Artificial intelligence-enhanced automation for M-mode echocardiographic analysis: ensuring fully automated, reliable, and reproducible measurements.

To enhance M-mode echocardiography's utility for measuring cardiac structures, we developed and evaluated an artificial intelligence (AI)-based automated analysis system for M-mode images through the aorta and left atrium [M-mode (Ao-LA)], and through the left ventricle [M-mode (LV)]. Our system, integrating two deep neural networks (DNN) for view classification and image segmentation, alongside an auto-measurement algorithm, was developed using 5,958 M-mode images [3,258 M-mode (LA-Ao), and 2,700 M-mode (LV)] drawn from a nationwide echocardiographic dataset collated from five tertiary hospitals. The performance of view classification and segmentation DNNs were evaluated on 594 M-mode images, while automatic measurement accuracy was tested on separate internal test set with 100 M-mode images as well as external test set with 280 images (140 sinus rhythm and 140 atrial fibrillation). Performance evaluation showed the view classification DNN's overall accuracy of 99.8% and segmentation DNN's Dice similarity coefficient of 94.3%. Within the internal test set, all automated measurements, including LA, Ao, and LV wall and cavity, resonated strongly with expert evaluations, exhibiting Pearson's correlation coefficients (PCCs) of 0.81-0.99. This performance persisted in the external test set for both sinus rhythm (PCC, 0.84-0.98) and atrial fibrillation (PCC, 0.70-0.97). Notably, automatic measurements, consistently offering multi-cardiac cycle readings, showcased a stronger correlation with the averaged multi-cycle manual measurements than with those of a single representative cycle. Our AI-based system for automatic M-mode echocardiographic analysis demonstrated excellent accuracy, reproducibility, and speed. This automated approach has the potential to improve efficiency and reduce variability in clinical practice.

Integrative Assessment of Cardiopulmonary Fitness Using Cardiopulmonary Exercise Test With Supine Bicycle Echocardiography in Patients Presenting Dyspnea.

BACKGROUND: Cardiopulmonary exercise test (CPET) with supine bicycle echocardiography (SBE) enables comprehensive physiologic assessment during exercise. We characterized cardiopulmonary fitness by integrating CPET-SBE parameters and evaluated its prognostic value in patients presenting with dyspnea. METHODS AND RESULTS: We retrospectively reviewed 473 consecutive patients who underwent CPET-SBE for dyspnea evaluation. A dimensionality reduction process was applied, transforming 24 clinical and CPET-SBE parameters into a 2-dimensional feature map, followed by patient clustering based on the data distribution. Clinical and exercise features were compared among the clusters in addition to the 5-year risk of clinical outcome (a composite of cardiovascular death and heart failure hospitalization). Maximum exercise effort (R >1) was achieved in 95% of cases. Through dimensionality reduction, 3 patient clusters were derived: Group 1 (n=157), 2 (n=104), and 3 (n=212). Median age and female proportion increased from Group 1 to 2, and 3, although resting echocardiography parameters showed no significant abnormalities among the groups. There was a worsening trend in the exercise response from Group 1 to 2 and 3, including left ventricular diastolic function, oxygen consumption, and ventilatory efficiency. During follow-up (median 6.0 [1.6-10.4] years), clinical outcome increased from Group 1 to 2 and 3 (5-year rate 3.7% versus 7.0% versus 13.0%, respectively; log-rank P=0.02), with higher risk in Group 2 (hazard ratio, 1.94 [95% CI, 0.52-7.22]) and Group 3 (3.92 [1.34-11.42]) compared with Group 1. CONCLUSIONS: Comprehensive evaluation using CPET-SBE can reveal distinct characteristics of cardiopulmonary fitness in patients presenting with dyspnea, potentially enhancing outcome prediction.

Mildly Reduced Renal Function Is Associated With Increased Heart Failure Admissions in Patients With Hypertrophic Cardiomyopathy.

