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.

Association of Blood Pressure Classification Using the 2017 American College of Cardiology/American Heart Association Blood Pressure Guideline With Risk of Heart Failure and Atrial Fibrillation.

BACKGROUND: Heart failure (HF) and atrial fibrillation (AF) are growing in prevalence worldwide. Few studies have assessed to what extent stage 1 hypertension in the 2017 American College of Cardiology/American Heart Association blood pressure (BP) guidelines is associated with incident HF and AF. METHODS: Analyses were conducted with a nationwide health claims database collected in the JMDC Claims Database between 2005 and 2018 (n=2 196 437; mean age, 44.0±10.9 years; 58.4% men). No participants were taking antihypertensive medication or had a known history of cardiovascular disease. Each participant was categorized as having normal BP (systolic BP <120 mm Hg and diastolic BP <80 mm Hg; n=1 155 885), elevated BP (systolic BP 120-129 mm Hg and diastolic BP <80 mm Hg; n=337 390), stage 1 hypertension (systolic BP 130-139 mm Hg or diastolic BP 80-89 mm Hg; n=459 820), or stage 2 hypertension (systolic BP ≥140 mm Hg or diastolic BP ≥90 mm Hg; n=243 342). Using Cox proportional hazards models, we identified associations between BP groups and HF/AF events. We also calculated the population attributable fractions to estimate the proportion of HF and AF events that would be preventable if participants with stage 1 and stage 2 hypertension were to have normal BP. RESULTS: Over a mean follow-up of 1112±854 days, 28 056 incident HF and 7774 incident AF events occurred. After multivariable adjustment, hazard ratios for HF and AF events were 1.10 (95% CI, 1.05-1.15) and 1.07 (95% CI, 0.99-1.17), respectively, for elevated BP; 1.30 (95% CI, 1.26-1.35) and 1.21 (95% CI, 1.13-1.29), respectively, for stage 1 hypertension; and 2.05 (95% CI, 1.97-2.13) and 1.52 (95% CI, 1.41-1.64), respectively, for stage 2 hypertension versus normal BP. Population attributable fractions for HF associated with stage 1 and stage 2 hypertension were 23.2% (95% CI, 20.3%-26.0%) and 51.2% (95% CI, 49.2%-53.1%), respectively. The population attributable fractions for AF associated with stage 1 and stage 2 hypertension were 17.4% (95% CI, 11.5%-22.9%) and 34.3% (95% CI, 29.1%-39.2%), respectively. CONCLUSIONS: Both stage 1 hypertension and stage 2 hypertension were associated with a greater incidence of HF and AF in the general population. The American College of Cardiology/American Heart Association BP classification system may help identify adults at higher risk for HF and AF events.

Semiquantitative assessed proteinuria and risk of heart failure: analysis of a nationwide epidemiological database.

BACKGROUND: Heart failure (HF) is increasing in prevalence worldwide. We explored whether adults with trace and positive proteinuria were at a high risk for incident HF compared with those with negative proteinuria using a nationwide epidemiological database. METHODS: This is an observational cohort study using the JMDC Claims Database collected between 2005 and 2020. This is a population-based sample [n = 1 021 943; median age 44 years (interquartile range 37-52); 54.8% men]. No participants had a known history of cardiovascular disease (CVD). Each participant was categorized into three groups according to the urine dipstick test results: negative proteinuria (n = 902 273), trace proteinuria (n = 89 599) and positive proteinuria (≥1+; n = 30 071). The primary outcome was HF. The secondary outcomes were myocardial infarction (MI), stroke and atrial fibrillation (AF). We performed multivariable Cox regression analyses to identify the association between the proteinuria category and incident HF and other CVD events. RESULTS: Over a mean follow-up of 1150 ± 920 days, 17 182 incident HF events occurred. After multivariable adjustment, hazard ratios for HF events were 1.09 [95% confidence interval (CI) 1.03-1.15] and 1.59 (95% CI 1.49-1.70) for trace proteinuria and positive proteinuria versus negative proteinuria, respectively. This association was present irrespective of clinical characteristics. A stepwise increase in the risk of MI, stroke and AF with proteinuria category was also observed. Our primary results were confirmed in participants after multiple imputations for missing values and in those having no medications for hypertension, diabetes mellitus and dyslipidemia. The discriminative predictive value for HF events improved by adding the results of urine dipstick tests to traditional risk factors [net reclassification improvement 0.0497 (95% CI 0.0346-0.0648); P < 0.001]. CONCLUSIONS: Not only positive proteinuria, but also trace proteinuria was associated with a greater incidence of HF in the general population. Semiquantitative assessment of proteinuria would be informative for the risk stratification of HF.

