BAYESIAN NETWORK AND DEMPSTER-SHAFER THEORY FOR EARLY DIAGNOSIS OF EYE DISEASES

An accurate self-diagnosis expert system would prevent the progression of chronic eye disease. However, developing an expert system for medical diagnose requires a robust reasoning capability. In the knowledge acquisition phase, a knowledge engineer faces several issues. For example, an eye disease...

Full description

Saved in:
Bibliographic Details
Published inCompusoft: an international journal of advanced computer technology Vol. 9; no. 4; pp. 3642 - 3651
Main Authors Kurniawan, Rahmad, Nazri, Mohd Zakree Ahmad, Abdullah, Siti Norul Huda Sheikh, Othman, Zulaiha Ali, Abdullah, Salwani
Format Journal Article
LanguageEnglish
Published Mumbai COMPUSOFT, An International Journal of Advanced Computer Technology 01.04.2020
Subjects
Artificial intelligence
Bayesian analysis
Comparative studies
Decision making
Dempster-Shafer Method
Diagnosis
Diagnostic systems
Expert systems
Experts
Eye diseases
Glaucoma
Knowledge
Knowledge acquisition
Literature reviews
Machine learning
Medical personnel
Neural networks
Patients
Performance evaluation
Reasoning
Reasoning programs
Research methodology
Researchers
Signs and symptoms
Online AccessGet full text

Cover

More Information
Summary:An accurate self-diagnosis expert system would prevent the progression of chronic eye disease. However, developing an expert system for medical diagnose requires a robust reasoning capability. In the knowledge acquisition phase, a knowledge engineer faces several issues. For example, an eye disease may contain several similar symptoms to another eye disease. Even worse, a patient may input a set of symptoms that can be attributable to several diseases, and these symptoms may not be readily quantifiable. Dempster-Shafer Theory (DST) and Bayesian Network (BN) are two commonly used techniques for combining uncertain evidence. The literature review showed that there have been no studies, either using BNs or DST, to diagnose eye diseases with a comparative study about both methods, BNs and DST. This paper study the effectiveness and reliability of DST and BN as the reasoning engine of an expert system for early diagnose of eye disease. The primary sources of knowledge on eye diseases are the patient files and human experts. Data were collected from hospitals and ophthalmologists in Riau, Indonesia. BN and DST framework was used to model and estimate the probability of eye diseases in supporting decision making, i.e. diagnosis. Rule-Based Reasoning and the Forward Chaining methods are applied in developing the reasoning structure. The Expert System Development Life Cycle (ESDLC) methodology is used to structure, plan and control the process of developing the expert system. In this study, 20 physical symptoms of illness obtained from the patients' files are used for diagnosing six types of eye diseases. The result of this study is accomplished by comparing the expert system diagnostic results with a human expert diagnostic result. Based on the testing of 10 eye diseases cases, the accuracy of the BN is higher compared to DST.
ISSN:2320-0790