Early Detection Of Cardiovascular Disease Research Articles

Discrete Wavelet Transform based ECG classification using gcForest: A deep ensemble method.

Cardiovascular diseases (CVDs) are the leading global cause of mortality, necessitating advanced diagnostic tools for early detection. The electrocardiogram (ECG) is pivotal in diagnosing cardiac abnormalities due to its non-invasive nature. This study aims to propose a novel approach for ECG signal classification, addressing the challenges posed by the complexity of ECG signals associated with various diseases. Our method integrates Discrete Wavelet Transform (DWT) for feature extraction, capturing salient features of cardiovascular diseases. Subsequently, the gcForest model is employed for efficient classification. The approach is tested on the MIT-BIH Arrhythmia Database. The proposed method demonstrates promising results on the MIT-BIH Arrhythmia Database, achieving a test accuracy of 98.55%, recall of 98.48%, precision of 98.44%, and an F1 score of 98.46%. Additionally, the model exhibits robustness and low sensitivity to hyper-parameters. The combined use of DWT and the gcForest model proves effective in ECG signal classification, showcasing high accuracy and reliability. This approach holds potential for improving early detection of cardiovascular diseases, contributing to enhanced cardiac healthcare.

Early Detection of Cardiovascular Disease with Different Machine Learning Approaches

With the increase in mortality rate around the world in recent years, cardiovascular diseases (CVD) have swiftly become a leading cause of morbidity, and therefore there arises a need for early diagnosis of disease to ensure effective treatment. With machine learning emerging as a promising tool for the detection, this study aims to propose and compare various algorithms for the detection of CVD via several evaluation metrics including accuracy, precision, F1 score, and recall. ML has the ability and potential to improve CVD prediction, detection, and treatment by analysis of patient information and identification of patterns that may be difficult for humans to interpret and detect. Several state-of-the-art ML and DL models such as Decision Tree, XGBoost, KNN, and ANN were employed. The results of these models reflect the potential of Machine Learning in the detection of CVD detection and subsequently highlight the need for their integration into clinical practice along with the suggestion of the development of robust and accurate models to improve the predictions. This integration, however, significantly helps in the reduction of the burden of CVD on healthcare systems.

Abstract A022: Detecting cardiovascular disease risk in early-stage endometrial cancer survivors: preliminary evidence of pulse wave velocity and social vulnerability index

Abstract BACKGROUND: Endometrial cancer survivors (ECS) experience high rates of cardiovascular disease (CVD) likely due to lifestyle and social-environmental factors, including high obesity rates up to 60%. Early detection of CVD is crucial in order to intervene; however, strategies to identify ECS most at risk for CVD are currently lacking. The gold-standard methodology to non-invasively measure CVD is pulse wave velocity (PWV), and one way to identify social-environmental susceptibility is the Centers for Disease Control social vulnerability index (SVI). PURPOSE: Therefore, the purpose of this study is to investigate (1) CVD risk in stage 1 ECS using PWV and (2) the social-environmental influence on CVD risk using SVI. METHODS: Stage 1 ECS who were 1-12 months post-treatment, with a BMI ≥ 25.0 kg/m2, age 50-80 years, and English speaking were recruited in the gynecology-oncology clinic. Oscillometric PWV was measured in a supine position via Mobil-O-Graph. Body composition [body fat percentage (%)] was measured via Bioelectrical Impedance Analysis. Participant zip code was used to determine SVI of their county of residence. SVI is defined as low-medium (0.00-0.49), medium-high (0.50-0.69), and high (0.70-1.00). Linear regression was used to compare PWV and SVI. RESULTS: Seventeen ECS (65% White, 25% Black, 5% Asian, 5% American Indian, 64 ± 7 years old, 6 ± 4 months post-treatment, 44 ± 6% body fat) participated in the study. Participants resided in counties with low-medium (18%), medium-high (24%), and high (58%) SVI and PWV was measured as 8.2 ± 0.8 m/s, 9.1 ± 0.8 m/s, and 9.7 ± 1.0 m/s respectively. The overall regression was not statistically significant (R=0.38, R2=0.14, F=1.15, p=0.34). DISCUSSION: Overall, PWV was elevated in ECS residing in counties with medium-high and high SVI categories compared to normative data. PWV can be used to non-invasively measure CVD risk in clinic in early-stage ECS. Despite failing to reach statistical significance, a 1.0 m/s change is considered to be a clinically meaningful difference in PWV. Therefore, ECS residing in counties with high SVI may be at greater CVD risk compared to those living in less vulnerable communities. Further research is needed, including a larger sample size, to identify successful interventions to reduce CVD in ECS most at risk. Citation Format: Lauren C. Bates-Fraser, Victoria Bae-Jump, Lee Stoner, Erik D. Hanson. Detecting cardiovascular disease risk in early-stage endometrial cancer survivors: preliminary evidence of pulse wave velocity and social vulnerability index [abstract]. In: Proceedings of the AACR Special Conference on Endometrial Cancer: Transforming Care through Science; 2023 Nov 16-18; Boston, Massachusetts. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(5_Suppl):Abstract nr A022.

