Title | ||
---|---|---|
Knowledge Based Decision Support System for Detecting and Diagnosis of Acute Abdomen Using Hybrid Approach |
Abstract | ||
---|---|---|
Acute abdomen is one of the emergency diseases which is difficult for follow-up treatment. In developing countries, the mortality and morbidity rate are increasing due to misdiagnosis, delay, lack of knowledge and shortage of skilled manpower. These factors affect the quality of health care service in hospitals and reduce the quality of decisions made by physicians. This research attempts to investigate the applicability KBDSS using integration of rule based and case-based reasoning approach so as to improve the quality of decision made by domain experts, to provide effective and efficient services to the patients and to improve shortage of human expert in specific domain area. Domain knowledge is acquired using semi-structured interview technique. Domain experts are selected from Felege hiwot referral hospital in Bahir-Dar. In addition, secondary data is acquired from different sources following DSR methodology. The conceptual model of the knowledge-based system used a decision tree structure which is easy to understand and interpret the procedures involved in patient diagnoses. Based on the conceptual model, the prototype is developed with SWI prolog and java software tools. Beyond the domain expert, the result shows the system has accuracy of 99% for acute abdominal cause classification, and 66% for severity level identification. Whereas, the accuracy value of physicians has 84% for acute abdominal cause classification, and 50% for severity level identification with regard to the final result. Therefore, the KBDSS can diagnose patients with highest accuracy. We were taking the final observed value as pivoting point to test the KBDSS. In the evaluation of the system that classified the stored attribute according to the target problem is 71.33% accuracy. As the result shows, the three reasoning approaches: hybrid, case-based, and rule-based has an accuracy of 87.66%, 70%, and 60% respectively to retrieve target attributes for the target problem. This shows that hybrid reasoning approach is recommended to health care decision support system. Automation of KBDSS has a high contribution to establish truthful decision-making process in patient's acute abdomen treatment. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-26630-1_6 | Communications in Computer and Information Science |
Keywords | Field | DocType |
Prolog,Java,Acute abdomen,KBDSS,Case-based,Rule-based,Hybrid | Health care,Decision tree,Data mining,Rule-based system,Domain knowledge,Conceptual model,Subject-matter expert,Computer science,Decision support system,Operations management,Medical diagnosis | Conference |
Volume | ISSN | Citations |
1026 | 1865-0929 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alemu Workneh | 1 | 0 | 0.34 |
Dereje Teferi | 2 | 0 | 0.68 |
Alemu Kumilachew | 3 | 0 | 0.34 |