Thesis Open Access

# An Integration of Prediction Model with the Knowledge Based System for Diagnosis and Treatment of Diabetes: In Case of Debre Berhan Referral Hospital

BELETEW, TILAHUN

### Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:creator>BELETEW, TILAHUN</dc:creator>
<dc:date>2018-06-01</dc:date>
<dc:description>Diabetes is one of the most prevalent non-communicable diseases when raised levels of glucose in the blood because the body cannot produce any or enough of the hormone insulin or use insulin effectively. If the disease is not managed on time, it will born long-term diabetic complications like retinopathy with potential loss of vision, nephropathy leading to renal failure, peripheral neuropathy with risk of foot ulcer, amputations and cardiovascular problem, as well as sexual dysfunction. International Diabetes federation 2017 report Ethiopia is the first ranked with 2.6 million from top 4 African countries for number of people with diabetes. It shows growing of long term complication and cause of death. These problems are lack of awareness, limitation in screening protocols, scarcity of specialist, less propaganda for intervention programs and poor accessibility to health care services. To struggle such problem, this study attempts to design and developed a prototype of an integration of prediction model with the knowledge based system that can provide advice for user to facilitate the diagnosis and treatment of diabetic patients. The knowledge is extracted for developed this knowledge based system using five data mining classification algorithm namely PART, J48, REPTree, Random Tree and Jrip, from Debre Berhan referral hospital diabetes dataset. After compared those algorithm, J48 decision tree Perform 98.84% correct result than the other and got enough rules that can be used for type of diabetes diagnosis. In other way, knowledge extracted from domain experts and document analysis for diabetes treatment. Hence, the prototype of knowledge based system which provides diabetic patient diagnosis and treatment was developed using SWI-Prolog 7.6.4 and Java NetBeans IDE 8.2 with JDK 8 for integrating with graphical user interface respectively. The overall performance achieves 91.9% accuracy with an average system performance. But, further researches should be done to increase the merits of integrating Data mining induced knowledge with knowledge base system.</dc:description>
<dc:relation>isbn:978-963-313-151-0</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:title>An Integration of Prediction Model with the Knowledge Based System for Diagnosis and Treatment of Diabetes: In Case of Debre Berhan Referral Hospital</dc:title>
<dc:type>info:eu-repo/semantics/doctoralThesis</dc:type>
<dc:type>publication-thesis</dc:type>
</oai_dc:dc>

155
71
views