Search

Background: Due to the limitations of current methods for detecting obstructive coronary artery disease (CAD), many individuals are mistakenly or unnecessarily referred for coronary angiography (CAG). Objectives: Our goal is to create a comprehensive database of heart sounds in CAD and develop accurate deep learning algorithms to efficiently detect obstructive CAD based on heart sound signals. This will enable effective screening before undergoing CAG. Methods: We included 320 subjects suspected of CAD who underwent CAG. We employed advanced filtering techniques and state-of-the-art deep learning models (VGG-16, 1D CNN, and ResNet18) to analyze the heart sound signals and identify obstructive CAD (defined as at least one ≥50 % stenosis). To assess the performance of our models, we prospectively recruited an additional 80 subjects for testing. Results: In the test set, VGG-16 exhibited the highest performance with an area under the ROC curve (AUC) of 0.834 (95 % CI, 0.736–0.930), while ResNet-18 and CNN-7 achieved AUCs of only 0.755 (95 % CI, 0.614–0.819) and 0.652 (95 % CI, 0.554–0.770) respectively. VGG-16 demonstrated a sensitivity of 80.4 % and specificity of 86.2 % in the test set. The combined diagnostic model of VGG and DF scores achieved an AUC of 0.915 (95 % CI: 0.855–0.974), and the AUC for VGG combined with PTP scores was 0.908 (95 % CI: 0.845–0.971). The sensitivity and specificity of VGG-16 exceeded 0.85 in patients with coronary artery occlusion and those with 3 vascular lesions. Conclusions: Our deep learning model, based on heart sounds, offers a non-invasive and efficient screening method for obstructive CAD. It is expected to significantly reduce the number of unnecessary referrals for downstream screening.

Objective We aimed to explore the association between periodontitis and abdominal aortic calcification (AAC) among a nationally representative sample of US adults.Design Cross- sectional study.Setting The National Health and Nutrition Examination Survey (2013–2014).Participants A total of 2149 participants aged 40 years or older who have complete information for periodontitis and AAC assessment test were included in this study.Primary and secondary outcome measures AAC scores can be accurately identified on lateral spine images obtained by dual-energy X-ray absorptiometry, and both the AAC-24 and AAC-8 semiquantitative scoring tools were used for AAC evaluation. Linear regression analysis was used to investigate the relationship between periodontitis and the AAC-8 and AAC-24 scores. Multivariate logistic regression models and reported ORs were used to examine the relationship between periodontitis and AAC.Results The prevalence of severe periodontitis combined with severe AAC was 8.49%–8.54%. According to the AAC-8 and AAC-24 score classifications, patients with severe periodontitis had higher odds of severe AAC (AAC-8 score ≥3: (OR: 2.53; 95% CI 1.04 to 6.17) and AAC-24 score >6: (OR: 3.60; 95% CI 1.48 to 8.78)). A positive association between mild–moderate periodontitis and severe AAC was found only when the AAC-24 score was applied (OR: 2.25; 95% CI 1.24 to 4.06). In the subgroup analyses, the likelihood ratio test showed no multiplicative interaction (all p value for interaction >0.05).Conclusions The findings showed that periodontitis is associated with an increased risk of severe AAC in the US population aged 40 years and older; this requires further large-scale prospective studies for confirmation.

Objective To investigate the association between red cell distribution width (RDW) and the RDW to platelet count ratio (RPR) and cardiovascular diseases (CVDs) and to further investigate whether the association involves population differences and dose–response relationships.Design Cross-sectional population-based study.Setting The National Health and Nutrition Examination Survey (1999–2020).Participants A total of 48 283 participants aged 20 years or older (CVD, n=4593; non-CVD, n=43 690) were included in this study.Primary and secondary outcome measures The primary outcome was the presence of CVD, while the secondary outcome was the presence of specific CVDs. Multivariable logistic regression analysis was performed to determine the relationship between RDW or the RPR and CVD. Subgroup analyses were performed to test the interactions between demographics variables and their associations with disease prevalence.Results A logistic regression model was fully adjusted for potential confounders; the ORs with 95% CIs for CVD across the second to fourth quartiles were 1.03 (0.91 to 1.18), 1.19 (1.04 to 1.37) and 1.49 (1.29 to 1.72) for RDW (p for trend