Multi-Feature Decision Fusion Network for Heart Sound Abnormality Detection and Classification.

The heart sound reflects the movement status of the cardiovascular system and contains the early pathological information of cardiovascular diseases. Automatic heart sound diagnosis plays an essential role in the early detection of cardiovascular diseases. In this study, we aim to develop a novel end-to-end heart sound abnormality detection and classification method, which can be adapted to different heart sound diagnosis tasks. Specifically, we developed a Multi-feature Decision Fusion Network (MDFNet) composed of a Multi-dimensional Feature Extraction (MFE) module and a Multi-dimensional Decision Fusion (MDF) module. The MFE module extracted spatial features, multi-level temporal features and spatial-temporal fusion features to learn heart sound characteristics from multiple perspectives. Through deep supervision and decision fusion, the MDF module made the multi-dimensional features extracted by the MFE module more discriminative, and fused the decision results of multi-dimensional features to integrate complementary information. Furthermore, attention modules were embedded in the MDFNet to emphasize the fundamental heart sounds containing effective feature information. Finally, we proposed an efficient data augmentation method to circumvent the diagnosis performance degradation caused by the lack of cardiac cycle segmentation in other end-to-end methods. The developed method achieved an overall accuracy of 94.44% and a F1-score of 86.90% on the binary classification task and a F1-score of 99.30% on the five-classification task. Our method outperformed other state-of-the-art methods and had good clinical application prospects.

Early Detection of Cardiovascular Disease Utilizing Machine Learning Techniques: Evaluating the Predictive Capabilities of Seven Algorithms

Heart disease is the leading cause of death in developed countries, as it causes many deaths annually. Despite the availability of effective treatments, heart disease remains a significant challenge to public health, so early detection is essential in enhancing patient outcomes and reducing mortality. Artificial intelligence seeks to help physicians make the right decisions about a patient's health condition. In this regard, the authors decided to utilize machine learning techniques (k-nearest neighbor, decision tree, linear regression, support vector machine, naïve bayes, multilayer perceptron, random forest) to contribute to the classification of the heart disease dataset, where it is determined whether a person is suffering or not. After that, the execution of all techniques will be measured, and the accuracy of each technique will be compared to determine the most suitable performer. The public dataset is organized from the UC Irvine machine learning repository and have significantly different characteristics. The dataset will be divided such that 80% of the data is designated for training and 20% is designated for testing. This article concluded that the adequate performance is for the multilayer perceptron technique, as it gained an accuracy of more than 88%, while the poor performance is for the decision tree technique, as it gained an accuracy of more than 79%.

