Impact of volume indices in bioelectrical impedance measurement on the assessment of cardiac function indices by echocardiography in hemodialysis patients.

INTRODUCTION: Cardiovascular events resulting from volume overload are a primary cause of mortality in hemodialysis patients. Bioelectrical impedance analysis (BIA) is significantly valuable for assessing the volume status of hemodialysis (HD) patients. In this article, we explore the correlation between the volume index measured by BIA and the cardiac function index assessed by echocardiography (ECG) in HD patients. METHODS: Between April and November 2018, we conducted a cross-sectional study involving randomly selected 126 maintenance HD patients. Comprehensive data on medical history and laboratory test results were collected. Subsequently, we investigated the correlation between volume indices measured by BIA and cardiac function parameters by ECG. RESULTS: We discovered a significant correlation between the volume indices measured by BIA and various parameter of cardiac function. The Left Ventricular Hypertrophy (LVH) group exhibited higher levels of the percentage of Extracellular Water (ECW%) and the percentage of Total Body Water (TBW%) compared to the Non-LVH group. Extracellular Water (ECW) and Third Interstitial Fluid Volume (TSFV) were identified as independent risk factors for Left Ventricular Mass (LVM), and both demonstrated a high predictive value for LVM. ECW% emerged as an independent risk factor for the Left Ventricular Mass Index (LVMI), with a high predictive value for LVMI. CONCLUSION: ECW and TSFV were found to be positively associated with cardiac function parameters in HD patients.

Left ventricular geometry characteristics and clinical outcomes in hemodialysis patients with heart failure with preserved ejection fraction.

BACKGROUND: The relationships among left heart remodeling, cardiac function, and cardiovascular events (CEs) in patients with heart failure (HF) with preserved ejection fraction (HFpEF) undergoing maintenance hemodialysis (MHD) remain unclear. We evaluated the echocardiographic characteristics and clinical outcomes of such patients with diverse left ventricular geometric (LVG) configurations. METHODS: Overall, 210 patients with HFpEF undergoing MHD (cases) and 60 healthy controls were enrolled. Cases were divided into four subgroups based on LVG and were followed up for three years. The primary outcomes were the first CEs and all-cause mortality. RESULTS: Left ventricular ejection fraction (LVEF) and right ventricular systolic function did significantly differ between cases and controls, whereas echocardiographic parameters of cardiac structure, diastolic function, and left ventricular global longitudinal strain (LVGLS) differed significantly. The proportion of cases with left ventricular hypertrophy (LVH) was 67.1%. In addition, 2.38%, 21.90%, 12.86%, and 62.86% of cases presented with normal geometry (NG), concentric remodeling (CR), eccentric hypertrophy (EH), and concentric hypertrophy (CH), respectively. The left atrial diameter (LAD) was the largest and cardiac output index was the lowest in the EH subgroup. The score of Acute Dialysis Quality Initiative Workgroup (ADQI) HF class was worse in the EH subgroup than in other subgroups at baseline. The proportions of cases free of adverse CEs in the EH subgroup at 12, 24, and 36 months were 40.2%, 14.8%, and 0%, respectively, and the survival rates were 85.2%, 29.6%, 3.7%, respectively, which were significantly lower than those in other subgroups. Multivariate Cox regression revealed that age, TNI (Troponin I), EH, left ventricular mass index (LVMI), age and EH configuration were independent risk factors for adverse CEs and all-cause mortality in the cases. CONCLUSION: Most patients with HFpEF receiving MHD have LVH and diastolic dysfunction. Among the four LVGs, patients with HFpEF undergoing MHD who exhibited EH had the highest risk of adverse CEs and all-cause mortality.

Enhanced classification of left ventricular hypertrophy in cardiac patients using extended Siamese CNN.