Background and objectiveThe association between sleep-related disorders and cardiovascular diseases (CVDs) remains controversial and lacks epidemiological evidence in the general population. We investigated whether sleep-related disorders are related to CVDs in a large, nationally representative, diverse sample of American adults.Materials and methodsData were collected from the National Health and Nutrition Examination Survey (NHANES) 2005–2008. Logistic regression was performed to explore associations of sleep-related disorders with the prevalence of total and specific CVDs. Stratified subgroup analysis was performed to exclude interactions between variables and sleep-related disorders. Non-linearity was explored using restricted cubic splines.ResultsIn total, 7,850 participants aged over 20 years were included. After controlling for confounders, multivariate regression analysis showed that sleep problems were associated increases in risk of 75% for CVD (OR: 1.75; 95% CI 1.41, 2.16), 128% for congestive heart failure (CHF) (OR: 2.28; 95% CI 1.69, 3.09), 44% for coronary heart disease (CHD) (OR: 1.44; 95% CI 1.12, 1.85), 96% for angina pectoris (AP) (OR: 1.96; 95% CI 1.40, 2.74), 105% for heart attack (OR: 2.05; 95% CI 1.67, 2.53) and 78% for stroke (OR: 1.78; 95% CI 1.32, 2.40). Daytime sleepiness was associated increases in risk of 54% for CVD (OR: 1.54; 95% CI 1.25, 1.89), 73% for CHF (OR: 1.73; 95% CI 1.22, 2.46), 53% for AP (OR: 1.53; 95% CI 1.12, 2.10), 51% for heart attack (OR: 1.51; 95% CI 1.18, 1.95), and 60% for stroke (OR: 1.60; 95% CI 1.09, 2.36). Participants with insufficient sleep had a 1.42-fold higher likelihood of CVD (OR: 1.42; 95% CI 1.13, 1.78) and a 1.59-fold higher likelihood of heart attack (OR: 1.59; 95% CI 1.19, 2.13) than participants with adequate sleep. Prolonged sleep-onset latency was associated with an increased risk of CVD (OR: 1.59; 95% CI 1.17, 2.15), CHF (OR: 2.08; 95% CI 1.33, 3.23) and heart attack (OR: 1.76; 95% CI 1.29, 2.41). Short sleep-onset latency was associated with a 36% reduction in stroke risk (OR: 0.64; 95% CI 0.45, 0.90). The association of sleep problems with CVD risk was more pronounced in the group younger than 60 years (p for interaction = 0.019), and the relationship between short sleep-onset latency and total CVD differed by sex (p for interaction = 0.049). Additionally, restricted cubic splines confirmed a linear relationship between sleep-onset latency time and CVD (p for non-linearity = 0.839) and a non-linear relationship between sleep duration and CVD (p for non-linearity

Background: Although machine learning (ML)-based prediction of coronary artery disease (CAD) has gained increasing attention, assessment of the severity of suspected CAD in symptomatic patients remains challenging. Methods: The training set for this study consisted of 284 retrospective participants, while the test set included 116 prospectively enrolled participants from whom we collected 53 baseline variables and coronary angiography results. The data was pre-processed with outlier processing and One-Hot coding. In the first stage, we constructed a ML model that used baseline information to predict the presence of CAD with a dichotomous model. In the second stage, baseline information was used to construct ML regression models for predicting the severity of CAD. The non-CAD population was included, and two different scores were used as output variables. Finally, statistical analysis and SHAP plot visualization methods were employed to explore the relationship between baseline information and CAD. Results: The study included 269 CAD patients and 131 healthy controls. The eXtreme Gradient Boosting (XGBoost) model exhibited the best performance amongst the different models for predicting CAD, with an area under the receiver operating characteristic curve of 0.728 (95% CI 0.623–0.824). The main correlates were left ventricular ejection fraction, homocysteine, and hemoglobin (p < 0.001). The XGBoost model performed best for predicting the SYNTAX score, with the main correlates being brain natriuretic peptide (BNP), left ventricular ejection fraction, and glycated hemoglobin (p < 0.001). The main relevant features in the model predictive for the GENSINI score were BNP, high density lipoprotein, and homocysteine (p < 0.001). Conclusions: This data-driven approach provides a foundation for the risk stratification and severity assessment of CAD. Clinical Trial Registration: The study was registered in www.clinicaltrials.gov protocol registration system (number NCT05018715).

In recent years, electronic stethoscopes have been combined with artificial intelligence (AI) technology to digitally acquire heart sounds, intelligently identify valvular disease and congenital heart disease, and improve the accuracy of heart disease diagnosis. The research on AI-based intelligent stethoscopy technology mainly focuses on AI algorithms, and the commonly used methods are end-to-end deep learning algorithms and machine learning algorithms based on feature extraction, and the hot spot for future research is to establish a large standardized heart sound database and unify these algorithms for external validation; in addition, different electronic stethoscopes should also be extensively compared so that the algorithms can be compatible with different. In addition, there should be extensive comparison of different electronic stethoscopes so that the algorithms can be compatible with heart sounds collected by different stethoscopes; especially importantly, the deployment of algorithms in the cloud is a major trend in the future development of artificial intelligence. Finally, the research of artificial intelligence based on heart sounds is still in the preliminary stage, although there is great progress in identifying valve disease and congenital heart disease, they are all in the research of algorithm for disease diagnosis, and there is little research on disease severity, remote monitoring, prognosis, etc., which will be a hot spot for future research.

In recent years, electronic stethoscopes have been combined with artificial intelligence (AI) technology to digitally acquire heart sounds, intelligently identify valvular disease and congenital heart disease, and improve the accuracy of heart disease diagnosis. The research on AI-based intelligent stethoscopy technology mainly focuses on AI algorithms, and the commonly used methods are end-to-end deep learning algorithms and machine learning algorithms based on feature extraction, and the hot spot for future research is to establish a large standardized heart sound database and unify these algorithms for external validation; in addition, different electronic stethoscopes should also be extensively compared so that the algorithms can be compatible with different. In addition, there should be extensive comparison of different electronic stethoscopes so that the algorithms can be compatible with heart sounds collected by different stethoscopes; especially importantly, the deployment of algorithms in the cloud is a major trend in the future development of artificial intelligence. Finally, the research of artificial intelligence based on heart sounds is still in the preliminary stage, although there is great progress in identifying valve disease and congenital heart disease, they are all in the research of algorithm for disease diagnosis, and there is little research on disease severity, remote monitoring, prognosis, etc., which will be a hot spot for future research. [ABSTRACT FROM AUTHOR]