Knowledgebase Systems in Neuro Science - A Study

International Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI), Vol.4, No.2, May 2015
DOI :10.5121/ijscai.2015.4201 1
KNOWLEDGEBASE SYSTEMS IN NEURO SCIENCE - A
STUDY
Dr. D.K. Sreekantha 1
, T.M. Girish 2
and Dr. R.V.Kulkarni3
1
Department of Computer Science & Engineering, NMAMIT, Nitte, Karnataka
2
Dept. of CS, Basaveshwar Science College, Bagalkot, Karnataka
3
Head, Dept. of Computer Studies, CSIBER, Kolhapur, Maharastra
ABSTRACT
The improvement of health and nutritional status of the society has been one of the thrust areas for social
developments programmes of the country. The present states of healthcare facilities in India are inadequate
when compared to international standards. The average Indian spending on healthcare is much below the
global average spending. Indian healthcare Industry is growing at the rapid pace of more than 18%, the
fastest in the world. The prospects for Indian healthcare are to the tune of USD 40 billion, while global
market is USD 1660 trillion. India has all the prospects to become medical tourism destination of the
world, because it has a large pool of low-cost scientifically trained technical personal and is one of the
favoured counties for cost effective healthcare. As per the reports of Global Burden of Neurological
Disorders Estimations and Projections survey there is big shortage of neurologist in India and around the
world. So Authors would like to develop an innovative IT based solution to help doctors in rural areas to
gain expertise in Neuro Science and treat patients like expert neurologist. This paper aims to survey the
Soft Computing techniques in treating neural patient’s problems used throughout the world
KEYWORDS
Neurology, Expert System, Soft Computing
1. INTRODUCTION
India is one of the favoured countries for cost effective healthcare and has all the potential to
become medical tourism destination of the world. The hospital and nursing home industry is
growing at rate of 20% annually. India is one of the top 3 countries, where companies plan to
spend most research and development funds over the next 3 years. The Indian clinical community
is populated with English speaking, western-trained graduates. Two thirds of healthcare spending
to the tune of USD 20 billion is out of pocket in private spending. India has 280 million strong
middle and upper middle class population with 10–12 million high income groups, which could
afford the lifestyle of their western counterparts. (Source : Economist Intelligence Unit, World
Industry Outlook – Healthcare and Pharmacuticals, 2010 CAGR Compound annual growth rate).
According to AAN2010 Practice Profile Form neurologists have devoted on average 42.3 hours a
week in practice 2010. The number of visits to hospital has increased to 81.8 on average per week
in 2010. These facts will signify the need for neurologist services in developing country like India
around the world. Hence the researchers are focusing on building an innovative IT based solution
to help novice doctors to treat neural patients in rural areas. During the last decade much research
effort has been devoted to the development of expert systems to cope with complex medical
decision-making.

2
An expert system is "an embodiment within a computer of a knowledge-based component, from
an expert skill, in such a form that the system can offer intelligent advice or make an intelligent
decision about a processing function." such a system uses expert knowledge to attain high levels
of performance in a narrow problem area. In the process of diagnosis, neurologists collect
historical data, neurologic signs, and symptoms to arrive at a "best guess" as to stroke type, which
then forms the basis for performing further diagnostic procedures such as computed tomography
(CT scan) or cardiologic or cerebrovascular tests.
2. SURVEY OF LITERATURE
The present work comprises an exhaustive survey of relevant literature of most relevant articles
on Soft Computing techniques applied in Neuro Science from reputed journals from IEEE
Transactions, Springer and Elsevier publishers and proceedings of international conferences.
Some selected articles from this survey are discussed by way of illustration.
Klaus Spitzer, Andreas Thie, Louis R. Caplan and Klaus Kunze [1] (1989) have designed a
prototype MICROSTROKE expert system to categorize and diagnose stroke type based on
clinical information. The knowledge base of MICROSTROKE includes information from large
stroke registries. The system first queries the physician-user for details of the patient's history,
information about the onset of stroke, accompanying symptoms and pertinent neurologic findings
and then sums the individual data items, factors in the a priori odds, and arrives at the
probabilities of different stroke types for a given patient. Stroke type diagnoses by
MICROSTROKE were correct in 72.8% of 250 cases in the Hamburg Stroke Data Bank, stroke
types can be of prime importance. Authors presented MICROSTROKE, the prototype of an
expert system for computer-supported stroke type diagnosis based only on clinical and historical
patient data available at the bedside; MICROSTROKE serves as an aid in the diagnostic work-up
of stroke as both a stroke patient data bank and as an educational tool in clinical teaching.
Cruz J, Barahona P, Figueiredo A.P, Veloso M and Carvalho M [2] (1994) have discussed a new
knowledge-based system called DARE for the diagnosis of neuromuscular disorders that
performs anatomic-physiological reasoning on a deep causal-functional model of the domain
knowledge. These characteristics make the system more flexible and general than similar systems
in this domain and favour its potential use in different local environments. This paper also
discusses the preliminary evaluation of the system performed in the European project ESTEEM,
as well as the work still required to make it a real clinical application. The current version of
DARE already achieved a quite acceptable diagnostic performance and many improvements can
done in the near future such as a need to extend the knowledge model either quantitatively
(representing more anatomical structures and functionalities) or qualitatively (including explicitly
the etiologic and temporal knowledge) and to support the adopted reasoning methods with more
formalized models (allowing the formal definition of reasoning tasks for diagnosis, prognosis and
patient treatment).
Christophe S. Herrmann [3] (1995) combined Fuzzy Logic, neural network and an expert system
to build a hybrid diagnosis system, a new approach to the acquisition of knowledge bases. This
system consists of a fuzzy expert system with a dual source knowledge base. Two sets of rules are
acquired, inductively from given examples and deductively formulated by a physician. A fuzzy
neural network serves to learn from sample data and allows extracting fuzzy rules for the
knowledge base. The diagnosis of electroencephalograms by interpretation of graph elements
serves as visualization for author’s approach. Preliminary results demonstrate the promising
possibilities offered.