Metabolically Healthy Obesity and the Risk of Cardiovascular Disease in the General Population　- Analysis of a Nationwide Epidemiological Database.

BACKGROUND: Obesity and metabolic disorders frequently coexist, and both are established risk factors for cardiovascular disease (CVD). Although the phenotype of obesity without metabolic disorders, referred to as metabolically healthy obesity (MHO), is attracting clinical interest, the pathophysiological impact of MHO remains unclear.Methods and Results:Using the Japan Medical Data Center database, we studied 802,288 subjects aged ≥20 years without any metabolic disorders or a prior history of CVD. MHO, defined as obesity (body mass index ≥25 kg/m2) with no metabolic disorders, was observed in 9.8% of the study population. The subjects' mean (±SD) age was 42.8±9.4 years and 44.7% were men. The mean follow-up period was 1,126±849 days. Multivariable Cox regression analysis showed that MHO alone did not significantly increase the risk of any CVD. However, abdominal obesity alone increased the risk of heart failure and atrial fibrillation. Moreover, the coexistence of MHO and abdominal obesity increased the risk of myocardial infarction, angina pectoris, heart failure, and atrial fibrillation. The incidence of stroke was not associated with the presence of MHO and abdominal obesity. CONCLUSIONS: Among individuals with no metabolic disorders, MHO alone did not significantly increase the subsequent CVD risk. However, individuals with comorbid MHO and abdominal obesity had a higher risk of myocardial infarction, angina pectoris, heart failure, and atrial fibrillation, suggesting the prognostic importance of abdominal obesity in subjects with MHO.

Impact of hospital volume on clinical outcomes of hospitalized heart failure patients: analysis of a nationwide database including 447,818 patients with heart failure.

BACKGROUND: Hospital volume is known to be associated with outcomes of patients requiring complicated medical care. However, the relationship between hospital volume and prognosis of hospitalized patients with heart failure (HF) remains not fully understood. We aimed to clarify the impact of hospital volume on clinical outcomes of hospitalized HF patients using a nationwide inpatient database. METHODS AND RESULTS: We studied 447,818 hospitalized HF patients who were admitted from January 2010 and discharged until March 2018 included in the Japanese Diagnosis Procedure Combination database. According to the number of patients, patients were categorized into three groups; those treated in low-, medium-, and high-volume centers. The median age was 81 years and 238,192 patients (53%) were men. Patients who had New York Heart Association class IV symptom and requiring inotropic agent within two days were more common in high volume centers than in low volume centers. Respiratory support, hemodialysis, and intra-aortic balloon pumping were more frequently performed in high volume centers. As a result, length of hospital stay was shorter, and in-hospital mortality was lower in high volume centers. Lower in-hospital mortality was associated with higher hospital volume. Multivariable logistic regression analysis fitted with generalized estimating equation indicated that medium-volume group (Odds ratio 0.91, p = 0.035) and high-volume group (Odds ratio 0.86, p = 0.004) had lower in-hospital mortality compared to the low-volume group. Subgroup analysis showed that this association between hospital volume and in-hospital mortality among overall population was seen in all subgroups according to age, presence of chronic renal failure, and New York Heart Association class. CONCLUSION: Hospital volume was independently associated with ameliorated clinical outcomes of hospitalized patients with HF.

Reverse J-shaped relationship between body mass index and in-hospital mortality of patients hospitalized for heart failure in Japan.

