A Symptom Distribution Method in Global Knowledge to Medical

Expert System

Widyastuti Andriyani

, Samekto Wibowo

, Laurentinus Sandhi Prasetya

and Istianto Kuntjoro

Master of Information Technology, STMIK AKAKOM, Jl. Raya Majapahit No. 143 Karangjambe, Yogyakarta, Indonesia

Department of Neuroscience, Universitas Gadjah Mada, Yogyakarta, Indonesia

Department of Anesthesiology, Panti Rapih Hospital, Yogyakarta, Indonesia

Fakulty of Medicine, Universitas Kristen Duta Wacana, Yogyakarta, Indonesia

Keywords:

Emergency unit, medical records, knowledge base, global knowledge, specialist doctors.

Abstract:

Changes to services in the medical ﬁeld will follow the changing of era, no longer relying on a single expert but

can adapt to multiple experts, by offering convenience to help emergency room doctors and specialist doctors.

The technology that will be discussed in this research is building a framework of knowledge of large-scale

medical experts. Knowledge is obtained by relying on medical record data as the results of that knowledge

that are used to distribute the symptoms according to specialist units in the hospital. Therefore, doctors who

are in the emergency unit can do ﬁrst aid to patients as well as to get the appropriate specialist information

based on a knowledge-based system with the patient’s condition, so that the work of the emergency room

doctor and specialist doctors can utilize the knowledge-based system in conducting care in patients and can

save observation time in examining other patients.

1 INTRODUCTION

In today’s digital era, a lot of research has been done

to develop a system towards digitalization. One part

of computer science that can help make work eas-

ier is artiﬁcial intelligence (AI) (Dzierzanowski et al.,

1985). An expert system is a part of AI that is built

based on expert knowledge and information from

books (Gorzalczany and McLeish, 1992). In its ap-

plication, expert systems are often used to diagnose

problems that occur in the community. One of the

development of expert systems is to help in the med-

ical ﬁeld (Dzierzanowski et al., 1985). During its

development, many systems were built using AI to

improve medical services (Krantz et al., 1988) and

(Cota et al., 2017), decision support (Razzouk et al.,

2006) – and (Navarra, 2016), to assist in diagnos-

ing diseases (Dzierzanowski et al., 1985), (Adlassnig

and Scheithauer, 1989), (Malmir et al., 2017). The

software that was successful in applying AI into the

medical ﬁeld to diagnose diseases in the 20th cen-

tury included MYCIN, SPHINX, LOCALIZE (Brazis

et al., 2012), PUFF, INTERNIST, and GAITSPERT

(Dzierzanowski et al., 1985), (Chorbev et al., 2009).

AI which is a ﬁeld of science has many branches that

can be applied in the medical ﬁeld. This can be seen

in the success of various software that uses differ-

ent methods(Dzierzanowski et al., 1985). MYCIN

has succeeded in becoming a system based on ex-

pert systems that is able to help medical staff provide

clinical consultations (Van Remoortere, 1979), (Li,

2010), SPHINX uses inference and pattern recogni-

tion methods capable of providing consultations re-

lated to jaundice (Sampat et al., 2005), to the IN-

TERNIST which is able to provide diagnoses in vari-

ous diseases (Miller et al., 1982).

In developing AI for medical purepose it is insep-

arable from the role of medical personnel and doc-

tors directly. The combination of knowledge pos-

sessed by experts in the medical ﬁeld with comput-

ing is an expert system. The expert system was de-

veloped from a simple display that was still in the

form of a command-line interface (CLI) (“Classiﬁca-

tion and diagnosis of diabetes: Standards of medical

care in Diabetesd2018,” 2018) until ﬁnally a graphical

user interface (GUI) version was developed that made

it easy for users to interact with the system (Gianni

et al., 2019). Even Bao, et al. (Schiller and Mandvi-

walla, 2007) has been able to develop an expert sys-

tem that can be used in several hospitals in rural ar-

Andriyani, W., Wibowo, S., Prasetya, L. and Kuntjoro, I.