3
The hybrid system, described in this article, introduces the following new paradigms of modelling
the cognitive task of diagnosis, Instead of either acquiring the whole knowledge base
automatically from examples, being an inductive learning method.
Leda Cosmides and John Tooby [4] (1997) have authored an article The Cognitive Neuroscience
of Social Reasoning. Cognitive scientists needed theoretical guidance that is grounded in
something beyond intuition. Authors need evolutionary biology's "adaptationist program", a
research strategy in which theories of adaptive function are key inferential tools, used to identify
and investigate the design of evolved systems. Using research on how human’s reason about
social exchange. The authors illustrated how theories of adaptive function can generate detailed
and highly testable hypotheses about the design of computational machines in the human mind
and reviewed research that tests for the presence of these machines. This research suggests that
the human computational architecture contains an expert system designed for reasoning about
cooperation for mutual benefit, with a subroutine specialized for cheaper detection. By using a
computational theory specifying the adaptive problems entailed by social exchange authors team
were able to predict, in advance, that certain very subtle changes in the content and context would
produce dramatic differences in how people reason. Authors concluded that the adaptationist
program is cognitive neuroscience's best hope for achieving this goal.
Jean-Marc Fellous, Jorge L. Armony and Joseph E. LeDoux [5] (2000) have published the article
Emotional Circuits and Computational Neuroscience. Emotion is clearly an important aspect of
the mind, yet it has been largely ignored by the "brain and mind (cognitive) sciences" in modern
times. However, there are signs that this is beginning to change. Authors discussed some issues
about the nature of emotion, describe what is known about the neural basis of emotion and
consider some efforts that have been made to develop computer-based models of different aspects
of emotion. It is important to distinguish between emotional experiences and the underlying
processes that lead to emotional experiences. One of the stumbling blocks to an adequate
scientific approach to emotion has been the focus of the field on constructing theories of the
subjective aspects of emotion. Studies of the neural basis of emotion and emotional learning have
instead focused on how the brain detects and evaluates emotional stimuli and how, on the basis of
such evaluations, emotional responses are produced. Computational approaches to emotional
processing are both possible and practical. Although relatively few models currently exist, this
situation is likely to change as researchers begin to realize the opportunities that are present in
this too-long neglected area.
Emmanuil Marakakis, Kostas Vassilakis, Emmanuil Kalivianakis, Sifis Micheloyiannis [6]
(2005) have designed Expert System for Epilepsy with Uncertainty, that derives differential
diagnosis about epilepsy cases in childhood, according to international classifications. This expert
system is intended to be used as a consultation system by neurologists. The physician specialist
can update the knowledge base of the system through a user friendly interface. Uncertainty is
handled by using weights and certainty factors. Meta-rules drive the reasoning process of the
system. The initial evaluation results of the system are very promising, i.e. 83.3% successful
diagnosis. HIPPOCRAT-EES preliminary results are satisfactory compared with the results of the
systems. The results from the evaluation of the decision support system in are as follows. The
system has derived correct diagnosis in 85.2% of patient cases, partial successful diagnosis in
8.2% of patient cases and absolute incorrect diagnosis in 6.6% of patient cases. The diagnosis of
the DSS is more accurate than the one of HIPPOCRAT-EES. On the other hand the DSS does not
derive alternative diagnoses as HIPPOCRAT-EES does. In addition, the KB of the DSS cannot be
updated by physicians like HIPPOCRAT-EES. The diagnosis of the system has been compared
with the diagnosis of three experts. The evaluation results are 72% correct diagnoses, 8% partially
correct diagnoses and 20% incorrect diagnoses.