Several lines of evidence demonstrated body mass index (BMI) to be inversely associated with outcomes of patients with HF, so-called obesity paradox. However, the relationship between BMI and outcomes of patients with HF in Japan has been poorly understood. This study sought to explore the relationship between BMI and in-hospital mortality of patients hospitalized for heart failure (HF) in Japan and whether BMI at hospital admission could be used for the risk stratification of hospitalized HF patients. We studied 407,722 patients hospitalized for HF between January 2010 and March 2018, using the Diagnosis Procedure Combination database, a national inpatient database in Japan. Patients were categorized into four groups: underweight (BMI < 18.5 kg/m2), 66,342 patients (16.3%); normal (18.5-24.9 kg/m2), 240,801 patients (59.1%); pre-obesity (25.0-29.9 kg/m2), 76,954 patients (18.9%); and obesity (≥ 30.0 kg/m2), 23,625 patients (5.8%). Pre-obese and obese patients were younger and more likely to be male. Advanced HF symptoms were more common among underweight patients. Multivariable logistic regression analysis fitted with generalized estimating equation showed that, compared with normal weight patients underweight patients had higher in-hospital mortality (odds ratio 1.50, 95% confidence interval 1.45-1.55), whereas pre-obese patients (odds ratio 0.80, 95% confidence interval 0.77-0.83) and obese patients (odds ratio 0.90, 95% confidence interval 0.84-0.97) had lower in-hospital mortality. Restricted cubic spline showed a reverse J-shaped relationship between BMI and in-hospital mortality with the bottoms of splines around BMI 26 kg/m2. In conclusion, underweight patients had higher, and pre-obese and obese patients had lower in-hospital mortality compared to patients with normal weight patients. Furthermore, restricted cubic spline indicated a reverse J-shaped relationship between BMI and in-hospital mortality. Our findings are informative for the risk stratification of patients hospitalized for HF according to BMI.

Possible Gender Difference in the Association Between Abdominal Obesity, Chronic Inflammation, and Preclinical Atherosclerosis in the General Population.

Chronic inflammation due to abdominal obesity plays a major role in the development of cardiovascular disease (CVD). Gender differences are well characterized in the development of CVD; however, in the association among abdominal obesity, chronic inflammation, and preclinical atherosclerosis, gender differences in the general population remain to be clarified. We retrospectively analyzed 1,163 subjects who underwent voluntary health checkups at our institute. We defined carotid artery plaque formation as carotid intima-media thickness ≥ 1.1 mm. Multiple regression analysis showed that waist circumference was a major independent predictor of increase in serum C-reactive protein (CRP) level in both men and women. Serum CRP level was significantly increased in men with carotid artery plaque formation, but not in women. Multivariable logistic regression analysis demonstrated that serum CRP level, as well as age and hypertension, was independently associated with carotid artery plaque formation only in men. This result may suggest a potential of gender-specific difference in the association between serum CRP level and the prevalence of carotid artery plaque formation. Further investigations are required to confirm our results and to clarify the underlying mechanism.

Percutaneous Mitral Valve Intervention Using MitraClip for Functional Mitral Regurgitation and Heart Failure.

Functional mitral regurgitation (FMR) frequently coexists with left ventricular systolic dysfunction and advanced heart failure, and typically has poor clinical outcomes. Although various therapeutic options including cardiac resynchronization therapy and surgical mitral intervention, have been proposed, an optimal treatment strategy for functional mitral regurgitation has not yet been established. Over the last decade, transcatheter mitral valve repair using MitraClip has emerged as a novel alternative therapeutic option for functional mitral regurgitation. In 2018, the COAPT trial demonstrated that MitraClip treatment reduced rehospitalization due to heart failure and all-cause death in patients with functional mitral regurgitation and heart failure. As a consequence, the MitraClip has become a very promising potential treatment for functional mitral regurgitation. In this review, we discuss and summarize the current status and future perspectives of the treatment for functional mitral regurgitation and heart failure.

Association of Cancer With Outcomes in Patients Hospitalized for Heart Failure.

