Subclinical atherosclerosis underlies most cardiovascular diseases, manifesting before clinical symptoms and representing a key focus for early prevention strategies. Recent advancements highlight the importance of early detection and management of subclinical atherosclerosis. This review underscores that traditional risk factor levels considered safe, such as low-density lipoprotein cholesterol (LDL-C) and glycated haemoglobin (HbA1c), may still permit the development of atherosclerosis, suggesting a need for stricter thresholds. Early-life interventions are crucial, leveraging the brain's neuroplasticity to establish lifelong healthy habits. Preventive strategies should include more aggressive management of LDL-C and HbA1c from youth and persist into old age, supported by public health policies that promote healthy environments. Emphasising early education on cardiovascular health can fundamentally shift the trajectory of cardiovascular disease prevention and optimise long-term health outcomes.
Humans ; Atherosclerosis/diagnosis* ; Risk Factors ; Cardiovascular Diseases/prevention & control* ; Cholesterol, LDL/blood* ; Glycated Hemoglobin ; Cardiology/trends* ; Heart Disease Risk Factors

Cardiovascular diseases and psychological disorders represent two major threats to human physical and mental health. Research on electrocardiogram (ECG) signals offers valuable opportunities to address these issues. However, existing methods are constrained by limitations in understanding ECG features and transferring knowledge across tasks. To address these challenges, this study developed a multi-resolution feature encoding network based on residual networks, which effectively extracted local morphological features and global rhythm features of ECG signals, thereby enhancing feature representation. Furthermore, a model compression-based continual learning method was proposed, enabling the structured transfer of knowledge from simpler tasks to more complex ones, resulting in improved performance in downstream tasks. The multi-resolution learning model demonstrated superior or comparable performance to state-of-the-art algorithms across five datasets, including tasks such as ECG QRS complex detection, arrhythmia classification, and emotion classification. The continual learning method achieved significant improvements over conventional training approaches in cross-domain, cross-task, and incremental data scenarios. These results highlight the potential of the proposed method for effective cross-task knowledge transfer in ECG analysis and offer a new perspective for multi-task learning using ECG signals.
Humans ; Electrocardiography/methods* ; Mental Health ; Algorithms ; Signal Processing, Computer-Assisted ; Machine Learning ; Arrhythmias, Cardiac/diagnosis* ; Cardiovascular Diseases ; Neural Networks, Computer ; Mental Disorders

Heart sounds are critical for early detection of cardiovascular diseases, yet existing studies mostly focus on traditional signal segmentation, feature extraction, and shallow classifiers, which often fail to sufficiently capture the dynamic and nonlinear characteristics of heart sounds, limit recognition of complex heart sound patterns, and are sensitive to data imbalance, resulting in poor classification performance. To address these limitations, this study proposes a novel heart sound classification method that integrates improved Mel-frequency cepstral coefficients (MFCC) for feature extraction with a convolutional neural network (CNN) and a deep Transformer model. In the preprocessing stage, a Butterworth filter is applied for denoising, and continuous heart sound signals are directly processed without segmenting the cardiac cycles, allowing the improved MFCC features to better capture dynamic characteristics. These features are then fed into a CNN for feature learning, followed by global average pooling (GAP) to reduce model complexity and mitigate overfitting. Lastly, a deep Transformer module is employed to further extract and fuse features, completing the heart sound classification. To handle data imbalance, the model uses focal loss as the objective function. Experiments on two public datasets demonstrate that the proposed method performs effectively in both binary and multi-class classification tasks. This approach enables efficient classification of continuous heart sound signals, provides a reference methodology for future heart sound research for disease classification, and supports the development of wearable devices and home monitoring systems.
Heart Sounds/physiology* ; Humans ; Algorithms ; Neural Networks, Computer ; Signal Processing, Computer-Assisted ; Deep Learning ; Cardiovascular Diseases/diagnosis* ; Classification Algorithms

