Veri madenciliği yöntemleri kullanarak yoğun bakım ünitesindeki hastaların sınıflandırması

Year 2021, , 319 - 328, 20.10.2021

Emine Coşkun , Esra Gündoğan , Mehmet Kaya , Reda Alhajj

https://doi.org/10.53070/bbd.990718

Abstract

Bu çalışma Türkiye’de kullanılan yoğun bakım basamaklandırma sistemindeki problemler göz önüne alınarak hazırlanmıştır. Yoğun bakımlarda hasta bakımı, hastaların takibi, hastalıkların kontrolü ve tüm bunların maliyeti, içinde zorluklar barındıran işlemlerdir. Bu sistemin kontrolünü kolaylaştırmak bu çalışmanın en önemli amaçlarındandır. Çalışma veri madenciliği yöntemlerinin uygulanmasını içermektedir. Yoğun bakımlarda tedavi gören hastaların gerçek verileri ile çalışılmıştır. Bu veriler üzerinde basamak değerleri referans alınarak sınıflandırma ve kümeleme işlemi yapılmıştır. Çalışma aynı zamanda yoğun bakım basamak sayısının arttırılması yönünde bir öneriyi içermektedir.

Keywords

veri madenciliği, makine öğrenmesi, yoğun bakım

Supporting Institution

FÜBAP

Project Number

MF.20.20

Patent classification in intensive care unit using data mining methods

Abstract

This study has been prepared by considering the problems in the intensive care classification system used in Turkey. In intensive care unit, patient care, patient follow-up, disease control and the cost of all these are procedures that have difficulties. Facilitating the control of this system is one of the most important aims of this study. The study includes the application of data mining methods. It has been studied with real data of patients treated in intensive care units. Classification and clustering processes have been performed on these data by taking place class values as reference. The study also includes a suggestion to increase the number of intensive care classes.

Keywords

data mining, machine learning, intensive care

Project Number

MF.20.20

References

• [1] Sülekli H.E. (2019), Investigation of Factors Affecting Mortality and Length of Stay in Intensive Care Units with Data Mining Methods ANKARA: Hacettepe University.
• [2] Can M.B, Çamur E, Koru M, Özkan Ö, Rzeyeva Z. (2009) Knowledge Discovery from Datasets: Data Mining, Baskent University.
• [3] Knaus WA, Draper EA, Wagner DP, Wagner DP. (1985) APACHE II: A severity of disease classification system. Crit Care Med; 13(10):818-829.
• [4] Knaus WA, Wagner DP, Draper EA, Zimmerman JE, Bergner M et al.(1991) The APACHE III prognostic system risk prediction of hospital mortality for critical III hospitalized adults. Chest;100(6):1619- 1636.
• [5] Le Gall JR, Loirat P, Alperovitch A et al.(1984) A simplified acute physiology score for ICU patients. Crit Care Med;12(11): 975-977.
• [6] Marshall JC, Cook DJ, Christou NV, Bernard GR, Sprung CL, Sibbald WJ.(1995) Multiple organ dysfunction score: a reliable descriptor of a complex clinical outcome. Crit Care Med. ;23(10):1638-52.
• [7] Karabıyık L.(2010) Scoring Systems in Intensive Care, Journal of Intensive Care;9(3):129-143.
• [8] Ramon, J. & Fierens, D. & Guiza, F. & Meyfroidt, G. & Blockeel, H. & Bruynooghe, M. & Berghe, G. (2007). Mining data from intensive care patines. Advanced Engineering Informatics. 21. 243-256. 10.1016/j.aei.
• [9] Teker, C , Çavmak, D , Yıldırım, B , Avcı, H .(2019) UNIT COSTING IN HEALTHCARE: CASE OF A PRIVATE HOSPITAL INTENSIVE CARE UNIT. Hacettepe Journal of Health Administration 22: 97-112.
• [10] Craven DE, Kunches LM, Lichtenberg DA et al.(1998) Nosocomial infection and fatality in medical and surgical intensive care unit patients. Arch Intern Med;148:1161-8.
• [11] Akkoç İ. (2017) Effect of Baseline Datas on the Survival of Intensive Care Unit Patients, Med Bull Haseki ;55:106-10.
• [12] Coskun E, Kaya M, Özer A.B, Karabulut E,(2020) Grouping of Intensive Care Patients with Artificial Intelligence, International Congress of Artificial Intelligence in Health.
• [13] Boyrazlı, H.K., Çınar, A. (2021) “Anomaly Detection in Crowded Scenes with Machine Learning Algorithms”, DUJE, vol. 12, no.2, pp. 229- 235.
• [14] Alpay Ö. (2017) Investigation of the Effect of Economic News on Bist 100 Index by Data Mining, Fırat University, Institute of Social Sciences.
• [15] Das, S.; Dey, A.; Pal, A.; Roy, N. (2015). Applications of artificial intelligence in machine learning: review and prospect, International Journal of Computer Applications, C. 115, Sayı. 9, 31–41.
• [16] Sarıman, G .(2014) " A Study of Clustering Techniques in Data Mining: Comparison of The KMeans and K-Medoids Clustering Algorithms ". Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi C:15: S:192-202.
• [17] Amasyalı, F. M., Ersoy, O. (2008). The performance factors of clustering ensembles, IEEE 16th Signal Processing and Communication Applications Conference, SIU.
• [18] Taşçı A.E., Onan, A. (2016). "K En Yakın Komşu Algoritması Parametrelerinin Sınıflandırma Performansı Üzerine Etkisinin İncelenmesi," Akademik Bilişim , Aydın, Turkey, pp.1-8.
• [19] Gündoğan E, Kaya M,(2020) Research paper classification based on Word2vec and community discovery, International Conference on Decision Aid Sciences and Application (DASA).
• [20] E. Çakmak, B. Kaya and M. Kaya,(2019) "Point-of-Interest Recommendation in Location-Based Social Networks," 2019 1st International Informatics and Software Engineering Conference (UBMYK),pp. 1-5