BACKGROUND: The complex clinical status of heart failure (HF) patients with concomitant cancer is gaining clinical interest. This study sought to explore the prevalence of cancer in patients with HF and its effect on outcomes using a nationwide inpatient database.Methods and Results:In total, 447,818 HF patients who were admitted and discharged between January 2010 and March 2018 were studied and included in the Diagnosis Procedure Combination (DPC) database. The median age was 81 years; 238,192 patients (53.2%) were men and 25,951 (5.8%) had concomitant cancer. The prevalence of cancer peaked in patients aged in their 70 s and 80 s and increased with time. Patients with cancer were older and more likely to be male. Cigarette smoking was more common in patients with cancer. Patients with cancer more frequently had infectious complications during hospitalization. Advanced medical procedures were less frequently performed for patients with cancer. In-hospital mortality was higher in patients with cancer than those without (10.0% vs. 6.7%, P<0.001). Among patients with cancer, in-hospital mortality was higher in patients with metastasis than those without (18.9% vs. 9.4%, P<0.001). Multivariable logistic regression analysis, fitted with a generalized estimating equation, indicated cancer is associated with higher in-hospital mortality (odds ratio 1.51, 95% confidential interval 1.43-1.59, P<0.001). CONCLUSIONS: Cancer was frequently observed in patients hospitalized for worsened HF, and its prevalence increased with time. The presence of cancer increased the risk of in-hospital death. Further studies are warranted to establish the optimal management strategy for HF patients with cancer in the field of cardio-oncology.

Association Between Changes in Body Weight and Fat Weight in Middle Age General Population.

Body weight gain in middle age is thought to be mainly attributable to body fat gain. However, the association between the change in body weight and change in fat weight is not fully understood. In this study, we aimed to clarify the association between the changes in body weight and fat weight in a middle-aged general population using a community-based cohort. We studied 3,193 subjects who underwent health check-ups. Fat weight was measured using a TANITA DC-270A body composition analyzer (Tanita Corporation, Tokyo). Good correlation was observed between the changes in body weight and fat weight (Pearson r = 0.88, P < 0.001). Among the study subjects, 408 (13%) were categorized in the weight loss group (weight loss ≥ 5%), 2,442 (76%) in the weight stable group, and 343 (11%) in the weight gain group (weight gain ≥ 5%). The percentage of change in fat weight in relation to the change in body weight was 65% on average in subjects with body weight loss, and 70% on average in those with body weight gain. Good correlation between changes in body weight and fat weight was observed regardless of age, gender, and baseline body mass index. A change in body weight was closely correlated with a change in fat weight among the middle-aged general population. Body weight change in the middle-age population appears to be mainly attributable to the change in fat weight.

Association Between Waist Circumference and Carotid Intima-Media Thickness in the General Population.

Waist circumference (WC) is measured for the assessment of abdominal obesity, whereas carotid intima-media thickness (IMT) is a marker of preclinical atherosclerosis. The relationship between WC and carotid IMT in the general population is not fully understood. In this study, we examined 1,182 subjects (658 men and 524 women, 62.3 ± 11.7 years on average) who underwent voluntary health check-ups and sought to determine the optimal cut-off value of WC for predicting carotid IMT thickness. Receiver operating characteristic curve analysis of WC was utilized to predict high carotid IMT (defined as carotid IMT ≥ 1.1 mm). We determined that the appropriate WC cut-off value was a WC ≥ 79 cm for men and women. There was a statistically significant difference in the prevalence of high carotid IMT between WC ≥ 79 cm and WC < 79 cm in both men and women. However, multivariable logistic regression analysis demonstrated that the WC category was independently associated with high carotid IMT in men, but not in women. Our study indicates that the optimal cut-off value of WC to identify preclinical atherosclerosis may be lower than the current Japanese diagnostic criteria for metabolic syndrome (MetS) in both men and women. Compared to women, the association between WC and preclinical atherosclerosis may be more pronounced in men.

Serial Changes in Clinical Presentations and Outcomes of 5,740 Patients Requiring Repeated Hospital Admissions (Four or More Times) due to Worsened Heart Failure.