BACKGROUND: The association between renal dysfunction and cardiovascular outcomes has yet to be determined in patients with hypertrophic cardiomyopathy (HCM). We aimed to investigate whether mildly reduced renal function is associated with the prognosis in patients with HCM. METHODS: Patients with HCM were enrolled at two tertiary HCM centers. Patients who were on dialysis, or had a previous history of heart failure (HF) or stroke were excluded. Patients were categorized into 3 groups by estimated glomerular filtration rate (eGFR): stage I (eGFR ≥ 90 mL/min/1.73 m², n = 538), stage II (eGFR 60-89 mL/min/1.73 m², n = 953), and stage III-V (eGFR < 60 mL/min/1.73 m², n = 265). Major adverse cardiovascular events (MACEs) were defined as a composite of cardiovascular death, hospitalization for HF (HHF), or stroke during median 4.0-year follow-up. Multivariable Cox regression model was used to adjust for covariates. RESULTS: Among 1,756 HCM patients (mean 61.0 ± 13.4 years; 68.1% men), patients with stage III-V renal function had a significantly higher risk of MACEs (adjusted hazard ratio [aHR], 2.71; 95% confidence interval [CI], 1.39-5.27; P = 0.003), which was largely driven by increased incidence of cardiovascular death and HHF compared to those with stage I renal function. Even in patients with stage II renal function, the risk of MACE (vs. stage I: aHR, 2.21' 95% CI, 1.23-3.96; P = 0.008) and HHF (vs. stage I: aHR, 2.62; 95% CI, 1.23-5.58; P = 0.012) was significantly increased. CONCLUSION: This real-world observation showed that even mildly reduced renal function (i.e., eGFR 60-89 mL/min/1.73 m²) in patients with HCM was associated with an increased risk of MACEs, especially for HHF.

Age-dependent implications of left ventricular hypertrophy regression in patients with hypertension.

Left ventricular hypertrophy (LVH) is a significant risk factor for cardiovascular mortality and morbidity in patients with hypertension. However, the effect of age on LVH regression or persistence and its differential prognostic value remain unclear. Therefore, we investigated the clinical implications of LVH regression in 1847 patients with hypertension and echocardiography data (at baseline and during antihypertensive treatment at an interval of 6-18 months) according to age. LVH was defined as a left ventricular mass index (LVMI) > 115 g/m2 and >95 g/m2 in men and women, respectively. LVH prevalence at baseline was not different according to age (age < 65 years: 42.6%; age ≥65 years: 45.7%; p = 0.187), but LVH regression was more frequently observed in the younger group (36.4% vs. 27.5%; p = 0.008). Spline curves and multiple linear regression analysis showed a significant relationship between reductions in systolic blood pressure and LVMI in the younger group (ß = 0.425; p < 0.001), but not the elderly group (ß = 0.044; p = 0.308). LVH regression was associated with a lower risk of the study outcome (composite of cardiovascular death and hospitalization for heart failure) regardless of age. In conclusion, the association between the reduction in blood pressure and LVH regression was prominent in patients with age < 65 years, but not in those with age ≥65 years. However, an association between LVH regression and lower risk of cardiovascular death and hospitalization for heart failure was observed regardless of patient age, suggesting the prognostic value of the LVH regression not only in the younger patients but also in elderly patients.

Irreversible myocardial injury attenuates the benefits of sacubitril/valsartan in heart failure patients.

BACKGROUND: Despite the established benefits of angiotensin receptor-neprilysin inhibitor (ARNI) in heart failure with reduced ejection fraction (HFrEF) across various etiologies, there are controversies regarding the effects of ARNI in patients with irreversible myocardial injury. The aim of this study is to investigate the impact of irreversible myocardial injury on the benefits of ARNI treatment in patients with HFrEF, consisted of both ischemic and non-ischemic etiologies. METHODS AND RESULTS: We conducted a retrospective single-center study including 409 consecutive patients with HFrEF treated with ARNI between March 2017 and May 2020. Irreversible myocardial injury was defined as nonviable myocardium without contractile reserve, which suggests a limited potential for recovery of left ventricular function and geometry. At baseline, irreversible myocardial injury was observed in 129 (31.5%) patients. Composite outcome was cardiovascular death or hospitalization for heart failure, which occurred in 56 (43.4%) and 61 (21.8%) patients with and without irreversible myocardial injury, respectively. On multivariable analysis, irreversible injury presence, but not ischemic etiology, was an independent predictor of composite outcome (hazard ratio 2.16, 95% confidence interval 1.33-3.49). Mediation analysis revealed that the increased risk of the composite outcome due to irreversible myocardial injury was mediated by attenuated LV reverse remodeling (Z value = 2.02, P = 0.043). CONCLUSIONS: The presence of irreversible myocardial injury was significantly associated with the response to ARNI treatment in patients with HFrEF, regardless of etiology.

Prognostic and Safety Implications of Renin-Angiotensin-Aldosterone System Inhibitors in Hypertrophic Cardiomyopathy: A Real-World Observation Over 2,000 Patients.

