and based on this, a design of an auxiliary diagnostic system compatible with the two methods is proposed, providing a new perspective for similar applied researches in the future.
Machine Learning ; Cardiovascular Diseases/diagnosis* ; Humans ; Electrocardiography ; Signal Processing, Computer-Assisted ; Diagnosis, Computer-Assisted ; Fuzzy Logic ; Electroencephalography

Objective To investigate whether there exist differences in the improvement of left ventricular diastolic function between angiotensin receptor-neprilysin inhibitor(ARNI)and angiotensin-converting enzyme inhibitor(ACEI)/angiotensin receptor blocker(ARB)in patients with hypertensive heart disease(HHD).Methods A retrospective cohort study was conducted on the HHD patients admitted in Department of Cardiovascular Diseases of our hospital from January 2021 to December 2024.The general information,echocardiographic parameters before and after treatment,and results of routine tests were collected.Finally,517 HHD patients were subjected,including 117 receiving ARNI treatment(ARNI group)and 400 getting ACEI/ARB treatment(ACEI/ARB group).A 1∶1 propensity score matching(PSM)was performed with a caliper value of 0.02,resulting in 89 matched cases for each group.Electrocardiography was performed to assess left ventricular diastolic dysfunction(LVDD),with various parameters,including left atrial volume index,early diastolic peak velocity at the interventricular septal portion of mitral annulus(septal e'),early diastolic peak velocity at the lateral wall portion of mitral annulus(lateral e'),tricuspid regurgitation velocity,and E/e'.These parameters were followed up and reassessed during the treatment period.Kaplan-Meier survival curve was plotted to compare the incidence of LVDD between the 2 groups.Multivariable logistic regression model was employed to identify the risk factors contributing to LVDD.Results The median follow-up time was 412(309,736)d in the whole cohort,and was 409(300,729)d for the patients after PSM.Kaplan-Meier survival analysis demonstrated that the incidence of LVDD was lower in the ARNI group than the ACEI/ARB group both before and after PSM(P<0.05).After treatment,the ARNI group obtained lower lateral e'[8.00(7.00,9.40)vs 9.00(7.10,10.30)cm/s,P<0.001],thinner left ventricular posterior wall thickness[12.20(10.80,12.80)vs 12.30(11.20,12.90)mm,P<0.048]when compared with the ACEI/ARB group.After adjusting for confounding factors,multivariable logistic regression analysis revealed that advanced age(OR=1.082,P<0.001),increased systolic blood pressure(OR=1.009,P=0.005),thicker left ventricular posterior wall thickness(OR=1.462,P<0.001),left atrial enlargement(OR=1.081,P<0.001),and use of calcium channel blocker(OR=1.548,P=0.006)were independent risk factors for LVDD,and positively correlated with the risk of LVDD.While,male(OR=0.709,P=0.043)and BMI(OR=0.933,P=0.006)were protective factors,which were negatively correlated with LVDD risk.Conclusion In HHD patients,ARNI is superior to ACEI/ARB in reducing the incidence of LVDD.