Heart failure (HF) is a major cause of death and hospitalization worldwide. In particular, hospital readmission due to worsened HF occurs frequently after the onset of HF. However, the association of repeated hospital admission with clinical manifestations and outcomes is unclear. The aim of this study was to clarify the serial changes in presentation and clinical course of patients requiring repeated hospital admission due to worsened HF. Among 466,921 patients who were admitted and discharged between January 2010 and March 2018, with the main discharge diagnosis of HF, we studied 5,740 patients who were hospitalized 4 times or more, using the Diagnosis Procedure Combination database. We evaluated serial changes in continuous data using the Jonckheere trend test, and categorical data using the Cochran-Armitage trend test. The median age of the patients was 78 years, and 3,326 patients (58%) were male. Body mass index and Barthel Index decreased with increased numbers of admissions. Patients requiring respiratory support and hemodialysis increased, whereas patients undergoing intra-aortic balloon pumping decreased with increased numbers of admissions. The length of hospital stay was prolonged and the interval between hospitalizations was shortened with increased numbers of hospital admissions. The in-hospital mortality rate was 8.8% at the fourth admission. In conclusion, this is the first large-scale real-world study on the serial changes in characteristics and outcomes of HF patients requiring repeated hospitalization, suggesting that repeated hospitalization might adversely affect the general status of patients with HF and result in a vicious clinical cycle.

Clinical impact of newly developed atrial fibrillation complicated with longstanding ventricular fibrillation during left ventricular assist device support: A case report.

BACKGROUND: Continuous-flow left ventricular assist devices (LVADs) improve survival and morbidity in patients with stage D heart failure. Management of LVADs for longer durations is necessary in some clinical settings, and a better understanding of the hemodynamics of patients using LVADs is warranted. Arrhythmia, including atrial (AA) and ventricular (VAs) arrhythmias, is a modifying factor of hemodynamics that is highly prevalent among patients with LVADs. However, the clinical impact of arrhythmias in various clinical settings in patients with LVAD, in which the hemodynamic load is likely to present as worsening of right heart failure, remains to be completely elucidated. CASE PRESENTATION: We describe the case of a patient under sustained ventricular fibrillation for extraordinarily long duration who was stabilized using LVAD support and in whom newly developed atrial fibrillation led to a significant worsening of right heart failure while using an LVAD. CONCLUSION: This case demonstrates the substantial clinical impact of AAs in the management of right heart failure using an LVAD.

The potential of the transformer-based survival analysis model, SurvTrace, for predicting recurrent cardiovascular events and stratifying high-risk patients with ischemic heart disease.

INTRODUCTION: Ischemic heart disease is a leading cause of death worldwide, and its importance is increasing with the aging population. The aim of this study was to evaluate the accuracy of SurvTrace, a survival analysis model using the Transformer-a state-of-the-art deep learning method-for predicting recurrent cardiovascular events and stratifying high-risk patients. The model's performance was compared to that of a conventional scoring system utilizing real-world data from cardiovascular patients. METHODS: This study consecutively enrolled patients who underwent percutaneous coronary intervention (PCI) at the Department of Cardiovascular Medicine, University of Tokyo Hospital, between 2005 and 2019. Each patient's initial PCI at our hospital was designated as the index procedure, and a composite of major adverse cardiovascular events (MACE) was monitored for up to two years post-index event. Data regarding patient background, clinical presentation, medical history, medications, and perioperative complications were collected to predict MACE. The performance of two models-a conventional scoring system proposed by Wilson et al. and the Transformer-based model SurvTrace-was evaluated using Harrell's c-index, Kaplan-Meier curves, and log-rank tests. RESULTS: A total of 3938 cases were included in the study, with 394 used as the test dataset and the remaining 3544 used for model training. SurvTrace exhibited a mean c-index of 0.72 (95% confidence intervals (CI): 0.69-0.76), which indicated higher prognostic accuracy compared with the conventional scoring system's 0.64 (95% CI: 0.64-0.64). Moreover, SurvTrace demonstrated superior risk stratification ability, effectively distinguishing between the high-risk group and other risk categories in terms of event occurrence. In contrast, the conventional system only showed a significant difference between the low-risk and high-risk groups. CONCLUSION: This study based on real-world cardiovascular patient data underscores the potential of the Transformer-based survival analysis model, SurvTrace, for predicting recurrent cardiovascular events and stratifying high-risk patients.

Sex Difference in the Association between Lipid Profile and Incident Cardiovascular Disease among Young Adults.

