A hybrid approach to medical decision-making: diagnosis of heart disease with machine-learning model

Heart disease is one of the most widely spreading and deadliest diseases across the world. In this study, we have proposed hybrid model for heart disease prediction by employing random forest and support vector machine. With random forest, iterative feature elimination is carried out to select heart disease features that improves predictive outcome of support vector machine for heart disease prediction. Experiment is conducted on the proposed model using test set and the experimental result evidently appears to prove that the performance of the proposed hybrid model is better as compared to an individual random forest and support vector machine. Overall, we have developed more accurate and computationally efficient model for heart disease prediction with accuracy of 98.3%. Moreover, experiment is conducted to analyze the effect of regularization parameter (C) and gamma on the performance of support vector machine. The experimental result evidently reveals that support vector machine is very sensitive to C and gamma.

Hyperhomocysteinemia as an Independent Risk Factor for Coronary Heart Disease. Comparison with Conventional Risk Factors

The present study was designed to evaluate the strength of association of raised plasma homocysteine concentration as a risk factor for coronary heart disease independent of conventional risk factor. It was a case control study conducted at Punjab Institute of Cardiology Lahore. A total of 210 subjects aged 25 to 60 years comprising of 105 newly admitted patients of CHD as cases and 105 age and sex matched healthy individuals with no history of CHD as control were recruited for the study. Fasting blood samples were obtained from cases and controls. Plasma homocysteine was analyzed by fluorescence polarization immunoassay (FPIA) method on automated immunoassay analyzer (Abbott IMX). Total cholesterol, triglyceride and HDL cholesterol were analyzed using calorimetric kit methods. The concentration of LDL cholesterol was calculated using Friedewald formula. The patients were also assessed for traditional risk factors such as age, sex, family history of CVD, hypertension, smoking and physical activity, and were compared with control subjects. The collected data was entered in SPSS version 24 for analysis and interpretation.The mean age in controls and experimental groups were 43.00± 8.42 years and 44.72± 8.59 years with statistically same distribution (p- value= 0.144). The mean plasma homocysteine for cases was 22.33± 9.22 µmol/L where as it was 12.59±3.73 µmol/L in control group. Highly significant difference was seen between the mean plasma level of homocysteine in cases and controls (p˂0.001).Simple logistic regression indicates a strong association of coronary heart disease with hyperhomocysteinemia (OR 7.45), which remained significantly associated with coronary heart disease by multivariate logistic regression (OR 7.10, 95%C1 3.12-12.83, p=0.000). The present study concludes that elevated levels of Plasma homocysteine is an independent risk factor for coronary heart disease independent of conventional risk factors and can be used as an indicator for predicting the future possibility for the onset of CVD.