A CASE BASED REASONING SYSTEM FOR DIAGNOSIS OF MALNUTRITION FOR UNDER-FIVE YEAR CHILDREN: THE CASE OF TIRUNESHE BEJING

Abstract

Malnutrition is a broad word that refers to an insufficient intake of nutrients to support healthy growth; it can refer to both under and overnutrition. It's possible that it's one of Ethiopia's leading causes of disease and mortality in children under the age of five. Lack of specialists, practitioners, and health facilities at lower level health institutions in order to detect and treat malnutrition at an early stage are some of the factors that exacerbate the spread of malnutrition in the country. Artificial Intelligence (AI) was used in the study to diagnose malnutrition by using computer tools that mimicked human intelligence. The general objective of this study was to design a case based reasoning system that provides expert advice for diagnosis of malnutrition under five year children. The examples were gathered from Tiruneshe Bejing General Hospital, and design principles were used to create a prototype case-based reasoning system. Domain specialists from Tiruneshe Bejing General Hospital were selected using a purposeful sampling strategy for knowledge acquisition, system testing, and assessment. The researcher utilized the jCOLIBRI version 1.1 implementation tools and the closest neighbor technique to create the prototype system. The produced prototype was put to the test in terms of system performance and user approval. 7 test cases and 6 domain experts were used to put the prototype to the test. The average accuracy and recall values acquired based on evaluating the system's performance were 71 percent and 83 percent, respectively. Domain specialists were also included in user acceptability testing, which resulted in an average of 83 percent approval. The CBR system's performance might be improved by adding more cases. This investigation yielded a positive outcome that satisfied the study's aims.