A Symptom Distribution Method in Global Knowledge to Medical Expert System.

DOI: 10.5220/0009431100490058

In Proceedings of the International Conferences on Information System and Technology (CONRIST 2019), pages 49-58

ISBN: 978-989-758-453-4

eas by using virtual machines that are connected to a

network. Further development of the expert system

that is connected to the network allows patients to do

longdistance consultations with several doctors or ex-

perts who are included in a system (Chambers and

Conway, 1992).

The use of expert systems in the medical ﬁeld it-

self is divided into several types, namely expert sys-

tems based on rules or logic and expert systems based

on mathematical or statistical computations (Liao,

2005).

2 LITERATURE REVIEW

In improving the accuracy of expert system diagnos-

tics in the health sector, researchers conducted a com-

bination of rule-based and statistical-based. This sec-

tion will discuss previous studies related to the expert

system in its application in the health sector or medi-

cal expert system. The expert system was developed

using a rule-based method, based on statistics, or a

combination of both.

2.1 Rule-based (Logic- based) Expert

System

An expert system based on logic leads to a manipula-

tion of objects rather than mathematical computations

(Dzierzanowski et al., 1985), (“Foundations of neural

networks, fuzzy systems, and knowledge engineer-

ing,” 1997), (Herry and Frize, 2003). This is more

due to understanding between the problem domain

and the knowledge held by experts (Dzierzanowski

et al., 1985), (Li, 2010), (Albert et al., 2015). Fur-

thermore, the expert system that is built will greatly

affect the health of the lives of patients (Hyeon et al.,

2016). Knowledge from experts which is applied to

a rule-based expert system is capable of representing

the relationship between problems and consequences

that will occur (Adlassnig and Scheithauer, 1989) in

the form of IFTHEN (Gianni et al., 2019). The ability

to represent these relationships is obtained based on a

logical approach from real-world cases that are trans-

ferred from expert knowledge (Aronson et al., 2005).

The use of rule-based expert systems in the medical

ﬁeld provides ease in enhancing system capabilities.

If one day the expert has a new experience or the ex-

pert’s knowledge increases in disease, then the rules

can be changed according to expert knowledge. For

example, there are rules which are deleted or added in

the diagnosis of disease to achieve better diagnostic

results, but the addition or deletion of rules cannot be

done instantly but requires veriﬁcation and validation

so that the expert system that is built remains stable

(Schiller and Mandviwalla, 2007).

In addition to making the expert system that is

built remain stable, veriﬁcation and validation are also

needed so that every rule and fact stored in the knowl-

edge base is still true and honestly made based on ex-

pert knowledge. Poor accuracy and incomplete rules

are of great concern in the validation of a rulebased

expert system (Lockwood and Chen, 1995), (Eya-

dat and Alsmadi, 2012). However, rule-based expert

systems have drawbacks, one of which is limitations

when the system is unable to explain or make a rule

against disease diagnosis so that it is combined with

several other methods in AI such as fuzzy logic (Sut-

ton et al., 2012) and (Das et al., 2013), data mining

(Mihaela-Adina and Gheorghis

a, 2015) , (Feﬁlatyev

et al., 2007) and semantics (Sakorn, 2016).

CONRIST 2019 - International Conferences on Information System and Technology

space

Figure 1: Rule-Based Medical Expert System.

2.2 Quantity Measure based (Statistics

based) Expert System

Expert systems that are based on mathematical com-

putations arise because some researchers consider

that sometimes the systems are not able to make

or explain a rule to achieve the correct diagno-

sis. The development of expert systems of this type

uses mathematical methods such as Bayesian for-

mulas (Sapna and Tamilarasi, 2009), artiﬁcial neu-

ral networks (Yahia et al., 2000), data mining tech-

niques (Mihaela-Adina and Gheorghis

a, 2015), and

optimization (Mihaela-Adina and Gheorghis

a, 2015).

