Multimodality Risk Assessment of Patients with Ischemic Heart Disease Using Deep Learning Models Applied to Electrocardiograms and Chest X-rays.

Comprehensive management approaches for patients with ischemic heart disease (IHD) are important aids for prognostication and treatment planning. While single-modality deep neural networks (DNNs) have shown promising performance for detecting cardiac abnormalities, the potential benefits of using DNNs for multimodality risk assessment in patients with IHD have not been reported. The purpose of this study was to investigate the effectiveness of multimodality risk assessment in patients with IHD using a DNN that utilizes 12-lead electrocardiograms (ECGs) and chest X-rays (CXRs), with the prediction of major adverse cardiovascular events (MACEs) being of particular concern.DNN models were applied to detection of left ventricular systolic dysfunction (LVSD) on ECGs and identification of cardiomegaly findings on CXRs. A total of 2107 patients who underwent elective percutaneous coronary intervention were categorized into 4 groups according to the models' outputs: Dual-modality high-risk (n = 105), ECG high-risk (n = 181), CXR high-risk (n = 392), and No-risk (n = 1,429).A total of 342 MACEs were observed. The incidence of a MACE was the highest in the Dual-modality high-risk group (P < 0.001). Multivariate Cox hazards analysis for predicting MACE revealed that the Dual-modality high-risk group had a significantly higher risk of MACE than the No-risk group (hazard ratio (HR): 2.370, P < 0.001), the ECG high-risk group (HR: 1.906, P = 0.010), and the CXR high-risk group (HR: 1.624, P = 0.018), after controlling for confounding factors.The results suggest the usefulness of multimodality risk assessment using DNN models applied to 12-lead ECG and CXR data from patients with IHD.

von Willebrand factor Ristocetin co-factor activity to von Willebrand factor antigen level ratio for diagnosis of acquired von Willebrand syndrome caused by aortic stenosis.

Background: Severe aortic stenosis (AS) causes acquired von Willebrand syndrome by the excessive shear stress-dependent cleavage of high molecular weight multimers of von Willebrand factor (VWF). While the current standard diagnostic method is so-called VWF multimer analysis that is western blotting under nonreducing conditions, it remains unclear whether a ratio of VWF Ristocetin co-factor activity (VWF:RCo) to VWF antigen levels (VWF:Ag) of <0.7, which can be measured with an automated coagulation analyzer in clinical laboratories and is used for the diagnosis of hereditary von Willebrand disease. Objectives: To evaluated whether the VWF:RCo/VWF:Ag is useful for the diagnosis of AS-induced acquired von Willebrand syndrome. Methods: VWF:RCo and VWF:Ag were evaluated with the VWF large multimer index as a reference, which represents the percentage of a patient's VWF high molecular weight multimer ratio to that of standard plasma in the VWF multimer analysis. Results: We analyzed 382 patients with AS having transaortic valve maximal pressure gradients of >30 mmHg, 27 patients with peripheral artery disease, and 46 control patients free of cardiovascular disease with osteoarthritis, diabetes, and so on. We assumed a large multimer index of <80% as loss of VWF large multimers since 59.0% of patients with severe AS had the indices of <80%, while no control patients or patients with peripheral artery disease, except for 2 patients, exhibited the indices of <80%. The VWF:RCo/VWF:Ag ratios, measured using an automated blood coagulation analyzer, were correlated with the indices (rs = 0.470, P < .001). When the ratio of <0.7 was used as a cut-off point, the sensitivity and specificity to VWF large multimer indices of <80% were 0.437 and 0.826, respectively. Conclusion: VWF:RCo/VWF:Ag ratios of <0.7 may indicate loss of VWF large multimers with high specificity, but low sensitivity. VWF:RCo/VWF:Ag ratios in patients with AS having a ratio of <0.7 may be useful for monitoring the loss of VWF large multimers during their clinical courses.

PGC-1α-mediated angiogenesis prevents pulmonary hypertension in mice.