Objective.Left ventricular hypertrophy (LVH) is the thickening of the left ventricle wall of the heart. The objective of this study is to develop a novel approach for the accurate assessment of LVH) severity, addressing the limitations of traditional manual grading systems.Approach.We propose the Multi-purpose Siamese Weighted Euclidean Distance Model (MSWED), which utilizes convolutional Siamese neural networks and zero-shot/few-shot learning techniques. Unlike traditional methods, our model introduces a cutoff distance-based approach for zero-shot learning, enhancing accuracy. We also incorporate a weighted Euclidean distance targeting informative regions within echocardiograms.Main results.We collected comprehensive datasets labeled by experienced echocardiographers, including Normal heart and various levels of LVH severity. Our model outperforms existing techniques, demonstrating significant precision enhancement, with improvements of up to 13% for zero-shot and few-shot learning approaches.Significance.Accurate assessment of LVH severity is crucial for clinical prognosis and treatment decisions. Our proposed MSWED model offers a more reliable and efficient solution compared to traditional grading systems, reducing subjectivity and errors while providing enhanced precision in severity classification.

Association between the atherogenic index of plasma and left ventricular hypertrophy in patients with obstructive sleep apnea: a retrospective cross-sectional study.

BACKGROUND: The atherogenic index of plasma (AIP) is a simple and reliable marker of insulin resistance and is closely associated with various cardiovascular diseases (CVDs). However, the relationships between AIP and left ventricular (LV) geometric indicators have not been adequately assessed. This study was carried out to investigate the association between AIP and LV geometric abnormalities in obstructive sleep apnea (OSA) patients. METHODS: This retrospective cross-sectional study included a total of 618 OSA patients (57.3 ± 12.4 years, 73.1% males, BMI 28.1 ± 4.2 kg/m2) who underwent echocardiography. Patients with OSA were diagnosed with clinical symptoms and an apnea-hypopnea index ≥ 5.0. LV hypertrophy (LVH) was defined as left ventricular mass index (LVMIh2.7) ≥ 50.0 g/m2.7 for men and 47.0 g/m2.7 for women. AIP was calculated as log10 (TG/HDL-C). RESULTS: Compared with the non-LVH group, AIP was significantly higher in the LVH group (0.19 ± 0.29 vs 0.24 ± 0.28, P = 0.024) and the concentric LVH group (0.18 ± 0.29, 0.19 ± 0.30, 0.20 ± 0.26 and 0.29 ± 0.29 in the control, concentric remodeling, eccentric hypertrophy and concentric hypertrophy groups, respectively, P = 0.021). Meanwhile, in the group of patients with the highest AIP tertile, the levels of LVMIh2.7 (42.8 ± 10.5, 43.2 ± 9.3 and 46.1 ± 12.1 in the T1, T2 and T3 groups, respectively, P = 0.003), and the prevalence of LVH (25.2%, 24.0% and 34.6% in the T1, T2 and T3 groups, respectively, P = 0.032) and concentric LVH (10.7%, 9.8% and 20.2% in the T1, T2 and T3 groups, respectively, P = 0.053) were higher compared with those in the other groups. Positive correlations between AIP and LV geometric indicators including the LVMIh2.7, LVMIBSA, LV mass (LVM), diastolic left ventricular inner diameter (LVIDd), diastolic left ventricular posterior wall thickness (PWTd) and diastolic interventricular septal thickness (IVSTd), were revealed according to correlation analysis (P < 0.05). Furthermore, AIP was independently associated with LVMIh2.7 according to multivariate linear regression model (ß = 0.125, P = 0.001). Notably, AIP remained independently associated with an elevated risk of LVH [odds ratio (OR) = 1.317 per 1 standard deviation (SD) increment, 95% confidence interval (CI): 1.058 - 1.639, P = 0.014) and concentric LVH (OR = 1.545 per 1 SD increment, 95% CI: 1.173 - 2.035, P = 0.002) after fully adjusting for all confounding risk factors by multivariate logistic regression analyses. CONCLUSIONS: AIP was independently associated with an increased risk of LVH and concentric LVH in OSA patients. Therefore, AIP, as a practical and cost-effective test, might be useful in monitoring hypertrophic remodeling of the heart and improving CVDs risk stratification in clinical management of OSA.

Agalsidase alfa long-term effect on left ventricular hypertrophy in Fabry disease.

