Ensemble Models for Classification of Coronary Artery Disease using Decision Trees

The foundation of data mining techniques using decision tree methods played a crucial role in the identification and classification of diseases. In the utilization of decision tree classifiers to develop the robust classifier for classification of Coronary Artery Disease data set namely Z-Alizadeh Sani and extension Z-Alizadeh Sani. We have used three decision tree techniques Random Forest (RF), Classification and Regression Tree (CART), J48 (C4.5) and made two ensemble models. These ensemble models have different combining rules like voting and stacking. The Voting Scheme model Vote (J48, RF, CART) and stacking Scheme model Stack (J48, RF, CART) have our proposed model. The findings are compared in individual and ensemble models classifier with 5-Fold Cross-Validation and 10-Fold Cross-Validation. The finding of the proposed ensemble models can be used in the detection and evaluation of Coronary Artery Disease (CAD).

Download Full-text

Coronary Artery Disease Prediction Using Decision Trees and Multinomial Naïve Bayes with k-Fold Cross Validation

Jurnal Inovasi Matematika ◽

10.35438/inomatika.v3i2.266 ◽

2021 ◽

Vol 3 (2) ◽

pp. 174-189

Author(s):

Endang S Kresnawati ◽

Yulia Resti ◽

Bambang Suprihatin ◽

M. Rendy Kurniawan ◽

Widya Ayu Amanda

Keyword(s):

Coronary Artery Disease ◽

Coronary Artery ◽

Decision Trees ◽

Statistical Learning ◽

Cross Validation ◽

Naive Bayes ◽

Naïve Bayes ◽

Disease Prediction ◽

Artery Disease ◽

Fold Cross Validation

Penyakit arteri koroner (coronary artery disease) menjadi penyebab utama kematian penduduk di dunia setidaknya selama dua dekade (2000-2019) dan mengalami peningkatan kematian terbesar dalam rentang waktu tersebut dibandingkan dengan penyebab kematian lainnya. Keberhasilan memprediksi penyakit arteri koroner secara dini berdasarkan data medis bermanfaat bagi pasien dan juga bagi kestabilan perekonomian negara. Tujuan penelitian ini adalah memprediksi penyakit arteri koroner jantung dengan mengimplementasikan dua metode statistical learning yaitu Multinomial Naïve Bayes dan pohon keputusan dengan validasi silang 10-fold, dimana variabel-variabel numerik didiskritisasi untuk memperoleh variabel-variabel kategorik. Hasil penelitian menunjukkan bahwa metode Pohon Keputusan memiliki kinerja yang lebih baik dibandingkan metode Multinomial Naïve Bayes dalam memprediksi penyakit arteri koroner. Ukuran kinerja metode Pohon Keputusan memperoleh tingkat akurasi 99,63 %, sensitivitas 100 %, spesifisitas 99,33%, presisi 99,23 %, dan nilai prediksi negatif (NPV) 100 %. Ukuran-ukuran ini mengindikasikan bahwa metode Pohon Keputusan layak digunakan untuk memprediksi penyakit arteri coroner, termasuk data independent berupa data penyakit arteri coroner lainnya dengan variable predictor yang sama. Hasil penelitian ini juga menunjukkan bahwa perbedaan rujukan dengan penelitian-penelitian sebelumnya dalam mendiskritisasi variabel numerik mampu meningkatkan kinerja metode dalam memprediksi penyakit arteri coroner.

Download Full-text

Identification of Coronary Artery Disease using Artificial Neural Network and Case Based Reasoning

Recent Advances in Computer Science and Communications ◽

10.2174/2666255813999200613225404 ◽

2020 ◽

Vol 13 ◽

Author(s):

Varun Sapra ◽

M.L Saini ◽

Luxmi Verma

Keyword(s):