4
Blacksmiths, Neurons Mauro Adenzato and Francesca Garbarini [7] (2006) authored the paper
Cognitive Science, Neuroscience and Anthropology - A Journey among Robots. In recent years,
neurophysiological and psychological research has highlighted a pragmatic version of the theory
of knowledge, a version in which the concept of simulation has been found to play a crucial role.
In fact, research on canonical and mirror neurons has shown that as if simulative schema is
required to perceive, categorize and understand the meaning of the external world. The present
study compares the cognitive paradigm of embodied cognition with Pierre Bourdieu’s practice
theory. Specifically, cognitive processes and cultural mechanisms are described as phenomena
that emerge from the dynamic interaction that exists between people’s practical abilities and the
structure of the local environment in which they act and live. A pragmatic conception of
knowledge has also emerged in the field of ethnological investigation. Indeed, the concepts of
resonance and empathy have proven to be essential instruments for ethnological knowledge. With
this new view of the relationship between mind and body and between culture and nature, there
are now greater opportunities for conducting interdisciplinary research in the natural sciences and
social sciences, research aimed at reconstituting the fracture that has existed for too long now
between humans as biological and cultural beings. As Jacob and Jeannerod (2005) observed, the
mirror neuron system is well designed for representing an agent’s motor intention, but not the
agent’s prior intention to execute an action. A discussion on the theoretical distinction between
motor intention and prior intention goes beyond the aims of the present work. Authors referred to
Becchio, Adenzato and Bara (2006) for a more exhaustive analysis of the issue.
Badri Adhikari, Md. Hasan Ansari, Priti Shrestha and Susma Pant [8] (2008) have developed a
Neurology Diagnosis System, which is concerned about the construction of a web-based expert
system. The objective of the system is to help the diagnosis process of neurology doctors.
Neurology is a medical specialty that deals with disorders of the nervous system. Doctors will use
the website as a helpful tool to diagnose their patients. The web application will collect rules of
the neurology domain and cases of the patients. Integrating the techniques of rule-based reasoning
and case-based reasoning a hybrid system can be constructed. The system will use the rules and
cases to achieve the objective of assisting the decision making process of the domain experts. The
proposed system will prove effective, efficient and will establish itself as a valuable asset of the
department and the hospital. Precise analysis of return on investment (ROI) and breakeven
analysis is difficult at this proposing stage of an academic project. It can be assured that the
project will prove economically feasible.
Murad Alaqtash, Huiying Yu, Richard Brower, Amr Abdelgawad, Eric Spier, and Thompson
Sarkodie-Gyan [9] (2010) have authored Application of Wearable Miniature Non-invasive
Sensory System in Human Locomotion using Soft Computing Algorithm. The authors have
designed and tested a wearable miniature non-invasive sensory system for the acquisition of gait
features. The sensors are placed on anatomical segments of the lower limb, and motion data was
then acquired in conjunction with electromyography (EMG) for muscle activities, and
instrumented treadmill for ground reaction forces (GRF). A relational matrix was established
between the limb-segment accelerations and the gait phases. This algorithm offers the possibility
to perform functional comparisons using different sources of information. It can provide a
quantitative assessment of gait function. This algorithm has clearly illustrated the possibility to
perform functional comparisons by using different sources of information.
The fuzzy similarity methodology depicts distinctions between the reference able-bodied and the
randomized test subjects within with a membership grade of belonging. This novel algorithm may
offer very reliable and efficient tools for the evaluation and assessment of gait function in several
ways: By building a rule-based system depicts the strength of relation between muscle activities,

