=Paper=
{{Paper
|id=Vol-2137/paper_15.pdf
|storemode=property
|title=Ontology Development in Patients Information System for Stroke Rehabilitation
|pdfUrl=https://ceur-ws.org/Vol-2137/paper_15.pdf
|volume=Vol-2137
|authors=Radhi Rafiee Afandi,Abduljalil Radman,Mahadi Bahari,Lailatul Qadri Zakaria,Muzaimi Mustapha,Waidah Ismail
|dblpUrl=https://dblp.org/rec/conf/icbo/AfandiRBZMI17
}}
==Ontology Development in Patients Information System for Stroke Rehabilitation==
https://ceur-ws.org/Vol-2137/paper_15.pdf
Ontology Development in Patients Information System for Stroke
Rehabilitation
*Radhi Rafiee Afandi1, Abduljalil Radman1, Mahadi Bahari2, Lailatul Qadri Zakaria3,
Muzaimi Mustapha4 and *Waidah Ismail1
1
Faculty of Science and Technology, Universiti Sains Islam Malaysia, Negeri Sembilan, Malaysia
2
Department of Information System, Universiti Teknologi Malaysia, Johor, Malaysia
3
Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Selangor, Malaysia
4
Department of Neurosciences, Universiti Sains Malaysia, Kelantan, Malaysia
ABSTRACT Ontology is a way to transfer information or knowledge about
Disability of upper limb parts is common for stroke survivors. Early im- something domain (Roussey et al., 2011). Ontology is built
plementation of well-organized upper limb treatment after stroke may re-
sult in fast recovery of upper limb functions. There are many treatments as a representative of knowledge background in a domain. In
and assessments to improve the ability in upper limb movements. However, addition, the ontology is built for enabling the effective shar-
the specialists in rehabilitation departments use patient information sys- ing of information (Fonseca, 2007). Information in ontology
tem (PIS) to store and manage all the patient’s information and assessment must be confirmed by a specialist domain, and can be extend
records. The information and assessment records of the patients usually are
obtained from various categories of assessment but it is inconsistent. This
and useful if shared with various parties. The important pro-
causes difficulties in seeking information, and needs to run all the assess- cess of developing an ontology is to identify goals and scope,
ments even those not important for the patients. In this paper, an ontology build, evaluate and document the ontology (Uschold & Grun-
in the development of PIS will be constructed to overcome the problem. inger, 1996). Related to this, ontologies can assist in PIS de-
The ontology enables semantic knowledge representation for upper limb
sign by providing a comprehensive model of the information
stroke rehabilitation. This ontology will be designed based on the Enterprise
Ontology, TOronto Virtual Enterprise Ontology, METHONTOLOGY and On- and process need for healthcare delivery (Fonseca, 2007).
tology Development 101. As a result, the proposed ontology will improve However, few researches has been done in developing an on-
the information management in PIS. tology for PIS to represent the domain area of stroke rehabil-
itation. In this paper, we will explain about the development
Keywords: Upper limb stroke, ontology, rehabilitation, Patients Information
System (PIS).
of an ontology for upper limb stroke rehabilitation in the PIS.
1 INTRODUCTION The remainder of this paper is organized as follows. Section
2 explains about methodology for the development of ontol-
Improving upper limb functions is an essential for stroke pa- ogy including the design of the ontology and as well as the
tients because upper limb is the most effective part for stroke
PIS framework. Finally, Section 3 concludes our final clari-
survivors (Ramírez et .al, 2015). The specialists in rehabili-
fications and future work.
tation departments have their responsibility to provide the
specific assessments for the stroke patients’ recovery. As we
know, all the patients’ information and assessment results are 2 METHODOLOGY
recorded to the Patients Information System (PIS). Currently, In the development of ontology, there is no specific method-
PIS still use relational databases for storing the data. The ologies (Smith et. al., 2007), as evidenced by various meth-
drawbacks of relational databases are that is shown only odologies from the literature which employed in many pro-
when request a query, and the semantic description of the da- jects. In this paper, the methodology for implementing an on-
tabase is represented using its schema only (Hohenstein, tology in PIS was adapted from (Ohgren & Sandkuhl, 2005)
1996). Result of this, ontologies have appeared as an alterna- which employs the Enterprise Ontology, TOronto Virtual En-
tive to relational databases in order to improve the perfor- terprise Ontology, METHONTOLOGY and Ontology Devel-
mance of PIS (Abas et. al., 2011). However, ontology-based opment 101. This methodology is suitable for small and me-
systems in rehabilitation department will help the specialists dium scale applications (Ohgren & Sandkuhl, 2005). The ad-
to easily manage the patient’s information and assessment vantages of this methodology are to reduce the development
records. time and effort to meet the specifications of PIS. The meth-
odology was divided into four phases: requirement analysis,
ontology development, implementation, evaluation and
* To whom correspondence should be addressed: radhirafiee@raudah.usim.my
and waidah@usim.edu.my
1
Afandi R. R et al.