BACKGROUND AND OBJECTIVES: The prognostic or safety implication of renin-angiotensin-aldosterone system inhibitors (RASi) in hypertrophic cardiomyopathy (HCM) are not well established, mainly due to concerns regarding left ventricular outflow tract (LVOT) obstruction aggravation. We investigated the implications of RASi in a sizable number of HCM patients. METHODS: We enrolled 2,104 consecutive patients diagnosed with HCM in 2 tertiary university hospitals and followed up for five years. RASi use was defined as the administration of RASi after diagnostic confirmation of HCM. The primary and secondary outcomes were all-cause mortality and hospitalization for heart failure (HHF). RESULTS: RASi were prescribed to 762 patients (36.2%). During a median follow-up of 48.1 months, 112 patients (5.3%) died, and 94 patients (4.5%) experienced HHF. Patients using RASi had less favorable baseline characteristics than those not using RASi, such as older age, more frequent history of comorbidities, and lower ejection fraction. Nonetheless, there was no difference in clinical outcomes between patients with and without RASi use (log-rank p=0.368 for all-cause mortality and log-rank p=0.443 for HHF). In multivariable analysis, patients taking RASi showed a comparable risk of all-cause mortality (hazard ratio [HR], 0.70, 95% confidence interval [CI], 0.43-1.14, p=0.150) and HHF (HR, 1.03, 95% CI, 0.63-1.70, p=0.900). In the subgroup analysis, there was no significant interaction of RASi use between subgroups stratified by LVOT obstruction, left ventricular (LV) ejection fraction, or maximal LV wall thickness. CONCLUSIONS: RASi use was not associated with worse clinical outcomes. It might be safely administered in patients with HCM if clinically indicated.

Impact of glycemic control on the progression of aortic stenosis: a single-center cohort study using a common data model.

BACKGROUND: Diabetes mellitus (DM) is a well-established risk factor for the progression of degenerative aortic stenosis (AS). However, no study has investigated the impact of glycemic control on the rate of AS progression. We aimed to assess the association between the degree of glycemic control and the AS progression, using an electronic health record-based common data model (CDM). METHODS: We identified patients with mild AS (aortic valve [AV] maximal velocity [Vpeak] 2.0-3.0 m/sec) or moderate AS (Vpeak 3.0-4.0 m/sec) at baseline, and follow-up echocardiography performed at an interval of ≥ 6 months, using the CDM of a tertiary hospital database. Patients were divided into 3 groups: no DM (n = 1,027), well-controlled DM (mean glycated hemoglobin [HbA1c] < 7.0% during the study period; n = 193), and poorly controlled DM (mean HbA1c ≥ 7.0% during the study period; n = 144). The primary outcome was the AS progression rate, calculated as the annualized change in the Vpeak (△Vpeak/year). RESULTS: Among the total study population (n = 1,364), the median age was 74 (IQR 65-80) years, 47% were male, the median HbA1c was 6.1% (IQR 5.6-6.9), and the median Vpeak was 2.5 m/sec (IQR 2.2-2.9). During follow-up (median 18.4 months), 16.1% of the 1,031 patients with mild AS at baseline progressed to moderate AS, and 1.8% progressed to severe AS. Among the 333 patients with moderate AS, 36.3% progressed to severe AS. The mean HbA1c level during follow-up showed a positive relationship with the AS progression rate (ß = 2.620; 95% confidence interval [CI] 0.732-4.507; p = 0.007); a 1%-unit increase in HbA1c was associated with a 27% higher risk of accelerated AS progression defined as △Vpeak/year values > 0.2 m/sec/year (adjusted OR = 1.267 per 1%-unit increase in HbA1c; 95% CI 1.106-1.453; p < 0.001), and HbA1c ≥ 7.0% was significantly associated with an accelerated AS progression (adjusted odds ratio = 1.524; 95% CI 1.010-2.285; p = 0.043). This association between the degree of glycemic control and AS progression rate was observed regardless of the baseline AS severity. CONCLUSION: In patients with mild to moderate AS, the presence of DM, as well as the degree of glycemic control, is significantly associated with accelerated AS progression.

Endocardial versus whole-myocardial tracking global longitudinal strain analysis in patients with hypertrophic cardiomyopathy: A preliminary comparative study.