Neural Network ◽

Coronary Artery Disease ◽

Coronary Artery ◽

Early Stage ◽

Second Phase ◽

Case Based Reasoning ◽

Data Set ◽

Artery Disease ◽

Severity Of The Disease ◽

Case Based

Background: Cardiovascular diseases are increasing at an alarming rate with very high rate of mortality. Coronary artery disease is one of the type of cardiovascular disease, which is not easily diagnosed in its early stage. Prevention of Coronary Artery Disease is possible only if it is diagnosed, at early stage and proper medication is done. Objective: An effective diagnosis model is important not only for the early diagnosis but also to check the severity of the disease. Method: In this paper, a hybrid approach is followed, with the integration of deep learning (multi-layer perceptron) with Case based reasoning to design analytical framework. This paper suggests two phases of the study, one in which the patient is diagnosed for Coronary artery disease and in second phase, if the patient is suffering from the disease then employing Case based reasoning to diagnose the severity of the disease. In the first phase, multilayer perceptron is implemented on reduced dataset and with time-based learning for stochastic gradient descent respectively. Results: The classification accuracy is increase by 4.18 % with reduced data set using deep neural network with time based learning. In second phase, if the patient is diagnosed as positive for Coronary artery disease, then it triggers the Case based reasoning system to retrieve from the case base, the most similar case to predict the severity for that patient. The CBR model achieved 97.3% accuracy. Conclusion: The model can be very useful for medical practitioners as a supporting decision system and thus can save the patients from unnecessary medical expenses on costly tests and can improve the quality and effectiveness of medical treatment.

Download Full-text

Classification of Coronary Artery Disease Using Deep Neural Network with Dimension Reduction Technique

2021 2nd International Conference for Emerging Technology (INCET) ◽

10.1109/incet51464.2021.9456322 ◽

2021 ◽

Author(s):

Pratibha Verma ◽

Vineet Kumar Awasthi ◽

Sanat Kumar Sahu

Keyword(s):

Neural Network ◽

Coronary Artery Disease ◽

Coronary Artery ◽

Dimension Reduction ◽

Deep Neural Network ◽

Reduction Technique ◽

Artery Disease

Download Full-text

Discordance between Body-Mass Index and Body Adiposity Index in the Classification of Weight Status of Elderly Patients with Stable Coronary Artery Disease

Journal of Clinical Medicine ◽

10.3390/jcm10050943 ◽

2021 ◽

Vol 10 (5) ◽

pp. 943

Author(s):

Bartosz Hudzik ◽

Justyna Nowak ◽

Janusz Szkodzinski ◽

Aleksander Danikiewicz ◽

Ilona Korzonek-Szlacheta ◽

...

Keyword(s):

Coronary Artery Disease ◽

Body Mass Index ◽

Coronary Artery ◽

Weight Status ◽

Stable Coronary Artery Disease ◽

Reference Method ◽

Normal Weight ◽

Body Adiposity ◽

Artery Disease

Background and Aims: Body-mass index (BMI) is a popular method implemented to define weight status. However, describing obesity by BMI may result in inaccurate assessment of adiposity. The Body Adiposity Index (BAI) is intended to be a directly validated method of estimating body fat percentage. We set out to compare body weight status assessment by BMI and BAI in a cohort of elderly patients with stable coronary artery disease (CAD). Methods: A total of 169 patients with stable CAD were enrolled in an out-patient cardiology clinic. The National Research Council (US) Committee on Diet and Health classification was used for individuals older than 65 years as underweight BMI < 24 kg/m2, normal weight BMI 24–29 kg/m2, overweight BMI 29–35 kg/m2, and obesity BMI > 35 kg/m2. In case of BAI, we used sex- and age-specific classification of weight status. In addition, body fat was estimated by bioelectrical impedance analysis (BImpA). Results: Only 72 out of 169 patients (42.6%) had concordant classification of weight status by both BMI and BAI. The majority of the patients had their weight status either underestimated or overestimated. There were strong positive correlations between BMI and BImpA (FAT%) (R = 0.78 p < 0.001); BAI and BImpA (FAT%) (R = 0.79 p < 0.001); and BMI and BAI (R = 0.67 p < 0.001). BMI tended to overestimate the rate of underweight, normal weight or overweight, meanwhile underestimating the rate of obesity. Third, BMI exhibited an average positive bias of 14.4% compared to the reference method (BImpA), whereas BAI exhibited an average negative bias of −8.3% compared to the reference method (BImpA). Multivariate logistic regression identified independent predictors of discordance in assessing weight status by BMI and BAI: BImpA (FAT%) odds ratio (OR) 1.29, total body water (%) OR 1.61, fat mass index OR 2.62, and Controlling Nutritional Status (CONUT) score OR 1.25. Conclusions: There is substantial rate of misclassification of weight status between BMI and BAI. These findings have significant implications for clinical practice as the boundary between health and disease in malnutrition is crucial to accurately define criteria for intervention. Perhaps BMI cut-offs for classifying weight status in the elderly should be revisited.