The use of expert systems based on mathematical

computations provides a jump in accuracy and a jump

in the speed of the diagnostic process. Mathematical

computations are not used to replace the rule-based

expert system, but rather to accomplish and improve

performance to cover the deﬁciencies that exist. Al-

though the system is capable of providing a good

spike in performance, but the use of expert systems

based on mathematical computations is limited to hu-

man ability to label (Valizadegan et al., 2013). This

can trigger debate from other medical personnel who

have different views based on knowledge and views

held (Sadideen et al., 2013). A simple example is a

usage of genes or offspring as a parameter or label in

making a diagnosis (Gay et al., 2013) and (Dharmar

et al., 2002).

Figure 2: Statistics-Based Medical Expert systems.

2.3 Medical Expert Systems Category

Technology development in the world of health is im-

portant. Starting from the examination process, di-

agnosis, to the patient care process must be done with

extreme care and precision. This becomes a challenge

for young doctors and paramedics who are just start-

ing a career in doing so, especially in dealing with

problems with a high degree of difﬁculty. Artiﬁcial

intelligence is a part of technologies that enables the

development of medical tools for junior paramedics

and doctors who are experienced in solving problems

they faced (Dharmar et al., 2002). One part of artiﬁ-

cial intelligence that is often used in the development

of these tools is the expert system (Dzierzanowski

et al., 1985), (Dharmar et al., 2002), (Tan et al., 2016).

The development of expert systems themselves can

be divided into several categories including diagnosis,

repair, instruction, interpretation, prediction, forecast-

ing, design and planning, monitoring, control, classi-

ﬁcation/identiﬁcation, discovery, debugging, and se-

lection (Tan et al., 2016).

2.3.1 Diagnosis

Diagnosis in the world of health requires compre-

hensive medical knowledge because sometimes the

causes of the disease (symptoms) can vary making it

difﬁcult for patients to identify their health conditions

(Sakorn, 2016). An expert system that is capable of

making the right diagnosis is expected to be able to

help patients and medical staff in making a diagnosis.

A Symptom Distribution Method in Global Knowledge to Medical Expert System

2.3.2 Repair

Repair in the medical expert system is referred to as a

system that is capable of providing solutions in treat-

ment for patient recovery.

2.3.3 Instruction

Instruction in the expert system is capable of provid-

ing a sequence of handling of disease.

2.3.4 Interpretation

The interpretation referred to in this medical expert

system is a system capable of processing input from

users both experts, medical personnel, and patients to

be able to provide diagnosis results and good treat-

ment recommendations.

2.3.5 Prediction

The ability of the expert system developed is in mak-

ing predictions about what will happen. Prediction

generated by the system can be in the form of disease

progression towards positive or negative.

2.3.6 Design and Planning

The system is capable of providing a framework and

work plan for handling patients based on the results

of the system’s diagnosis of disease. Planning and

handling generated by the system can be knowledge

given by experts at the time of manufacture and the

results of learning the system (if the expert system

can learn).

2.3.7 Monitoring and Control

The capability of the expert system is in monitoring

patient conditions and comparing them with previous

conditions. Then the system is capable of providing

new treatment solutions to the development of the pa-

tient’s condition. Such monitoring and control capa-

bilities are very helpful for medical personnel in han-

dling patients who must be monitored closely and in

detail.

2.3.8 Classiﬁcation and Identiﬁcation

Classiﬁcation is the ability of an expert system to

classify the type of disease to the patient’s condition.

While identiﬁcation is the capability of an expert sys-

tem in recognizing patients from their symptoms.

2.3.9 Discovery

In the development, there is an expert system that is

capable of recognizing and/or discovering a new type

of disease based on symptoms and the development

of the patient’s condition.

2.3.10 Discovery

Expert systems with this category are expert systems

that are capable of ﬁxing errors both independently

and with the help of experts.

Figure 3: The Use of Medical Expert System.