BACKGROUND AND OBJECTIVES: We investigated whether the feasibility of left ventricular (LV) global longitudinal strain (GLS) in hypertrophic cardiomyopathy (HCM) varies according to the methodology (e.g. endocardial vs. whole myocardial tracking techniques). METHODS: We retrospectively analyzed 111 consecutive patients with HCM (median age, 58 years; male, 68.5%) who underwent both transthoracic echocardiography (TTE) and cardiac magnetic resonance imaging (apical 29.7%, septal 33.3%, and diffuse or mixed 37.0%). TTE-whole myocardial and TTE-endocardial GLS were measured and compared in terms of association with late gadolinium enhancement (LGE) extent and discrimination performance for extensive LGE (>15% of the LV myocardium). RESULTS: Although TTE-whole myocardial and TTE-endocardial GLS were significantly correlated, absolute TTE-endocardial GLS values (19.3 [16.2-21.9] %) were higher than TTE-whole myocardial GLS values (13.3[10.9-15.6] %, p<0.001). Both TTE-derived GLS parameters were significantly correlated with the LGE extent and independently associated with extensive LGE (odds ratio [OR] 1.30, p = 0.022; and OR 1.24, p = 0.013, respectively). Discrimination performance for extensive LGE was comparable between TTE-whole myocardial and TTE-endocardial GLS (area under the curve [AUC], 0.747 and 0.754, respectively, pdifference = 0.610). However, among patients with higher LV mass index (>70 g/m2), only TTE-whole myocardial GLS correlated with LGE extent and was independently associated with extensive LGE (OR 1.35, p = 0.042), while TTE-endocardial GLS did not. Additionally, TTE-whole myocardial GLS had better discrimination performance for extensive LGE than TTE-endocardial GLS (AUC, 0.705 and 0.668, respectively, pdifference = 0.006). CONCLUSION: TTE-derived GLS using either the endocardial or whole myocardial tracking technique is feasible in patients with HCM. However, in those with severe hypertrophy, TTE-whole myocardial GLS is better than TTE-endocardial GLS.

Left ventricular global longitudinal strain as a prognosticator in hypertrophic cardiomyopathy with a low-normal left ventricular ejection fraction.

AIMS: The aim of this study was to investigate the prognostic utility of left ventricular (LV) global longitudinal strain (LV-GLS) in patients with hypertrophic cardiomyopathy (HCM) and an LV ejection fraction (LVEF) of 50-60%. METHODS AND RESULTS: This retrospective cohort study included 349 patients with HCM and an LVEF of 50-60%. The primary outcome was a composite of cardiovascular death, including sudden cardiac death (SCD) and SCD-equivalent events. The secondary outcomes were SCD/SCD-equivalent events, cardiovascular death (including SCD), and all-cause death. The final analysis included 349 patients (mean age 59.2 ± 14.2 years, men 75.6%). During a median follow-up of 4.1 years, the primary outcome occurred in 26 (7.4%), while the secondary outcomes of SCD/SCD-equivalent events, cardiovascular death, and all-cause death occurred in 15 (4.2%), 20 (5.7%), and 34 (9.7%), respectively. After adjusting for age, atrial fibrillation, ischaemic stroke, LVEF, and left atrial volume index, absolute LV-GLS (%) was independently associated with the primary outcome [adjusted hazard ratio (HR) 0.88, 95% confidence interval (CI) 0.788-0.988, P = 0.029]. According to receiver operating characteristic analysis, 10.5% is an optimal cut-off value for absolute LV-GLS in predicting the primary outcome. Patients with an absolute LV-GLS ≤ 10.5% had a higher risk of the primary outcome than those with an absolute LV-GLS > 10.5% (adjusted HR 2.54, 95% CI 1.117-5.787, P = 0.026). Absolute LV-GLS ≤ 10.5% was an independent predictor for each secondary outcome (P < 0.05). CONCLUSIONS: LV-GLS was an independent predictor of a composite of cardiovascular death, including SCD/SCD-equivalent events, in patients with HCM and an LVEF of 50-60%. Therefore, LV-GLS can help in risk stratification in these patients.

Rate of Change in 10-Year Atherosclerotic Cardiovascular Disease Risk and Its Implications for Primary Prevention.

BACKGROUND: Contemporary cardiovascular primary prevention is based on the assessment of the 10-year risk of atherosclerotic cardiovascular disease (ASCVD). However, the clinical implications of temporal change in the 10-year ASCVD risk estimate (∆10-year ASCVD risk/year) are unknown. METHODS: A total of 211 077 participants without established ASCVD and with repetitive 10-year ASCVD risk assessment at an interval of 4 to 5 years were selected from the Korean National Health Insurance Service data. The primary end point was a composite of myocardial infarction, stroke, coronary revascularization, and all-cause death. RESULTS: ASCVD event rates were proportional to the ∆10-year ASCVD risk/year regardless of the baseline 10-year ASCVD risk. Adjusted hazard ratio for ASCVD events per 1% increase in ∆10-year ASCVD risk/year was 1.53 (95% CI, 1.44-1.63), 1.24 (95% CI, 1.15-1.32), 1.18 (95% CI, 1.13-1.23), and 1.05 (95% CI, 1.00-1.10) in those with a baseline 10-year ASCVD risk of <5%, 5% to 7.5%, 7.5% to 20%, and ≥20%, respectively. Appropriate control of risk factors, including low-density lipoprotein cholesterol, blood pressure, body mass index, exercise habits, and smoking status, was associated with lower ASCVD event rates, whereas failure to control these risk factors resulted in higher ASCVD event rates. CONCLUSIONS: The temporal change in 10-year ASCVD risk over a period of 4 to 5 years reflects success or failure in controlling major cardiovascular risk factors and indicates the risk of future ASCVD events. The ∆10-year ASCVD risk/year can be used as an indicator of primary prevention and guide the application of preventive measures.

