Abstract:IntroductionLeft ventricular hypertrophy (LVH) is an independent risk factor for cardiovascular morbidity and mortality in hypertensive patients (1-3). Even though some results regarding the relationship between hypertrophy and the severity of hypertension are contradictory, a number of studies have reported that the prevalence of hypertrophy increases with the severity of hypertension (4, 5).Essential hypertension is a multifactorial condition affecting a large percentage of the adult Turkish population (33.7… Show more
“…This is not surprising according to [17] that elevated blood pressure corresponds with high LVMI. Moreover, GATAN identifies more subtle relations between lab results and LVMI, including potassium, vitamin D, calcium, diabetes status, bun, renin et al These top-ranked features accord with previous researches ([15, 18, 19]), demonstrating that feature ranking by analyzing the learned weights is a reasonable heuristic for interpreting deep neural networks. Fig.…”
Section: Resultssupporting
confidence: 78%
“…However, the Pearson correlation between LVMI and calcium is 0.00 for the entire dataset, -0.10 for LVMI <120. In previous studies [15, 16], it was shown that patients with LVH have strong positive correlation with serum calcium level compared to those without LVH. Our observations are consistent with these findings.…”
BackgroundAccurate predictive modeling in clinical research enables effective early intervention that patients are most likely to benefit from. However, due to the complex biological nature of disease progression, capturing the highly non-linear information from low-level input features is quite challenging. This requires predictive models with high-capacity. In practice, clinical datasets are often of limited size, bringing danger of overfitting for high-capacity models. To address these two challenges, we propose a deep multi-task neural network for predictive modeling.MethodsThe proposed network leverages clinical measures as auxiliary targets that are related to the primary target. The predictions for the primary and auxiliary targets are made simultaneously by the neural network. Network structure is specifically designed to capture the clinical relevance by learning a shared feature representation between the primary and auxiliary targets. We apply the proposed model in a hypertension dataset and a breast cancer dataset, where the primary tasks are to predict the left ventricular mass indexed to body surface area and the time of recurrence of breast cancer. Moreover, we analyze the weights of the proposed neural network to rank input features for model interpretability.ResultsThe experimental results indicate that the proposed model outperforms other different models, achieving the best predictive accuracy (mean squared error 199.76 for hypertension data, 860.62 for Wisconsin prognostic breast cancer data) with the ability to rank features according to their contributions to the targets. The ranking is supported by previous related research.ConclusionWe propose a novel effective method for clinical predictive modeling by combing the deep neural network and multi-task learning. By leveraging auxiliary measures clinically related to the primary target, our method improves the predictive accuracy. Based on featue ranking, our model is interpreted and shows consistency with previous studies on cardiovascular diseases and cancers.
“…This is not surprising according to [17] that elevated blood pressure corresponds with high LVMI. Moreover, GATAN identifies more subtle relations between lab results and LVMI, including potassium, vitamin D, calcium, diabetes status, bun, renin et al These top-ranked features accord with previous researches ([15, 18, 19]), demonstrating that feature ranking by analyzing the learned weights is a reasonable heuristic for interpreting deep neural networks. Fig.…”
Section: Resultssupporting
confidence: 78%
“…However, the Pearson correlation between LVMI and calcium is 0.00 for the entire dataset, -0.10 for LVMI <120. In previous studies [15, 16], it was shown that patients with LVH have strong positive correlation with serum calcium level compared to those without LVH. Our observations are consistent with these findings.…”
BackgroundAccurate predictive modeling in clinical research enables effective early intervention that patients are most likely to benefit from. However, due to the complex biological nature of disease progression, capturing the highly non-linear information from low-level input features is quite challenging. This requires predictive models with high-capacity. In practice, clinical datasets are often of limited size, bringing danger of overfitting for high-capacity models. To address these two challenges, we propose a deep multi-task neural network for predictive modeling.MethodsThe proposed network leverages clinical measures as auxiliary targets that are related to the primary target. The predictions for the primary and auxiliary targets are made simultaneously by the neural network. Network structure is specifically designed to capture the clinical relevance by learning a shared feature representation between the primary and auxiliary targets. We apply the proposed model in a hypertension dataset and a breast cancer dataset, where the primary tasks are to predict the left ventricular mass indexed to body surface area and the time of recurrence of breast cancer. Moreover, we analyze the weights of the proposed neural network to rank input features for model interpretability.ResultsThe experimental results indicate that the proposed model outperforms other different models, achieving the best predictive accuracy (mean squared error 199.76 for hypertension data, 860.62 for Wisconsin prognostic breast cancer data) with the ability to rank features according to their contributions to the targets. The ranking is supported by previous related research.ConclusionWe propose a novel effective method for clinical predictive modeling by combing the deep neural network and multi-task learning. By leveraging auxiliary measures clinically related to the primary target, our method improves the predictive accuracy. Based on featue ranking, our model is interpreted and shows consistency with previous studies on cardiovascular diseases and cancers.