5
limb-segment accelerations, and gait phases. By comparing the reference muscle activities within
gait phases with a randomized input-matrix through a fuzzy similarity algorithm.
Youssouf EL ALLIOUI and Omar EL BEQQALI [10] (2010) have authored the article
O’Neurolog – Building, an Ontology for Neurology in Mobile Environment, The (context aware
services). A crucial requirement for the context-aware service provisioning is the dynamic
retrieval and interaction with local resources, i.e., resource discovery. The high degree of
dynamicity and heterogeneity of mobile environments requires rethinking and/or extending
traditional discovery solutions to support more intelligent service search and retrieval,
personalized to user context conditions. Authors research work aims at providing suitable
answering mechanisms of mobile requests by taking into account user contexts (preferences,
profiles, physical location, temporal information…). This paper proposes ontology, called
O’Neurolog, to capture semantic knowledge a valuable in Neurology domain in order to assist
users (doctor, patient, administration …) when querying Neurology knowledge bases in mobile
environment. First, authors designed a domain specific ontology, called O’Neurolog that
incorporates concepts drawn from raw data and expert knowledge. In fact, data and knowledge
discovery is a crucial activity in pervasive environments where mobile users need to be provided
with personalized results due to limited physical characteristics of portable devices. Another
interesting future issue authors envision dealing which is the resolution of conflicts that may arise
between value or priority preferences. Authors believe that a possible approach may be the
definition of meta-preferences, as authors have began the formalization in section.
Faran Baig, M. Saleem Khan, Yasir Noor and M. Imran [11] (2011) have designed model of
Fuzzy Logic Medical Diagnosis Control System, This research work addresses the medical
diagnosis regarding the normality of a human function in human brain and the diagnosis of
haemorrhage and brain tumour. It enhances the control strategies in the medical field to diagnose
a disease. The simulation results are found in agreement with the design based calculated results.
This research work proposes to develop a control system to enhance the efficiency to diagnose a
disease related to human brain. Both the design model and simulation result are same. The
designed system can be extended for any number of inputs. Normal, haemorrhage and the brain
tumour all depend on the inputs protein, red blood cell, lymphocytes, neutrophils and eosinophils.
Authors defined this system for any number of inputs. As the inputs are the blood cells and the
designed system use five blood cells as inputs, similarly authors defined this system more than
five Inputs to get more efficient human diagnose results. The design work was being carried out
to design state of the art fuzzy logic medical diagnosis control system in future using FPGAs.
Dragan Simić, Svetlana Simić, and Ilija Tanackov [12] (2011) authored the article An Approach
of Soft Computing Applications in Clinical Neurology, this paper briefly introduces various soft
computing techniques and presents miscellaneous applications in clinical neurology domain.
Authors presented applications of soft computing models of the cutting edge researches in
neurology domain, specifically for EMG and EEG signals. This paper only indicates some
researches based on hybrid soft computing and expert and decision support systems. Also,
researches on implementation of different artificial intelligence techniques – hybrid soft
computing methods can be applied to almost all medical domains, neurology included.
Rajdeep Borgohain and Sugata Sanyal [13] (2011) designed Rule Based Expert System for
Cerebral Palsy Diagnosis. The use of artificial intelligence is finding prominence not only in core
computer areas, but also in cross disciplinary areas including medical diagnosis. The expert
system takes user input and depending on the symptoms of the patient, diagnoses and if the
patient is suffering from Cerebral Palsy. The expert system also classifies the Cerebral Palsy as
mild, moderate or severe based on the presented symptoms. Authors have discussed the design
and implementation of a rule based Expert System for Cerebral Palsy Diagnosis. This expert

6
system helps to diagnose Cerebral Palsy and classify it as mild, moderate or severe. In the
implementation, authors have taken the most classical symptoms of Cerebral Palsy and given a
weight age to each of the symptom and according to the feedback given by the user.
The expert system can go a great deal in supporting the decision making process of medical
professionals and also help parents having children with Cerebral Palsy to assess their children
and to take appropriate measures to manage the disease.
Imianvan Anthony Agboizebeta and Obi Jonathan Chukwuyeni [14] (2012) have authored
Cognitive analysis of multiple sclerosis utilizing fuzzy cluster means Multiple sclerosis, often
called MS, is a disease that affects the central nervous system (the brain and spinal cord). Myelin
provides insulation for nerve cells improves the conduction of impulses along the nerves and is
important for maintaining the health of the nerves. In multiple sclerosis, inflammation causes the
myelin to disappear. Genetic factors, environmental issues and viral infection may also play a role
in developing the disease. MS is characterized by life threatening symptoms such as; loss of
balance, hearing problem and depression. This paper presents a diagnostic fuzzy cluster means
system to help in diagnosis of Multiple sclerosis using a set of symptoms. This advanced system
which uses clustered data set is more precise than the traditional system. The classification,
verification and matching of symptoms to the two groups of clusters (Relapsing/remitting
multiple sclerosis and Primary Progressive Multiple Sclerosis) was necessary especially in some
complex scenarios. This paper demonstrates the practical application of ICT (Information and
communication technology) in the domain of diagnostic pattern appraisal in medicine by
determining the extent of membership of individual symptoms. The model proposed allows for
the classification of matching of cluster groups to multiple sclerosis symptoms. The fuzzy-cluster
means model proposed in this paper appears to be a more useful.
Sujit Das, Pijush Kanti Ghosh and Samarjit Kar [15] (2012) have authored Hypertension
Diagnosis: A Comparative Study using Fuzzy Expert System and Neuro Fuzzy System.
Hypertension is called the silent killer because it has no symptoms and can cause serious trouble
if left untreated for a long time. It has a major role for stroke, heart attacks, heart failure,
aneurysms of the arteries, peripheral arterial diseases, chronic kidney disease etc. Then this paper
presents a comparative study between fuzzy expert system (FES) and feed forward back
propagation based neuro fuzzy system (NFS) for hypertension diagnosis. This paper also presents
a comparison among the learning functions (LM, GD and BR) where Levenberg-Marquardt based
learning function shows its efficiency over the others. Comparison between FES and NFS shows
the effectiveness of using NFS over FES. Here, the input data set has been collected from 10
patients whose ages are between 20 and 40 years, both for male and female. It has shown that the
neuro fuzzy system used in this study has the capacity to produce higher overall prediction
accuracy than particular fuzzy expert system architecture. Based on this observation authors
concluded that NFS represents a useful method for medical diagnostic task of finding
hypertension risk factor. Different ANN training algorithms were shown to lead to different
diagnostic results among which Levenberg- Marquardt is proved to be optimal. Development of
NFS would be more helpful to medical experts and new coming practitioner for diagnosing the
hypertension in proper order. For feed forward back propagation based neural network, authors
have taken the membership values of related linguistic variables (low, medium and high) as input
of age, BMI, BP and Heart Rate and as output (less, moderate and severe) for Hypertension risk
evaluation. In this present study, FES shows hypertension risk is moderate for 5 patients and less
for the other five patients. But NFS shows severe risk for 5 patients, less risk for 4 patients and
moderate risk for 1 patient which is close to medical observation as released by a team of experts.
Future goal of this study is to present the adaptive neuro fuzzy inference system (ANFIS) for
diagnosis of Hypertension and to make a comparative study with the existing system. More rules
and more symptoms might be added in the future research work for more precise diagnosis.