INTRODUCTION: Fabry disease (FD) is an X-linked lysosomal storage disorder affecting glycosphingolipid metabolism. Most FD patients have cardiac involvement, mainly manifested as left ventricular hypertrophy (LVH), leading to early death due to complications (arrhythmias, valvular disease, vascular involvement). Early initiation of enzyme replacement therapy (ERT) before fibrosis development has been associated with better cardiac outcomes in terms of left ventricular mass index (LVMI) and functional parameters. METHODS: A retrospective observational study was conducted in patients with FD treated with agalsidase alfa for at least 2 years. The primary objectives were: [a] to assess the annual rate of change in LVMI; [b] to define the overall incidence of stability, regression or progression of LVMI. RESULTS: Forty-nine patients were included in the final analysis, with a median follow-up of 7 years. The overall change in LVMI was 0.38 g/m2.73/year, without significant influence of baseline LVH, gender, age at ERT initiation, LV ejection fraction, body mass index, renal disease, and classical cardiovascular risk factors. Long-term ERT with agalsidase alfa was associated with stabilization of LVMI in 98% of patients with FD and was independent of the same covariables. CONCLUSION: Our results are in line with previous literature of comparable FD populations and probably represent the first study of its kind in Argentina. We here highlight the importance of cardiac morphometric stability as a positive outcome of ERT.

Introducción: La enfermedad de Fabry (EF) es una enfermedad de almacenamiento lisosomal ligada al cromosoma X que afecta el metabolismo de glicoesfingolípidos. La mayoría de pacientes EF tienen afectación cardíaca, manifestada principalmente como hipertrofia ventricular izquierda (HVI), que conduce a muerte prematura secundaria a complicaciones (arritmias, valvulopatías, afectación vascular). El tratamiento de reemplazo enzimático (TRE) precoz, iniciado antes del desarrollo de la fibrosis, se relaciona con mejores resultados cardíacos en términos del índice de masa ventricular izquierda (IMVI) y parámetros funcionales. Métodos: Se realizó un estudio retrospectivo observacional en que se incluyeron pacientes con EF tratados con agalsidasa alfa por al menos 2 años. Los objetivos primarios fueron: [a] evaluar el cambio anual del IMVI; [b] definir la incidencia global de estabilidad, regresión o progresión del IMVI. Resultados: Se incluyeron 49 pacientes, con seguimiento (mediana) de 7 años. El cambio global en el IMVI fue 0.38 g/m2.73/año, sin influencia significativa de HVI basal, sexo, edad de inicio de TRE, fracción de eyección del VI, índice de masa corporal, insuficiencia renal y factores de riesgo cardiovascular clásicos. La TRE a largo plazo con agalsidasa alfa se relacionó con la estabilización del IMVI en el 98% de los pacientes con EF, independientemente de las mismas covariables. Conclusión: Nuestros resultados están en línea con la bibliografía previa de poblaciones comparables y, probablemente, representan el primer estudio de este tipo en Argentina. Se destaca la importancia de la estabilidad morfométrica cardíaca como resultado positivo de la TRE.

Obesity and Risk of Incident Left Ventricular Hypertrophy in Community-Dwelling Populations With Hypertension: An Observational Study.

BACKGROUND: The aim of this study was to evaluate the association between obesity and risk of incident left ventricular hypertrophy (LVH) in community-dwelling populations with hypertension and investigate whether this association would be attenuated by a lower achieved systolic blood pressure (SBP). METHODS AND RESULTS: We used the EMINCA (Echocardiographic Measurements in Normal Chinese Adults) criteria, which were derived from healthy Chinese populations to define LVH. A total of 2069 participants with hypertension and without LVH (obesity 20.4%) were included. The association between obesity and risk of incident LVH was evaluated using Cox proportional hazard models and stratified by achieved follow-up SBP levels (≥140, 130-139, and <130 mm Hg). These analyses were also assessed using the American Society of Echocardiography/European Association of Cardiovascular Imaging criteria, which were derived from European populations to define LVH. After a median follow-up of 2.90 years, the rates of incident LVH in the normal-weight, overweight, and obese groups were 13.5%, 20.3%, and 27.8%, respectively (P<0.001). In reference to normal weight, obesity was associated with increased risk of incident LVH (adjusted hazard ratio [aHR], 2.51 [95% CI, 1.91-3.29]), which was attenuated when achieved SBP was <130 mm Hg (aHR, 1.78 [95% CI, 0.99-3.19]). This association remained significant when achieved SBP was ≥140 mm Hg (aHR, 3.45 [95% CI, 2.13-5.58]) or at 130 to 139 mm Hg (aHR, 2.32 [95% CI, 1.23-4.36]). Differences in these findings were noted when LVH was defined by the American Society of Echocardiography/European Association of Cardiovascular Imaging criteria. CONCLUSIONS: Obesity was associated with incident LVH and an SBP target <130 mm Hg might be needed to attenuate this risk in patients with hypertension and obesity.

