Prototype Knowledge Based System for Anxiety Mental Disorder Diagnosis
No Thumbnail Available
Date
2011-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Mental health is the basic building block for the entire healthy life of a person. There
is a motto which explains the significance of mental health as “Without mental health
no health!” Mental health problems touch every aspects of human life such as
humans’ general health condition, work, family life, social relations, etc.
However, mental health issue is one of the neglected issues throughout the world.
Particularly, in developing countries, mental health has the least attention it deserves.
Ethiopia is one of the developing countries. In Ethiopia, mental health issue is not
getting sufficient attentions. The major challenge for mental health service in the
country is shortage of skilled mental health professionals. In Ethiopia, the number of
mental disorder patients and mental health professionals are disproportionate too. Due
to this the distribution of mental health professionals is greatly unfair. Lacks of
knowledge among primary health care workers, the allocation of insufficient budgets
for mental health issue, and the absence of adequate awareness about mental illnesses
are the other challenges that are creating obstacles to address mental health services
satisfactorily.
In an attempt to address such problems, the objective of this research work is to look
into the possibility of applying knowledge based systems technology to diagnose
patients with anxiety mental disorders by developing prototype knowledge based
system that can mimic /simulate the services of psychiatrists and psychologists.
To achieve this objective, knowledge is acquired using both structured and
unstructured extensive interviews with three experts, which are selected purposively
from Amanuel Mental Specialized Hospital and Rank Higher Clinic. Additionally,
knowledge is acquired from secondary sources by using document analysis method of
knowledge elicitation.
The knowledge acquired is modelled using decision tree structure that represents
concepts, parameters and procedures involved in anxiety disorders diagnoses. Based
on the model, the prototype is developed with SWI Prolog by using ‘if – then’ rules.
The prototype developed uses backward chaining to infer the rules and extract
conclusions and recommendations.
XI
Domain experts evaluate the prototype and satisfactory result is found; about 86% of
system evaluators accept the prototype. Additionally, the performance of the system is
evaluated by using predictive validation technique with twenty test cases. The result
of the validation revealed the accuracy of the prototype to be 85%.
The prototype knowledge based system needs further studies to expand its scope and
to enhance the performance of it by integrating with other knowledge representation
techniques.
Description
Keywords
Knowledge Based System