Journal
IEEE ACCESS
Volume 8, Issue -, Pages 189503-189512Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.3026214
Keywords
Heart; Diseases; Machine learning; Medical diagnostic imaging; Convolutional neural networks; Heart disease prediction; convolutional neural network; deep learning
Categories
Funding
- Subject on Cadre Health Care of Sichuan Province Study on Reperfusion Strategy Without the Stent Implantation in Elderly Patients with segment elevation myocardial infarction (STEMI) [CGY2019-216]
Ask authors/readers for more resources
The diagnosis of heart disease has become a difficult medical task in the present medical research. This diagnosis depends on the detailed and precise analysis of the patients clinical test data on an individuals health history. The enormous developments in the field of deep learning seek to create intelligent automated systems that help doctors both to predict and to determine the disease with the internet of things (IoT) assistance. Therefore, the Enhanced Deep learning assisted Convolutional Neural Network (EDCNN) has been proposed to assist and improve patient prognostics of heart disease. The EDCNN model is focused on a deeper architecture which covers multi-layer perceptrons model with regularization learning approaches. Furthermore, the system performance is validated with full features and minimized features. Hence, the reduction in the features affects the efficiency of classifiers in terms of processing time, and accuracy has been mathematically analyzed with test results. The EDCNN system has been implemented on the Internet of Medical Things Platform (IoMT) for decision support systems which helps doctors to effectively diagnose heart patients information in cloud platforms anywhere in the world. The test results show compared to conventional approaches such as Artificial Neural Network (ANN), Deep Neural Network (DNN), Ensemble Deep Learning-based smart healthcare system (EDL-SHS), Recurrent neural network (RNN), Neural network ensemble method (NNE), based on the analysis the designed diagnostic system can efficiently determine the risk level of heart disease effectively. Test results show that a flexible design and subsequent tuning of EDCNN hyperparameters can achieve a precision of up to 99.1%;.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available