Applying Advanced NN-based Decision Support Scheme for Heart Diseases Diagnosis

Abstract

Heart diagnosis equipment is not always available in every medical center, especially in the rural areas where less support and care. Physician intuition and experience are not always enough to attain high quality medical results. Therefore, medical errors and unwanted results are reasons for a need for unconventional computer-based diagnosis systems, which in turns reduce medical fatal errors, increasing the patient safety and save lives. The proposed system, which is based on Artificial Neural Networks (ANNs), provides a decision support system to classify the heart diseases: mitral stenosis, aortic stenosis and ventricular septal defect. Additionally, the system offers a promising opportunity to develop an operational screening and testing device for heart disease diagnosis and can provide great assistance for clinicians to make advanced heart sound diagnosis, especially in rural areas where high tech devices may not be available. Series of experiments have been conducted, using real medical data, to test the performance and accuracy of the proposed system. Compared results revealed that the system performance and accuracy are excellent, with a heart diseases classification accuracy of 92%.

Heart Disease Binary and Multiclass Classification Using Deep Learning Hybridized with Ensemble Learner

“…Imaging solutions and Chatbots for diagnosing disease can both benefit from DLT's ability to recognise patterns. Cardiology, pulmonology, electroencephalography, genetics, pathology, ophthalmology, clinical chemistry, and gynaecology are only some of the medical specialties that make use of artificial neural networks (ANN) [17]. Important efforts are also being put into studying heart diagnostics.…”

Non-Invasive Nocturnal Hypoglycemia Detection for Insulin-Dependent Diabetes Mellitus Using Genetic Fuzzy Logic Method

“…To develop classi¯cation models for medical diagnosis, advanced computational intelligence techniques 10,11 such as fuzzy inference system (FIS), 12 support vector machine (SVM), 13 neural networks (NNs), 14,15 adaptive-network-based fuzzy inference system, 16,17 and recurrent fuzzy neural network 18 have been successfully applied to cardiovascular response, 19,20 breast cancer 21 and blood cell detection, 22 skull and brain, 23,24 dermatologic disease, 25 heart disease diagnosis, 26,27 radiation therapy, 28 lung sound, 29 polysomnographic signal classi¯cation 12 and tumor tracking problem. 30 Each technology has its own advantages, for example, fuzzy system is famous because of its expert knowledge in representing linguistic rules.…”