Ana səhifə

Electronic physician


Yüklə 2.11 Mb.
səhifə8/8
tarix27.06.2016
ölçüsü2.11 Mb.
1   2   3   4   5   6   7   8

Table2. Experiment1: In this experiment we have used just partial domain knowledge (some rules used by cardiologists*).




Normal

PVC

Unknown

Normal

0

0

100

PVC

0

98

2

Other

0

0

200

*Rate of correct classification 74.5, Error rate 25.5%
Table3. Experiment2: In this experiment we have used the traditional similarity measures enriched by the same rules used in experiment1*.




Normal

PVC

Unknown

Normal

100

0

0

PVC

0

98

2

Other

3

86

111

*Classification rate 77.25%, Error rate 22.75%

Table4. Experiment3: in this experiment we have used the proposed fuzzy similarity measures enriched by the same rules used in the above experiments*.




Normal

PVC

Unknown

Normal

100

0

0

PVC

0

100

0

Other

0

0

200

*Classification rate 100%, Error rate 0%

4. Discussions

By applying the fuzzy similarity measures enriched by the partial domain knowledge we have obtained the best rate of correct classification (Experiment3) in which the classifier recognizes all queries. The first experiment demonstrates that the traditional experts systems have an important weakness (The rate of correct classification is just 74%) this big uncertainty is caused by: 1) Using just partial knowledge 2) The measures of ECG parameters was approximate. The second experiment prove the impact of the knowledge intensive case based reasoning comparing with the traditional experts systems approach but the traditional similarity metrics is less accurate than the proposed metrics in the last experiments. There are some works which combine between the fuzzy approach and the Case based reasoning as in which they incorporate the traditional case base paradigm by the Fuzzy Logic concepts in a flexible, extensible component-based architecture (15). Also which enforce the case based reasoning by a fuzzy logic system (16). Other researchers also introduce a fuzzy model for the representation of a CBR system (17). In our approach we combine the fuzzy sets with the traditional similarity measures function for generating an understandable response (Similar, not similar and unknown) which increases the system precision and the transparency.

There are also other works in the cardiac arrhythmias diagnosis in which they apply different approaches and intelligent techniques for the classification and automatic recognizing (1, 18). Others have used the Fuzzy approach, another researchers have used Support Vector Machines , or some hybrid models as (2, 3, 4, 18). The proposed approach as (4) recognizes all test data which prove that this original proposition ensure an accurate classification. The classifier can generate the unknown response which indicates the abnormality of the cardiac beat this criteria is very important which is original comparing with the cited approaches. The transparency of the response is ensured by recording the trace of the decision during the reasoning process. The use of separate and specialized cognitive agents ensures the flexibility of the classifier where we can integrate another agent for other cardiac arrhythmia.
5. Conclusion

In this work we have merged two CBR variants: The distributed CBR and the knowledge intensive CBR. The integration of fuzzy sets in the similarity measures helped to increase the accuracy of our system, improve the performance and decrease the learning complexity. Many original contributions was integrated in this work as: 1)The unknown response for inferring the abnormal cardiac beats 2) The combination of many optimization algorithms in the learning and the cases retrieving processes 3)The personalization of the reasoning criteria in deferent level of the classification which support the specialization of the system for deferent cases. 4) The flexibility and the scalability of the classifier are improved in the model by the multi-agent system approach.




Acknowledgements:

In this work we would like to thank so much every person who shares with us some useful information or ensuring for us his guide. We would like also to give special thanks for Pr Thomas Roth-Bergopher, Pr D. Aha and Pr Klaus-Dieter Althoff for their advises and help in ICCBR’10 Doctoral consortium.


Corresponding Author:

Abdeldjalil Khelassi,

Faculty of Sciences, Tlemcen University,

Tlemcen, Algeria

Tel: 021343286149

Fax: 021343286308.



