Aim. This study proposes a new artificial intelligence model based on cardiovascular computed tomography for more efficient and precise recognition of Tetralogy of Fallot (TOF). Methods. Our model is a structurally optimized stochastic pooling convolutional neural network (SOSPCNN), which combines stochastic pooling, structural optimization, and convolutional neural network. In addition, multiple‐way data augmentation is used to overcome overfitting. Grad‐CAM is employed to provide explainability to the proposed SOSPCNN model. Meanwhile, both desktop and web apps are developed based on this SOSPCNN model. Results. The results on ten runs of 10‐fold crossvalidation show that our SOSPCNN model yields a sensitivity of 92.25 ± 2.19, a specificity of 92.75 ± 2.49, a precision of 92.79 ± 2.29, an accuracy of 92.50 ± 1.18, an F1 score of 92.48 ± 1.17, an MCC of 85.06 ± 2.38, an FMI of 92.50 ± 1.17, and an AUC of 0.9587. Conclusion. The SOSPCNN method performed better than three state‐of‐the‐art TOF recognition approaches.
18 July 2022 in Environmental Science and Pollution Research
Background: Plasticizers, also called phthalates, are a group of chemicals widely used in daily life. A previous report showed no significant association between phthalate metabolite concentrations and mortality. We investigated the association of urinary phthalate levels and individual phthalate metabolite levels with all-cause and cardiovascular disease (CVD) mortality after standardizing the phthalate concentration.Methods: A total of 6,625 participants were recruited from a nationally representative sample of adults aged 40 years or older who were enrolled in the National Health and Nutrition Examination Survey (NHANES) between 2003 and 2014 and were followed up through December 31, 2015. Data were analyzed from January 2021 to June 2021. NHANES-linked updated National Death Index public access files were used to acquire information on mortality status and cause of death. The present study conducted extended follow-up of an earlier analysis. Cox proportional hazard models were performed to calculate the hazard ratios (HRs) and 95% confidence intervals (CIs) of covariate-adjusted creatinine standardization urinary phthalate concentrations with all-cause and CVD mortality after adjusting for demographics, lifestyle factors and comorbidity variables.Results: The mean ± standard deviation age of all participants in the final study was 59.9±12.6 years old, and 49.6% of the participants were male. The median follow-up time was 73 months (range 1-157 months). At the censoring date of December 31, 2015, 3,023 participants were identified as deceased (13.4%). A fully adjusted Cox model showed that a urinary di(2-ethylhexyl) phthalate (DEHP) concentration >= 83.4 ng/mL was associated with a slight increase in all-cause mortality (HR 1.27, 95% CI 1.03, 1.57, P for trend= 0.014) and CVD mortality (HR 2.19, 95% CI 1.35, 3.54, P for trend= 0.002). Similarly, urinary mono-2-ethyl-5-carboxypentyl phthalate (MECPP) levels >= 39.2 ng/mL were associated with increased CVD mortality (HR 2.33, 95% CI 1.45, 3.73, P for trend < 0.001). Restricted cubic spline analyses suggested linear associations of DEHP and MECPP levels with all-cause and CVD mortality.Conclusion: In this large nationally representative sample of American adults, high urinary DEHP and MECPP were significantly associated with all-cause and CVD mortality after adjusting for demographics, lifestyle factors and comorbidity variables.
6 September 2021 in Environmental Health and Preventive Medicine
Background: The effects of environmental chemical exposure on blood pressure (BP) have been confirmed, but the association between exposure to secondhand smoke (SHS) and hypertension risk and BP in the general population remains unknown. Methods: Cross-sectional associations between SHS exposure and hypertension risk and BP values were evaluated using data for subjects who participated in the National Health and Nutrition Examination Survey (NHANES), 1999–2016. Logistic regression and linear regression were performed after adjusting for age, sex, race, alcohol consumption, poverty-to-income ratio (PIR), body mass index (BMI), estimated glomerular filtration rate, physical activity, diabetes, cardiovascular disease, and NHANES cycle. Restricted cubic spline models were created to display the potential nonlinear association between SHS and BP levels. Results: Higher risk of hypertension was found at the highest SHS concentrations (OR = 1.13, 95% CI 1.04, 1.24, P for trend = 0.007). Additionally, SHS exposure had a strong positive association with systolic blood pressure (SBP) but was negatively associated with diastolic blood pressure (DBP). Furthermore, the nonlinear model result showed a significant association between SHS and SBP (P = 0.017); however, the nonlinear model result was not significant for SHS or DBP. Conclusions: Our results suggest a potential association between high SHS exposure and the risk of hypertension. Further research is needed to elucidate the underlying mechanisms.