A Mobile Phone-Based Expert System for Disease Diagnosis - E-Healthcare Systems and Wireless Communications - page 228

ease diagnosis. The system is based on Bayesian
classifiers. Mu-Jung and Mu-Yen (2007) proposed
a framework for intelligent disease diagnosis sys-
tem named CMDS - Chinese Medical Diagnostic
System. Medical ontology was integrated for the
system development, and the methodologies of
its implementation for digestive health. CMDS
uses web interface and expert system technology
to act as human expertise and diagnose a number
of digestive system diseases. CMDS provides a
truly precise analysis for digestive system disease
and the prototype system can diagnose up to 50
types of diseases. The satisfactory performance
of the system has proven that it could act as a
consultant. Al-Ahmar (2009) investigated the
potential of object-oriented model for expert sys-
tem and developed an object-oriented prototype
expert system for diagnosis of fungal diseases of
date palm. Fahad et al. (2008) presented a web-
based expert system for wheat crop in Pakistan.
The expert system covers two main classes of
problems namely, diseases and pests, normally
encountered in wheat crop.
Although automated disease diagnosis systems
have been developed, they are either web-based or
standalone applications which puts the computer
illiterates and those who lack access to computers
due to economic reasons at a disadvantage. This
work, however, presents a mobile phone-based
disease diagnosis system to cater for the needs
of these categories of people.

IDE 6.5. Jess (Java Expert System Shell), which
is a robust inference engine for developing expert
systems for the Java platform, was used to carry
out the diagnosis.

MOBILE PHONE-BASED DISEASE
DIAGNOSIS SYSTEM (MPDDS)

The MPDDS prototype diagnoses some kinds of
fever common in the sub-Saharan Africa: Malaria
fever, Typhoid fever, Yellow fever, etc. The user
can specify his symptoms by checking the check
boxes against the symptoms noticed. After that,
the screen for the choice of the severity of the
symptoms is displayed for the user to either select
if the symptoms are severe or mild. Once this is
done, the symptoms are sent into the working
memory of Jess where the inference engine uses
forward chaining to determine the nature of the
ailment. The diagnosed disease is then stored in
the working memory from where it is extracted
and sent back to the user. Jess provides a property
called salience which is a kind of rule priority.
Activated rules of the highest salience will fire
first, followed by rules of lower salience. Declaring
a low salience value for a rule makes it fire after
all other rules of higher salience. A high value
makes a rule fire before all rules of lower salience.
The default salience value is zero. The order in
which multiple rules of the same salience are fired
is determined by the active conflict resolution
strategy. Jess comes with two strategies: “depth”
and “breadth.” In the “depth” strategy, the most
recently activated rules will fire before others
of the same salience. In the “breadth” strategy,
rules fire in the order in which they are activated
(“Ernest”, 2008). Figure 4 shows a screenshot
of the list of the symptoms. Figure 5 shows the
screenshot for the selection of the severity of the
symptoms, while Figure 6 is a screenshot of the
diagnosed disease.

METHODOLOGY

In carrying out this work, physicians were inter-
viewed as to the nature of the symptoms of the
diseases diagnosed by the system and the reasoning
process normally applied in their diagnosis. All
these were coded into machine implementable
format. J2ME (Java 2, Micro Edition) was used
for developing the application using NetBeans