Cardiovascular Disease Preliminary Diagnosis Application Using SQL Queries: Filling Diagnostic Gaps in Resource-Constrained Environments

Cardiovascular diseases (CVDs) are chronic diseases associated with a high risk of mortality and morbidity. Early detection of CVD is crucial to initiating timely interventions, such as appropriate counseling and medication, which can effectively manage the condition and improve patient outcomes. This study introduces an innovative ontology-based model for the diagnosis of CVD, aimed at improving decision support systems in healthcare. We developed a database model inspired by ontology principles, tailored for the efficient processing and analysis of CVD-related data. Our model’s effectiveness is demonstrated through its integration into a web application, showcasing significant improvements in diagnostic accuracy and utility in resource-limited settings. Our findings indicate a promising direction for the application of artificial intelligence (AI) in early CVD detection and management, offering a scalable solution to healthcare challenges in diverse environments.

M2AI-CVD: Multi-modal AI approach cardiovascular risk prediction system using fundus images

ABSTRACT Cardiovascular diseases (CVD) represent a significant global health challenge, often remaining undetected until severe cardiac events, such as heart attacks or strokes, occur. In regions like Qatar, research focused on non-invasive CVD identification methods, such as retinal imaging and dual-energy X-ray absorptiometry (DXA), is limited. This study presents a groundbreaking system known as Multi-Modal Artificial Intelligence for Cardiovascular Disease (M2AI-CVD), designed to provide highly accurate predictions of CVD. The M2AI-CVD framework employs a four-fold methodology: First, it rigorously evaluates image quality and processes lower-quality images for further analysis. Subsequently, it uses the Entropy-based Fuzzy C Means (EnFCM) algorithm for precise image segmentation. The Multi-Modal Boltzmann Machine (MMBM) is then employed to extract relevant features from various data modalities, while the Genetic Algorithm (GA) selects the most informative features. Finally, a ZFNet Convolutional Neural Network (ZFNetCNN) classifies images, effectively distinguishing between CVD and Non-CVD cases. The research’s culmination, tested across five distinct datasets, yields outstanding results, with an accuracy of 95.89%, sensitivity of 96.89%, and specificity of 98.7%. This multi-modal AI approach offers a promising solution for the accurate and early detection of cardiovascular diseases, significantly improving the prospects of timely intervention and improved patient outcomes in the realm of cardiovascular health.

A novel attention-based cross-modal transfer learning framework for predicting cardiovascular disease

Cardiovascular disease (CVD) remains a leading cause of death globally, presenting significant challenges in early detection and treatment. The complexity of CVD arises from its multifaceted nature, influenced by a combination of genetic, environmental, and lifestyle factors. Traditional diagnostic approaches often struggle to effectively integrate and interpret the heterogeneous data associated with CVD. Addressing this challenge, we introduce a novel Attention-Based Cross-Modal (ABCM) transfer learning framework. This framework innovatively merges diverse data types, including clinical records, medical imagery, and genetic information, through an attention-driven mechanism. This mechanism adeptly identifies and focuses on the most pertinent attributes from each data source, thereby enhancing the model’s ability to discern intricate interrelationships among various data types. Our extensive testing and validation demonstrate that the ABCM framework significantly surpasses traditional single-source models and other advanced multi-source methods in predicting CVD. Specifically, our approach achieves an accuracy of 93.5%, precision of 92.0%, recall of 94.5%, and an impressive area under the curve (AUC) of 97.2%. These results not only underscore the superior predictive capability of our model but also highlight its potential in offering more accurate and early detection of CVD. The integration of cross-modal data through attention-based mechanisms provides a deeper understanding of the disease, paving the way for more informed clinical decision-making and personalized patient care.