E-mail: khelassi.a@gmail.com
References

  1. W Jiang, SG Kong - Block-Based Neural Networks for Personalized ECG Signal Classification-Neural Networks, IEEE Trans on neural networks , 2007, vol. 18, no6, pp. 1750-1761 ISSN 1045-9227.

  2. Frediric, M., and Soowhan, H.(1996), classification of cardiac Arrythmias using Fuzzy ARTMAP, IEEE Trans. Biomed. Eng. Vol. 43, no 4, Apr 1996.

  3. Lu H.L, and al 2000, An Automated ECG Classification System Based on Neuro-Fuzzy System, Computers in cardiology IEEE Trans. Biomed. Eng., Vol 48, pp. 1265- 1271, Nov 2001.

  4. Yüksel Özbay and al “Integration of type-2 fuzzy clustering and wavelet transform in a neural network based ECG classifier” Expert Systems with Applications Volume 38, Issue 1, January 2011, Pages 1004-1010

  5. Axel E. Bernal, and al “Similarity Based Classification’’ ADVANCES IN INTELLIGENT DATA ANALYSIS Lecture Notes in Computer Science, 2003, Volume 2810/2003, 187-197, DOI: 10.1007/978-3-540-45231-7_18

  6. MIT-BIH arrhythmia database [http://www.physionet.org/physiobank/database/mitdb/]

  7. J. Bensaid, 2004, Électrocardiogramme normal de l’adulte, EMC - Cardiologie-Angéiologie, Vol. 1, N. 1, pp. 2-10.

  8. Kareem S. Aggour, and al ‘’SOFT-CBR: a self-optimizing fuzzy tool for case-based reasoning’’ 5th ICCBR Pages: 5-19 2003

  9. Aamodt, E. Plaza (1994); Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches. AI Communications. IOS Press, Vol. 7: 1, pp. 39-59.

  10. Plaza Enri and al. Distributed case-based reasoning.The Knowledge engineering review2006, Vol. 20, N. 3, pp. 261-265.

  11. Agnar Aamodt “Knowledge-Intensive Case-Based Reasoning in CREEK” ADVANCES IN CASE-BASED REASONING Lecture Notes in Computer Science, 2004, Volume 3155/2004, 793-850, DOI: 10.1007/978-3-540-28631-8_1 Springer

  12. Claudio Baccigalupo and Enric Plaza “A Case-Based Song Scheduler for Group Customised Radio” ICCBR 2007.

  13. MIT-BIH arrhythmia database [http://www.physionet.org/physiobank/database/mitdb/]

  14. Pan J. et Tompkins W.J. A real time QRS detection algorithme IEEE Trans. Biomed. Eng. Vol. 23(4) pp. 230-236, (1985).

  15. Kareem S. Aggour, and al ‘’SOFT-CBR: a self-optimizing fuzzy tool for case-based reasoning’’ 5th ICCBR Pages: 5-19 2003

  16. Meijun Yang1, Qiang Shen “Reinforcing fuzzy rule-based diagnosis of turbomachines with case-based reasoning” International Journal of Knowledge-Based and Intelligent Engineering Systems Volume 12, Number 2 / 2008 page 173-181

  17. Voskoglou, M.G. Fuzzy Sets in Case-Based Reasoning; Fuzzy Systems and Knowledge Discovery, 2009. FSKD '09. Sixth International Conference on Issue 14-16 Aug. 2009 Volume: 6 page(s): 252 – 256

  18. M. Moavenian, Hamid Khorrami ‘’ A qualitative comparison of Artificial Neural Networks and Support Vector Machines in ECG arrhythmias classification’’ Expert Systems with Applications Volume 37, Issue 4, April 2010, Pages 3088-3093


Original Article
Formative evaluation of Hospital Information System According to ISO 9241-10: A case study from Iran
Narjes Mirabootalebi11, RahelehMalaekeh 2, Hamidreza Mahboobi 3

1. Instructor, Department of Health Information Technology, Hormozgan University of Medical Sciences, Bandar Abbas, Iran

2. Department of Health Information Technology and Information Management, Tehran University of Medical Science, Tehran, Iran

3. Infectious and Tropical Disease Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
elham761@gmail.com
Abstract:

Introduction: Today, different information systems are operated in hospitals in Iran to manage the admission, discharge, radiology, pharmacy, accounting and other procedures. Inappropriate HIS system causes wasting of time, consumption of more energy and increasing the costs.