“…There is much debate in current medical literature regarding the association of cholecalciferol deficiency and LVH in essential hypertension from various countries. [10][11][12] The finding of low serum cholecalciferol shows highly negative correlation that was in descending order as shown in Table-II, the finding is in agreement with a recent study from Pakistan. 8 The serum PTH and serum calcium were found elevated in LVH cases, this is being highly consistent with previous studies.…”
Section: Table-iii Correlation Of Left Ventricular Hypertrophy In Casessupporting
Objective: To assess the correlation of vitamin cholecalciferol and serum calcium with left ventricular hypertrophy (LVH) in essential hypertension patients presenting at a tertiary care hospital. Study Design: Cross Sectional Comparative study. Setting: Department of Cardiology and Medicine, Liaquat University of Medical and Health Sciences, Jamshoro, Sindh. Period: July 2019 to January 2021. Material & Methods: 100 diagnosed LVH+ Essential Hypertenison cases and 100 diagnosed essential hypertension (controls) were selected through non- probability purposive sampling. Echocardiography, serum cholecalciferol, calcium, phosphate, parathyroid hormone (PTH), alkaline phosphatase (ALP), urea and creatinine were measured form sera. Devereux’s formula measured the LV thickness LVH. SPSS ver. 21.0 analyzed the descriptive statistics and compared the variables at 95% Confidence interval (P≤0.05). Results: Serum calcium, phosphate and parathyroid hormone were found elevated in LVH cases compared to control (P=0.0001). Cholecalciferol in LVH cases was low noted as 27.3±7.84 ng/dl compared to 39.5±0.43 ng/dl in controls (P=0.0001). Cholecalciferol in mild, moderate and severe LVH cases was descending order as 30.67±7.84, 24.76±7.72 and 14.96±6.12 mm respectively (P-0.0001). Serum cholecalciferol proves inverse association (r= -0.180) with LVH (p=0.003). Conclusion: The present study reports vitamin cholecalciferol deficiency increases the chances of left ventricular hypertrophy through increased secretion of parathyroid hormone that induces de – novo protein synthesis of ventricular myocardium.
“…Calcium homeostasis impairment also is a prominent feature in the transition from compensatory hypertrophy to heart failure [ 54 ]. In additional, hemodynamics can be altered by variations in serum calcium through changes in left ventricular stroke volume and output [ 28 ]; and essential hypertension can alter calcium metabolism which in turn provokes the development of myocardial hypertrophy [ 57 ].…”
BackgroundLeft ventricular hypertrophy (LVH) is prevalent in patients with type 2 diabetes mellitus (T2DM). Recent studies show that an increase in albumin-adjusted serum calcium level is associated with an elevated risk of T2DM. We speculate that increased serum calcium levels in T2DM patients are related to LVH prevalence.MethodsIn this echocardiographic study, 833 normocalcemia and normophosphatemia patients with T2DM were enrolled. The associations between serum calcium and metabolic parameters, left ventricular mass index (LVMI), as well as the rate of LVH were examined using bivariate linear correlation, multivariate linear regression and logistic regression, respectively. The predictive performance of serum calcium for LVH was evaluated using the area under the receiver operating characteristic curve (AUC).ResultsPatients with LVH have significantly higher serum calcium than those without LVH. Serum calcium was positively associated with total cholesterol, triglycerides, low-density lipoprotein cholesterol, serum uric acid, HOMA-IR and fasting plasma glucose. Multivariate linear regression analysis demonstrated that serum calcium was independently associated with LVMI (p < 0.001). In comparison with patients in the lowest serum calcium quartile, the odds ratio (OR) for LVH in patients in the highest quartile was 2.909 (95% CI 1.792-4.720; p < 0.001). When serum calcium was analyzed as a continuous variable, per 1 mg/dl increase, the OR (95% CI) for LVH was [2.400 (1.552-3.713); p < 0.001]. Serum calcium can predict LVH (AUC = 0.617; 95% CI (0.577-0.656); p < 0.001).ConclusionsAlbumin-adjusted serum calcium is associated with an increased risk of LVH in patients with T2DM.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
