Prognosis Of Heart Disease Research Articles

Computational Learning Model for Prediction of Heart Disease Using Machine Learning Based on a New Regularizer.

Heart diseases are characterized as heterogeneous diseases comprising multiple subtypes. Early diagnosis and prognosis of heart disease are essential to facilitate the clinical management of patients. In this research, a new computational model for predicting early heart disease is proposed. The predictive model is embedded in a new regularization based on decaying the weights according to the weight matrices' standard deviation and comparing the results against its parents (RSD-ANN). The performance of RSD-ANN is far better than that of the existing methods. Based on our experiments, the average validation accuracy computed was 96.30% using either the tenfold cross-validation or holdout method.

Standardized B and M Mode Echocardiographic Indices of Egyptian Donkeys (Equus asinus) with a Special Focus on the Influence of Sex and Body Weight

Echocardiography is one of the foremost vital devices in veterinary cardiology. It is a safe, non-invasive, important diagnostic imaging instrument that enables the heart to be morphologically and clinically measured in real-time. It has been used in many animals to determine heart parameters so the purpose of this study was to determine the standardized normal echocardiographic ranges in normal healthy Egyptian donkeys with a special focus on the influence of sex and body weight. Echocardiographic examination has done for 42 adult healthy Egyptian donkeys, which were 20 males and 22 females, the age ranged between 3 and 12 years old and the weight ranged between 180–260 kg. Body condition score ranged between 4 to 6. The echocardiographic measurements of different heart dimensions were represented by mean± SD: LVFWs (cm) 1.98±0.22 , LVIDs (cm) 2.92±0.45, IVSs (cm) 2.2±0.21, LVFWd (cm) 1.52±0.18, LVIDd (cm) 4.64±0.39, IVSd (cm) 1.22±0.18, RVIDd (cm) 3.49±0.29 and AOd (cm) 3.44±0.31 and Heart function indices as follows: FS (%) 46.44±4.88 EF (%) 78.27±5.20. and there is a significant increase in the LVIDd and IVSd during diastole in males rather than females and there is a positive correlation between echocardiographic parameters and body weight.We concluded that the body weight as a variable has a positive correlation with the echocardiographic measurements and sex as a variable has a moderate influence in some parameters in males rather than females and the variables will assist us to make an accurate diagnosis, differential diagnosis and prognosis of heart diseases in Egyptian donkeys.

Analysis of the Effect of Hidden Layer Units on Coronary Heart Prediction Using the Radial Basis Functions Algorithm

Heart disease is a disease that occurs due to disturbances in the heart, especially when pumping blood so that it can cause death. Nearly half of deaths in the United States and other developed countries are caused by heart disease. Therefore, an early prognosis of heart disease is needed to prevent the risk of coronary heart disease. One thing that can be done is to predict coronary heart disease sufferers using the neural network method. This study conducted an analysis of the effect of hidden layer units on the neural network radial basis functions algorithm to predict coronary heart disease sufferers. This study obtained the highest accuracy at 10 hidden layers, namely 85.08%.

Sarcopenia-derived exosomal micro-RNA 16-5p exerts the cardio-repair disturbance via pro-apoptotic mechanism in myocardial infarction of mice