Methodology: This study was conducted in Dr. Ali Shariati Hospital in Iran. We employed Isometric Formative Evaluation questionnaire to analyze the hospital information system. Also, interviewing method was applied to complete information from departments' officials.

Results: From 101 people under investigation in this study, it was agreed on 27 people (26.7%) suitability for task criteria, 46 people (45.5%) by controllability criteria, 27 people (26.7%) to suitability for individualization criteria, 69 people (68.3%) to suitability for learning criteria, 41 people (40.6%) by error tolerant criteria, 46 people (45.5%) by self description criteria, 53 people (52.5%) by conformity whit user expectation of Hospital Information System in Dr. Ali Shariati Hospital.

Conclusion: Findings indicate Hospital Information System criteria are not efficient. It is necessary either to use nationally applicable software in information system of Medical Sciences Universities across the country or different software having international standards of medical information should be used.

Bibliographic Information of this article:

[Narjes Mirabootalebi, RahelehMalaekeh, Hamidreza Mahboobi. Formative evaluation of Hospital Information System According to ISO 9241-10: A case study from Iran. Electronic Physician, 2012;4(2):572-575. Available at: http://www.ephysician.ir/2012/572-575.pdf ]. (ISSN: 2008-5842). http://www.ephysician.ir


Keywords: Hospital Information System (HIS); Formative evaluation; Standard; ISO 9241-10

© 2009-2012 Electronic Physician

1. Introduction

Information Technology (IT) has the potential to improve the quality, safety, and efficiency of health care. Diffusion of IT in health care is generally low (1). Hospital information system is one of the most common systems that is designed to support provided services by healthcare service providers. This system enhances quality of health and care data, increasingly. This computer database is used to create communication, store health information and manage information (2-4). Therefore hospital information system (HIS) is a comprehensive, integrated information system designed to manage the administrative, financial and clinical aspects of a hospital. As an area of medical informatics, the introduction of a HIS into a hospital was purported to reduce the time spent on administrative and clinical activities by electronic data processing. However, adoption has been slow, and a key concern has been that staffs will require more time to complete their work using HIS. And also Most available HIS have lots of deficiencies in data gathering, so hospital managers decided to keep their paper records and same time use HIS (5, 6).

During the past 10 years, the validity of computerized information systems for several departments has been widely reported the impact of electronic medical record systems on primary care, pediatrics, intensive care units and radiation oncology have been analyzed (7, 8, and 9), and the effects of a HIS on Medical Records department staff was undeniable (10). So far, evaluations of HIS have been undertaken focusing mainly on financial aspects or considering the patients interests. A major aspect has been neglected: The user! Nurses, physicians and other healthcare employees, working with the software, spend a lot of time each day by filling in forms, reviewing medical inspection results and handling an amount of information for administration needs (11). The aim of the\is study was to perform a formative evaluation of Hospital Information System According to ISO 9241-10 in Dr. Ali Shariati Hospital in Bandar Abbas, Iran.
2. Materials and Methods