CONRIST 2019 - International Conferences on Information System and Technology

space space

A Symptom Distribution Method in Global Knowledge to Medical Expert System

space space

Source of Figure 3 : (Shortliffe, 2012), (Fieschi

et al., 1982), (Brazis et al., 2012), (Aikins et al.,

1983), (Miller et al., 1982), (Dzierzanowski et al.,

1985), (Weissman et al., 1974), (Dharmar et al.,

2002), (Chorbev et al., 2009), (Li, 2010), (Tseng and

Wu, 2011), (Zeki et al., 2012), (Tabibi et al., 2013),

(Toloie and Mohsen, 2010), (Albert et al., 2015),

(Hyeon et al., 2016), (Poli, 2015), (Malmir et al.,

2017), (Sakorn, 2016), (Cioara et al., 2018), (Lee and

Wang, 2010), (Mutawa, 2019), (Biyouki et al., 2015),

(Oyelade et al., 2018), (Nkamgang et al., 2019), (Jana

et al., 2019), (Estefania et al., 2016), (Biyouki et al.,

2015), (Elena et al., 2016), (Hashi et al., 2017), (Feﬁ-

latyev et al., 2007), (Valizadegan et al., 2013), (Aish-

warya and Anto, 2014).

3 GROUP EXPERT

This research will propose a group expert system

model (GDSS) that can be used in the Emergency

Unit (ER). The GDSS is capable of diagnosing patient

symptoms, physical examinations, and the anamne-

sis, and distribute the results of diagnoses to special-

ist doctors so that they can be followed up faster and

better.

CONRIST 2019 - International Conferences on Information System and Technology

space

Figure 4: Group Expert System

Figure 4 is an illustration of the application of the

system carried out in the ER. The doctor on duty in

the ER is responsible for examining the patient’s con-

dition: physical examination, anamnesis and symp-

toms and laboratory results (if previously a labora-

tory examination has been conducted) that the pa-

tient has come to at the ER. Global Knowledge is a

gathering place for all knowledge obtained from the

patient’s medical record, input data: physical symp-

toms, anamnesis, and laboratory examination results

(if a laboratory examination is conducted). Data from

global knowledge is distributed to expert systems that

are owned by each specialist doctor. The ﬁnal results

of the expert system of each specialist doctor will pro-

vide the results of the diagnosis and treatment care of

the patient in the ER.

3.1 Knowledge Representation

After the knowledge acquisition process has been

completed, the knowledge is transformed into a

knowledge base and a rule base which is then col-

lected, coded, organized and illustrated in another de-

sign form into a systematic form. The way to repre-

sent data into knowledge is in the form of attributes,

rules, semantic networks, frames, logic and produc-

tion rules (Leung and Wong, 1991), (“Proceedings of

the 1997 20th Annual International ACM SIGIR Con-

ference on Research and Development in Information

Retrieval,” 1997). It aims to simplify the data so that it

is easy to understand and make the program develop-

ment process effective. The expert system uses pro-

duction rules derived from decision trees and decision

tables.

3.2 Building a Knowledge Base

In building a knowledge base, two algorithms are

needed, namely an algorithm to receive knowledge

and an algorithm to ﬁll knowledge.

Algorithm for receiving knowledge. The follow-

ing algorithm is the algorithm used in the system to

receive knowledge from experts. This algorithm is

used to ﬁll all specialist medical doctors and symp-

toms data.

Figure 5: Algorithm 1 Receive Input for Knowledge Base

Row 1: Procedure deﬁnition, without parameter.

Row 2: Fill in the input Available variable with true

value. As long as input Available variable value is

true, the input is still available to be ﬁlled into the

knowledge.

Row 3-6: Looping for data input (code, specialist

medical doctor code, and symptoms). This part is

used to receive input and then ﬁll those input into a

knowledge base (available in algorithm 2).

3.3 Algorithm for Filling Knowledge

There are three parameters to carry out this procedure,

namely code (code of symptoms), specialist code

(code for specialist doctors), and symptoms (knowl-

edge of symptoms).

Figure 6: Algorithm 2 Fill in the Knowledge Base

Row 1: Procedure deﬁnition. This procedure

needs 3 parameters: Code (for symptoms code), Spe-

cialist Code (for specialist medical doctor who has the

knowledge about this symptoms), and then Symptoms

(for symptoms knowledge).

Row 2-4: Fill all three parameters into local variabel

for later processing.