Pulmonary hypertension (PH) is a life-threatening disease characterized by a progressive narrowing of pulmonary arterioles. Although VEGF is highly expressed in lung of patients with PH and in animal PH models, the involvement of angiogenesis remains elusive. To clarify the pathophysiological function of angiogenesis in PH, we compared the angiogenic response in hypoxia (Hx) and SU5416 (a VEGFR2 inhibitor) plus Hx (SuHx) mouse PH models using 3D imaging. The 3D imaging analysis revealed an angiogenic response in the lung of the Hx-PH, but not of the severer SuHx-PH model. Selective VEGFR2 inhibition with cabozantinib plus Hx in mice also suppressed angiogenic response and exacerbated Hx-PH to the same extent as SuHx. Expression of endothelial proliferator-activated receptor γ coactivator 1α (PGC-1α) increased along with angiogenesis in lung of Hx-PH but not SuHx mice. In pulmonary endothelial cell-specific Ppargc1a-KO mice, the Hx-induced angiogenesis was suppressed, and PH was exacerbated along with increased oxidative stress, cellular senescence, and DNA damage. By contrast, treatment with baicalin, a flavonoid enhancing PGC-1α activity in endothelial cells, ameliorated Hx-PH with increased Vegfa expression and angiogenesis. Pulmonary endothelial PGC-1α-mediated angiogenesis is essential for adaptive responses to Hx and might represent a potential therapeutic target for PH.

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.

Family with congenital contractural arachnodactyly due to a novel multiexon deletion of the FBN2 gene.

Congenital contractural arachnodactyly (CCA) is caused by pathogenic FBN2 variants; however, the contributions of copy number variations (CNVs) to CCA are still unknown. Here, we report on a familial case of CCA, in which a novel multiexon deletion of exons 35-39 in FBN2 was identified after simple CNV prediction.

The Effectiveness of a Deep Learning Model to Detect Left Ventricular Systolic Dysfunction from Electrocardiograms.

Deep learning models can be applied to electrocardiograms (ECGs) to detect left ventricular (LV) dysfunction. We hypothesized that applying a deep learning model may improve the diagnostic accuracy of cardiologists in predicting LV dysfunction from ECGs. We acquired 37,103 paired ECG and echocardiography data records of patients who underwent echocardiography between January 2015 and December 2019. We trained a convolutional neural network to identify the data records of patients with LV dysfunction (ejection fraction < 40%) using a dataset of 23,801 ECGs. When tested on an independent set of 7,196 ECGs, we found the area under the receiver operating characteristic curve was 0.945 (95% confidence interval: 0.936-0.954). When 7 cardiologists interpreted 50 randomly selected ECGs from the test dataset of 7,196 ECGs, their accuracy for predicting LV dysfunction was 78.0% ± 6.0%. By referring to the model's output, the cardiologist accuracy improved to 88.0% ± 3.7%, which indicates that model support significantly improved the cardiologist diagnostic accuracy (P = 0.02). A sensitivity map demonstrated that the model focused on the QRS complex when detecting LV dysfunction on ECGs. We developed a deep learning model that can detect LV dysfunction on ECGs with high accuracy. Furthermore, we demonstrated that support from a deep learning model can help cardiologists to identify LV dysfunction on ECGs.

Percutaneous coronary intervention for delayed coronary obstruction due to endothelialization of self-expandable transcatheter heart valve: a case report.

BACKGROUND: Coronary obstruction is one of the serious complications associated with transcatheter aortic valve implantation (TAVI). Delayed coronary obstruction (DCO) is a rare manifestation of coronary obstruction. CASE SUMMARY: A 91-year-old woman was diagnosed with severe aortic stenosis. She underwent TAVI with a self-expandable valve, without any complications. After 8 months, she was readmitted to our hospital for effort angina. Transthoracic echocardiogram and myocardial scintigraphy suggested left coronary artery ischaemia. Computed tomography revealed that the transcatheter heart valve (THV) frame was covered with a low-density mass that occluded the left coronary sinus (LCS). Transoesophageal echocardiogram showed a Doppler signal flowing from the non-coronary sinus to the LCS through the roundabout route between the aortic wall and the THV. Percutaneous coronary intervention was performed for the roundabout route. Although intravascular ultrasound after the implantation of one drug-eluting stent showed the underexpansion of the stent, another stent deployment improved the expansion. After the procedure, her symptom improved. DISCUSSION: Reportedly, the mechanism of DCO occurring months or years after TAVI is thought to be thrombus formation or THV endothelialization. In our case, the low-density mass was considered to be endothelium which developed along the THV frame. Low sinotubular junction height and higher THV position could be the underlying mechanisms of DCO. Percutaneous coronary intervention is a possible treatment option for DCO caused by THV endothelialization.