AIM: Using a nationwide epidemiological database, we sought to examine whether there was a sex difference in the association between lipid profiles and subsequent cardiovascular disease (CVD) in young adults. METHODS: Medical records of 1,909,362 young adults (20-49 years old) without a prior history of CVD and not taking lipid-lowering medications were extracted. We conducted multivariable Cox regression analyses to identify the association between the number of abnormal lipid profiles and incident CVD. RESULTS: After a mean follow-up of 3.4±2.6 years, myocardial infarction (MI), angina pectoris (AP), stroke, and heart failure (HF) developed in 2,575 (0.1%), 26,006 (1.4%), 10,748 (0.6%), and 24,875 (1.3%) subjects, respectively. The incidence of MI, AP, and HF increased with the number of abnormal lipid profiles in both men and women, whereas the incidence of stroke increased with the number of abnormal lipid profiles only in men but not in women. Multivariable adjusted hazard ratios (HRs) for MI per 1-point higher abnormal lipid profile were 1.57 (95% confidence interval [CI] 1.49-1.65) in men and 1.25 (95% CI 1.07-1.47) in women. HRs for AP, stroke, and HF per 1-point higher abnormal lipid profile were 1.14 (95% CI 1.12-1.16), 1.06 (95% CI 1.02-1.09), and 1.10 (95% CI 1.08-1.12) in men and 1.18 (95% CI 1.13-1.23), 1.09 (95% CI 1.03-1.16), and 1.10 (95% CI 1.05-1.14) in women. CONCLUSION: Our analysis demonstrated an association between the number of abnormal lipid profiles and incident CVD in both men and women. The association between the number of abnormal lipid profiles and incident MI was pronounced in men.

Potential value of saline-induced Pd/Pa ratio in patients with coronary artery stenosis.

Background: Fractional flow reserve (FFR) is the current gold standard for identifying myocardial ischemia in individuals with coronary artery stenosis. However, FFR is not penetrated as much worldwide due to time consumption, costs associated with adenosine, FFR-related discomfort, and complications. Resting physiological indexes may be widely accepted alternatives to FFR, while the discrepancies with FFR were found in up to 20% of lesions. The saline-induced Pd/Pa ratio (SPR) is a new simplified option for evaluating coronary stenosis. However, the clinical implication of SPR remains unclear. Objectives: In the present study, we aimed to compare the accuracies of SPR and resting full-cycle ratio (RFR) and to investigate the incremental value of SPR in clinical practice. Methods: In this multicenter prospective study, 112 coronary lesions (105 patients) were evaluated by SPR, RFR, and FFR. Results: The overall median age was 71 years, and 84.8% were men. SPR was correlated more strongly with FFR than with RFR (r = 0.874 vs. 0.713, respectively; p < 0.001). Using FFR < 0.80 as the reference standard variable, the area under the receiver-operating characteristic (ROC) curve for SPR was superior to that of RFR (0.932 vs. 0.840, respectively; p = 0.009). Conclusion: Saline-induced Pd/Pa ratio predicted FFR more accurately than RFR. SPR could be an alternative method for evaluating coronary artery stenosis and further investigation including elucidation of the mechanism of SPR is needed (225 words).

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.

Incorporation of Retinal Arteriolosclerosis into Risk Stratification of Blood Pressure Category According to the 2017 ACC/AHA Blood Pressure Guideline.