Abnormal Heart Sound Detection using Time-Frequency Analysis and Machine Learning Techniques

Phonocardiogram (PCG) signals contains valuable information pertaining to heart valve functionality, rendering them potentially useful for early detection of cardiovascular diseases. Automated classification of heart sounds harbors great promise for identifying cardiac pathologies. This paper introduces a novel automated approach to classify normal and abnormal heart sounds. Our methodology involves partitioning heart sounds into four segments: S1, S2, systolic, and diastolic, followed by extraction of time–frequency and time-statistical features. Prior to data classification, we employ two techniques - particle Swarm optimization (PSO) and Sequential Forward Feature Selection (SFFS) - for efficient feature selection. We assess the performance of the proposed method on the Physionet Challenge 2016 database, utilizing the 10-fold cross-validation method. To address the issue of dataset imbalance, we apply the synthetic minority over-sampling technique (SMOTE) to create balanced datasets. Our approach surpasses existing methods in the literature, as evidenced by its superior accuracy, sensitivity, and specificity metrics. Specifically, our method achieves an accuracy of 98.03%, a sensitivity of 97.64%, and a specificity of 98.43% in distinguishing normal from abnormal heart sounds on the Physionet database. These findings outperform the results obtained by previously established methods evaluated on the Physionet 2016 challenge database.

Use of computed tomography coronary calcium score for prediction of cardiovascular events in cancer patients: a retrospective cohort analysis

BackgroundCT- coronary calcium score, is one of the most studied and widely available modalities in cardiovascular medicine. Coronary artery calcium score (CACS) is an established predictor of coronary artery disease. The ‘standard of care’ diagnostic modality to measure CACS is ECG-gated Cardiac Multi-Detector Computed Tomography. There is convincing evidence of a strong association between CACS and major cardiovascular (CV) events in asymptomatic individuals. Cancer patients (C) may have a higher risk for CV disease than non-cancer patients (NC) related not only to cancer treatments but also to shared biological factors and pathways. Thus, identifying tools for early detection of CV disease in this population is of utmost importance.MethodsA retrospective cohort analysis was performed with patients from Cleveland Clinic Florida and Ohio who had CACS from 2017 to 2021. Patients who had cancer diagnosis prior to CACS were matched to NC for age and sex. CV events after their index CACS events were compared between C and NC, and matched control and propensity analysis were conducted.ResultsTen thousand seven hundred forty-two patients had CACS; 703 cancer patients had CACS and were eligible. Extensive CACS (> 400) were significantly higher in cancer, 94 (13.37%) vs non-cancer patients, 76 (10.83%), P = 0.011. Furthermore, after propensity matched analysis, CACS > 400 was 14.8% in C vs 9.6% in NC, P = < 0.05. CV events were similar in both cohorts (p = NS), despite less CV risk factors in cancer patients (P = < 0.05). For the combined moderate (101–400) & extensive (> 400) CACS, the prevalence of stroke and peripheral arterial disease, a marker of systemic atherosclerosis, was significantly higher in patients with cancer (P < 0.01).ConclusionsDespite having fewer CV risk factors in our study, similar CACS in cancer patients are suggestive of a higher prevalence of CV disease independent of traditional risk factors. High CACS and the overall prevalence of vascular events were more frequent in patients with cancer. Higher prevalence of peripheral arterial disease and cerebrovascular accident further suggests the increased atherosclerotic burden in C.

The Comparative Early Prediction Model for Cardiovascular Disease Using Machine Learning

Cardiovascular disease (CVD) is a leading cause of death and a major contributor to disability. Early detection of cardiovascular disease using ANFIS has the potential to reduce costs and simplify treatment. This study aims to develop a prediction model using ANFIS (Adaptive Neuro-Fuzzy Inference System) for early detection of cardiovascular disease. The dataset used consists of 500 data with 12 features, including various risk factors such as blood sugar levels, cholesterol, uric acid, systolic blood pressure, diastolic blood pressure, body mass index (BMI), age, smoking habits, lifestyle, genetic factors, and gender, and one label feature. This study compares cardiovascular disease prediction models using machine learning methods, namely Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), and ANFIS. The development of the KNN algorithm involves the value of K=5 with the Euclidian distance measure. The SVM algorithm used a kernel cache of 200 and a convergence epsilon of 0.001. The ANFIS model was built using 500 data sets divided into training (70%) and testing (30%) data, with learning rate variations of 0.01, 0.05, 0.1, 0.2, and 0.5. The results of testing the early detection model show for SVM, the accuracy value is 0.760, the precision value is 0.839, and the recall value is 0.671. For the KNN model, the accuracy value is 0.758, the precision value is 0.768, and the recall value is 0.771. As for the ANFIS model, the accuracy value reaches 0.989, precision value 0.996, and recall value 0.988. The model using ANFIS has the highest performance. Further study of the model using ANFIS with learning rate variations shows that a learning rate of 0.1 provides the most optimal performance.