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

OBJECTIVES: Cardiovascular disease (CVD) poses a major threat to global health. Evaluating atherosclerosis in asymptomatic individuals can help identify those at high risk of CVD. This study aims to establish an individualized nomogram prediction model to estimate the risk of vascular plaque formation in asymptomatic individuals. METHODS: A total of 5 655 participants who underwent CVD screening at the Health Management Center of The Third Xiangya Hospital, Central South University, between January 2022 and June 2024 we retrospectively enrolled. Using simple random sampling, participants were divided into a training set (n=4 524) and a validation set (n=1 131) in an 8꞉2 ratio. Demographic and clinical data were collected and compared between groups. Multivariate logistic regression analysis was used to identify independent factors associated with vascular plaques and to construct a nomogram prediction model. The predictive performance and clinical utility of the model were evaluated using receiver operating characteristic (ROC) curves, the Hosmer-Lemeshow goodness-of-fit test, calibration plots, and decision curve analysis (DCA). RESULTS: The mean age of participants was 52 years old. There were 3 400 males (60.12%). The overall detection rate of vascular plaque in the screening population was 49.87% (2 820/5 655). No statistically significant differences were observed in clinical indicators between the training and validation sets (all P>0.05). Multivariate Logistic regression analysis identified age, systolic blood pressure, high-density lipoprotein (HDL), low-density lipoprotein (LDL), lipoprotein(a), male sex, smoking history, hypertension history, and diabetes history as independent risk factors for vascular plaque in asymptomatic individuals (all P<0.05). The area under the curve (AUC) of the nomogram model for predicting vascular plaque risk were 0.778 (95% CI 0.765 to 0.791, P<0.001) in the training set and 0.760 (95% CI 0.732 to 0.787, P<0.001) in the validation set. The Hosmer-Lemeshow goodness-of-fit test indicated good model calibration (training set: P=0.628; validation set: P=0.561). The calibration curve plotted using the Bootstrap method demonstrated good agreement between predicted probabilities and actual probabilities. DCA showed that the nomogram provided a clinical net benefit for predicting vascular plaque risk when the threshold probability ranged from 0.02 to 0.99. CONCLUSIONS The nomogram prediction model for vascular plaque risk, constructed using readily available and cost-effective physical examination indicators, exhibited good predictive performance. This model can assist in the early identification and intervention of asymptomatic individuals at high risk for cardiovascular disease.
Humans ; Male ; Middle Aged ; Female ; Nomograms ; Retrospective Studies ; Risk Factors ; Plaque, Atherosclerotic/diagnosis* ; Aged ; Adult ; Physical Examination ; Logistic Models ; Cardiovascular Diseases/epidemiology* ; ROC Curve

Vascular aging refers to the degenerative changes in vascular wall structure and vasodilatory function, forming the pathophysiological basis for the onset and progression of cardiovascular disease (CVD). Pulse wave velocity (PWV), a non-invasive method for evaluating and detecting early vascular aging, has achieved significant results in predicting CVD risk and evaluating the efficacy of pharmacological treatments. PWV can effectively predict CVD risk across various populations, including healthy individuals, patients with hypertension, diabetes, and chronic inflammatory diseases. In patients with comorbidities such as hypertension, pharmacological interventions, such as anti-inflammatory, lipid-lowering, anti-hypertensive, and anti-diabetic treatments, can effectively reduce PWV and thus slow down vascular aging. Therefore, PWV is not only a vital tool for assessing early vascular aging but also an important indicator for evaluating treatment outcomes. Regular monitoring of PWV levels is of great significance in predicting CVD risk, evaluating therapeutic efficacy, and guiding clinical decision-making.
Humans ; Pulse Wave Analysis/methods* ; Cardiovascular Diseases/diagnosis* ; Aging/physiology* ; Vascular Stiffness/physiology* ; Hypertension/physiopathology* ; Risk Factors ; Blood Vessels/physiopathology*