Aortic Complex Rupture After Transcatheter Aortic Valve Implantation.

Aortic complex rupture is one of the most critical complications associated with transcatheter aortic valve implantation (TAVI). Its incidence is rare, and its mechanism varies by case; therefore, it is difficult to identify the predictors of complex rupture. Herein, we report a clinical case series of aortic complex rupture. Within our cohort, the frequency of complex rupture was 0.8% (4/497 consecutive patients) with an in-hospital mortality of 0. Among these four patients with complex rupture, two underwent emergent thoracotomy and surgical hemostasis without a heart-lung machine and surgical aortic valve replacement, whereas the other two were conservatively managed. The case overview revealed the following similarities: all the patients were elderly, small women; balloon-expandable valves were used; the annulus area was small with heavily calcified leaflet; and aggressive treatment strategy was used (i.e., oversizing and post-dilatation). In such cases, TAVI should be performed with a careful strategy. Once aortic complex rupture occurs, damage can be minimized through cooperation with an institutional heart team and calm management.

Clinical Impact of Intraventricular Conduction Abnormalities After Transcatheter Aortic Valve Implantation With Balloon-Expandable Valves.

Transcatheter aortic valve implantation (TAVI) often causes intraventricular conduction abnormalities (ICA), particularly left bundle branch block (LBBB) and advanced atrioventricular block, requiring pacemaker implantation (PMI). However, the relation between ICA and clinical outcomes after TAVI with balloon-expandable valves remains unclear, particularly in the Asian population. This retrospective study included all patients who underwent TAVI with balloon-expandable valves from October 2013 to September 2016. We defined ICA as new onset of complete LBBB (CLBBB) or PMI within 2 weeks after TAVI. We divided the patients into 2 groups: those with and without ICA (new-ICA and no-ICA groups) and we assessed 1-year outcome. Two hundred one consecutive patients underwent TAVI using balloon-expandable valves (mean age, 84.8 ± 5.7 years; women, 64%). ICA occurred in 47 patients (23%), 37 patients (18%) developed CLBBB, and 34 patients recovered from CLBBB within 1 year after TAVI. Ten patients (5%) who developed symptomatic bradycardia required PMI within 2 weeks after TAVI. At 30 days after PMI, 7 patients already had a very low ventricular pacing rate, and 6 patients who recovered from bradycardia needed pacing at 1 year. Patients with ICA tended to have high 1-year all-cause mortality, but there was no significant difference between the 2 groups (12% vs 7%, p = 0.15). In conclusion, ICA occurred in 23% of patients after TAVI with balloon-expandable valves, and approximately 90% of them recovered from ICA during the follow-up. There was no significant difference in 1-year all-cause mortality between the new-ICA and no-ICA groups.

Frequency Measurement System of Optical Clocks Without a Flywheel Oscillator.

We developed a system for the remote frequency comparison of optical clocks. The system does not require a flywheel oscillator at the remote end, making it possible to evaluate optical frequencies even in laboratories, where no stable microwave reference, such as an Rb clock, a Cs clock, or a hydrogen maser exists. The system is established by the integration of several systems: a portable carrier-phase two-way satellite frequency transfer station and a microwave signal generation system by an optical frequency comb from an optical clock. The measurement was as quick as a conventional method that employs a local microwave reference. We confirmed the system uncertainty and instability to be at the low 10-15 level using an Sr lattice clock.