Abstract Background Sarcopenia is a pathophysiological malfunction induced by skeletal muscle atrophy, and several studies reported an association between sarcopenia-induced cardiac cachexia and poor prognosis in heart disease. Since only a few established animal models are recently available, the underlying mechanism of disturbed cardiac repair accompanied with sarcopenia remains poorly understood. Purpose We hypothesized that specific microRNAs in sarcopenia-derived exosomes play crucial roles in disturbed cardiac repair with sarcopenia, and these microRNAs directly exacerbate cardiomyocyte injury following cardiac ischemia and reperfusion. Methods We developed a novel sarcopenia-induced cardiac repair disturbance mouse model that is induced by tail suspension (TS) 7 days after a 45-min coronary occlusion of cardiac ischemia and reperfusion (I/R). The reduction of the left ventricular ejection fraction (LVEF) after I/R was compared in mice with TS [I/R-TS(+), n=14] and without [I/R-TS(−), n=12] by echocardiography. To investigate the exosomal mechanism of cardiac repair disturbance, a comprehensive analysis of extracted exosomal microRNAs from mice serum was performed in the 2 groups at day 8. Then, we investigated the impact of the identified candidate microRNA in neonatal rat cardiomyocytes (NRVMs). After 4 days in primary culture, candidate microRNA was transfected into NRVMs under hypoxic culture conditions. TUNEL analysis and quantitative PCR analysis of apoptosis-related genes were performed on the NRVMs. Results At day 8 after I/R, the LVEF of I/R-TS(+) was not significantly ameliorated compared to that of I/R-TS(−) (ΔLVEF; 1.59±6.92 vs. 8.04±7.71% p=0.034). Four candidate microRNAs obtained from I/R mice serum were identified in the microRNA array analysis. The re-analysis of these candidate micro-RNAs using all I/R mice demonstrated that the level of mir-16-5p in I/R-TS(+) was raised by approximately nine-fold than that in I/R-TS(−) (9.67±13.35 vs. 0.99±1.41, p<0.05). Next, an in vitro experimental model using a microRNA mimic revealed that apoptosis in NRVMs was greatly enhanced by the transfection of a mir-16-5p mimic in hypoxic culture conditions (mir-16-5p vs. control = 5.77±2.84 vs. 1.72±0.55%, p<0.01). Furthermore, by qRT-PCR analysis, the expression of CASP3 and TRP53 were upregulated in NRVMs treated with a mir-16-5p mimic than in control NRVMs. Conclusion Myocardial I/R injury in sarcopenia ended in cardiac repair disturbance accompanying with the enhanced expression of exosomal-mir-16-5p. A pro-apoptotic effect of mir-16-5p may exacerbate myocardial I/R injury and thus can be a novel therapeutic target for cardiac repair disturbance in sarcopenia. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): Japan Society for the Promotion of Science

The evaluation of anxiety, depression and Type D personality in a sample of cardiac patients

Many psychological factors influence the onset and prognosis of heart disease, among the most studied, there are personality traits, depressive and anxious experiences. Type D personality, characte...

Elevated homocysteine, as a biomarker of cardiac injury, in panic disorder patients due to oxidative stress.

Background and ObjectivePatients with panic disorder (PD) suffer from elevated oxidative stress as a consequence of serotonin metabolism disorder. These patients have elevated serotonin concentration and catabolism of serotonin via monoamine oxidase. The aim of the present study was to evaluate serum homocysteine concentration and its relationship with oxidative stress level in PD patients, regarding homocysteine as a diagnostic biomarker of heart disease.Materials & MethodSixty patients with PD according to the DSM‐5 diagnostic criteria for a panic attack and 60 healthy individuals were included in the present study.Peripheral venous blood samples were taken from patients. Erythrocytes and serum were separated from blood, and RBC hemolysates were prepared to investigate oxidative stress indices including glutathione and glutathione peroxidase. Serum homocysteine and carbonyl groups concentrations were measured in all samples. Data were analyzed using ANOVA, and p < .05 was considered significant.ResultsResults showed that serum carbonyl groups concentration was significantly higher in patients with PD than in healthy individuals (p < .001). The results also indicated decreased serum glutathione concentration and glutathione peroxidase activity in patients (p < .003). In addition, elevated homocysteine concentration in PD patients serum was observed during the present study (p < .003).ConclusionOur findings support that patients with PD experience higher levels of oxidative stress, due to impaired serotonin metabolism, which is related to the prognosis of heart disease in these patients.

Carbohydrate antigen 125 for mortality risk prediction following acute myocardial infarction

Carbohydrate antigen 125 (CA125) is a congestion and inflammation biomarker and has been proved to be related to a worse prognosis in heart diseases. However, the precise relationship between elevated CA125 in patients with ST-segment elevation myocardial infarction (STEMI) has not yet been sufficiently studied. We set out to determine the association of CA125 with all-cause mortality at 6 months in STEMI. CA125, N-terminal pro brain natriuretic peptide (NTproBNP) and high sensitive C-reactive protein (hs-CRP) were measured in 245 patients admitted consecutively with STEMI undergoing coronary angioplasty. The mean age in our sample was 63.7 years, 64.9% were males, 28.3% had diabetes and 17.7% presented with acute heart failure (Killip ≥ 2). The median serum level of CA125 was 8.1 U/ml. At 6 months, the rate of all-cause mortality was 18% (44 patients). Receiver operating characteristic curve analysis demonstrated that CA125 presented similar performance to predict mortality as NTproBNP and hs-CRP. Patients with CA125 ≥ 11.48 had a higher rate of mortality (Hazard Ratio = 2.07, 95% confidence interval = 1.13–3.77, p = 0.017) than patients with CA125 < 11.48. This study suggests that elevated CA125 levels might be used to identify patients with STEMI with a higher risk of death at 6 months. CA125 seems to be a similar predictor of mortality compared to NTproBNP and hs-CRP.