This descriptive-analytical study used standard isometric questionnaire 9241 to investigate whether hospital information system of Dr. Ali Shariati hospital can meet user requirements and have necessary usability. Part 10 of this standard is about investigation of system's usefulness. Statistical population of study composed of all personnel in Dr. Ali Shariati hospital in Bandar Abbas. In other word, this study used Yaman formula and information was gathered by presenting and distribution of isometric standard questionnaire (suitability for the task (15 questions), self-descriptiveness (12 questions), controllability (11 questions), conformity with users expectations (8 questions), error tolerant (15 questions), suitability for Individualization(6 questions), suitability for learning(8 questions)) that its reliability and validity were approved. Concerning first part of questionnaire some questions is available in short isometric that reliability and validity of questionnaire were approved in Alipour and Shahmorad' research (12, 13). In addition, questionnaire related to hospital information system was used to better identification of hospital information system of Dr. Ali Shariatihospital. Data analysis was done using descriptive test( such as frequency and percent for qualitative data and mean and standard deviation for quantitative data) and Chi-square test by SPSS 20 software .using frequency distribution and percentage in three categories including favorable (81-100), rather favorable (51-80) and unfavorable (0-50), test mining was used to survey relations between variables.


3. Results

142 copies of the questionnaires were distributed according to number of hospital information system's users in Shariati hospital and from these questionnaires 101(71%) were returned.





Figure 1. Frequency of User View Point about Iso Metric Criteria in Shariati Hospital

Users from all departments participated in this study including: clinic, emergency, admission and medical documents, pathobiology, radiology, discharge, pharmacy, cash desk, surgery room, surgery department, gynecology division, neonatology division and labor. 101 samples were included 6 male (5.9%) and 95 female (94.1%) and the most individuals, 65 (64.3%), were under 35 years old. More than 69(68.3%) have less than 10 years of work experience. From statistical population of study, the most samples, 25 (24.7%), were related to surgery department and less one, 2 (1.9%), were related to pathobiology and pharmacy, in addition 53 (52.5%) were experts, 32 (31.7%) were associated and reminders were under advanced diploma. Concerning the comments' frequency table, there are 53(52.5%) rather favorable ideas about conformity with users expectations criteria, 27(26/7%) rather favorable idea about suitability for the task and unfavorable comments' frequency about system are including 27(26.7%) suitability for Individualization and 32(31.7%) suitability for learning. Concerning the importance level of these criteria from the view points of users, the suitability for the task criteria 84(83%) and level of error tolerant criteria 68(67.5%) were the most important ones (Figure 1).


4. Discussions

Concerning suitability of system for doing tasks and level of importance in hospital information system of Dr. Ali Shariati hospital, 27 people (26.7%) considered it as favorable system; in comparison with Alipour' research about evaluation of hospital information system of children's hospital from the view points of users according to ISO 9241-10, 69 (72.7%) were agreed to this criteria and in Homburg and Hess research titled "Evaluation of Hospital Information System of German Hospitals" this criteria obtained 72% agreement (11). Arbiter, Mr.Saeedi, considers the most important purposes of information system as bellow (14):



  • Improving the efficiency of personnel

  • Omission the repetitive and unnecessary procedures

  • Mining statics and information by faster and more accurate methods

  • Making data relation by medical engineering systems

Regarding self description criteria of system, 46 people (45.5%) considered system as unfavorable. It means that Findings of this research aren’t collinear with the same researches andindicate the weakness of Dr. Ali Shariati hospital' HIS (6). From the point of Controllability criteria of Dr. Ali Shariati hospital' HIS, 46 users (45.5) considered system as rather favorable and 54 (53.3%) as unfavorable. In comparison to research findings of Alipour et al. 46.9% of users were agreed with system. The most importance advantage of an appropriate information system is error deduction. Despite of lake of ability to control fault static data in system, according reports in form of valid and valuable statistical indexes such as bed occupancy rate and graphic charts, it can detect incorrect data easily and show the route of plotted problems (15). From the point of conformity with users expectations criteria Dr. Ali Shariati hospital' HIS, the results indicate that HIS is compliance with user requirements.

