Türkiye’nin toplam sağlık harcaması tahmini için trend-artık ayrıştırması temelli bir modelleme yaklaşımı

Yıl 2024, Cilt: 39 Sayı: 4, 2539 - 2550, 20.05.2024

Rezzan Yardımcı , Eşref Boğar

https://doi.org/10.17341/gazimmfd.1317413

Öz

Sağlık harcamalarının doğru tahmini, sağlık sistemleri ve politikaların sürdürülebilirliği açısından oldukça önemli bir konudur. Bu çalışma kapsamında Türkiye’nin toplam sağlık harcamasını yüksek doğrulukla tahmin etmek için trend-kalıntı ayrıştırması temelli bir model önerilmiştir. Önerilen model iki aşamalı bir tahmin prosedürüne sahiptir. İlk aşamada, polinomiyal regresyon kullanılarak sağlık harcaması zaman serisinin trendi belirlenmektedir. İkinci aşamada ise zaman serisinin trendden arındırılmış kısmını modellemek için doğrusal parametreleri en küçük kareler tahmin yöntemiyle ve doğrusal olmayan parametreleri sinir ağı algoritmasıyla optimize edilmiş bir kalıntı modeli önerilmiştir. 1999-2021 yıllarına ait sağlık harcaması verileri kullanılarak önerilen modelin performansı gri modeller, regresyon modelleri, üstel yumuşatma modelleri ve ARIMA modelleri ile karşılaştırılmıştır. 1999-2015 yıllarının eğitim 2016-2021 yıllarının ise test için kullanılmasıyla elde edilen sonuçlar, önerilen modelin diğer modellerden daha iyi modelleme ve tahmin performansına sahip olduğunu göstermektedir. Bu nedenle, 2022-2030 yılları için Türkiye’nin toplam sağlık harcaması önerilen model ile tahmin edilmiş olup 2030 yılında 2,2 trilyon TL değerine ulaşacağı öngörülmüştür.

Anahtar Kelimeler

Sağlık harcaması tahmini, zaman serisi ayrıştırması, modelleme, regresyon, sinir ağı algoritması

