METHODS: We first tested ten traditional machine learning algorithms, and then the three-best performing algorithms (three types of SVM) were used in the rest of the study. To improve the performance of these algorithms, a data preprocessing with normalization was carried out. Moreover, a genetic algorithm and particle swarm optimization, coupled with stratified 10-fold cross-validation, were used twice: for optimization of classifier parameters and for parallel selection of features.
RESULTS: The presented approach enhanced the performance of all traditional machine learning algorithms used in this study. We also introduced a new optimization technique called N2Genetic optimizer (a new genetic training). Our experiments demonstrated that N2Genetic-nuSVM provided the accuracy of 93.08% and F1-score of 91.51% when predicting CAD outcomes among the patients included in a well-known Z-Alizadeh Sani dataset. These results are competitive and comparable to the best results in the field.
CONCLUSIONS: We showed that machine-learning techniques optimized by the proposed approach, can lead to highly accurate models intended for both clinical and research use.
MATERIALS AND METHODS: Pro-arrhythmic properties in electrocardiographic and intracellular recordings were compared in young and aged, peroxisome proliferator-activated receptor-γ coactivator-1β knockout (Pgc-1β-/-) and wild type (WT), Langendorff-perfused murine hearts, during regular and programmed stimulation (PES), comparing results by two-way ANOVA.
RESULTS AND DISCUSSION: Young and aged Pgc-1β-/- showed higher frequencies and durations of arrhythmic episodes through wider PES coupling-interval ranges than WT. Both young and old, regularly-paced, Pgc-1β-/- hearts showed slowed maximum action potential (AP) upstrokes, (dV/dt)max (∼157 vs. 120-130 V s-1), prolonged AP latencies (by ∼20%) and shortened refractory periods (∼58 vs. 51 ms) but similar AP durations (∼50 ms at 90% recovery) compared to WT. However, Pgc-1β-/- genotype and age each influenced extrasystolic AP latencies during PES. Young and aged WT ventricles displayed distinct, but Pgc-1β-/- ventricles displayed similar dependences of AP latency upon (dV/dt)max resembling aged WT. They also independently increased myocardial fibrosis. AP wavelengths combining activation and recovery terms paralleled contrasting arrhythmic incidences in Pgc-1β-/- and WT hearts. Mitochondrial dysfunction thus causes pro-arrhythmic Pgc-1β-/- phenotypes by altering AP conduction through reducing (dV/dt)max and causing age-dependent fibrotic change.
OBJECTIVE: The current study aims to elucidate the two-way fluid-structure interaction (FSI) analysis of the blood flow and the effect of stenosis on hemodynamic parameters.
METHODS: A patient-specific 3D model of the left coronary artery was constructed based on computed tomography (CT) images. The blood is assumed to be incompressible, homogenous, and behaves as Non-Newtonian, while the artery is considered as a nonlinear elastic, anisotropic, and incompressible material. Pulsatile flow conditions were applied at the boundary. Two-way coupled FSI modeling approach was used between fluid and solid domain. The hemodynamic parameters such as the pressure, velocity streamline, and wall shear stress were analyzed in the fluid domain and the solid domain deformation.
RESULTS: The simulated results reveal that pressure drop exists in the vicinity of stenosis and a recirculation region after the stenosis. It was noted that stenosis leads to high wall stress. The results also demonstrate an overestimation of wall shear stress and velocity in the rigid wall CFD model compared to the FSI model.
OBJECTIVE: The aim of this study is to analyze the multiphase pulsatile blood flow in the left coronary artery tree with stenosis.
METHODS: The 3D left coronary artery model was reconstructed using 2D computerized tomography (CT) scan images. The Red Blood Cell (RBC) and varying hemodynamic parameters for single and multiphase blood flow conditions were analyzed.
RESULTS: Results asserted that the multiphase blood flow modeling has a maximum velocity of 1.017 m/s and1.339 m/s at the stenosed region during the systolic and diastolic phases respectively. The increase in Wall Shear Stress (WSS) observed at the stenosed region during the diastole phase as compared during the systolic phase. It was also observed that the highest Oscillatory Shear Index (OSI) regions are found in the downstream area of stenosis and across the bifurcations. The increase in RBCs velocity from 0.45 m/s to 0.6 m/s across the stenosis was also noticed.
CONCLUSION: The computational multiphase blood flow analysis improves the understanding and accuracy of the complex flow conditions of blood elements (RBC and Plasma) and provides the progression of the disease development in the coronary arteries. This study helps to enhance the diagnosis of the blocked (stenosed) arteries more precisely compared to the single-phase blood flow modeling.
METHODS: The Casson fluid was used to model the blood that flows under the influences of uniformly distributed magnetic field and oscillating pressure gradient. The governing fractional differential equations were expressed using the Caputo Fabrizio fractional derivative without singular kernel.
RESULTS: The analytical solutions of velocities for non-Newtonian model were then calculated by means of Laplace and finite Hankel transforms. These velocities were then presented graphically. The result shows that the velocity increases with respect to Reynolds number and Casson parameter, while decreases when Hartmann number increases.
CONCLUSIONS: Casson blood was treated as the non-Newtonian fluid. The MHD blood flow was accelerated by pressure gradient. These findings are beneficial for studying atherosclerosis therapy, the diagnosis and therapeutic treatment of some medical problems.