Background: Transesophageal echocardiography (TEE) is the first technique of choice for evaluating the left atrial appendage flow velocity (LAAV) in clinical practice, which may cause some complications. Therefore, clinicians require a simple applicable method to screen patients with decreased LAAV. Therefore, we investigated the feasibility and accuracy of a machine learning (ML) model to predict LAAV. Method: The analysis included patients with atrial fibrillation who visited the general hospital of PLA and underwent transesophageal echocardiography (TEE) between January 2017 and December 2020. Three machine learning algorithms were used to predict LAAV. The area under the receiver operating characteristic curve (AUC) was measured to evaluate diagnostic accuracy. Results: Of the 1039 subjects, 125 patients (12%) were determined as having decreased LAAV (LAAV < 25 cm/s). Patients with decreased LAAV were fatter and showed a higher prevalence of persistent AF, heart failure, hypertension, diabetes and stroke, and the decreased LAAV group had a larger left atrium diameter and a higher serum level of NT-pro BNP than the control group (p < 0.05). Three machine-learning models (SVM model, RF model, and KNN model) were developed to predict LAAV. In the test data, the RF model performs best (R = 0.608, AUC = 0.89) among the three models. A fivefold cross-validation scheme further verified the predictive ability of the RF model. In the RF model, NT-proBNP was the factor with the strongest impact. Conclusions: A machine learning model (Random Forest model)-based simple clinical information showed good performance in predicting LAAV. The tool for the screening of decreased LAAV patients may be very helpful in the risk classification of patients with a high risk of LAA thrombosis.
Background and Objective. Atherosclerotic extent was proved to be associated with adverse cardiac events. Risk scores derived by coronary computed tomography angiography (CCTA) could identify high-risk group among patients with nonobstructive coronary artery disease (CAD), but the ability is still uncertain in the presence of diabetes mellitus (DM). The purpose of this study was to investigate the prognostic value of the atherosclerotic extent shown by CCTA in diabetic patients with nonobstructive CAD. Methods and Results. 813 DM patients (mean age years, 48.1% male) referred for CCTA due to suspected CAD in 2015-2017 were consecutively included. During a median follow-up of 31.77 months, 50 major adverse cardiovascular events (MACEs) (6.15%) were experienced, including 2 cardiovascular deaths, 14 nonfatal myocardial infarctions, 27 unstable anginas requiring hospitalization, and 7 strokes. Three groups were defined based on coronary stenosis combined with Leiden score as normal, nonobstructive , and nonobstructive . Cox models were used to assess the prognosis of plaque burden within these groups. An incremental incidence of MACE rates was observed. After adjustment for age, gender, and presence of high-risk plaque, the group of showed a higher risk than (HR: 1.88, 95% CI: 1.03-3.42, ). Similar results were observed when segment involvement score (SIS) was used for sensitivity analysis. Conclusion. Atherosclerotic extent was associated with the prognosis of DM patients with nonobstructive coronary artery disease, highlighting the importance of better risk stratification and management.
Conventional prognostic risk analysis in patients undergoing noninvasive imaging is based upon a limited selection of clinical and imaging findings, whereas machine learning (ML) algorithms include a greater number and complexity of variables. Therefore, this paper aimed to explore the predictive value of integrating coronary plaque information from coronary computed tomographic angiography (CCTA) with ML to predict major adverse cardiovascular events (MACEs) in patients with suspected coronary artery disease (CAD). Patients who underwent CCTA due to suspected coronary artery disease with a 30-month follow-up for MACEs were included. We collected demographic characteristics, cardiovascular risk factors, and information on coronary plaques by analyzing CCTA information (plaque length, plaque composition and coronary artery stenosis of 18 coronary artery segments, coronary dominance, myocardial bridge (MB), and patients with vulnerable plaque) and follow-up information (cardiac death, nonfatal myocardial infarction and unstable angina requiring hospitalization). An ML algorithm was used for survival analysis (CoxBoost). This analysis showed that chest symptoms, the stenosis severity of the proximal anterior descending branch, and the stenosis severity of the middle right coronary artery were among the top three variables in the ML model. After the 22nd month of follow-up, in the testing dataset, ML showed the largest C-index and AUC compared with Cox regression, SIS, SIS score + clinical factors, and clinical factors. The DCA of all the models showed that the net benefit of the ML model was the highest when the treatment threshold probability was between 1% and 9%. Integrating coronary plaque information from CCTA based on ML technology provides a feasible and superior method to assess prognosis in patients with suspected coronary artery disease over an approximately three-year period.
Purpose: To investigate the incremental value of noncontrast chest computed tomography (CT)-derived parameters, such as coronary artery calcium score (CACS) and epicardial adipose tissue volume (EATv), in predicting subclinical carotid atherosclerosis above traditional risk factors in community-based asymptomatic populations of northern China. Materials and Methods: A total of 2195 community-based asymptomatic individuals were enrolled from Jidong Oilfield in accordance with the PERSUADE study. CACS and EATv were measured on noncontrast chest CT. Demographics and ideal cardiovascular health score (ICHS) were collected through questionnaires. We recalculated the ideal cardiovascular health risk score (ICHRS) (ICHRS=14−ICHS) and standardized the parameters as log-CACS and body mass index adjusted EATv (i-EATv). Subclinical carotid atherosclerosis was assessed by Doppler sonography and defined as any prevalence of average carotid intima-media thickness ≥1.00 mm, appearance of carotid plaque, and carotid arterial stenosis in the areas of extracranial carotid arteries on both sides. Results: A total of 451 (20.55%) individuals presented subclinical carotid atherosclerosis. CACS and EATv were significantly greater in the subclinical group, while ICHS was lower. In multivariate logistic regression, ICHRS (odds ratio [OR]=1.143, 95% confidence interval [CI]: 1.080-1.210, P<0.001), log-CACS (OR=1.701, 95% CI: 1.480-1.955, P<0.001), and i-EATv (OR=1.254, 95% CI: 1.173-1.341, P<0.001) were found to be independent risk predictors for subclinical carotid atherosclerosis. In receiver-operating characteristic curve analysis, when combined with male sex and age level, the area under the curve of the ICHRS basic model increased from 0.627 (95% CI: 0.599-0.654) to 0.757 (95% CI: 0.732-0.781) (P<0.0001). Further adding log-CACS and i-EATv, the area under the curve demonstrated a statistically significant improvement (0.788 [95% CI: 0.765-0.812] vs. 0.757 [95% CI: 0.732-0.781], P<0.0001). Conclusion: Noncontrast chest CT-derived parameters, including CACS and EATv, could provide significant incremental improvement for predicting subclinical carotid atherosclerosis beyond the conventional risk assessment model based on ICHRS.