7
Vida Groznika, Matej Guida, Aleksander Sadikova, Martin Mozinaa, Dejan Georgiev, Veronika
Kragelj, Samo Ribari, Zvezdan Pirtosek and Ivan Bratkoa [16] (2012) have authored the article
Artificial Intelligence in Medicine. This paper describes the use of expert’s knowledge in
practice and the efficiency of a recently developed technique called argument-based machine
learning (ABML) in the knowledge elicitation process. Authors are developing a neurological
decision support system to help the neurologists differentiate between three types of tremors:
Parkinsonian, essential and mixed tremor (comorbidity). The system is intended to act as a second
opinion for the neurologists and most importantly to help them reduce the number of patients in
the “gray area” that require a very costly further examination (DaTSCAN). Authors strived to
elicit comprehensible and medically meaningful knowledge in such a way that it does not come at
the cost of diagnostic accuracy. 122 patients were enrolled into the study. The classification
accuracy of the final model was 91%. Equally important, the initial and the final models were
also evaluated for their comprehensibility by the neurologists. All 13 rules of the final model
were deemed as appropriate to be able to support its decisions with good explanations. This paper
demonstrates ABML’s advantage in combining machine learning and expert knowledge. The
accuracy of the system is very high with respect to the current state-of-the-art in clinical practice
and the system’s knowledge base is assessed to be very consistent from a medical point of view.
Authors have also measured the net time involvement of the expert in building a knowledge base
for the system. Authors believe ABML saves a significant amount of expert’s time and the
experts agreed that the process itself felt very natural and stimulating.
Rajdeep Borgohain and Sugata Sanyal [17] (2012) have discussed the implementation of a rule
based expert system for diagnosing neuromuscular diseases. The proposed system is implemented
as a rule based expert system in JESS for the diagnosis of Cerebral Palsy, Multiple Sclerosis,
Muscular Dystrophy and Parkinson’s disease. In this system, the user is presented with a list of
questionnaires about the symptoms of the patients based on which the disease of the patient is
diagnosed and possible treatment is suggested. This system can aid and support the patients
suffering from neuromuscular diseases to get an idea of their disease and possible treatment for
the disease. Author’s presented an expert system for diagnosis of neuromuscular disorders, which
is used to diagnose some of the most common neuromuscular diseases i.e. Cerebral Palsy,
Muscular Dystrophy, Parkinson’s disease and Multiple Sclerosis. The system is a rule based
expert system implemented using the Java Expert System Shell using the backward chaining
mechanism. The expert system can go a great deal in supporting the decision making process of
medical professionals and also help patients with neuromuscular disorders and give an overview
of the disease and treatment options.
A.Sh.AMOOJI [18] (2013) has authored the article the application of expert systems in medical
diagnosis, which is very interesting and it creates considerable importance system of diagnosis.
The proposed system can help doctors and patients in providing decision support system,
interactive training tools and expert skills. The system constitutes part of intelligent system for
diagnosis of neurological diseases that used in one of the great hospital in Tehran. All of the
neurological diseases diagnoses have been investigated in this project. The system constitutes part
of intelligent system of diagnosis of neurological diseases. The present expert system is evolving
and increasing efficiency for all neurological diseases. Therefore the work was aimed to design a
system for the diagnosis of neurological diseases using FC (Fuzzy Cognitive) which is a
successful application of Lotfizadeh's fuzzy set theory. It is a reasonable tool for dealing with
uncertainty and imprecision and the knowledge of a physician can be modelled using an FC.
Usefulness and power of a FC depends on its knowledge base which consists of a data base and a
rule base. It is observed that the performance of a FC mainly depends on its rule base, and
optimizing the membership function distributions stored in the data base is a fine tuning process.