The Risk of Heart Failure Progression in Patients With Patent Foramen Ovale: Differential Risk Associated With Device Closure.

BACKGROUND: A patent foramen ovale (PFO) can unload left atrial pressure via an interatrial shunt. We investigated whether device closure of PFO is associated with a subsequent risk of heart failure (HF), particularly in patients with structural heart disease or atrial fibrillation (AF). METHODS: We enrolled 4,804 consecutive patients who underwent transesophageal echocardiography at tertiary medical centers in Korea between 2007 and 2019. The primary outcome was the 4-year risk of HF hospitalization. Underlying structural heart disease was determined by echocardiography. RESULTS: A PFO was observed in 981 (20.4%) patients, where 161 underwent device closure. During follow-up (median, 3.5 [1.4-6.4] years), the primary outcome was lower in patients with PFO than in those without (2.6% vs 4.0%; adjusted hazard ratio [aHR], 0.65; 95% CI, 0.45-0.94; P = .021). Among the patients with PFO, the primary outcome was higher in the device closure group than in the no-closure group (5.5% vs 1.2%; aHR, 5.59; 95% CI, 4.26-7.34; P < .001). A consistent result was found in patients with structural heart disease or AF (9.6% vs 3.9%; aHR, 2.55; 95% CI, 1.95-3.33; P < .001), demonstrating an increased risk of the primary outcome proportionate to the number of combined structural abnormalities. However, no significant association was observed between the primary outcome and PFO closure in those without structural heart disease or AF (1.7% vs 1.5%; aHR, 1.22; 95% CI, 0.99-1.50; P = .054). CONCLUSION: Patients with underlying structural heart disease or AF may be predisposed to symptomatic HF progression after PFO closure. Therefore, careful medical surveillance with optimal risk management is needed in these patients.

Impact of coronary artery revascularization on long-term outcome in hypertrophic cardiomyopathy patients: a nationwide population-based cohort study.

Limited data are available on the long-term outcomes in patients with hypertrophic cardiomyopathy (HCM) patients with significant coronary artery disease (CAD) requiring revascularization. We investigated the risk of cardiovascular outcomes in HCM patients who underwent coronary revascularization compared to the control group without HCM. HCM patients aged ≥ 20 years were enrolled from the Korean National Health Insurance Database. Information on the diagnosis and previous medical history was obtained from the claims data. Cardiovascular outcomes were identified during 8-year after coronary revascularization in HCM patients (HCM group) and matched controls without HCM (non-HCM control group). A total of 431 patients in the HCM group and 1968 in the non-HCM control group were analyzed. The risk of all-cause death, cardiovascular death, sudden cardiac death (SCD), ischemic stroke, and hospitalization due to heart failure was significantly higher in the HCM group than in the non-HCM group, with prominent risk increase of cardiovascular death (adjusted hazard ratio [HR] 2.27, 95% confidence interval [CI] 1.63-3.15, P < 0.001) and ischemic stroke (adjusted HR 2.38, 95% CI 1.55-3.64, P < 0.001). Beyond 1-year after revascularization, the HCM group still had a significantly higher risk of cardiovascular death, SCD, and ventricular fibrillation/tachycardia compared to the non-HCM group. Mortality and major cardiovascular outcomes occurred more frequently in HCM patients with significant CAD requiring revascularization, compared to the matched non-HCM control group. Active and regular surveillance for concomitant risk factors and relevant intervention are warranted in HCM patients at increased risk for CAD.

Data-driven mortality risk prediction of severe degenerative mitral regurgitation patients undergoing mitral valve surgery.

