Prevention of cardiovascular disease

Association between electrocardiographic abnormalities and flood exposure among middle-aged and elderly people: A national longitudinal study in China

BACKGROUND

Flooding has become more frequent and intensive due to climate change, particularly in Asian countries. However, evidence on the long-term health effects of floods from large-scale studies on the vulnerable aged population in China is insufficient. This study analyzed the long-term effects of exposure to flood on electrocardiographic (ECG) abnormalities, a commonly used indicator of cardiovascular disease (CVD) screening, in middle-aged and elderly people.

METHOD

We evaluated the Chinese National Stroke Screening Survey data of 80,711 follow-up records from 38,375 participants aged > 40 years with two or more visits between 2013 and 2018 in this longitudinal study. Flood exposure was assessed as the presence of a satellite-detected flooded area within 500 m of the residence within 5 years before the survey date. The association between ECG abnormalities and flood exposure was analyzed using a random effects model with multiple adjustments. As age is an important CVD risk factor, a varying-coefficient function was derived to estimate the nonlinear modifying effect of age on the association between ECG abnormalities and flood exposure. The strata-specific associations between ECG abnormalities and flood exposure were applied to characterize vulnerability to flood.

RESULTS

The fully adjusted model suggested that flood exposure was associated with an increased risk for ECG abnormalities among the middle-aged and elderly population (odds ratio [OR] 1.74, 95 % confidence interval [CI] 1.49, 2.03). The ORs of flood exposure for ECG suggesting atrial fibrillation, ST depression, and left ventricular hypertrophy were 1.85 (95 % CI 1.16, 2.94), 6.92 (95 % CI 5.23, 9.16), and 1.55 (95 % CI 0.66, 3.65), respectively. These associations were generally robust in various subpopulations, while a sublinear curve for the negative modifying effect of age was observed on the population vulnerability to flood.

CONCLUSION

Flood exposure was associated with an increased long-term risk for an ECG abnormality. The need for effective measures to mitigate vulnerability to flood is not negligible in China.

Prediction for cardiovascular diseases based on laboratory data: An analysis of random forest model

Background

To establish a prediction model for cardiovascular diseases (CVD) in the general population based on random forests.

Methods

A retrospective study involving 498 subjects was conducted in Xi'an Medical University between 2011 and 2018. The random forest algorithm was used to screen out the variables that greatly affected the CVD prediction and to establish a prediction model. The important variables were included in the multifactorial logistic regression analysis. The area under the curve (AUC) was compared between logistic regression model and random forest model.

Results

The random forest model revealed the variables, including the age, body mass index (BMI), fasting blood glucose (FBG), diastolic blood pressure (DBP), triglyceride (TG), systolic blood pressure (SBP), total cholesterol (TC), waist circumference, and high‐density lipoprotein‐cholesterol (HDL‐C), were more significant for CVD prediction; the AUC was 0.802 in CVD prediction. Multifactorial logistic regression analysis indicated that the risk factors for CVD included the age [odds ratio (OR): 1.14, 95% confidence intervals (CI): 1.10‐1.17, P < .001], BMI (OR: 1.13, 95% CI: 1.06‐1.20, P < .001), TG (OR: 1.11, 95% CI: 1.02‐1.22, P = .023), and DBP (OR: 1.04, 95% CI: 1.02‐1.06, P = .001); the AUC was 0.843 in CVD prediction. The established logistic regression prediction model was Logit P = Log[P/(1 − P)] = −11.47 + 0.13 × age + 0.12 × BMI + 0.11 × TG + 0.04 × DBP; P = 1/[1 + exp(−Logit P)]. People were prone to develop CVD at the time of P > .51.

Conclusions

A prediction model for CVD is developed in the general population based on random forests, which provides a simple tool for the early prediction of CVD.

Is coronary calcium scoring too late? Total body arterial calcium burden in patients without known CAD and normal MPI

BACKGROUND

Patients with normal myocardial perfusion imaging (MPI) have a good prognosis. However, pre-clinical coronary and extracoronary atherosclerosis may exist in the absence of myocardial ischemia.

METHODS

154 Egyptian patients (mean age 53 years) underwent whole-body non-contrast CT following normal MPI.

RESULTS

Atherosclerosis in the form of calcification was observed in ≥1 vascular bed in 115 of 154 (75%) patients. This included the iliofemoral (62%), abdominal aorta (53%), thoracic aorta (47%), coronary (47%), and carotid (25%) vascular beds. Mean total body calcium score was 3172 ± 530 AU. Extracoronary atherosclerosis in patients with a zero coronary artery calcium (CAC) score was common, occurring in the above-listed beds 42%, 36%, 29%, and 7% of the time, respectively. CAC was rarely present without iliofemoral or abdominal aortic calcification.

CONCLUSION

Quantitative assessment of calcification in different vascular beds demonstrates that extracoronary atherosclerosis is common in patients who have normal MPI. Atherosclerotic calcifications are most common in the iliofemoral arteries and abdominal aorta, which typically predate coronary calcifications. An imaging strategy to detect extracoronary atherosclerosis could lead to greater understanding of the natural history of atherosclerosis in its long pre-clinical phase and possibly to earlier preventive strategies.

Research on Improved Depth Belief Network-Based Prediction of Cardiovascular Diseases

Quantitative analysis and prediction can help to reduce the risk of cardiovascular disease. Quantitative prediction based on traditional model has low accuracy. The variance of model prediction based on shallow neural network is larger. In this paper, cardiovascular disease prediction model based on improved deep belief network (DBN) is proposed. Using the reconstruction error, the network depth is determined independently, and unsupervised training and supervised optimization are combined. It ensures the accuracy of model prediction while guaranteeing stability. Thirty experiments were performed independently on the Statlog (Heart) and Heart Disease Database data sets in the UCI database. Experimental results showed that the mean of prediction accuracy was 91.26% and 89.78%, respectively. The variance of prediction accuracy was 5.78 and 4.46, respectively.