Row 5: Persistently write code, spCode, and symp-

toms into knowledge base.

A Symptom Distribution Method in Global Knowledge to Medical Expert System

3.4 Inference Algorithm

The inference algorithm of the system is divided

into two, namely the input distribution algorithm ac-

cording to the patient’s symptoms and the algorithm

to ﬁnd the appropriate specialist to deal with these

symptoms.

Input distribution algorithm for patient symptoms

Row 1: Procedure deﬁnition. It does not need any

parameter and is used for all patient symptoms’ input.

Output of this procedure is an array which consists of

all symptoms’ code for the patient and all specialist

codes who are able to handle the symptoms.

Figure 7: Algorithm 3 Input Symptoms

Row 2: specialist Array initialization. This array

is a 2 dimensions array which consists of [symptom

code] [list of specialist medical doctor]. At the of the

procedure, this array will be ﬁlled.

Row3: symptoms Available initialization. This vari-

able is used to mark the symptoms whether they are

still available or not.

Row 4-8: Looping as long as the data still available

for input. For every loop, symptom Code will become

the input and will be ﬁlled into local variable (code).

The code variable will become the parameter to ﬁnd

the specialist in algorithm 4. Upon ﬁnishing, this pro-

cedure will return two dimensions array which con-

sists of all symptoms (codes) and all specialist codes

for every symptom (all Specialist Code).

Seeking algorithm for an appropriate specialist

This step, the step where the symptoms of the

patient will be related to the specialist’s knowledge

based on the knowledge of each specialist.

Figure 8: Algorithm 4 Input Symptoms

Row 1: Function deﬁnition. This function needs

one parameter: code (code of symptom for which the

specialist doctors are about to ﬁnd. This function re-

turns array value which consists of all specialist med-

ical doctors for the symptom.

Row 2: array Sp initialization, begins with empty

value.

Row 3: Fill in Code into local variable code.

Row 4-10: Looping to read all records in knowledge

base. In every loop, symptom code in knowledge base

is read and become an input for symptom CodeKb

(row 5). If the code is the same as symptom CodeKb

then specialist medical doctor in knowledge base will

be put into arraySp (row 6-8).

Row 11: Return arraySp value which has already

ﬁlled with all specialist medical doctors for the symp-

toms.

4 CONCLUSIONS

The results of this study are an algorithm that will

be implemented in the next journal, which is an al-

gorithm that is implemented in real conditions in the

emergency unit and the distribution of symptoms to

patients received by each Specialist unit based on the

knowledge possessed by specialists in the unit emer-

gency. Knowledge data is extracted from medical

record data obtained at the hospital. The results of

this algorithm are a knowledge base that can produce

a conclusion of the type of disease so that it will help

the work of doctors in the ward of the emergency

unit and specialist units in making further observa-

tions and treatments on these patients.

REFERENCES

Adlassnig, K.-P. and Scheithauer, W. (1989). Performance

evaluation of medical expert systems using roc curves.

Computers and biomedical research, 22(4):297–313.

Aikins, J. S., Kunz, J. C., Shortliffe, E. H., and Fallat, R. J.

(1983). Puff: An expert system for interpretation of

pulmonary function data. Computers and biomedical

research, 16(3):199–208.

Aishwarya, S. and Anto, S. (2014). A medical expert sys-

tem based on genetic algorithm and extreme learning

machine for diabetes disease diagnosis. International

Journal of Science, Engineering and Technology Re-

search (IJSETR), 3(5):75–80.

Albert, M., Gors, M., and Schilling, K. (2015). Telemed-

ical applications with rulebased descision-and

information-systems (tardis). IFAC-PapersOnLine,

48(10):7–11.

Aronson, J. E., Liang, T.-P., and MacCarthy, R. V. (2005).

Decision support systems and intelligent systems, vol-

ume 4. Pearson Prentice-Hall Upper Saddle River, NJ,

USA:.

CONRIST 2019 - International Conferences on Information System and Technology

Biyouki, S. A., Turksen, I., and Zarandi, M. F. (2015).