8
The proposed work can be further improved and lengthened for the automation of disease (cancer,
heart disease, arthritis) prediction with the help of genetic algorithm and microarray gene
expression. Real data from health care organizations and agencies needs to be collected and all
the available techniques will be compared for the optimum accuracy.
Vahid Eslami, Sadreddin Rouhani-Esfahani, Nima Hafezi-Nejad, Farshid Refaeian, Siamak
Abdi, and Mansoureh Togha[19] (2013). A computerized expert system for diagnosing primary
headache based on International Classification of Headache Disorder. The authors developed a
computerized program designed to diagnose primary headache based on international
classification of headache disorders, criteria for use by physicians. An appropriate questionnaire
was designed according to the ICHD-II criteria for all types of primary headaches and the
computerized system provided diagnosis based on the criteria. The software was tested by
analyzing 80 patients, recruited from an outpatient headache clinic, affected by primary headache.
Each patient with a unique card number was interviewed up to 15 minutes. At the end of each
day, software and neurologist diagnoses were evaluated for each patient. Of 80 patients, the
software was able to come up with correct results in 78 cases. The age of the patients ranged from
30 to 80 years old. Migraine headache accounted for 71 cases, five patients had tension type
headache, and 2 had cluster headaches; all were correctly diagnosed by software. Two cases were
not concordant with the neurologist’s diagnosis. The neurologist diagnosed these two cases as
“Medical overuse syndrome headache” and “cluster headache”, which authors software was not
able to diagnosis them. This software permitted the diagnosis of more than 97% of the patients
similar to the physician's. Authors hope this questionnaire and applying the software to diagnose
headache based on ICHD could be of help to better the diagnosis of headaches.
Atul Krishan Sharma and Stuti Gupta [20] (2014) have developed Neurological Disorder
Diagnosis System. This paper presents an account of Rule-Based Expert System (RBES) for
Neurological Disorders, i.e., Alzheimer, Parkinson, Tetanus disease, Cerebral Palsy, Meningitis,
Epilepsy, Multiple Sclerosis, Stroke, Cluster headache, Migraine, Meningitis. Neurological
disorders are mainly concerned with the malfunctioning of nervous system. Detection and
monitoring of neurological disorders at early stage is essential for quality life and facilitate
necessary diagnosis and treatment of the diagnosed disease. The focus of this paper is the
development of Neurological Disorder Diagnosis System (NDDS), which can act as home agent
to detect the disorder with accuracy to that of an expert. The system consists of a knowledge base
with some facts. On the basis of these facts the medical practitioner will fed symptoms as input.
The system by applying inference procedures will return the output as results. More than 10 types
of neurological diseases can be diagnosed and treated by the system. In this paper, Neurological
Disorder Diagnosis System (NDDS) a rule based expert system is developed which helps in
diagnosing a nervous system disorder by analyzing the observed symptoms. This expert system is
developed to be used as a consultation system for neurologists and researchers in order to reach a
decision. The system developed is different from previously developed systems is in terms of
accuracy. The system is developed to be near possible as accurate as a human expert. This system
can be made advanced to deal with uncertainty using Fuzzy Based Reasoning Techniques. Fuzzy
logic provides high accuracy for problems based on uncertainty. The system can also be
developed as touch screen systems which can act as pocket systems to detect neurological
disorders.
Maíra Junkes-Cunha, Glauco Cardozo, Christine F Boos and Fernando de Azevedo [21] (2014)
have authored Implementation of expert systems to support the functional evaluation of stand-to-
sit activity background, functional evaluation of sit-to-stand and stand-to-sit activities was often
used by physiotherapists in patients with neurological and musculoskeletal disorders. The
observation of the way these activities are executed is essential in identifying kinesiological
problems.