AIM: We investigated whether retinal arteriolosclerosis (RA) could be used for cardiovascular disease (CVD) risk stratification of individuals categorized according to the 2017 American College of Cardiology (ACC)/American Heart Association (AHA) Blood Pressure (BP) guideline. METHODS: We studied 291,522 participants without a history of CVD and not taking any BP-lowering medications from the JMDC Claims Database. RA was defined as Keith-Wagener-Barker system grade ≥ 1. Each participant was classified into one of the six groups: (1) normal or elevated BP without RA, (2) normal or elevated BP with RA, (3) stage 1 hypertension without RA, (4) stage 1 hypertension with RA, (5) stage 2 hypertension without RA, and (6) stage 2 hypertension with RA. RESULTS: Median (interquartile range) age was 46 (40-53) years, and 141,397 (48.5%) of the participants were men. During a mean follow-up of 1,223±830 days, 527 myocardial infarction (MI), 5,718 angina pectoris, 2,890 stroke, and 5,375 heart failure (HF) events occurred. Multivariable Cox regression analyses revealed that the risk of CVD increased with BP category, and this association was pronounced by the presence of RA. Compared with normal or elevated BP without RA, the hazard ratios (HRs) for MI (HR 1.17, 95% CI 0.93-1.47) were higher in stage 1 hypertension without RA. The HRs for MI further increased in stage 1 hypertension with RA (1.86 [1.17-2.95]). This association was present in stroke and HF. CONCLUSION: Incorporation of the assessment for RA may facilitate the CVD risk stratification of people classified based on the 2017 ACC/AHA BP guideline, particularly for those categorized in stage 1 hypertension.

Promoting analysis of real-world data: Prospects for preventive cardiology in Japan.

According to the statistics for 2018 in Japan, cardiovascular disease and cerebrovascular disease were the most common causes of death (cardiovascular disease with 208,210, cerebrovascular disease with 108,165), and these two diseases account for 23.2% of all deaths. Stroke, especially cerebral hemorrhage, was the main cause of death in Japan after World War II. Along with improved management of hypertension, the mortality rate from cerebral hemorrhage reached a high of 266.7 per 100,000 men in 1960 and 213.9 per 100,000 women in 1951, then decreased to 15.9 per 100,000 men and 6.9 per 100,000 women in 2013. However, mortality from lifestyle-related diseases such as metabolic syndrome and ischemic heart disease has been on the rise since 1990 due to the westernization of diet, urban lifestyles, and lack of exercise habits. Moreover, since aging is the greatest risk factor for heart failure, the number of patients with heart failure in Japan will inevitably increase in the future. A large amount of evidence has demonstrated that prevention and proper management of risk factors can reduce the future incidence of cardiovascular disease. Specific health checkups (metabolic syndrome checkups) have been carried out in Japan since 2008. Big data on physical examinations are valuable real-world data that can be utilized for clinical research. As the importance of preventive cardiology increases in the future, we should analyze the real-world data from health checkups in Japan in detail and disseminate these results to clinical practice, which will contribute to development of preventive cardiology and the promotion of public health.

Fasting plasma glucose and subsequent cardiovascular disease among young adults: Analysis of a nationwide epidemiological database.

BACKGROUND AND AIMS: Using a nationwide epidemiological database, we aimed to clarify the association of fasting plasma glucose (FPG) with subsequent cardiovascular disease (CVD) risk among young adults. METHODS AND RESULTS: Medical records of 1,180,062 young adults (20-49 years old) without a prior history of CVD and who were not taking antidiabetic medications were extracted from the Japan Medical Data Center. We categorized the study population into four groups: normal, FPG level<100 mg/dL (1,007,747 individuals), normal-high, FPG level of 100-109 mg/dL (126,602 individuals), impaired fasting glucose (IFG), FPG level of 110-125 mg/dL (32,451 individuals), and diabetes mellitus (DM), FPG level ≥126 mg/dL (13,262 individuals). The mean age was 39.7 ± 6.9 years, and 57.0% of the study population were men. Mean follow-up period was 1201 ± 905 days on average. Multivariable Cox regression analysis showed that IFG (hazard ratio [HR]; 1.38) and DM (HR; 2.09) increased the risk of myocardial infarction. Normal-high (HR; 1.11), IFG (HR; 1.18), and DM (HR; 1.59) groups had an elevated angina pectoris risk. DM (HR; 1.31) increased the risk of stroke compared to normal FPG levels. Normal-high levels (HR; 1.10), IFG (HR; 1.22) and DM (HR; 1.58) elevated the risk of heart failure. DM (HR; 1.69) increased the risk of atrial fibrillation. CONCLUSIONS: Our analysis of a nationwide epidemiological database demonstrated a close association of the FPG category with subsequent CVD risk. Our results exemplify the importance of optimal FPG maintenance for the primary prevention of CVD in young adults.