AIMS: The outcomes of mitral valve replacement/repair (MVR) in severe degenerative mitral regurgitation (MR) patients depend on various risk factors. We aimed to develop a risk prediction model for post-MVR mortality in severe degenerative MR patients using machine learning. METHODS AND RESULTS: Consecutive severe degenerative MR patients undergoing MVR were analysed (n = 1521; 70% training/30% test sets). A random survival forest (RSF) model was constructed, with 3-year post-MVR all-cause mortality as the outcome. Partial dependency plots were used to define the thresholds of each risk factor. A simple scoring system (MVR-score) was developed to stratify post-MVR mortality risk. At 3 years following MVR, 90 patients (5.9%) died in the entire cohort (59 and 31 deaths in the training and test sets). The most important predictors of mortality in order of importance were age, haemoglobin, valve replacement, glomerular filtration rate, left atrial dimension, and left ventricular (LV) end-systolic diameter. The final RSF model with these six variables demonstrated high predictive performance in the test set (3-year C-index 0.880, 95% confidence interval 0.834-0.925), with mortality risk increased strongly with left atrial dimension >55 mm, and LV end-systolic diameter >45 mm. MVR-score demonstrated effective risk stratification and had significantly higher predictability compared to the modified Mitral Regurgitation International Database score (3-year C-index 0.803 vs. 0.750, P = 0.034). CONCLUSION: A data-driven machine learning model provided accurate post-MVR mortality prediction in severe degenerative MR patients. The outcome following MVR in severe degenerative MR patients is governed by both clinical and echocardiographic factors.

Atrial Functional Tricuspid Regurgitation: Importance of Atrial Fibrillation and Right Atrial Remodeling and Prognostic Significance.

BACKGROUND: Little is known about the determinants and outcomes of significant atrial functional tricuspid regurgitation (AFTR). OBJECTIVES: The authors aimed to identify risk factors for significant TR in relation to atrial fibrillation-flutter (AF-AFL) and assess its prognostic implications. METHODS: The authors retrospectively studied patients with mild TR with follow-up echocardiography examinations. Significant TR was defined as greater than or equal to moderate TR. AFTR was defined as TR, attributed to right atrial (RA) remodeling or isolated tricuspid annular dilatation, without other primary or secondary etiology, except for AF-AFL. The Mantel-Byar test was used to compare clinical outcomes by progression of AFTR. RESULTS: Of 833 patients with mild TR, 291 (34.9%) had AF-AFL. During the median 4.6 years, significant TR developed in 35 patients, including 33 AFTRs. Significant AFTR occurred in patients with AF-AFL more predominantly than in those patients without AF-AFL (10.3% vs 0.6%; P < 0.001). In Cox analysis, AF-AFL was a strong risk factor for AFTR (adjusted HR: 8.33 [95% CI: 2.34-29.69]; P = 0.001). Among patients with AF-AFL, those who developed significant AFTR had larger baseline RA areas (23.8 vs 19.4 cm2; P < 0.001) and RA area-to-right ventricle end-systolic area ratio (3.0 vs 2.3; P < 0.001) than those who did not. These parameters were independent predictors of AFTR progression. The 10-year major adverse cardiovascular event was significantly higher after progression of AFTR than before or without progression (79.8% vs 8.6%; Mantel-Byar P < 0.001). CONCLUSIONS: In patients with mild TR, significant AFTR developed predominantly in patients with AF-AFL, conferring poor prognosis. RA enlargement, especially with increased RA area-to-right ventricle end-systolic area ratio, was a strong risk factor for progression of AFTR.

Risk of incident mental disorders in hypertrophic cardiomyopathy: a nationwide propensity-matched study.

AIMS: We sought to determine the risk of mental disorders in patients with hypertrophic cardiomyopathy (HCM) compared with those without HCM. METHODS AND RESULTS: This is a retrospective propensity score-matched cohort study using nationwide population-based data from the Korean National Health Insurance Service. Overall, 4046 patients with HCM and 12138 matched individuals were followed up until the first diagnosis of mental disorders or the end of the follow up. The primary outcome was a composite of incident mood, anxiety, stress-related, or somatoform disorders. Secondary outcomes included two components of the primary outcome (i.e. mood disorders and anxiety/stress-related/somatoform disorders). During a median follow-up period of 4.1 years, the incidence rate of the primary outcome was 54.4 and 31.5/1000 person-years among the HCM and control groups, respectively, resulting in a hazard ratio (HR) of 1.719 (95% confidence interval: 1.589-1.860). Within the first month after HCM diagnosis, the HR for the primary outcome was 3.074 (2.096-4.508). Beyond 1 month, the HRs decreased, ranging from 2.281 (1.952-2.665) during 1-12 months, to 2.087 (1.831-2.380) during 12-36 months and 1.258 (1.090-1.452) after 36 months of follow up. Similar results were observed for the secondary outcomes. In sensitivity analysis, the risk of the specific categories of mental disorders, including single or recurrent depressive episodes and anxiety disorders, was also higher in patients with HCM than matched controls. CONCLUSION: HCM was significantly associated with the risk of incident mental disorders, particularly within 1 year after HCM diagnosis, underscoring the importance of screening mental health problems, including mood and anxiety disorders, in patients with HCM.

