Age prediction from coronary angiography using a deep neural network: Age as a potential label to extract prognosis-related imaging features.

Coronary angiography (CAG) is still considered the reference standard for coronary artery assessment, especially in the treatment of acute coronary syndrome (ACS). Although aging causes changes in coronary arteries, the age-related imaging features on CAG and their prognostic relevance have not been fully characterized. We hypothesized that a deep neural network (DNN) model could be trained to estimate vascular age only using CAG and that this age prediction from CAG could show significant associations with clinical outcomes of ACS. A DNN was trained to estimate vascular age using ten separate frames from each of 5,923 CAG videos from 572 patients. It was then tested on 1,437 CAG videos from 144 patients. Subsequently, 298 ACS patients who underwent percutaneous coronary intervention (PCI) were analysed to assess whether predicted age by DNN was associated with clinical outcomes. Age predicted as a continuous variable showed mean absolute error of 4 years with R squared of 0.72 (r = 0.856). Among the ACS patients stratified by predicted age from CAG images before PCI, major adverse cardiovascular events (MACE) were more frequently observed in the older vascular age group than in the younger vascular age group (p = 0.017). Furthermore, after controlling for actual age, gender, peak creatine kinase, and history of heart failure, the older vascular age group independently suffered from more MACE (hazard ratio 2.14, 95% CI 1.07 to 4.29, p = 0.032). The vascular age estimated based on CAG imaging by DNN showed high predictive value. The age predicted from CAG images by DNN could have significant associations with clinical outcomes in patients with ACS.

Automatic Detection of Left Ventricular Dilatation and Hypertrophy from Electrocardiograms Using Deep Learning.

Left ventricular dilatation (LVD) and left ventricular hypertrophy (LVH) are risk factors for heart failure, and their detection improves heart failure screening. This study aimed to investigate the ability of deep learning to detect LVD and LVH from a 12-lead electrocardiogram (ECG). Using ECG and echocardiographic data, we developed deep learning and machine learning models to detect LVD and LVH. We also examined conventional ECG criteria for the diagnosis of LVH. We calculated the area under the receiver operating characteristic (AUROC) curve, sensitivity, specificity, and accuracy of each model and compared the performance of the models. We analyzed data for 18,954 patients (mean age (standard deviation): 64.2 (16.5) years, men: 56.7%). For the detection of LVD, the value (95% confidence interval) of the AUROC was 0.810 (0.801-0.819) for the deep learning model, and this was significantly higher than that of the logistic regression and random forest methods (P < 0.001). The AUROCs for the logistic regression and random forest methods (machine learning models) were 0.770 (0.761-0.779) and 0.757 (0.747-0.767), respectively. For the detection of LVH, the AUROC was 0.784 (0.777-0.791) for the deep learning model, and this was significantly higher than that of the logistic regression and random forest methods and conventional ECG criteria (P < 0.001). The AUROCs for the logistic regression and random forest methods were 0.758 (0.751-0.765) and 0.716 (0.708-0.724), respectively. This study suggests that deep learning is a useful method to detect LVD and LVH from 12-lead ECGs.

Crystal transformation and host molecular motions in CO2 adsorption process of a metal benzoate pyrazine (M(II) = Rh, Cu).

For the purpose of investigating the correlation between host gas adsorption ability and structural flexibility, the combination of metal benzoate complexes [M(II)(2)(bza)(4)] (M(II) = Rh (a), Cu (b); bza = benzoate) and pyrazine derivatives (pyz = pyrazine (1), 2-mpyz = 2-methylpyrazine (2), 2,3-dmpyz = 2,3-dimethylpyrazine (3)) yields a series of one-dimensionally assembled complexes. The study of the adsorption properties of this series was examined for CO(2), H(2), N(2), O(2), and Ar gases at 195 K (CO(2)) or at 77 K (all others). The adsorption manners of these complexes are similar for each gas, while the pressure at which adsorption started or rapidly grew increased with a rise in the number of methyl groups in the case of adsorbable gases. The maximum amount of adsorption was a positive integer, e.g., 3 molecules per M(2) unit for 1 and 2 and 2 molecules per M(2) unit for 3 in the case of CO(2) adsorption for all complexes at 0.1 MPa of adsorbable gases. Structural transformation was observed accompanying gas adsorption. This transformation was observed when the adsorption amount reached 1 molecule per M(2) unit, suggesting a correlation of the adsorption amount and dynamic adsorption behavior. Single-crystal X-ray analyses of nonincluded crystals and CO(2) inclusions for all hosts (1-3) revealed that large structural changes occurred through CO(2) adsorption to increase the inner space for adsorption gases, depending on the substituents on the pyrazine ring. These facts were confirmed as a transition by DSC measurements using a mixed CO(2)/N(2) gas atmosphere. Solid-state (1)H and (2)H NMR studies of the crystalline sample of 1a and its partially deuterated samples of 1a' (deuterated phenyl group) and 1a'' (deuterated pyrazine) revealed rapid 180 degree-flip motions of the aromatic rings of the host skeletons, which form the walls of the channels. These "rotating" motions would help the diffusion of CO(2) molecules through a narrow channel at relatively low pressure. Indeed, the motions of phenyl groups and methyl-substituted pyrazine moieties of phenyl deuterated 3a were confirmed to be very slow by solid-state (1)H and (2)H NMR spectra, where the amount of adsorbed gas molecules was small for 3a at 0.1 MPa of CO(2).