Fuzzy rule-based expert system for diagnosis of thy-

roid disease. In 2015 IEEE Conference on Compu-

tational Intelligence in Bioinformatics and Computa-

tional Biology (CIBCB), pages 1–7. IEEE.

Brazis, P. W., Masdeu, J. C., and Biller, J. (2012). Local-

ization in clinical neurology. Lippincott Williams &

Wilkins.

Chambers, R. and Conway, G. (1992). Sustainable rural

livelihoods: practical concepts for the 21st century.

Institute of Development Studies (UK).

Chorbev, I., Mihajlov, D., and Jolevski, I. (2009). Web

based medical expert system with a self training

heuristic rule induction algorithm. In 2009 First

International Confernce on Advances in Databases,

Knowledge, and Data Applications, pages 143–148.

IEEE.

Cioara, T., Anghel, I., Salomie, I., Barakat, L., Miles, S.,

Reidlinger, D., Taweel, A., Dobre, C., and Pop, F.

(2018). Expert system for nutrition care process of

older adults. Future Generation Computer Systems,

80:368–383.

Cota,

E., Ribeiro, L., Bezerra, J. S., Costa, A., da Silva,

R. E., and Cota, G. (2017). Using formal methods for

content validation of medical procedure documents.

International journal of medical informatics, 104:10–

25.

Das, S., Ghosh, P. K., and Kar, S. (2013). Hypertension di-

agnosis: a comparative study using fuzzy expert sys-

tem and neuro fuzzy system. In 2013 IEEE Inter-

national Conference on Fuzzy Systems (FUZZ-IEEE),

pages 1–7. IEEE.

Dharmar, C., Srinivasan, S., Mital, D., and Haque, S.

(2002). Expert system for the diagnosis of neona-

tal jaundice for use by medical ﬁeld personnel. In

7th International Conference on Control, Automation,

Robotics and Vision, 2002. ICARCV 2002., volume 2,

pages 1002–1006. IEEE.

Dzierzanowski, J. M., Bourne, J. R., Shiavi, R., Sandell,

H. S., and Guy, D. (1985). Gaitspert: An expert sys-

tem for the evaluation of abnormal human locomotion

arising from stroke. IEEE transactions on biomedical

engineering, (11):935–942.

Elena, A., Acevedo, A., Felipe, F., and Avil

es, P. (2016).

Expert system for the diagnosis of vertebral column

diseases. In 2016 IEEE 36th Central American and

Panama Convention (CONCAPAN XXXVI), pages 1–

4. IEEE.

Estefania, C.-R., Garc

ıa-S

aez, G., Rigla, M., Villaplana, M.,

Pons, B., and Hernando, M. E. (2016). Automatic

classiﬁcation of glycaemia measurements to enhance

data interpretation in an expert system for gestational

diabetes. Expert Systems with Applications, 63:386–

396.

Eyadat, A. and Alsmadi, I. (2012). Automatic coverage

evaluation for a medical expert system. In 2012 Ninth

International Conference on Information Technology-

New Generations, pages 867–872. IEEE.

Feﬁlatyev, S., Ivanovskiy, T. V., Hall, L. O., Goldgof, D. B.,

Pobi, S., Greenstien, H., Pathak, A. P., and Garrett,

C. R. (2007). Clinical deployment of a medical ex-

pert system to increase accruals for clinical trials:

Challenges. In 2007 IEEE International Conference

on Systems, Man and Cybernetics, pages 1482–1487.

IEEE.

Fieschi, M., Joubert, M., Fieschi, D., and Roux, M.

(1982). Sphinx—a system for computer-aided diagno-

sis. Methods of information in medicine, 21(03):143–

148.

Gay, P., L

opez, B., Pl

a, A., Saperas, J., and Pous, C. (2013).

Enabling the use of hereditary information from pedi-

gree tools in medical knowledge-based systems. Jour-

nal of biomedical informatics, 46(4):710–720.

Gianni, F., Mora, S., and Divitini, M. (2019). Rapiot toolkit:

Rapid prototyping of collaborative internet of things

applications. Future Generation Computer Systems,

95:867–879.

