Abstract
Klinik Destek Sistemleri (KDS) sağlık
hizmet kalitesini akıllı bir seçimle hekimlere bilgi sunarak arttırmayı amaçlar.
Klinisyenler tanı koyma sürecindeki gözden kaçmaların önüne geçmek ve tanıyı
gözden geçirmek için KDS sistemini kullanırlar. Bu sistemler hasta verilerini
ve öyküsünü inceleyerek tanı sürecinde hekimlere yardımcı olmak için
oluşturulmuştur. Aksiyon kuralları bir tahminden başka bir tahmin için uyumlu
bir tahmin yapabilme ve strateji geliştirme yöntemleridir. Bu çalışmamız
aksiyon kurallarında nesne-odaklı yeni bir algoritma kullanımını içerir. Bu
algoritma elde edilen aksiyon kurallarını önce “aşağıdan yukarı” stratejisi ile
başlatır, sonra uzman sistem yardımıyla nesne odaklı veri madeni oluşumunu
sağlar. İleri safhasında ise seçilen hastaların verilerini ayrıştırıp en üstün nitelikteki
test verilerini çıkarır. Sonuç olarak elde edilen verileri hastanın öyküsü ve fiziksel
muayene bulguları ile karşılaştırır. Bu sistem nesne odaklı olarak tasarlanmış
ve diğer sistemlere göre daha hızlı çözümleyici ve güçlüdür. Bu nesne odaklı yapıda
işlev yapan algoritma daha kısa sürede ve tekrarlamalar olmadan sonuca ulaşmayı
sağlar. Hekimler tam isabetli olmayan bir tanıyı aksiyon kuralları algoritması yardımı ile yeniden sınıflandırılarak
hastaya tanı koymada ve hastalık yönetme sürecinde önemli bir gelişme
sağlayabilir.
Abstract:
Clinical Decision Support Systems (CDSS) can be
used ingeniously to assist clinicians and health care providers make clinical
decisions. Physicians and decision makers utilize a CDSS to make better
diagnoses and to revisit it in terms of refining final outcome. Action rules
are defined and extracted patterns that they can predict coherent and congruent
strategies from one state to another. This study is a new algorithm for action
rules based on object-orientation. It initiates as a “bottom-up breath-first strategy” and later it
constitutes object-driven data with an expert system. Then it mines the
patents’ data selected with the highest values of attributes to get a desired
effect on a decision feature. This object-driven strategy, where the redundancy
is eliminated, is faster than the classical strategy for identifying action
rules. Action rules can be implemented as an assistant for physicians as well
as for impartial diagnoses to be validated by reclassification.
References
- Ras ZW, Tsa LS. Discovering extended action-rules (System DEAR). Intelligent Information Systems. Proceedings of the IIS' 2003 Symposium, Advances in Soft Computing, Springer; 2003; 6(8) p. 293-300.
- Ras ZW, Dardzinska A. Action rules discovery - a new simplified strategy. Foundations of Intelligent Systems, Esposito F. et al. (Eds.), LNAI, No. 4203 Springer. 2006; 445-453.
- Ras ZW, Tzacheva A, Tsay, LS, Gurdal O. Mining for interesting action rules. Proceedings of IEEE/WIC/ACM International Conference on Intelligent Agent Technology, Compiegne University of Technology, France. 2005 Sep 19-22; Compeigne, France p.187-93.
- Gürdal O, Dardzinska A. New Approach to Clinical Medicine by Action Rules. Int. Journal of Development Research, 2017; 7(1): 11032-9.
- Dardzinska A. Action rules mining. Studies in Computational Intelligence, Springer Publication, Springer-Verlag, Berlin: Springer-Verlag; 2013.
- Agrawal R, Imielinski, T, Swami A. Mining association rules between sets of items in large databases. In: Buneman P, Jajodia S, editors. Proceedings of ACM SIGMOD International Conference on Management of data; 1993 May 25-28; Washington DC. New York: ACM; 1993; p. 207-16.
- Pawlak Z.. Information systems - theoretical foundations. Information Systems Journal. 1981 6, 205-218.
- Ras ZW, Dardzinska A. Action Rules Discovery without pre-existing classification rule. In: Chien-Chung C, Grzymala-Busse JW, Ziarko, WP, editors. Proceedings of 6th International Conference on Rough Sets and Current Trends in Computing; 2008 Oct 23-25; Akron, Ohio.p Berlin: Springer-Verlag, 2008. p. 181-90.
- Hajja A, Ras ZW, Wieczorkowska A. Hierarchical object-driven action rules. J. Intell. Inf. Syst. 2014; 42 (2): 207-32.