Download Full-text

Expert system based detection and classification of coronary artery disease using ranking methods and nonlinear attributes

Multimedia Tools and Applications ◽

10.1007/s11042-021-11528-1 ◽

2022 ◽

Author(s):

Ram Sewak Singh ◽

Demissie Jobir Gelmecha ◽

D. K. Sinha

Keyword(s):

Coronary Artery Disease ◽

Coronary Artery ◽

Expert System ◽

Ranking Methods ◽

Artery Disease

Download Full-text

Classification of Coronary Artery Disease Using Multilayer Perceptron Neural Network

International Journal of Applied Evolutionary Computation ◽

10.4018/ijaec.2021070103 ◽

2021 ◽

Vol 12 (3) ◽

pp. 35-43

Author(s):

Pratibha Verma ◽

Vineet Kumar Awasthi ◽

Sanat Kumar Sahu

Keyword(s):

Neural Network ◽

Coronary Artery Disease ◽

Artificial Neural Network ◽

Coronary Artery ◽

Multilayer Perceptron ◽

Artificial Neural ◽

Artery Disease ◽

Artificial Neural Network Ann ◽

Hidden Layer

Coronary artery disease (CAD) has been the leading cause of death worldwide over the past 10 years. Researchers have been using several data mining techniques to help healthcare professionals diagnose heart disease. The neural network (NN) can provide an excellent solution to identify and classify different diseases. The artificial neural network (ANN) methods play an essential role in recognizes diseases in the CAD. The authors proposed multilayer perceptron neural network (MLPNN) among one hidden layer neuron (MLP) and four hidden layers neurons (P-MLP)-based highly accurate artificial neural network (ANN) method for the classification of the CAD dataset. Therefore, the ten-fold cross-validation (T-FCV) method, P-MLP algorithms, and base classifiers of MLP were employed. The P-MLP algorithm yielded very high accuracy (86.47% in CAD-56 and 98.35% in CAD-59 datasets) and F1-Score (90.36% in CAD-56 and 98.83% in CAD-59 datasets) rates, which have not been reported simultaneously in the MLP.

Download Full-text

Ischaemic heart disease in women

ESC CardioMed ◽

10.1093/med/9780198784906.003.0679 ◽

2018 ◽

pp. 2836-2840

Author(s):

Martha Gulati

Keyword(s):

Myocardial Infarction ◽

Coronary Artery Disease ◽

Heart Disease ◽

Coronary Artery ◽

Ischaemic Heart Disease ◽

Obstructive Coronary Artery Disease ◽

Diagnostic Testing ◽

Atypical Presentation ◽

Artery Disease

The more atypical presentation of women makes the diagnostic evaluation of symptomatic women challenging and results in more frequent referral for diagnostic testing to improve the precision of the ischaemic heart disease likelihood estimate. The classification of ischaemic heart disease and myocardial infarction has moved beyond the diagnosis of obstructive coronary artery disease and encompasses ischaemia that can occur in the presence and absence of obstructive coronary artery disease. Consideration of the different pathophysiology of ischaemia that may occur in women needs to be considered in the evaluation and treatment of ischaemic heart disease in women.

Download Full-text

Classification of Brain Tumors from MRI Images Using a Convolutional Neural Network

Applied Sciences ◽

10.3390/app10061999 ◽

2020 ◽

Vol 10 (6) ◽

pp. 1999 ◽

Cited By ~ 7

Author(s):

Milica M. Badža ◽

Marko Č. Barjaktarović

Keyword(s):

Neural Network ◽

Machine Learning ◽

Brain Tumors ◽

Convolutional Neural Network ◽

Cross Validation ◽

Magnetic Resonance Images ◽

Generalization Capability ◽

Data Set ◽

Fold Cross Validation

The classification of brain tumors is performed by biopsy, which is not usually conducted before definitive brain surgery. The improvement of technology and machine learning can help radiologists in tumor diagnostics without invasive measures. A machine-learning algorithm that has achieved substantial results in image segmentation and classification is the convolutional neural network (CNN). We present a new CNN architecture for brain tumor classification of three tumor types. The developed network is simpler than already-existing pre-trained networks, and it was tested on T1-weighted contrast-enhanced magnetic resonance images. The performance of the network was evaluated using four approaches: combinations of two 10-fold cross-validation methods and two databases. The generalization capability of the network was tested with one of the 10-fold methods, subject-wise cross-validation, and the improvement was tested by using an augmented image database. The best result for the 10-fold cross-validation method was obtained for the record-wise cross-validation for the augmented data set, and, in that case, the accuracy was 96.56%. With good generalization capability and good execution speed, the new developed CNN architecture could be used as an effective decision-support tool for radiologists in medical diagnostics.

Download Full-text