Mortality impact of low CAC density predominantly occurs in early atherosclerosis: explainable ML in the CAC consortium.

BACKGROUND: Machine learning (ML) models of risk prediction with coronary artery calcium (CAC) and CAC characteristics exhibit high performance, but are not inherently interpretable. OBJECTIVES: To determine the direction and magnitude of impact of CAC characteristics on 10-year all-cause mortality (ACM) with explainable ML. METHODS: We analyzed asymptomatic subjects in the CAC consortium. We trained ML models on 80% and tested on 20% of the data with XGBoost, using clinical characteristics â€‹+ â€‹CAC (ML 1) and additional CAC characteristics of CAC density and number of calcified vessels (ML 2). We applied SHAP, an explainable ML tool, to explore the relationship of CAC and CAC characteristics with 10-year all-cause and CV mortality. RESULTS: 2376 deaths occurred among 63,215 patients [68% male, median age 54 (IQR 47-61), CAC 3 (IQR 0-94.3)]. ML2 was similar to ML1 to predict all-cause mortality (Area Under the Curve (AUC) 0.819 vs 0.821, p â€‹= â€‹0.23), but superior for CV mortality (0.847 vs 0.845, p â€‹= â€‹0.03). Low CAC density increased mortality impact, particularly ≤0.75. Very low CAC density ≤0.75 was present in only 4.3% of the patients with measurable density, and 75% occurred in CAC1-100. The number of diseased vessels did not increase mortality overall when simultaneously accounting for CAC and CAC density. CONCLUSION: CAC density contributes to mortality risk primarily when it is very low ≤0.75, which is primarily observed in CAC 1-100. CAC and CAC density are more important for mortality prediction than the number of diseased vessels, and improve prediction of CV but not all-cause mortality. Explainable ML techniques are useful to describe granular relationships in otherwise opaque prediction models.

Differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM model.

Differential diagnosis of left ventricular hypertrophy (LVH) is often obscure on echocardiography and requires numerous additional tests. We aimed to develop a deep learning algorithm to aid in the differentiation of common etiologies of LVH (i.e. hypertensive heart disease [HHD], hypertrophic cardiomyopathy [HCM], and light-chain cardiac amyloidosis [ALCA]) on echocardiographic images. Echocardiograms in 5 standard views (parasternal long-axis, parasternal short-axis, apical 4-chamber, apical 2-chamber, and apical 3-chamber) were obtained from 930 subjects: 112 with HHD, 191 with HCM, 81 with ALCA and 546 normal subjects. The study population was divided into training (n = 620), validation (n = 155), and test sets (n = 155). A convolutional neural network-long short-term memory (CNN-LSTM) algorithm was constructed to independently classify the 3 diagnoses on each view, and the final diagnosis was made by an aggregate network based on the simultaneously predicted probabilities of HCM, HCM, and ALCA. Diagnostic performance of the algorithm was evaluated by the area under the receiver operating characteristic curve (AUC), and accuracy was evaluated by the confusion matrix. The deep learning algorithm was trained and verified using the training and validation sets, respectively. In the test set, the average AUC across the five standard views was 0.962, 0.982 and 0.996 for HHD, HCM and CA, respectively. The overall diagnostic accuracy was significantly higher for the deep learning algorithm (92.3%) than for echocardiography specialists (80.0% and 80.6%). In the present study, we developed a deep learning algorithm for the differential diagnosis of 3 common LVH etiologies (HHD, HCM and ALCA) by applying a hybrid CNN-LSTM model and aggregate network to standard echocardiographic images. The high diagnostic performance of our deep learning algorithm suggests that the use of deep learning can improve the diagnostic process in patients with LVH.

Prognostic Implications of Mechanical Phenotypes in Heart Failure Characterized by 3-Chamber Strain Echocardiography.

Background Heart failure (HF) involves dysfunction of the left ventricle (LV) as well as left atrium and right ventricle. We characterized mechanical phenotypes of HF using 3-chamber strain echocardiography and compared their clinical outcomes. Methods and Results We retrospectively analyzed 3574 patients (median age, 74 years; male 52.8%) with acute HF who underwent 3-chamber strain echocardiography. Patients were classified as with LV, left atrium, or right ventricle myopathy if their corresponding strain values (LV global longitudinal strain, left atrium reservoir strain, and right ventricle global longitudinal strain) were lower than median cutoffs, respectively. The mechanical phenotypes of individual patients were characterized according to the combined myopathy. The primary outcome was a composite end point of 5-year all-cause mortality and HF hospitalization. During follow-up (median, 25.8 months), the primary outcome occurred in 1877 (52.5%) patients. Three-chamber strain values were independent predictors for the primary outcome. An incremental trend was observed for the primary outcome, along with the increasing numbers of combined myopathy. Each mechanical phenotype exhibited an increased risk of the primary outcome, with the highest risk observed in patients with 3-chamber myopathy (hazard ratio, 1.67 [95% CI, 1.42-1.96]). The prognostic significance of the mechanical phenotypes was feasible across the conventional HF subtypes stratified by LV ejection fraction. In HF with preserved ejection fraction, the presence of left atrium and right ventricle myopathy significantly increased the primary outcome, regardless of combined left ventricle myopathy. Conclusions Assessment of 3-chamber strain in HF enables characterization of distinctive mechanical phenotypes, which provides an independent prognostic value that may support long-term risk stratification.