Different Machine Learning Models Based Heart Disease Prediction

Heart related disease is one of the crucial reasons for high amount of people’s death in the whole countries and it’s considered as life forbidding disorder, in addition to that this effect takes place in whole earth. Heart disease will affect the early stage of age peoples also. Thus, heart related disease creates the more challenges to people living and identify the causes and detection step is more important in nowadays. So, we need to develop of automatic system with more accurate and reliable for early detection of heart disease. For this reason, various machine learning models are developed to predict heart related disease; different medical data package is processed to automatic analysis with get more accuracy. In this paper, we discuss the available machine learning models such as KNN, SVM, DT and RF algorithms for prognosis of heart disease with high certitude, precision and recall.

A comparison of data mining methods for diagnosis and prognosis of heart disease

Heart disease is a term that covers a range of disorders that affect heart. Medical diagnosis is a very important and it is a complicated task that should be performed properly and efficiently. The needs for new tools able to help doctors in predicting and diagnosis heart disease which is highly recognised. In the present study first, the dataset containing total instances of 439 with 14 attributes were obtained from several medical centres in Tehran, Iran. Secondly, five data mining techniques were used: the naïve Bayes, ANN, random forest and C4.5 decision trees and random tree algorithms. From the experimental result it is observed that the Random forest algorithm with (94.53, 0.945, 0.969, 0.945, 0.916) for accuracy, F-measure, specificity, sensitivity and kappa rate produce a higher performance for our classification model when compared with other algorithms.

A comparison of data mining methods for diagnosis and prognosis of heart disease

Heart disease is a term that covers a range of disorders that affect heart. Medical diagnosis is a very important and it is a complicated task that should be performed properly and efficiently. The needs for new tools able to help doctors in predicting and diagnosis heart disease which is highly recognised. In the present study first, the dataset containing total instances of 439 with 14 attributes were obtained from several medical centres in Tehran, Iran. Secondly, five data mining techniques were used: the naive Bayes, ANN, random forest and C4.5 decision trees and random tree algorithms. From the experimental result it is observed that the Random forest algorithm with (94.53, 0.945, 0.969, 0.945, 0.916) for accuracy, F-measure, specificity, sensitivity and kappa rate produce a higher performance for our classification model when compared with other algorithms.

Utilizing IoT wearable medical device for heart disease prediction using higher order Boltzmann model: A classification approach

Globally, the prognosis of heart disease can be improved by early diagnosis and treatment. However, existing automatic systems for diagnosing heart disease are hampered by the requisite big data. This paper introduces an Internet of Things-based medical device for collecting patients’ heart details before and after heart disease. The information, which is continuously transmitted to the health care center, is processed using the higher order Boltzmann deep belief neural network (HOBDBNN). The deep learning method learns heart disease features from past analysis, and achieves efficiency by the effective manipulation of complex data. Following experiments, the performance of the system is evaluated based on characteristics such as f-measure, sensitivity, specificity, loss function, and receiver operating characteristic (ROC) curve. The HOBDBNN method and IoT-based analysis recognize heart disease with 99.03% accuracy with minimum time complexity (8.5 s), effectively minimizing heart disease mortality by reducing the complexity of diagnosing heart disease.

The long-term prognosis of heart diseases for different metabolic phenotypes: a systematic review and meta-analysis of prospective cohort studies.