Gorzalczany, M. B. and McLeish, M. (1992). Combina-

tion of neural networks and fuzzy sets as a basis for

medical expert systems. In [1992] Proceedings Fifth

Annual IEEE Symposium on Computer-Based Medi-

cal Systems, pages 412–420. IEEE.

Hashi, E. K., Zaman, M. S. U., and Hasan, M. R. (2017).

An expert clinical decision support system to predict

disease using classiﬁcation techniques. In 2017 In-

ternational Conference on Electrical, Computer and

Communication Engineering (ECCE), pages 396–

400. IEEE.

Herry, C. and Frize, M. (2003). Design considerations for

a medical thermographic expert system. In Proceed-

ings of the 25th Annual International Conference of

the IEEE Engineering in Medicine and Biology So-

ciety (IEEE Cat. No. 03CH37439), volume 2, pages

1252–1255. IEEE.

Hyeon, J., Oh, K.-J., Kim, Y. J., Chung, H., Kang, B. H.,

and Choi, H.-J. (2016). Constructing an initial knowl-

edge base for medical domain expert system using in-

duct rdr. In 2016 International Conference on Big

Data and Smart Computing (BigComp), pages 408–

410. IEEE.

Jana, B., Oswal, K., Mitra, S., Saha, G., and Banerjee, S.

(2019). Detection of peripheral arterial disease using

doppler spectrogram based expert system for point-of-

care applications. Biomedical Signal Processing and

Control, 54:101599.

Krantz, K., Youssef, H., and Newcomb, R. (1988). Medical

usage of an expert system for recognizing chaos. In

Proceedings of the Annual International Conference

of the IEEE Engineering in Medicine and Biology So-

ciety, pages 1303–1304. IEEE.

Lee, C.-S. and Wang, M.-H. (2010). A fuzzy expert sys-

tem for diabetes decision support application. IEEE

Transactions on Systems, Man, and Cybernetics, Part

B (Cybernetics), 41(1):139–153.

Leung, K. and Wong, M. (1991). Inducing and reﬁning rule-

based knowledge from inexact examples. Knowledge

Acquisition, 3(3):291–315.

Li, L.-b. (2010). Study on experts scheduling strategy of

collective consultation in long-distance medical sys-

tem. In 2010 International Conference on Manage-

ment and Service Science, pages 1–4. IEEE.

A Symptom Distribution Method in Global Knowledge to Medical Expert System

Liao, S.-H. (2005). Expert system methodologies and appli-

cations—a decade review from 1995 to 2004. Expert

systems with applications, 28(1):93–103.

Lockwood, S. and Chen, Z. (1995). Knowledge validation

of engineering expert systems. Advances in Engineer-

ing Software, 23(2):97–104.

Malmir, B., Amini, M., and Chang, S. I. (2017). A medical

decision support system for disease diagnosis under

uncertainty. Expert Systems with Applications, 88:95–

108.

Mihaela-Adina, M. and Gheorghis

a, P. (2015). An ex-

pert system architecture for managing the biomateri-

als used in medical devices. In 2015 7th International

Conference on Electronics, Computers and Artiﬁcial

Intelligence (ECAI), pages P–67. IEEE.

Miller, R. A., Pople Jr, H. E., and Myers, J. D. (1982).

Internist-i, an experimental computer-based diagnos-

tic consultant for general internal medicine. New Eng-

land Journal of Medicine, 307(8):468–476.

Mutawa, AM, A. M. A. (2019). Multilayered rule-based

expert system for diagnosing uveitis. Artiﬁcial intelli-

gence in medicine, 99:101691.

Navarra, S. e. a. (2016). Decision table editor: A web appli-

cation for the management of the international tables

for mortality coding.

Nkamgang, O. T., Tchiotsop, D., Fotsin, H. B., Talla, P. K.,

Dorr, V. L., and Wolf, D. (2019). Automating the clin-

ical stools exam using image processing integrated in

an expert system. Informatics in Medicine Unlocked,

15:100165.