BACKGROUND: The hemoglobin glycation index (HGI) was developed to quantify glucose metabolism and individual differences and proved to be a robust measure of individual glycosylated hemoglobin (HbA1c) bias. Here, we aimed to explore the relationship between different HGIs and the risk of 5-year major adverse cardiovascular events (MACEs) by performing a large multicenter cohort study in China. METHODS: A total of 9791 subjects from the Risk Evaluation of Cancers in Chinese Diabetic Individuals: a Longitudinal Study (the REACTION study) were divided into five subgroups (Q1-Q5) with the HGI quantiles (≤5th, >5th and ≤33.3th, >33.3th and ≤66.7th, >66.7th and ≤95th, and >95th percentile). A multivariate logistic regression model constructed by the restricted cubic spline method was used to evaluate the relationship between the HGI and the 5-year MACE risk. Subgroup analysis between the HGI and covariates were explored to detect differences among the five subgroups. RESULTS: The total 5-year MACE rate in the nationwide cohort was 6.87% (673/9791). Restricted cubic spline analysis suggested a U-shaped correlation between the HGI values and MACE risk after adjustment for cardiovascular risk factors ( χ2 = 29.5, P <0.001). After adjustment for potential confounders, subjects with HGIs ≤-0.75 or >0.82 showed odds ratios (ORs) for MACE of 1.471 (95% confidence interval [CI], 1.027-2.069) and 2.222 (95% CI, 1.641-3.026) compared to subjects with HGIs of >-0.75 and ≤-0.20. In the subgroup with non-coronary heart disease, the risk of MACE was significantly higher in subjects with HGIs ≤-0.75 (OR, 1.540 [1.039-2.234]; P = 0.027) and >0.82 (OR, 2.022 [1.392-2.890]; P <0.001) compared to those with HGIs of ≤-0.75 or >0.82 after adjustment for potential confounders. CONCLUSIONS We found a U-shaped correlation between the HGI values and the risk of 5-year MACE. Both low and high HGIs were associated with an increased risk of MACE. Therefore, the HGI may predict the 5-year MACE risk.
Humans ; Cohort Studies ; Longitudinal Studies ; Diabetes Mellitus, Type 2/diagnosis* ; Maillard Reaction ; Glycated Hemoglobin ; Cardiovascular Diseases

Cardiovascular disease is the leading cause of death worldwide, accounting for 48.0% of all deaths in Europe and 34.3% in the United States. Studies have shown that arterial stiffness takes precedence over vascular structural changes and is therefore considered to be an independent predictor of many cardiovascular diseases. At the same time, the characteristics of Korotkoff signal is related to vascular compliance. The purpose of this study is to explore the feasibility of detecting vascular stiffness based on the characteristics of Korotkoff signal. First, the Korotkoff signals of normal and stiff vessels were collected and preprocessed. Then the scattering features of Korotkoff signal were extracted by wavelet scattering network. Next, the long short-term memory (LSTM) network was established as a classification model to classify the normal and stiff vessels according to the scattering features. Finally, the performance of the classification model was evaluated by some parameters, such as accuracy, sensitivity, and specificity. In this study, 97 cases of Korotkoff signal were collected, including 47 cases from normal vessels and 50 cases from stiff vessels, which were divided into training set and test set according to the ratio of 8 : 2. The accuracy, sensitivity and specificity of the final classification model was 86.4%, 92.3% and 77.8%, respectively. At present, non-invasive screening method for vascular stiffness is very limited. The results of this study show that the characteristics of Korotkoff signal are affected by vascular compliance, and it is feasible to use the characteristics of Korotkoff signal to detect vascular stiffness. This study might be providing a new idea for non-invasive detection of vascular stiffness.
Humans ; Vascular Stiffness ; Neural Networks, Computer ; Cardiovascular Diseases/diagnosis* ; Sensitivity and Specificity

Humans ; Child ; Cardiovascular Diseases/diagnosis* ; Exercise Test ; Oxygen Consumption

Cardiovascular disease is a major threat to human health and has become the leading cause of death worldwide; therefore, early diagnosis and treatment are of great value. Due to its miniaturization, integration, and ease of operation, microfluidic technology enables the rapid, multi-target detection of cardiovascular disease markers and significantly facilitates the early and rapid diagnosis of cardiovascular disease. This article reviews the research progress of microfluidics in cardiovascular disease detection, analyzes its advantages and weaknesses in the rapid detection of protein, lipid, and nucleic acid biomarkers, hopes to provide a reference to promote the quick detection technology of cardiovascular disease, and thus proposes new considerations for the early management of cardiovascular disease.
Humans ; Microfluidics ; Cardiovascular Diseases/diagnosis* ; Biomarkers ; Early Diagnosis