Artificial intelligence in cardiovascular medicine: An updated review of the literature.

Screening and early detection of cardiovascular disease (CVD) are crucial for managing progress and preventing related morbidity. In recent years, several studies have reported the important role of Artificial intelligence (AI) technology and its integration into various medical sectors. AI applications are able to deal with the massive amounts of data (medical records, ultrasounds, medications, and experimental results) generated in medicine and identify novel details that would otherwise be forgotten in the mass of healthcare data sets. Nowadays, AI algorithms are currently used to improve diagnosis of some CVDs including heart failure, atrial fibrillation, hypertrophic cardiomyopathy and pulmonary hypertension. This review summarized some AI concepts, critical execution requirements, obstacles, and new applications for CVDs.

ANRIL, H19 and TUG1: a review about critical long non-coding RNAs in cardiovascular diseases.

Cardiovascular diseases are the leading cause of death worldwide. They are non-transmissible diseases that affect the cardiovascular system and have different etiologies such as smoking, lipid disorders, diabetes, stress, sedentary lifestyle and genetic factors. To date, lncRNAs have been associated with increased susceptibility to the development of cardiovascular diseases such as hypertension, acute myocardial infarction, stroke, angina and heart failure. In this way, lncRNAs are becoming a very promising point for the prevention and diagnosis of cardiovascular diseases. Therefore, this review highlights the most important and recent discoveries about the mechanisms of action of the lncRNAs ANRIL, H19 and TUG1 and their clinical relevance in these pathologies. This may contribute to early detection of cardiovascular diseases in order to prevent the pathological phenotype from becoming established.

Hidden Markov Models for early detection of cardiovascular diseases

Hidden Markov Models for early detection of cardiovascular diseases

Diagnostic yield of a proactive strategy for early detection of cardiovascular disease versus usual care in adults with type 2 diabetes or chronic obstructive pulmonary disease in primary care in the Netherlands (RED-CVD): a multicentre, pragmatic, cluster-randomised, controlled trial

Progressive cardiovascular diseases (eg, heart failure, atrial fibrillation, and coronary artery disease) are often diagnosed late in high-risk individuals with common comorbidities that might mimic or mask symptoms, such as chronic obstructive pulmonary disease (COPD) and type 2 diabetes. We aimed to assess whether a proactive diagnostic strategy consisting of a symptom and risk factor questionnaire and low-cost and accessible tests could increase diagnosis of progressive cardiovascular diseases in patients with COPD or type 2 diabetes in primary care. In this multicentre, pragmatic, cluster-randomised, controlled trial (RED-CVD), 25 primary care practices in the Netherlands were randomly assigned to usual care or a proactive diagnostic strategy conducted during routine consultations and consisting of a validated symptom questionnaire, followed by physical examination, N-terminal-pro-B-type natriuretic peptide measurement, and electrocardiography. We included adults (≥18 years) with type 2 diabetes, COPD, or both, who participated in a disease management programme. Patients with an established triple diagnosis of heart failure, atrial fibrillation, and coronary artery disease were excluded. In the case of abnormal findings, further work-up or treatment was done at the discretion of the general practitioner. The primary endpoint was the number of newly diagnosed cases of heart failure, atrial fibrillation, and coronary artery disease, adjudicated by an expert clinical outcome committee using international guidelines, at 1-year follow-up, in the intention-to-treat population. Between Jan 31, 2019, and Oct 7, 2021, we randomly assigned 25 primary care centres: 11 to usual care and 14 to the intervention. We included patients between June 21, 2019, and Jan 31, 2022. Following exclusion of ineligible patients and those who did not give informed consent, 1216 participants were included: 624 (51%) in the intervention group and 592 (49%) in the usual care group. The mean age of participants was 68·4 years (SD 9·4), 482 (40%) participants were female, and 734 (60%) were male. During 1 year of follow-up, 50 (8%) of 624 participants in the intervention group and 18 (3%) of 592 in the control group were newly diagnosed with heart failure, atrial fibrillation, or coronary artery disease (adjusted odds ratio 2·97 [95% CI 1·66-5·33]). This trial is registered with the Netherlands Trial Registry, NTR7360, and was completed on Jan 31, 2023. An easy-to-use, proactive, diagnostic strategy more than doubled the number of new diagnoses of heart failure, atrial fibrillation, and coronary artery disease in patients with type 2 diabetes or COPD in primary care compared with usual care. Although the effect on patient outcomes remains to be studied, our diagnostic strategy might contribute to improved early detection and timely initiation of treatment in individuals with cardiovascular disease. Dutch Heart Foundation.