Pulse wave signal-driven machine learning for identifying left ventricular enlargement in heart failure patients.

BACKGROUND: Left ventricular enlargement (LVE) is a common manifestation of cardiac remodeling that is closely associated with cardiac dysfunction, heart failure (HF), and arrhythmias. This study aimed to propose a machine learning (ML)-based strategy to identify LVE in HF patients by means of pulse wave signals. METHOD: We constructed two high-quality pulse wave datasets comprising a non-LVE group and an LVE group based on the 264 HF patients. Fourier series calculations were employed to determine if significant frequency differences existed between the two datasets, thereby ensuring their validity. Then, the ML-based identification was undertaken by means of classification and regression models: a weighted random forest model was employed for binary classification of the datasets, and a densely connected convolutional network was utilized to directly estimate the left ventricular diastolic diameter index (LVDdI) through regression. Finally, the accuracy of the two models was validated by comparing their results with clinical measurements, using accuracy and the area under the receiver operating characteristic curve (AUC-ROC) to assess their capability for identifying LVE patients. RESULTS: The classification model exhibited superior performance with an accuracy of 0.91 and an AUC-ROC of 0.93. The regression model achieved an accuracy of 0.88 and an AUC-ROC of 0.89, indicating that both models can quickly and accurately identify LVE in HF patients. CONCLUSION: The proposed ML methods are verified to achieve effective classification and regression with good performance for identifying LVE in HF patients based on pulse wave signals. This study thus demonstrates the feasibility and potential of the ML-based strategy for clinical practice while offering an effective and robust tool for diagnosing and intervening ventricular remodeling.

Ethnicity differences in geometric remodelling and myocardial composition in hypertension unveiled by cardiovascular magnetic resonance.

AIMS: Hypertensive patients of African ancestry (Afr-a) have higher incidences of heart failure and worse clinical outcomes than hypertensive patients of European ancestry (Eu-a), yet the underlying mechanisms remain misunderstood. This study investigated right (RV) and left (LV) ventricular remodelling alongside myocardial tissue derangements between Afr-a and Eu-a hypertensives. METHODS AND RESULTS: 63 Afr-a and 47 Eu-a hypertensives underwent multi-parametric cardiovascular magnetic resonance. Biventricular volumes, mass, function, mass/end-diastolic volume (M/V) ratios, T2 and pre-/post-contrast T1 relaxation times, synthetic extracellular volume, and myocardial fibrosis (MF) were measured. 3D shape modelling was implemented to delineate ventricular geometry. LV and RV mass (indexed to body-surface-area) and M/V ratio were significantly greater in Afr-a than Eu-a hypertensives (67.1 ± 21.7 vs. 58.3 ± 16.7 g/m2, 12.6 ± 3.48 vs. 10.7 ± 2.71 g/m2, 0.79 ± 0.21 vs. 0.70 ± 0.14 g/mL, and 0.16 ± 0.04 vs. 0.13 ± 0.03 g/mL, respectively; P < 0.03). Afr-a patients showed greater basal interventricular septum thickness than Eu-a patients, influencing LV hypertrophy and RV cavity changes. This biventricular remodelling was associated with prolonged T2 relaxation time (47.0 ± 2.2 vs. 45.7 ± 2.2 ms, P = 0.005) and higher prevalence (23% vs. 4%, P = 0.001) and extent of MF [2.3 (0.6-14.3) vs. 1.6 (0.9-2.5) % LV mass, P = 0.008] in Afr-a patients. Multivariable linear regression showed that modifiable cardiovascular risk factors and greater end-diastolic volume, but not ethnicity, were independently associated with greater LV mass. CONCLUSION: Afr-a hypertensives had distinctive biventricular remodelling, including increased RV mass, septal thickening and myocardial tissue abnormalities compared with Eu-a hypertensives. From this study, modifiable cardiovascular risk factors and ventricular geometry, but not ethnicity, were independently associated with greater LV myocardial mass.