This meta-analysis aimed to assess the association of different categories of weight and metabolic status with risk of heart diseases including myocardial infarction (MI), cardiovascular diseases (CVDs), and heart failure (HF). Data from relevant studies were identified systematically by searching PubMed and Scopus search engines up to 29 May 2018. Prospective studies were included in the analyses with metabolically healthy normal weight (MHNW) as the reference. Pooled RRs and 95% CI were calculated using random-effects or fixed-effect models when appropriate. Subgroup analysis was applied to define possible sources of heterogeneity. Overall, 21 studies (n = 778,401 participants) were eligible for the present meta-analysis. Generally, the risk of CVDs for all metabolic phenotypes in metabolically unhealthy obese increased compared with the MHNW group. A significant positive association between all metabolic phenotypes and the risk of HF was also observed expect for MHOW (RR = 1.10, 95% CI: 0.60-2.00, P = 0.76) and MHO phenotypes (RR = 0.96, 95% CI: 0.25-3.77, P = 0.95). Moreover, MUHO phenotype was associated with greater risk of MI compared with the MHNW phenotype (RR = 1.82, 95% CI: 1.50-2.22, P < 0.001, respectively). Our findings showed that all metabolically unhealthy phenotypes in different categories of weight were associated with increased incident of CVDs/HF and MI. Furthermore, healthy overweight and obese subjects had increased risk of CVDs.

Analysis Of Single And Hybrid Data Mining Techniques For Prediction Of Heart Disease Using Real Time Dataset

Data mining and healthcare has strong relations as data mining is a process where we can analyze enormous set of data and after extraction meaning of data can be understood. As medical data is in bulk which leads to the need of data analytics tool for extraction of useful information or knowledge .Disease Prediction is one of the applications where many researchers are working so that they can answer whether to apply single or compound data mining technique. Heart related disease is the major cause of deaths in past decades. Use of single technique in treatment of heart disease is showing variable accuracy. Current leading research study is all about to check the effect of compound data mining technique will show enhanced results in the prognosis of heart related disease or not, but the major issue arises of identification a suitable treatment for heart disease patient. This survey paper notify gap in research findings on heart disease prognosis and prescription data and proposes a model which will fill the gap and shows enhanced accuracy.

Copeptin level in the early prediction of cardiorenal syndrome in rats.

Copeptin (CPP) has been considered as a useful marker for prediction of prognosis in heart diseases. However, CPP has not been investigated sufficiently in cardiorenal syndrome (CRS). The present study aimed to investigate the value of CPP level in predicting CRS in rats with partial nephrectomy combined with myocardial infarction (SNX + MI). A total of 60 male Sprague-Dawley rats were used to establish the CRS model by partial nephrectomy combined with MI. The rats were randomly divided into blank control (CK), SNX, MI and CRS groups. Changes in serum and urine CPP concentrations, hemodynamics, blood pressure, and renal function were examined 1-5 weeks after modeling. The predictive values of CPP in the occurrence of CRS in rats were evaluated using receiver operating characteristic (ROC) curve. The results showed that serum CPP in the CRS group in 1-5 weeks and urine CPP in 3 weeks after modeling increased significantly compared with the CK group. Also, serum B-type natriuretic peptide (BNP) in 1 and 3 weeks and urine BNP in 4-5 weeks after modeling increased significantly. No correlation was found between serum or urine CPP, BNP and BUN levels 1 week after modeling in the CRS group. The ROC curve analysis showed that the area under the curve of CRS predicted by serum CPP at 1 week was 0.908 with 56.59 pg/ml as the cutoff point, and its diagnostic sensitivity and specificity were 87.5 and 80.0%, respectively. To conclude, SNX + MI may be used to establish CRS rat model with cardiac and renal damage. Serum CPP may serve as a specific biomarker for the early prediction of CRS.

Mean platelet volume as diagnostic and therapeutic marker of risk and prognosis of heart disease

Increased mean platelet volume (MPV) is associated with platelet reactivity and is a predictor of cardiovascular risk and unprovoked nervous thromboembolism. Mean platelet volume is a precise measure of platelet size. Studies have reported the use of MPV as a biomarker for predicting ischemic stroke in atrial fibrillation patients as well as in anticoagulant prescription and rhythm-control therapy. Moreover, MPV may predict cardiovascular event outcome following percutaneous coronary intervention in patients with coronary artery disease. MPV may predict residual platelet reactivity in dual antiplatelet therapy. Factors influencing MPV result were discussed. This review centered on the reports that MPV may be a biomarker of risk and prognosis of prevalent heart diseases.