Men with erectile dysfunction (ED) should be screened for cardiovascular risk factors - Cost-benefit considerations in Swiss men.

Background: Current evidence indicates that erectile dysfunction (ED) is an independent risk factor for future cardiovascular events. This study aimed to estimate the cost-effectiveness of screening and subsequent preventive treatment for cardiovascular risk factors among men newly diagnosed with ED from the Swiss healthcare system perspective. Methods: Based on known data on ED and cardiovascular disease (CVD) prevalence and incidence costs and effects of a screening intervention for cardiovascular risk including corresponding cardiovascular prevention in men with ED were calculated for the Swiss population over a period of 10 years. Results: Screening and cardiovascular prevention over a period of 10 years in Swiss men with ED of all seriousness degrees, moderate and severe ED only, or severe ED only can probably avoid 41,564, 35,627, or 21,206 acute CVD events, respectively. Number needed to screen (NNS) to prevent one acute CVD event is 30, 23, and 10, respectively. Costs for the screening intervention are expected to be covered at the seventh, the fifth, and the first year, respectively. Conclusion: Screening and intervention for cardiovascular risk factors in men suffering from ED is a cost-effective tool not only to strengthen prevention and early detection of cardiovascular diseases but also to avoid future cardiovascular events.

Emerging Biomarkers for Early Detection of Cardiovascular Disease

This extensive study explores the field of novel biomarkers for the early detection of cardiovascular disease (CVD), looking at a variety of indicators, including circulating endothelial cells, growth differentiation factor-15 (GDF-15), high-sensitivity C-reactive protein (hs-CRP), microRNAs, and myeloperoxidase (MPO). The review emphasizes how important these indicators are to improving CVD risk assessment, prognosis, and treatment plans. While each biomarker offers distinct insights into particular facets of cardiovascular health, multi-biomarker panel integration is suggested for a more thorough knowledge. The paper also discusses the difficulties with standardization, moral issues, and legal restrictions related to using these biomarkers in therapeutic settings. In addition, the revolutionary potential of these new biomarkers in conjunction with state-of-the-art technologies is emphasized, providing a promising path towards precision cardiovascular care and customized medicine

CAT-Seg: cascaded medical assistive tool integrating residual attention mechanisms and Squeeze-Net for 3D MRI biventricular segmentation