9
There are different methodologies used to describe the stand-to-sit activity and its evaluation is
not yet standardized, which makes the practical application of resources on clinical observation
difficult. The objective of this study is to automate the decision making process of an evaluation
protocol, developed in previous study and facilitate its utilization by professionals in the area.
The developed expert systems can support the physiotherapist in evaluating stand-to-sit activity
through a conclusion suggestion about the “level of inadequacy” for the “degree of inadequacy”
searched during its execution. Results of experts evaluation analyzed through statistical methods
indicate that the automation of protocols contributed to the standardization of the evaluation of
stand-to-sit activity and that it has application for teaching purposes.
Komal R. Hole and Prof.Vijay S.Gulhane Rule-Based Expert System for the Diagnosis of
Memory Loss Diseases [22] (2014).The paper presents a Rule-based Expert System for Memory
Loss Disease with the help of rules and facts. Also the Case-based approach is used for saving the
cases and for comparing the new case with previously saved cases. It will initially discuss
different approaches in designing of Medical Diagnosis Expert Systems with focus on all the
information about the memory loss. The different symptoms and causes of memory loss at
different age groups and the precautions for any kind of memory loss are covered. It is an attempt
to focus on some of very important diseases related to memory loss like Alzheimer’s disease,
Parkinson’s disease, Huntington’s disease, and dementia which are among the most common
types of memory loss diseases. The rule-based and case-based reasoning can be used for
designing diagnostic system. Case-based reasoning is often used where experts find it hard to
articulate their thought processes when solving problems. Expert system is a computer program
designed to model the ability of solving a problem by a human. In this dissertation an expert
system has been introduced to diagnose and suggest the treatments for the type of memory loss
diseases. Hence, first the purpose and goals of an expert system were defined and then the
relevant research reviewed. The case-based medical expert system prototype that supports
diagnosis of common diseases was developed. Several properties of this model remain to be to be
investigated. It should be tested on several more databases. Unfortunately databases are typically
proprietary and difficult to obtain. Future prospects for medical databases should be good since
some hospitals are now using computerized record system instead of traditional paper based. It
should be fairly easy to generate data for machine diagnosis.
3. CONCLUSIONS
This literature survey reveals that many researchers have applied soft computing techniques to
neurology problems. At the outset authors concluded that even after having significant research
in this field. The practical use of expert system by a neurologist in Indian hospitals is limited.
Authors would like to conduct an field survey of this aspect and would like to explore why the
use of research tools developed has not been/could not been applied in practice. This survey
would help us to understand the difficulties and limitations of such tools/software in Indian
context.
Authors would like develop an innovative solution which will suit our Indian neurologist doctors
requirements particularly remote and rural areas.
ACKNOWLEDGEMENTS
The authors would like to express gratitude to NMAM Institute of Technology, Nitte and
Basaveshwar Science College, Bagalkot for their support and funding present research. Authors

10
would like to thank the Vision Group of Science and Technology, Government of Karnataka for
sponsoring the project under K-Fist Level-1 Project Soft Computing Applications in Business and
Industry sectors (GRD – 248, 2013-14)
REFERENCES
[1] Klaus Spitzer, Andreas Thie, Louis R. Caplan and Klaus Kunze (1989), The MICROSTROKE Expert
System for Stroke Type Diagnosis, American Heart Association Print ISSN: 0039-2499. Online
ISSN: 1524-4628 doi: 10.1161/01.STR.20.10.1353,Stroke.;20:1353-1356
http://stroke.ahajournals.org/content/20/10/1353
[2]. Cruz J, Barahona P, Figueiredo A.P, Veloso M, Carvalho M. UNINOVA (1994), DARE: a
Knowledge-Based System for the Diagnosis of Neuromuscular Disorders, Hospital Egas Moniz,
Hospital Santa Maria, pp :1-12
[3]. Christophe S. Herrmann (1995) A Hybrid Fuzzy - Neural Expert System for Diagnosis, Pp
494-500, herrmann@intellektik.informatik.th-darmstadt.de
[4]. Leda Cosmides and John Tooby (1997), The Cognitive Neuroscience of Social Reasoning, The New
Cognitive Neurosciences Second Edition, A Bradford Book The MIT Press Cambridge,
Massachusetts London, England, Pp : 1259-1270
[5]. Jean-Marc Fellous, Jorge L. Armony and Joseph E. LeDoux (2000), Emotional Circuits and
Computational Neuroscience, Road Map: Connectionist Psychology Related Reading: Conditioning;
Emotion-Cognition Interactions; Sparse Coding in the Primate Cortex, Pp : 1-6
[6]. Emmanuil Marakakis, Kostas Vassilakis, Emmanuil Kalivianakis, Sifis Micheloyiannis (2005) Expert
System for Epilepsy with Uncertainty, AIML 05 Conference, 19-21 December 2005, CICC, Cairo,
Egypt http://www.cs.teicrete.gr
[7]. Blacksmiths, Mauro Adenzato and Francesca Garbarini (2006), The As If in Cognitive Science,
Neuroscience and Anthropology A Journey among Robots and Neurons, Theory & Psychology, Sage
Publications. Vol. 16(6): 747–759 DOI: 10.1177/0959354306070515 www.sagepublications.com
University of Turin
[8]. Badri Adhikari, Md. Hasan Ansari, Priti Shrestha and Susma Pant (September 25, 2008 ) “Neurology
Diagnosis System”, Module
[9]. Murad Alaqtash, Huiying Yu, Richard Brower, Amr Abdelgawad, Eric Spier and Thompson
Sarkodie-Gyan (2010), Application of Wearable Miniature Non-invasive Sensory System in Human
Locomotion Using Soft Computing Algorithm
[10]. Youssouf EL ALLIOUI and Omar EL BEQQALI (September 2010), O’Neurolog– Building an
Ontology for Neurology in Mobile Environment, IJCSNS International Journal of Computer Science
and Network Security, VOL.10, No.9,
[11]. Faran Baig, M. Saleem Khan, Yasir Noor, M. Imran, Faran Baig et al. (5 May 2011), Design Model
of Fuzzy Logic Medical Diagnosis Control System, International Journal on Computer Science and
Engineering (IJCSE) ISSN : 0975-3397 Vol. 3, Pp:2093-108
[12]. Dragan Simić, Svetlana Simić, and Ilija Tanackov (2011), An Approach of Soft Computing
Applications in Clinical Neurology E. Corchado, M. Kurzyński, M. Woźniak (Eds.): HAIS 2011,
Part II, LNAI 6679, Pp. 429–436, 2011. © Springer-Verlag Berlin Heidelberg
[13]. Rajdeep Borgohain, Sugata Sanyal (2011) Rule Based Expert System for Cerebral Palsy Diagnosis,
Pp : 1-4
[14]. Imianvan Anthony Agboizebeta and Obi Jonathan Chukwuyeni (January 2012), Cognitive Analysis of
Multiple Sclerosis Utilizing Fuzzy Cluster Means, International Journal of Artificial Intelligence &
Applications (Ijaia), Vol.3, No.1, Tripplejo2k2@Yahoo.Com
[15]. Sujit Das, Pijush Kanti Ghosh and Samarjit Kar (2012), Hypertension Diagnosis: A Comparative
Study using Fuzzy Expert System and Neuro Fuzzy System, Pp: 1-7.
[16]. Vida Groznika, Matej Guida, Aleksander Sadikova, Martin Mozinaa, Dejan Georgiev, Veronika
Kragelj, Samo Ribari, Zvezdan Pirtosek, Ivan Bratkoa(2012), Artificial Intelligence in Medicine
Contents lists available at SciVerse ScienceDirect Artificial Intelligence in Medicine journal, No. of
Pages 12
[17]. Rajdeep Borgohain, Sugata Sanyal (2012) Rule Based Expert System for Diagnosis of Neuromuscular
Disorders, Pp : 1-5