Body Mass Index, Muscle Mass, and All-Cause Mortality in Patients With Acute Heart Failure: The Obesity Paradox Revisited.

Background and Objectives: Lower body mass index (BMI) is considered a poor prognostic factor in patients with heart failure (HF). We aimed to investigate the clinical impact of BMI on the risk of mortality in patients with acute HF (AHF) across various phenotypes. Methods: We retrospectively identified 4,146 registry patients with AHF and BMI data. The study population was categorized according to the WHO Asia-Pacific BMI classification: BMI <18.5 kg/m2 (underweight; n=418), BMI 18.5-23 kg/m2 (ideal; n=1,620), BMI 23-25 kg/m2 (overweight; n=828), BMI 25-30 kg/m2 (obesity I; n=1,047), and BMI ≥30 kg/m2 (obesity II; n=233). The risk of all-cause mortality was compared between these 5 groups. Results: During a median follow-up of 32 months, 1,732 patients (41.8%) died. Compared to patients with obesity II, those with overweight, ideal BMI or underweight status had a higher risk of mortality (overweight: hazard ratio [HR], 1.606; 95% confidence interval [CI], 1.016-2.539; p=0.042) (ideal BMI: HR, 1.744; 95% CI, 1.112-2.734; p=0.015) (underweight: HR, 2.729; 95% CI, 1.686-4.417; p<0.001). Higher risk of mortality among patients with lower BMI was observed regardless of age, sex, hypertension, diabetes, ischemic heart disease, atrial fibrillation, and HF phenotype. Furthermore, low muscle index (total muscle mass/height2), calculated using serum cystatin C data in a subset of 579 patients, was associated with higher mortality risk. Conclusions: A lower BMI is associated with a higher risk of mortality in patients with AHF. This obesity paradox is observed in AHF regardless of comorbidities and HF phenotype.

Comparison of cardiovascular and renal outcomes between dapagliflozin and empagliflozin in patients with type 2 diabetes without prior cardiovascular or renal disease.

BACKGROUND: Cardiovascular and renal benefits of sodium glucose co-transporter 2 inhibitors (SGLT2i) have been clearly demonstrated. However, studies comparing the effects of dapagliflozin and empagliflozin are scarce. In addition, relatively few studies have analyzed the effects of SGLT2i in diabetic patients without established atherosclerotic cardiovascular disease (ASCVD), chronic kidney disease (CKD), or heart failure (HF), and current guidelines recommend SGLT2i and other antidiabetic drugs equally in this population. Therefore, we aimed to compare the clinical outcomes between dapagliflozin, empagliflozin, and dipeptidyl peptidase-4 inhibitors (DPP4i) in patients with type 2 diabetes without prior ASCVD, CKD, or HF. METHODS: Using a propensity-score matching method, we retrospectively analyzed 921 patients treated with dapagliflozin, 921 patients treated with empagliflozin, and 1842 patients treated with DPP4i (control group). Study outcomes comprised composite coronary events (acute coronary syndrome and coronary revascularization), composite ischemic events (coronary events and stroke), and composite heart failure and renal events. RESULTS: During follow up (median, 43.4 months), the incidence of composite coronary events was significantly lower in the SGLT2i groups than in the control group, and the incidence of composite ischemic events was lower in the dapagliflozin group than in the control group. Dapagliflozin and empagliflozin both demonstrated significant benefits in terms of HF and renal outcomes, supported by renoprotective effects, as assessed by the change in glomerular filtration rate. At 24-36 months of treatment, the empagliflozin group had higher low-density lipoprotein cholesterol levels, and lower glycated hemoglobin levels, compared to those in the dapagliflozin and control groups. CONCLUSION: SGLT2i use was associated with a significantly reduced risk of ASCVD, HF hospitalization, and renal events, compared to that with DPP4i use among diabetic patients without prior ASCVD, CKD, or HF. There were no significant differences in clinical outcomes between dapagliflozin and empagliflozin, supporting a SGLT2i class effect.