An Expert System for the Diagnosis and Treatment of Ischaemic Heart Disease: Cardexp

Kékes, Ede; Kakas, M.; Aszalos, J.; Préda, István; Barcsák, J; Kovács, Julia; Antalóczy, Z

doi:10.1007/978-1-4613-1025-9_41

Cited by 2 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many works (such as [2][3][4][5][6]) have already been carried out on the development of expert systems for IHD diagnosis and treatement with the use of intelligent systems such as fuzzy logic, genetic algorithm and artificial neural network. The existing expert systems using conventional neural network face problem with accuracy.…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network for Heart Disease Medical Prescription Expert System

Omer¹,

Sheta

Adrees

et al. 2018

IJEEI

View full text Add to dashboard Cite

One of the most common causes of death is Ischaemic heart disease (IHD). Clinical decisions are often made based on doctors' intuition and experience rather than on the knowledge-rich data hidden in the database, which leads to unwanted errors and excessive medical costs that affects the quality of service provided to patients. On the other hand, there is lack of cardiologist and IHD specialist in developing countries. Therefore, the development of an expert system that improves the diagnostic and therapeutic decision model of IHD creates a universal need. The expert system is developed based on the cardiologist expertises in diagnosing IHD symtomps and the given prescriptions. This work attempts to increase the accuracy and the effectiveness of the expert system to treat IHD patient by leveraging deep neural networks and adopting deep learning strategy for Retristic Boltzman Machine (RBM). The deep neural network in this work has 152 neurons in the input layer, 52 neurons in the output layer, and 4 hidden layer. Experimental results show that the proposed system achieves up to 0.00974 error level in the training sessions and average improvement of 0.7322% in term of accuracy compared to expert system with standard machine learning in the testing phase. Some results that have discrepancies are consulted to the cardiologist to confirm the results.

show abstract

Section: Introductionmentioning

confidence: 99%