maintenance. Each phase of the ontology development is 7. Management
used for the next phase. The illustration of this methodology 8. Supplementary
is shown in Fig. 1 that also shows the results of each phase. 9. Care planning
10. Score ranking
Phase 1: Requirement Analysis
This phase is to analyze the needs of developing ontologies. Next, we use the top-down approach which identifies the
In the process of developing an ontology, there are few things common class relating to the classification of objects that de-
to note: fined before. This ontology is divided into six main catego-
1.What is a domain that ontology used? ries: specialist, patients, proforma, session, therapy, and fol-
2.Why this ontology should be built? low up.
3.What are the problems that exist in the selected domain?
4.Who will use this ontology? Phase 2: Ontology Development
5.What is the scope of ontology? This Ontology will be developed by using Protégé version
5.2.0. This Protégé is an open source and developed by the
Stanford Center for BioMedical Informatics Research. It was
supported by the National Institute of General Medical Sci-
ences. In this platform, we will build up a domain and appli-
cation model based on the ontology knowledge. Protégé
made it possible to build an ontology in Ontology Web Lan-
guage (OWL) with an efficient and easy way, and to access,
edit and use the existing ontology (Lozano-Rubi et. al., 2014
& Knublauch et. al., 2004). The steps taken to develop the
ontology is as follows:
1. Create classes: all classes or subclasses are under the Thing
Fig. 1. Ontology development methodology [12].
class in Protégé. This will show the class hierarchy for each
category that was identified during the process of defining the
After analysing the Clinical Data Proforma from Hospital
concepts inserted in the Protégé.
Universiti Sains Malaysia (HUSM), the objects to build up
2. Create properties: the properties are divided into object
the ontology are created. Table 1 shows 10 tangible objects
properties and data properties:
were created based on HUSM’s Proforma form. These ob-
a. Object properties: connect between two objects or in-
jects were set as individuals or objects that serve as the basis
stances.
of determining the classification in ontology development.
b. Data properties: connect one instance of the literal kind
of data Extension Markup Language (XML) schema or the
The methodology to define the concepts and relationships is
Resource Description Framework (RDF) literal attribute
a middle-out approach which began with the important con-
owned by the object or instance.
cepts and made precise generalizations or specifications. The
3. Create Individual: lists of tangible objects were inserted in
basic concept should be identified first and used to drive the
the Protégé as individual. The number of tangible objects in-
development process of ontology (Domingue & Anutariya,
crease from time to time based on the data given by HUSM.
2008). This begins with a look at the common features for the
4. Insert the literal value for each individual.
tangibles as a function of the object to form class and rela-
tionship between classes. To facilitate the definition of class,
Fig. 2 shows the design of the ontology for the whole part of
things are divided into small groups, so the similar character-
classes and the tangibles. It shows the relation of that classes
istics of the things are studied carefully. Accordingly, the
with the other classes as well as the relation between individ-
things were placed in the same class according to the similar
uals inside each class and other individuals. Based on this de-
characteristics.
sign, the specialist (i.e. physician, therapist, and nurse) have
an access into PIS to monitor and insert the patients’ infor-
Table 1. Tangibles in Proforma
mation based on the assessment results.
