Claim Missing Document
Check
Articles

Found 2 Documents
Search

Study of Machine Learning Algorithm on Phonocardiogram Signals for Detecting of Coronary Artery Disease Satria Mandala; Miftah Pramudyo; Ardian Rizal; Maurice Fikry
Indonesia Journal on Computing (Indo-JC) Vol. 5 No. 3 (2020): December, 2020
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2020.5.3.536

Abstract

Several methods of detecting coronary artery disease (CAD) have been developed, but they are expensive and generally use an invasive catheterization method. This research provides a solution to this problem by developing an inexpensive and non-invasive digital stethoscope for detecting CAD. To prove the effectiveness of this device, twenty-one subjects consisting of 11 CAD patients and 10 healthy people from Hasan Sadikin Hospital Bandung were selected as validation test participants. In addition, auscultation was carried out at four different locations around their chests, such as the aorta, pulmonary, tricuspid, and mitral. Then the phonocardiogram data taken from the stethoscope were analyzed using machine learning. To obtain optimal detection accuracy, several types of kernels such as radial basis function kernel (RBF), polynomial kernel and linear kernel of Support Vector Machine (SVM) have been analyzed. The experimental results show that the linear kernel outperforms compared to others; it provides a detection accuracy around 66%. Followed by RBF is 56% and Polynomial is 46%. In addition, the observation of phonocardiogram signals around the aorta is highly correlated with CAD, giving an average detection accuracy for the kernel of 66%; followed by 44% tricuspid and 43% pulmonary.
Predictors of Appropriate Shocks and Ventricular Arrhythmia in Indonesian with Brugada Syndrome Ardian Rizal; Sunu Budhi Raharjo; Dicky Armein Hanafy; Yoga Yuniadi
Jurnal Kardiologi Indonesia Vol 40 No 2 (2019): Indonesian Journal of Cardiology: April-June 2019
Publisher : The Indonesian Heart Association

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30701/ijc.v40i2.767

Abstract

Background : Brugada syndrome is an inherited disease characterized by an increased risk of sudden cardiac death owing to ventricular arrhythmias in the absence of structural heart disease. It has been reported that this syndrome is more prevalent in South-East Asia than in Western countries. Furthermore, genetic studies showed important contributions of several gene mutations to the phenotype of BrS. These suggest that ethnic difference play significant roles in the pathogenesis of BrS. In addition, ICD implantation remains the cornerstone management with a low rate of appropriate shocked. Therefore, it is important to investigate patients’ characteristics for risk stratification. Our objective to investigate the clinical, electrocardiography (ECG) and electrophysiological characteristics that can be used as predictor of appropriate shock due to ventricular arrhythmia (VA) in Indonesian patients with BrS. Methods : We analyse data from Brugada syndrome registry at National Cardiovascular Centre Harapan Kita since January 2013. Total 22 patients were included. Characteristics of BrS that we analysed were baseline characteristics (age and sex), Clinical finding (syncope, cardiac arrest), ECG finding (spontaneous type 1 or drug induced) and Electrophysiology study result (inducible VA and RV ERP). We also added some new ECG characteristic (S wave in lead 1, S wave duration in V1, Fragmented QRS, Junction ST elevation and early repolarization pattern in infero-lateral) to be analysed. Our end point are appropriate shock during ICD interrogation for those who have been implanted an ICD, and documented VA for those who didn’t receive ICD. Result : We found high incidence of appropriate ICD’s shock in our population (50% in our study vs 5-11.5% in real world). Predictors of appropriate shock and documented VA are history of syncope (p = 0.045; OR 2.57 [1.44-4.59]), spontaneous type-1 ECG (p = 0.005) and right ventricular effective refractory period (RV ERP) of <200 ms (p=0.018). Other parameters that have been reported to correlate with the occurrence of VA (S Wave in lead 1 (p = 0.530), early repolarization pattern (p = 0.578), fragmented QRS (p = 0.601), S Wave duration (p = 0.365) and J Point STE (p = 0.800) were found to be not correlated to appropriate shock in our populations. Conclusion : History of syncope, spontaneous type-1 Brugada ECG and RV ERP of <200 ms have predictive values for risk stratification of Indonesian patients with Brugada syndrome. Keywords : Brugada Syndrome, Ventricular arrhythmia, ICD shock