11
[18]. A.Sh. Amooji (2013) The Expert System for Diagnosis of Neurological Diseases Using Fuzzy
Cognitive, Baki Universitetinin Xəbərləri, №3 Fizika-Riyaziyyat Elmləri Seriyası 2013 İnformatika,
Pp:95-102, It_Iranian@Yahoo.Co
[19]. Vahid Eslami, Sadreddin Rouhani-Esfahani, Nima Hafezi-Nejad, Farshid Refaeian, Siamak
Abdi, And Mansoureh Togha A Computerized Expert System For Diagnosing Primary Headache
Based On International Classification Of Headache Disorder, (ICHD-II) Copyright © Eslami Et Al.;
Licensee Springer. 2013 This Article Is Published Under License To Biomed Central Ltd.
(Http://Creativecommons.Org/Licenses/By/2.0)
[20]. Atul Krishan Sharma , Stuti Gupta Neurological Disorder Diagnosis System www.ijraset.com Vol. 2
Issue VI, June 2014 ISSN: 2321-9653, International Journal for research in applied science and
engineering technology (ijraset)
[21]. Maíra Junkes-Cunha, Glauco Cardozo, Christine F Boos and Fernando de Azevedo, (2014)
Implementation of expert systems to support the functional evaluation of stand-to-sit activity, Bio
Medical Engineering On Line 2014, 13:98 http://www.biomedical-engineering-
online.com/content/13/1/98
[22]. Miss. Komal R. Hole, Prof.Vijay S.Gulhane.Rule-Based Expert System for the Diagnosis of Memory
Loss Diseases. IJISET - International Journal of Innovative Science, Engineering & Technology, Vol.
1 Issue 3, May 2014. www.ijiset.com ISSN 2348 - 7968
AUTHORS
Prof. Dr. D.K.Sreekantha is serving as Professor in the Dept. of Computer Science &
Engineering, NMAM Institute of Technology, Nitte Karnataka. His areas of interest are
Soft Computing, Expert Systems, Knowledge Management, Risk Management, Banking,
Finance and Business Applications. He has completed two funded research projects
Mr. T.M.Girish is a faculty in the Dept. of Computer Science in Basaveshwar
Science College, Bagalkot. His areas of Interest are Soft Computing and Medical
Applications
Prof. Dr. R.V.Kulkarni is the Head, Dept. of Computer Studies, CSIBER institute,
Kolhapur, 8 students have been awarded Ph.D under his guidance. He has authored more
60 papers in International journals

Knowledgebase Systems in Neuro Science - A Study

More Related Content

What's hot (18)

Similar to Knowledgebase Systems in Neuro Science - A Study (20)

More from IJSCAI Journal (20)

Recently uploaded (20)

Knowledgebase Systems in Neuro Science - A Study