No. Things
1. Physician
2. Therapist In proforma, the initial information of the patients is inserted
3. Nurse during the first day of their admission in the rehabilitation
4. Minimum data department. This information is regarded the minimum data.
5. Clinical The main part of this ontology design is the session of the
6. Diagnosis
2
Ontology Development in Patients Information System for Stroke Rehabilitation
Fig. 2. Ontology design for PIS
patients for their weekly assessment (i.e. therapy and follow proper classification or category for each object, including
up assessments). the relationship between the concepts of the ontology. Feed-
back from the users on the prototype will be recorded for im-
Therapy assessment includes the class of clinical, diagnosis, proving the ontology design.
management and related information data from the assess-
ment that run by each stroke patients. While for follow up Phase 3: Implementation (Developing a User-interface for
assessment, patients need to come back to the rehabilitation Testing)
department in order to run other assessments that include as- The analysis will be conducted based on PIS prototype
sessment for care planning and score ranking. through the testing made by users. The prototype system is
needed to send the user's query in SPARQL form. PIS proto-
In addition, the validation and improvement of this ontology type will be develop to test and verify the usability and vali-
is needed. This process is correcting errors in the classifica- date the objectives and scope of the designed ontology are
tion and the object based on the requirements (i.e. Clinical achieved. PIS is a web-based application and it will be de-
Data Proforma) given by the domain experts. The relation- velop using PHP language and JavaScript. To access the in-
ship between the class and individual also needs to be revised formation on this ontology is via RDF/XML format. There-
so that there is no error in reasoning process. Improvements fore, some of the Javascript semantics libraries will be used
are also possible if there are any updates in the list of objects (i.e. jOW and jQuery) to allow an access to the RDF/XML
that are registered as tangible objects in Proforma. Among the file format. In addition, Netbeans Integrated Development
possible errors is the literal value of individual properties Environment (IDE) will be used as a platform for developing
data. The domain expert is required to validate the inserted the prototype interface. The proposed ontology will be stored
data so the reliability of ontology development is high. in RDF/XML file format. Fig. 3 shows the framework of the
PIS prototype that will be created based on the guidance of
For the ontology testing and maintenance, the tests will be previous studies about SPARQL query processing (Samreen
performed by the user and based on the PIS prototype. Result et. al., 2013 & Malik et. al., 2012) and OWL files (Lozano-
of this process can predict the perfection of the development Rubi et. al., 2014).
of upper limb stroke ontology. This is crucial for ensuring a
3
Afandi R. R et al.
other categories. Besides, it shows the instances of the clini-
cal data that is “Handedness” and “Flu vaccination”.
Phase 4: Evaluation and Maintenance
The testing process towards the perfection and usability of
ontology data will be using PIS prototype. The prototype will
be tested and evaluated by 10 specialists in Rehabilitation De-
partment at HUSM.
3 CONCLUSION AND FUTURE WORK
We have presented an ontology design for implementation in
PIS at Rehabilitation Department, HUSM. The ontology in-
cludes the key factors acknowledged through a requirement
study and also review the previous research paper. With the
proposed ontology in this paper, we aim to facilitate the spe-
cialists in order to manage the information including the pa-
tients’ assessments. We also aim at sharing and integrating
Fig. 3. PIS prototype framework. this knowledge with other ontologies. As a future work, we
Fig. 4. The interface of the category in therapy assessment
The first interface design of the PIS system prototype is will continue the implementation and evaluation of the pro-
shown in Fig. 4. It shows the classification of the category posed ontology in PIS. This evaluation will deal with the spe-
that is created based on the tangible objects. These tangible cialists to validate the usability of the PIS in stroke rehabili-
objects (i.e. Clinical, Diagnosis, Management, and Related tation department.
Information) are placed under the therapy assessment cate-
gory. The information related to the clinical data displays a
therapy assessment and the relation of this category with
4
Ontology Development in Patients Information System for Stroke Rehabilitation
ACKNOWLEDGEMENT Lozano-Rubí R., Pastor X., and Lozano E. (2014). OWLing Clinical Data
Authors wish to thank all participants who participated in the Repositories with the Ontology Web Language. JMIR Med. Informatics,
study. This research is funded by NEWTON-UNGKU 2(2):1-17.
OMAR FUND via international grant research with code Malik S. K. and Rizvi S. (2012). A Framework for SPARQL Query Pro-
USIM/INT-NEWTON/FST/IHRAM/053000/41616. Finally, cessing, Optimization and Execution with Illustrations. Int. J. Comput.
thanks to Hospital Universiti Sains Malaysia (HUSM) for the Inf. Syst. Ind. Manag. Appl. 4:208–218.
contributions in this project. Musen M. A. (1999). Scalable software architectures for decision support.
Methods of information in medicine. 38(4-5):229–38.