Differential associations between abnormal cardiac left ventricular geometry types and cerebral white matter disease.

OBJECTIVES: Reduced cardiac outflow due to left ventricular hypertrophy has been suggested as a potential risk factor for development of cerebral white matter disease. Our study aimed to examine the correlation between left ventricular geometry and white matter disease volume to establish a clearer understanding of their relationship, as it is currently not well-established. METHODS: Consecutive patients from 2016 to 2021 who were ≥18 years and underwent echocardiography, cardiac MRI, and brain MRI within one year were included. Four categories of left ventricular geometry were defined based on left ventricular mass index and relative wall thickness on echocardiography. White matter disease volume was quantified using an automated algorithm applied to axial T2 FLAIR images and compared across left ventricular geometry categories. RESULTS: We identified 112 patients of which 34.8 % had normal left ventricular geometry, 20.5 % had eccentric hypertrophy, 21.4 % had concentric remodeling, and 23.2 % had concentric hypertrophy. White matter disease volume was highest in patients with concentric hypertrophy and concentric remodeling, compared to eccentric hypertrophy and normal morphology with a trend-P value of 0.028. Patients with higher relative wall thickness had higher white matter disease volume (10.73 ± 10.29 cc vs 5.89 ± 6.46 cc, P = 0.003), compared to those with normal relative wall thickness. CONCLUSION: Our results showed that abnormal left ventricular geometry is associated with higher white matter disease burden, particularly among those with abnormal relative wall thickness. Future studies are needed to explore causative relationships and potential therapeutic options that may mediate the adverse left ventricular remodeling and its effect in slowing white matter disease progression.

Deep learning to detect left ventricular structural abnormalities in chest X-rays.

BACKGROUND AND AIMS: Early identification of cardiac structural abnormalities indicative of heart failure is crucial to improving patient outcomes. Chest X-rays (CXRs) are routinely conducted on a broad population of patients, presenting an opportunity to build scalable screening tools for structural abnormalities indicative of Stage B or worse heart failure with deep learning methods. In this study, a model was developed to identify severe left ventricular hypertrophy (SLVH) and dilated left ventricle (DLV) using CXRs. METHODS: A total of 71 589 unique CXRs from 24 689 different patients completed within 1 year of echocardiograms were identified. Labels for SLVH, DLV, and a composite label indicating the presence of either were extracted from echocardiograms. A deep learning model was developed and evaluated using area under the receiver operating characteristic curve (AUROC). Performance was additionally validated on 8003 CXRs from an external site and compared against visual assessment by 15 board-certified radiologists. RESULTS: The model yielded an AUROC of 0.79 (0.76-0.81) for SLVH, 0.80 (0.77-0.84) for DLV, and 0.80 (0.78-0.83) for the composite label, with similar performance on an external data set. The model outperformed all 15 individual radiologists for predicting the composite label and achieved a sensitivity of 71% vs. 66% against the consensus vote across all radiologists at a fixed specificity of 73%. CONCLUSIONS: Deep learning analysis of CXRs can accurately detect the presence of certain structural abnormalities and may be useful in early identification of patients with LV hypertrophy and dilation. As a resource to promote further innovation, 71 589 CXRs with adjoining echocardiographic labels have been made publicly available.

Left ventricular hypertrophy and left atrial diameter are associated with mortality risk in haemodialysis patients: a retrospective cohort study.