Circulating miRNA Expression Profiling and Target Prediction in Patients Receiving Dexmedetomidine

Background/Aims: Circulating miRNAs could serve as biomarkers for diagnosis or prognosis of heart diseases and cerebrovascular diseases. Dexmedetomidine has protective effects in various organs. The effects of dexmedetomidine on circulating miRNAs remain unknown. Here, we investigated differentially expressed miRNA and to predict the target genes of the miRNA in patients receiving dexmedetomidine. Methods: The expression levels of circulating miRNAs of 3 patients were determined through high through-put miRNA sequencing technology. Target genes of the identified differentially expressed miRNAs were predicted using TargetScan 7.1 and miRDB v.5. Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) were used to conduct functional annotation and pathway enrichment analysis of target genes respectively. Results: Twelve differentially expressed miRNAs were identified. Five miRNAs were upregulated (hsa-miR-4508, hsa-miR-novel-chr8_87373, hsa-miR-30a-3p, hsa-miR-novel-chr16_26099, hsa-miR-4306) and seven miRNAs (hsa-miR-744-5p, hsa-miR-320a, hsa-miR-novel-chr9_90035, hsa-miR-101-3p, hsa-miR-150-5p, hsa-miR-342-3p, and hsa-miR-140-3p) were downregulated after administration of dexmedetomidine in the subjects. The target genes and pathways related to the differentially expressed miRNAs were predicted and analyzed. Conclusion: The differentially expressed miRNAs may be involved in the mechanisms of action of dexmedetomidine. Specific miRNAs, such as hsa-miR-101-3p, hsa-miR-150-5p and hsa-miR-140-3p, are new potential targets for further functional studies of dexmedetomidine.

Enfermedad cardiaca inducida por radioterapia

The heart disease induced by cancer treatments, such as chemotherapy and radiotherapy, is increasingly being seen as a prevalent disease, and as such it needs to be taken into account for its appropriate follow-up, prevention and treatment. Previously, this research group published the review, “Chemotherapy-induced cardiotoxicity from the molecular basis to the clinical perspective”, which included a review of the different aspects, including the pathophysiology, treatment, and prognosis of heart disease induced by radiotherapy.

Prognosis of Heart Disease in Obesity – The Obesity Paradox

Prognosis of Heart Disease in Obesity – The Obesity Paradox

Mean platelet volume: a potential biomarker of the risk and prognosis of heart disease.

Platelets are essential for progression of atherosclerotic lesions, plaque destabilization, and thrombosis. They secrete and express many substances that are crucial mediators of coagulation, inflammation, and atherosclerosis. Mean platelet volume (MPV) is a precise measure of platelet size, and is routinely reported during complete blood count analysis. Emerging evidence supports the use of MPV as a biomarker predicting the risk of ischemic stroke in patients with atrial fibrillation, and as a guide for prescription of anticoagulation and rhythm-control therapy. In addition, MPV may predict the clinical outcome of percutaneous coronary intervention (PCI) in patients with coronary artery disease and indicate whether additional adjunctive therapy is needed to improve clinical outcomes. This review focuses on the current evidence that MPV may be a biomarker of the risk and prognosis of common heart diseases, particularly atrial fibrillation and coronary artery disease treated via PCI.

Development of a high sensitivity C-reactive protein immunoassay and comparison with a commercial kit

ABSTRACTC-reactive protein (CRP) is intricately sensitive marker of inflammation, infection, and tissue damage. Role in the prognosis of heart diseases has been recently discovered. This study aimed to develop a cost-effective and high-sensitivity CRP immunoassay for use in cardiac risk assessment. Assay was optimized for coating, blocking of capturing antibody, dilution, and reaction time of the conjugate and sample volume. For normal reference range, CRP was determined in serum samples from apparently healthy volunteers. For clinical validation, CRP was determined in samples of acute coronary syndrome patients by in-house and commercial assays. The lower detection limit of in-house assay was 0.16 µg/L. Intra and inter assay imprecision was 4.39%, 4.6% and 8.6%, 9.3%, respectively. The correlation between the CRP levels by the two assays was r = 0.861. Sensitivity, specificity, predictive value for a positive test, and a negative test of in-house assay was 95.3%, 92.8%, 95.3%, and 92.8%, respectively. At lower-end CRP levels of both kits correlated very well but showed variation at upper end. In-house assay showed high sensitivity and reliability at lower end and it is hoped that will help to evaluate cardiac risk assessment (after improvement at upper end) in clinically poor settings.