REFERENCES Ohgren A., and Sandkuhl K. (2005). Towards a Methodology for Ontology
Development in Small and Medium-Sized. Engineering, no. chapter 2,
Abas H.I., Mohd. Yusof M., and Mohd Noah S.A. (2011). The application
pp. 369–376.
of ontology in a clinical decision support system for acute postoperative
Ramírez-Fernández C., García-Canseco E., Morán A., Gómez-Montalvo J.
pain management. International Conference on Semantic Technology
(2015). Ontology-based Design Model of Virtual Environments for Up-
and Information Retrieval, STAIR 2011.
per Limb Motor Rehabilitation of Stroke Patients. Proceedings of the
Avison D., and Young T., (2007). Time to rethink health care and ICT, Com-
3rd 2015 Workshop on ICTs for improving Patients Rehabilitation Re-
mun ACM;50(6):69–74.
search Techniques - REHAB'15.
Berg M. (2003). The search for synergy: interrelating medical work and pa-
Roussey, C., Pinet, F., Kang, M. & Corcho, O. (2011). Chapter 2: An Intro-
tient care information systems. Methods Inf Med, 42(4):337–44.
duction to Ontologies and Ontology Engineering Catherine. Dlm.
Domingue J. and Anutariya C. (2008). The Semantic Web. 3rd Asian Se-
Falquet, G., Métral, C., Teller, J., Tweed, C. (pnyt). Ontologies in Urban
mantic Web Conference, ASWC, Bangkok, Thailand. Germany:
Development Projects, hlm. 9-38. London: Springer-Verlag.
Springer-Verlag Berlin Heidelberg.
Saad S., Salim N., Zainal H., and Muda Z. (2011). A process for building
Fonseca F. (2007). The double role of ontologies in information science re-
domain ontology: An experience in developing Solat ontology. Proceed-
search. Journal of the Association for Information Science and Technol-
ings of the 2011 International Conference on Electrical Engineering and
ogy; 58(6):786–93.
Informatics, ICEEI 2011.
Gennari J., Musen M., Fergerson R., Grosso W., Crubezy M., Eriksson H.,
Samreen S., Mirza J. S. and Rasheed A. (2013). RDF and OWL Ontology
Noy N., and Tu S. (2003). The evolution of Protégé: an environment for
Building of Web Applications. Res. J. Inf. Technology, 5(4):109-117.
knowledge-based systems development. International Journal of Human
Smith B., Ashburner M., Rosse C., Bard J., Bug, W. (2007). The OBO
Computer Studies, 58(1):89–123.
Foundry: coordinated evolution of ontologies to support biomedical data
Hammond W. E., Cimino J. J. (2006). Standards in Biomedical Informatics.
integration. Nature Biotechnology. 25(11):1251–5.
In: Shortliffe EH, editor. Biomedical Informatics: Computer Applica-
Smith B., Kusnierczyk W., Schober D., Ceusters W. (2006). Towards a Ref-
tions in Health Care and Biomedicine. New York, NY: Springer.
erence Terminology for Ontological Research and Development in the
Hohenstein, U. (1996). Bridging the gap between OWL and relational data-
Biomedical Domain. CEUR, 222:57– 65.
bases. ECOOP ’96 — Object-Oriented Programming, 1098, 398–420.
Uschold, M. & Gruninger, M. 1996. Ontologies: Principles, Methods and
Hong K. and Saver J. (2009). Quantifying the Value of Stroke Disability
Application. Knowledge Engineering Review, 11(2):93-136.
Outcomes: WHO Global Burden of Disease Project Disability Weights
Whyte J. John L. Melvin N. C. (1996). Functional Evaluation of Stroke Pa-
for Each Level of the Modified Rankin Scale. Stroke, 40(12):3828–
tients. (N. Chino & J. L. Melvin, Eds., 2016). Tokyo: Springer Japan.
3833.
http://doi.org/10.1007/978-4-431-68461-9.
Knublauch H., Fergerson R., Noy N.F., and Musen M.A. (2004). The
Zhao C. and Zhang L. (2013). Research of Information Presentation for Elec-
Protege OWL Plugin: An Open Development Environment for Seman-
tronic Medical Record Based on Ontology. In 2013 6th International
tic Web Applications”. Proceeding of the 3rd Int. Semant. Web Conf.
Conference on Information Management, Innovation Management and
(ISWC 2004), pp. 229-243.
Industrial Engineering, pages 489–492.
Kuziemsky C., Lau F. (2007). A four-stage approach for ontology-based
health information system design. 11th Conference on Artificial Intelli-
gence in Medicine (AIME).
5