Findings of a research by Ebadi Azar et al. shows the most factors for satisfying users are ease of reading, maintenance services and ease of work with program; Finance, human and technical investments are strongly emphasized to approach to organization and user requirements (16). From the point of error tolerant criteria rate of HIS, 41 users (40.6) considered the system as rather favorable. In case of any problem in first stage system allows omitting or other action and data can be returned after 10 min but only by administration of server (17).
5. Conclusion

In summary, Users with the less computer knowledge can enter information requirements and data records. Learning this system is so easy from the view points of users and managers. Regarding this matter that an appropriate system should include these criteria in high level to meet its implementation purposes, observation is a key factor in developing a favorable information system.


Acknowledgements:

The authors thank all of the participants who cooperated in this study. We especially thank Dr. Samiyeh Karimi and Raziyeh Dehghan for Their support.


Corresponding Author:

Raheleh Malaeke

Department of Health Information Technology and Information Management,

Tehran University of Medical Science,

Tehran, Iran

Tel: +98.9173586177



E-mail: elham761@gmail.com


References

  1. Amiri M.Sadeghi E. Khosravi A.Self-Assessment of the Managers and Network Operators about the Effect of Hospital Information System on the Performance and Processes of Imam Hossein Hospital in Shahroud.HealthInformation Management Journal.2011,8(4):490-499

  2. Farzandipour M.SadoghiF.Meidani Z.Hospital Information Systems User Needs Analysis: A Vendor Survey.Journal of Health Informatics in Developing Countries.2011.147-154

  3. Indah Mohd A.Surya Sumarni H.Assessing User Satisfaction of using Hospital Information System (HIS) in Malaysia.International Conference on Social Science and Humanity.IACSIT Press, Singapore.2011.210-213

  4. OzkanS.Baykal N.Evaluation of a Hospital Information System in an International Context: Towards Implementing PB-ISAM in Turkey.The Electronic Journal of Information Systems in Developing Countries.2006,28(2):1-10

  5. SamianH.Hospital Information Management Systems.Mazandaran University of Medical Science.2005,15(49):73-80

  6. Kimaroh H.Twaakyondo M.Analysing the hindrance to the use of information and technology for improving efficiency ofhealth care delivery system in Tanzania .Tanzania Health Research Bulletin.2005,7(2):189-197

  7. Lendon K. Electronic Medical Record Systems as a basis for Computer based Patient Records. JAHIMA 1993; 64:50,52,54

  8. Hesse KA, Siebens H. Clinical Information Systems for Primary Care. Med. Inform. 2002; 9:39–59.

  9. Thiru K, Hassey A. Systematic Review of Scope and Quality of Electronic Patient Record Data in Primary Care. Br Med J. 2003;326: 1070–2

  10. Salenius SA, MargolesL.AnElectronic Medical Record System with Direct Data-Entry and Research Capabilities. Int J RadiatOncolBiolPhys 1992;24:369–76.

  11. Kai-ChristophHamborg,Brigitte Vehse, Usability Evaluation of Hospital information System.Electronic Journal of Information Systems Evaluation Volume 7 Issue 1(2004)21-30

  12. Alipour. J. S. Hoseini.Perspectives on Hospital Information System in Medical Practice.Hormozgan Medical SciencesJournal .2009.14:140-147

  13. ShahmoradiL.Evaluationof Hospital Information System based on Iso 9241-10.Tehran University of Medical Sciences Journal.2008.15:132-140

  14. Ghazi-SaeediM, Davarpanah A. Health Information Management. 1th ed. Tehran: Mahan press; 2007

  15. LippeveldT ,SauerbornR .Framework for Designing Health Information System.WHO.Geneve. 2000

  16. EbadiFardazar F, Ansari H, Zohour A, Marashi SS. Study of users' attitudes about the computerized hospital information systems (HIS). Payesh, Journal of The Iranian Institute For Health Sciences Research. 2007;6:11-18.

  17. Funeral Director.Electronic Death Registration System, System Manuals or Guides.http://vitalsupport.odh.ohio.gov/gd/Templates/Pages/odh/.aspx.(accessed 21 July 2009).



1   2   3   4   5   6   7   8


Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©atelim.com 2016
rəhbərliyinə müraciət