Cardiac image segmentation is a critical step in the early detection of cardiovascular disease. The segmentation of the biventricular is a prerequisite for evaluating cardiac function in cardiac magnetic resonance imaging (CMRI). In this paper, a cascaded model CAT-Seg is proposed for segmentation of 3D-CMRI volumes. CAT-Seg addresses the problem of biventricular confusion with other regions and localized the region of interest (ROI) to reduce the scope of processing. A modified DeepLabv3+ variant integrating SqueezeNet (SqueezeDeepLabv3+) is proposed as a part of CAT-Seg. SqueezeDeepLabv3+ handles the different shapes of the biventricular through the different cardiac phases, as the biventricular only accounts for small portion of the volume slices. Also, CAT-Seg presents a segmentation approach that integrates attention mechanisms into 3D Residual UNet architecture (3D-ResUNet) called 3D-ARU to improve the segmentation results of the three major structures (left ventricle (LV), Myocardium (Myo), and right ventricle (RV)). The integration of the spatial attention mechanism into ResUNet handles the fuzzy edges of the three structures. The proposed model achieves promising results in training and testing with the Automatic Cardiac Diagnosis Challenge (ACDC 2017) dataset and the external validation using MyoPs. CAT-Seg demonstrates competitive performance with state-of-the-art models. On ACDC 2017, CAT-Seg is able to segment LV, Myo, and RV with an average minimum dice symmetry coefficient (DSC) performance gap of 1.165%, 4.36%, and 3.115% respectively. The average maximum improvement in terms of DSC in segmenting LV, Myo and RV is 4.395%, 6.84% and 7.315% respectively. On MyoPs external validation, CAT-Seg outperformed the state-of-the-art in segmenting LV, Myo, and RV with an average minimum performance gap of 6.13%, 5.44%, and 2.912% respectively.

A Novel Convolutional Neural Network Deep Learning Implementation for Cuffless Heart Rate and Blood Pressure Estimation

Cardiovascular diseases (CVDs) affect components of the circulatory system responsible for transporting blood through blood vessels. The measurement of the mechanical force acting on the walls of blood vessels, as well as the blood flow between heartbeats and when the heart is at rest, is known as blood pressure (BP). Regular assessment of BP can aid in the prevention and early detection of CVDs. In the present research, a deep learning algorithm was developed to accurately calculate both blood pressure (BP) and heart rate (HR) by extracting relevant features from photoplethysmogram (PPG), electrocardiogram (ECG), and ABP signals. This algorithm was implemented using the Medical Information Mart for Intensive Care (MIMIC-II) dataset. It captures vital blood pressure-related features extracted from the PPG signal and accounts for the time relationship with the ECG. The algorithm also determines the values of systolic blood pressure (SBP) and diastolic blood pressure (DBP) based on the ABP waveform through a convolutional neural network and stepwise multivariate linear regression. In comparison with other established BP measurement methods, our proposed approach achieved better results, with a mean absolute error (MAE) of approximately 4.7 mmHg for SBP and 2.1 mmHg for DBP, respectively. The standard deviation (STD) for SBP and DBP was approximately 7.6 mmHg and 3.9 mmHg, respectively. This study makes a valuable contribution to the healthcare field by introducing a novel, cost-effective continuous BP measurement method with improved accuracy while also minimizing the data dimension without losing any important information.

DS-CNN: Dual-Stream Convolutional Neural Networks-Based Heart Sound Classification for Wearable Devices

Cardiovascular diseases (CVDs) is considered a serious public health problem due to the uncertainty of its onset. Consuming wearable devices have increasing popularities for healthcare monitoring, and many of them are capable of continuous monitoring and early detection of CVDs. This paper proposes a framework for heart sound detection that can be considered for deployment on smart wearable devices to screen CVDs conveniently. A dual-stream convolutional neural network (DS-CNN) is developed to detect abnormal ones from short-term heart sound recordings. Preprocessing module is first employed for noise filtering and amplitude normalization. Then short-time Fourier transform and higher-order spectral are introduced for feature extraction, whose products are subsequently fed into the DS-CNN for screening abnormal heart sound signals. Two open accessible datasets are employed for performance evaluation. The results well demonstrate the classification accuracy of the proposed DS-CNN, and also indicate its advantages for adapting to heart sound recordings collected by different equipments.