Oyelade, O., Obiniyi, A., Junaidu, S., and Adewuyi, S.

(2018). Patient symptoms elicitation process for

breast cancer medical expert systems: A semantic web

and natural language parsing approach. Future Com-

puting and Informatics Journal, 3(1):72–81.

Poli, V. S. R. (2015). Method of fuzzy conditional inference

and application to fuzzy medical expert systems. In

2015 International Conference on Fuzzy Theory and

Its Applications (iFUZZY), pages 115–120. IEEE.

Razzouk, D., Mari, J. d. J., Shirakawa, I., Wainer, J., and

Sigulem, D. (2006). Decision support system for the

diagnosis of schizophrenia disorders. Brazilian jour-

nal of medical and biological research, 39(1):119–

128.

Sadideen, H., Alvand, A., Saadeddin, M., and Kneebone, R.

(2013). Surgical experts: born or made? International

Journal of Surgery, 11(9):773–778.

Sakorn, M. (2016). Medical expert system based ontology

for diabetes disease diagnosis. In 2016 7th IEEE In-

ternational Conference on Software Engineering and

Service Science (ICSESS), pages 383–389. IEEE.

Sampat, M. P., Markey, M. K., Bovik, A. C., et al. (2005).

Computer-aided detection and diagnosis in mammog-

raphy. Handbook of image and video processing,

2(1):1195–1217.

Sapna, S. and Tamilarasi, A. (2009). Fuzzy relational equa-

tion in preventing diabetic heart attack. In 2009 Inter-

national Conference on Advances in Recent Technolo-

gies in Communication and Computing, pages 635–

637. IEEE.

Schiller, S. Z. and Mandviwalla, M. (2007). Virtual team re-

search: An analysis of theory use and a framework for

theory appropriation. Small group research, 38(1):12–

59.

Shortliffe, E. (2012). Computer-based medical consulta-

tions: MYCIN, volume 2. Elsevier.

Sutton, C., McCallum, A., et al. (2012). An introduction to

conditional random ﬁelds. Foundations and Trends



in Machine Learning, 4(4):267–373.

Tabibi, S. T., Zaki, T. S., and Ataeepoor, Y. (2013). De-

veloping an expert system for diabetics treatment ad-

vices. International Journal of Hospital Research,

2(3):155–162.

Tan, C., Wahidin, L., Khalil, S., Tamaldin, N., Hu, J.,

and Rauterberg, G. (2016). The application of ex-

pert system: A review of research and applications.

ARPN Journal of Engineering and Applied Sciences,

11(4):2448–2453.

Toloie, A. and Mohsen, S. (2010). Designing an expert sys-

tem for suggesting the blood cancer treatment. Jour-

nal of Health Administration, 13(40):41–50.

Tseng, M.-H. and Wu, H.-C. (2011). A two-dimensional

fuzzy repertory grid approach for building medical ex-

pert systems. In 2011 International Conference on

Machine Learning and Cybernetics, volume 1, pages

183–188. IEEE.

Valizadegan, H., Nguyen, Q., and Hauskrecht, M. (2013).

Learning classiﬁcation models from multiple experts.

Journal of biomedical informatics, 46(6):1125–1135.

Van Remoortere, P. (1979). Computer-based medical con-

sultations: Mycin: Eh shortliffe: Published by north-

holland, amsterdam and ny, 1976, 264 pages, us

$19.95, isbn 0-444-00179-4.

Weissman, S., Diers, A., and Bemesderfer, S. (1974). Psy-

chiatric services in a youth corrections unit. Psychi-

atric Services, 25(9):602–605.

Yahia, M., Mahmod, R., Sulaiman, N., and Ahmad, F.

(2000). Rough neural expert systems. Expert Systems

with Applications, 18(2):87–99.

Zeki, T. S., Malakooti, M. V., Ataeipoor, Y., and Tabibi,

S. T. (2012). An expert system for diabetes diagno-

sis. American Academic & Scholarly Research Jour-

nal, 4(5):1.

CONRIST 2019 - International Conferences on Information System and Technology