- Geffner H, Wainer J. Modeling action, knowledge and control. In:Prade H, editor. ECAI 98: Proceedings of 13th European Conference on Artificial Intelligence; 1998 August 23-28; Brighton UK. New York: Wiley-Blackwell; 1998 p. 532–6.
- Adomavicius G, Tuzhilin A. Discovery of actionable patterns in databases: The action hierarchy approach. Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining; 1997 Aug 14-17. The AAAI Press; 1997. p. 111-4.
- Tsay L-S, Ras ZW. Action rules discovery: system DEAR2, method and experiments. Journal of Experimental & Theoretical Artificial Intelligence, 2005; 17(1–2): 119–28.
- Bobrowski, L. 1992 HEPAR: Computer system for diagnosis support and data analysis. Prace IBIB 31, Institute of Biocybernetics and Biomedical Engineering, Polish Academy of Sciences, Warsaw, Poland.
- http://logic.mimuw.edu.pl/~rses/about.html.
Abstract
References
- Ras ZW, Tsa LS. Discovering extended action-rules (System DEAR). Intelligent Information Systems. Proceedings of the IIS' 2003 Symposium, Advances in Soft Computing, Springer; 2003; 6(8) p. 293-300.
- Ras ZW, Dardzinska A. Action rules discovery - a new simplified strategy. Foundations of Intelligent Systems, Esposito F. et al. (Eds.), LNAI, No. 4203 Springer. 2006; 445-453.
- Ras ZW, Tzacheva A, Tsay, LS, Gurdal O. Mining for interesting action rules. Proceedings of IEEE/WIC/ACM International Conference on Intelligent Agent Technology, Compiegne University of Technology, France. 2005 Sep 19-22; Compeigne, France p.187-93.
- Gürdal O, Dardzinska A. New Approach to Clinical Medicine by Action Rules. Int. Journal of Development Research, 2017; 7(1): 11032-9.
- Dardzinska A. Action rules mining. Studies in Computational Intelligence, Springer Publication, Springer-Verlag, Berlin: Springer-Verlag; 2013.
- Agrawal R, Imielinski, T, Swami A. Mining association rules between sets of items in large databases. In: Buneman P, Jajodia S, editors. Proceedings of ACM SIGMOD International Conference on Management of data; 1993 May 25-28; Washington DC. New York: ACM; 1993; p. 207-16.
- Pawlak Z.. Information systems - theoretical foundations. Information Systems Journal. 1981 6, 205-218.
- Ras ZW, Dardzinska A. Action Rules Discovery without pre-existing classification rule. In: Chien-Chung C, Grzymala-Busse JW, Ziarko, WP, editors. Proceedings of 6th International Conference on Rough Sets and Current Trends in Computing; 2008 Oct 23-25; Akron, Ohio.p Berlin: Springer-Verlag, 2008. p. 181-90.
- Hajja A, Ras ZW, Wieczorkowska A. Hierarchical object-driven action rules. J. Intell. Inf. Syst. 2014; 42 (2): 207-32.
- Geffner H, Wainer J. Modeling action, knowledge and control. In:Prade H, editor. ECAI 98: Proceedings of 13th European Conference on Artificial Intelligence; 1998 August 23-28; Brighton UK. New York: Wiley-Blackwell; 1998 p. 532–6.
- Adomavicius G, Tuzhilin A. Discovery of actionable patterns in databases: The action hierarchy approach. Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining; 1997 Aug 14-17. The AAAI Press; 1997. p. 111-4.
- Tsay L-S, Ras ZW. Action rules discovery: system DEAR2, method and experiments. Journal of Experimental & Theoretical Artificial Intelligence, 2005; 17(1–2): 119–28.
- Bobrowski, L. 1992 HEPAR: Computer system for diagnosis support and data analysis. Prace IBIB 31, Institute of Biocybernetics and Biomedical Engineering, Polish Academy of Sciences, Warsaw, Poland.
- http://logic.mimuw.edu.pl/~rses/about.html.
Details
| Subjects | Clinical Sciences |
|---|---|
| Journal Section | Araştırma Makaleleri |
| Authors | |
| Publication Date | December 1, 2017 |
| Submission Date | August 8, 2017 |
| Acceptance Date | August 20, 2017 |
| Published in Issue | Year 2017 Volume: 24 Issue: 4 |
Süleyman Demirel Üniversitesi Tıp Fakültesi Dergisi/Medical Journal of Süleyman Demirel University is licensed under Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International.