BACKGROUND: Cardiovascular death is the main cause of death in patients with end-stage kidney disease (ESKD). Left ventricular hypertrophy (LVH) and left atrial diameter (LAD) enlargement are frequent cardiac alterations in patients with ESKD and are major risk factors for cardiovascular events. However, it remains unclear whether there is an association between combined LAD or LVH and all-cause or cardiovascular mortality in this population. METHODS: A single-centre, retrospective cohort study including 576 haemodialysis (HD) patients was conducted. Patients were evaluated by cardiac ultrasound, and the study cohort was divided into four groups according to LAD and LVH status: low LAD and non-LVH; low LAD and LVH; high LAD and non-LVH; and high LAD and LVH. We used Kaplan-Meier analysis and Cox proportional hazard regression to analyse all-cause and cardiovascular mortality after multivariate adjustment. RESULTS: LAD was associated with an increased risk of all-cause mortality (HR 2.371, 1.602-3.509; p < 0.001). No significant differences were found between LVH and the risk of all-cause mortality. Patients with high LAD and LVH had significantly greater all-cause and cardiovascular mortality than did those with low LAD and non-LVH after adjustments for numerous potential confounders (HR 3.080, 1.608-5.899; p = 0.001) (HR 4.059, 1.753-9.397; p = 0.001). CONCLUSION: Among maintenance haemodialysis (MHD) patients, LAD was more strongly associated with mortality than was LVH. A high LAD and LVH are associated with a greater risk of mortality. Our results emphasize that the occurrence of LAD and LVH in combination provides information that may be helpful in stratifying the risk of MHD patients.

Discordance interpretation of left ventricular size between echocardiography and cardiac magnetic resonance in pediatric patients with aortic/mitral regurgitation.

PURPOSE: This study investigated discordance between echocardiography (echo) and cardiac magnetic resonance (CMR) measurements of the left ventricle (LV) in pediatric patients with aortic and/or mitral regurgitation (AR/MR). METHODS: Retrospective cohort study of pediatric patients. The cohorts were comprised of patients with AR/MR vs. non-AR/MR. Left ventricular end diastolic volume (LVEDV) by CMR and left ventricular internal diameter diastolic (LVIDd) by echo were obtained from clinical reports then echo images were reviewed to remeasure LVEDV by bullet method. Left ventricular internal diameter systolic (LVIDs) and left ventricular ejection fraction (LVEF) measurements by echo and LVEF by CMR were obtained from clinical reports. Fractional shortening (FS%) was recalculated. Z-scores were calculated using normative data. Correlation between echo and CMR LV measurements was assessed using correlation coefficients. Bland-Altman plots assessed bias between imaging modalities. Receiver operator characteristic (ROC) analysis was performed for detection of LV enlargement and LV dysfunction. RESULTS: AR/MR patients had greater discrepancy in LV size interpretation by Z-score compared to non-AR/MR patients. This discrepancy persisted when the bullet method short axis measurements were incorporated. There was negative bias in echo-based measurements compared to CMR. The diagnostic performance of echo in identifying moderate LV enlargement was worse for AR/MR pediatrics patients. CONCLUSION: The discordant interpretation of LV size by echo compared to CMR is worse in pediatric patients with AR/MR when compared to patients without AR/MR even when short axis measurements are incorporated. This finding suggests non-uniform geometrical changes in the LV as it enlarges due to AR/MR.

Association Between Elevated Body Mass Index and Cardiac Organ Damage in Children and Adolescents: Evidence and Mechanisms.

INTRODUCTION: Although a number of pathophysiological aspects of childhood obesity have been reported, few information are available on obesity-related cardiac organ damage. AIM: The present study was aimed at assessing the impact of anthropometric, blood pressure (BP) and metabolic variable on cardiac structure and function in youth. METHODS: In 78 subjects aged 5-16 years attending the outpatient clinic of cardiovascular risk (Valencia, Spain) anthropometric and metabolic variables, clinic and ambulatory BP and echocardiographic parameters were assessed. Subjects were also classified according to the presence of insulin resistance. RESULTS: Subjects mean age (± SD) amounted to 12.03 ± 2.4 years and males to 53.8%. Ten subjects were normoweight, 11 overweight, 39 obese, and 18 severely obese. No significant difference in office and ambulatory BP was detected among different bodyweight groups. A significant direct correlation was observed between left ventricular mass index (LVMI) and obesity markers [body mass index (BMI): r = 0.38, waist circumference (WC): r = 0.46, P < 0.04 for both]. Left ventricular hypertrophy, relative wall thickness and left atrial diameter were significantly related to BMI and WC. In contrast, office and ambulatory BP were unrelated to other variables, and differences in LVMI among different BP phenotypes were not significant. When partitioning the population by insulin resistance, LVMI, adjusted for confounders, was significantly greater in the insulin-resistant group. CONCLUSIONS: In children and adolescents characterized by different body weight patterns, weight factors "per se" and the related insulin resistance state appear to represent the main determinants of LVMI and left ventricular hypertrophy, independently on BP values and BP phenotypes.

One-shot screening: Utilization of a two-dimensional convolutional neural network for automatic detection of left ventricular hypertrophy using electrocardiograms.

BACKGROUND AND OBJECTIVE: Left ventricular hypertrophy (LVH) can impair ejection function and elevate the risk of heart failure. Therefore, early detection through screening is crucial. This study aimed to propose a novel method to enhance LVH detection using 12-lead electrocardiogram (ECG) waveforms with a two-dimensional (2D) convolutional neural network (CNN). METHODS: Utilizing 42,127 pairs of ECG-transthoracic echocardiogram data, we pre-processed raw data into single-shot images derived from each ECG lead and conducted lead selection to optimize LVH diagnosis. Our proposed one-shot screening method, implemented during pre-processing, enables the superimposition of waveform source data of any length onto a single-frame image, thereby addressing the limitations of the one-dimensional (1D) approach. We developed a deep learning model with a 2D-CNN structure and machine learning models for LVH detection. To assess our method, we also compared our results with conventional ECG criteria and those of a prior study that used a 1D-CNN approach, utilizing the same dataset from the University of Tokyo Hospital for LVH diagnosis. RESULTS: For LVH detection, the average area under the receiver operating characteristic curve (AUROC) was 0.916 for the 2D-CNN model, which was significantly higher than that obtained using logistic regression and random forest methods, as well as the two conventional ECG criteria (AUROC of 0.766, 0.790, 0.599, and 0.622, respectively). Incorporating additional metadata, such as ECG measurement data, further improved the average AUROC to 0.921. The model's performance remained stable across two different annotation criteria and demonstrated significant superiority over the performance of the 1D-CNN model used in a previous study (AUROC of 0.807). CONCLUSIONS: This study introduces a robust and computationally efficient method that outperforms 1D-CNN models utilized in previous studies for LVH detection. Our method can transform waveforms of any length into fixed-size images and leverage the selected lead of the ECG, ensuring adaptability in environments with limited computational resources. The proposed method holds promise for integration into clinical practice as a tool for early diagnosis, potentially enhancing patient outcomes by facilitating earlier treatment and management.

Cardio-Ankle Vascular Index as a Marker of Left Ventricular Hypertrophy in Treated Hypertensives: Findings From the Pamela Study.

BACKGROUND: Findings regarding the association between Cardio-Ankle Vascular Index (CAVI) and cardiac hypertension-mediated organ damage (HMOD), such as left ventricular hypertrophy (LVH) assessed by echocardiography, in elderly hypertensive patients are scanty. We sought to investigate this issue in the hypertensive fraction of the general population treated with anti-hypertensive drugs enrolled in the Pressioni Monitorate E Loro Associazioni (PAMELA) study. METHODS: The study included 239 out of 562 participants who attended the second and third surveys of the PAMELA study performed after 10 and 25 years from the initial evaluation. Data collection included medical history, anthropometric parameters, office, home, ambulatory blood pressure (BP), blood examinations, echocardiography, and CAVI measurements. RESULTS: In the whole study sample (age 69 ±â€…9 years, 54% males), CAVI was positively correlated with age, office, home, ambulatory systolic BP, LV mass (LVM) index, and negatively associated with body mass index (BMI). In multivariate analysis, CAVI was associated with the LVM index (P < 0.05) independently of major confounders. The participants with LVH exhibited significantly higher CAVI (10.6 ±â€…2.8 vs. 9.2 ±â€…1.8 m/s P < 0.001), larger left atrial diameter, and lower LV ejection fraction values than their counterparts without it. The CAVI value of 9.4 m/s was the best cut-off for prediction of LVH in the whole sample. CONCLUSIONS: Our study provides new evidence of an independent association between CAVI and LVH in treated elderly hypertensive patients and suggests that the use of this metric of arterial stiffness could not only be used to evaluate vascular damage but also to stratify the risk of LVH.