Kaynakça

• 1. Organization for Economic Co-operation and Development. OECD Database. https://data.oecd.org/. May 8, 2023
• 2. Mechanic D. and Rochefort D. A., Comparative Medical Systems, Annual Review of Sociology, 22 (1), 239-270, 1996
• 3. Akar S., An Investigation of The Relationship among Health Expenditures, Relative Price of Health Expenditures and Economic Growth in Turkiye, Journal of Management and Economics, 21 (1), 311-322, 2014
• 4. Turkish Statistical Institute. Health Spending Statistics 2021. https://data.tuik.gov.tr/Bulten/Index?p=Saglik-Harcamalari-Istatistikleri-2021-45728. Published December 7, 2022. Date accessed May 8, 2023.
• 5. Chaabouni S. and Abednnadher C., Modelling and forecasting of Tunisia’s health expenditures using artificial neural network and ARDL models, International Journal of Medical Science and Public Health, 2 (3), 495-504, 2013.
• 6. Guemmegne J.T., Kengwoung-Keumo J-J., Tabotabai M.A. and Singh K.P., Modeling the dynamics of the U.S. healthcare expenditure using a hyperbolastic function, Advances and Applications in Statistics, 42 (2), 95-117, 2014.
• 7. Klazoglou P. and Dritsakis N., Modeling and forecasting of us health expenditures using ARIMA models, Advances in Panel Data Analysis in Applied Economic Research, Editor: Nicholas Tsounis, Aspasia Vlachvei, Springer International Publishing, 457-472, 2018.
• 8. Özcan T. and Tüysüz F., Healthcare expenditure prediction in Türkiye by using genetic algorithm based grey forecasting models, Operations Research Applications in Health Care Management, Editor: Cengiz Kahraman, Y. İlker Topçu, Springer International Publishing, 159-190, 2018.
• 9. Wu W., Ma X., Zhang Y., Wang Y. and Wu X., Analysis of novel FAGM (1,1, ta) model to forecast health expenditure of China, Grey Systems: Theory and Application, 9 (2), 232-250, 2019.
• 10. Ramezanian M., Haghdoost A., Mehrolhassani M.H., Abolhallaje M., Dehnavieh R., Najafi B. and Fazaeli A.A., Forecasting health expenditures in Iran using the ARIMA model (2016-2020), Medical Journal of the Islamic Republic of Iran (MJIRI), 33 (25), 1-4, 2019.
• 11. Atalan A., Çınar Z. and Çınar M., A trendline analysis for healthcare expenditure per capita of OECD members, Sigma Journal of Engineering and Natural Sciences, 11 (1), 23-35, 2020.
• 12. Atalan A., Forecasting for healthcare expenditure of Türkiye covering the years of 2018-2050, Gümüşhane University Journal of Health Sciences, 9 (1), 8-16,2020.
• 13. Zheng A., Fang Q., Zhu Y., Jiang C., Jin F. and Wang X., An application of ARIMA model for predicting total health expenditure in China for 1978-2022, Journal of Global Health, 10 (1), 1-8, 2020.
• 14. Ceylan Z and Atalan A., Estimation of expenditure per capita of Türkiye using artificial intelligence techniques with genetic algorithm-based feature selection, Journal of Forecasting, 40 (2), 279-290, 2021.
• 15. Güleryüz D., Predicting health spending in Türkiye using the GPR, SCR, DT models, Acta Infologica, 5 (1), 155-166, 2021.
• 16. Jia H., Jiang H., Yu J., Zhang J., Cao P. and Yu X., Total health expenditure and its driving factors in China: A grey Theory analysis, Healthcare, 9 (2), 2021.
• 17. Kazemian M., Abdi Z. and Meskarpour-Amiri M., Forecasting Iran national health expenditures: General model and conceptual framework, Journal of Education and Health Promotion, 11 (87), 1-7, 2022.
• 18. Lou M., Prediction of hospital health expenditure based on GM (1.1) grey clustering model, 2nd International Conference on Business Administration and Data Science (BADS 2022), Atlantis Press, 1164-1169, 2023.
• 19. Song J., Zhang L., Jiang Q., Ma Y., Zhang X., Xue G., Shen X. and Wu X., Estimate the daily consumption of natural gas in district heating system based on a hybrid seasonal decomposition and temporal convolutional network model, Applied Energy, 309, 118444, 2020.
• 20. Cekim H. O., Tekin S. and Özel G., Prediction of the earthquake magnitude by time series methods along the East Anatolian Fault, Turkey, EARTH Science Informatics, 14 (3), 1339-1348, 2021.
• 21. Kaytez F., A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption, Energy, 197, 117200, 2020.
• 22. Dejamkhooy A., Dastfan A. and Ahmadyfard A., Modeling and Forecasting monstationary voltage fluctuation based on grey system theory, IEEE Transactions on Power Delivery 32 (3), 1212-1219, 2014.
• 23. Wang Z-X., A genetic Algorithm-based grey method for forecasting food demand after snow disasters: an empirical study, Natural Hazards, 68, 675-686, 2013.
• 24. Hu Y-C., Forecasting tourism demand using fractional grey prediction models with Fourier series, Annals of Operations Research, 300 (2), 467-491, 2021.
• 25. Sadollah A., Sayyaadi H., Yadav A., A dynamic metaheuristic optimization model inspired by biological nervous systems: Neural Network Algorithm, Applied Soft Computing, 71, 747-782, 2018.
• 26. Balıkçı V., Gemici Z., Taner T., Dalkılıç A.S., Forecasting natural gas demand in Istanbul by artificial neural networks method and planning of city gate stations, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (2), 1017-1027, 2024.
• 27. Sebatlı Sağlam A., Çavdur F., Earthquake intensity estimation via an artificial neural network: Examination of different network designs and training algorithms, Journal of the Faculty of Engineering Architecture of Gazi University, 37 (4), 2133-2145, 2022.
• 28. Ju-Long D., Control problems of grey systems, Systems & Control Letters, 1 (5), 288-294, 1982.
• 29. Zhang F.S., Liu F., Zhao W.B., Sun Z.A. and Jiang G.Y., Application of grey Verhulst model in middle and long term load Forecasting, Power Sytem Technology, 27 (5), 37-29, 2003.
• 30. Cui J., Liu S.F., Zeng B. and Xie N., A novel grey forecasting model and its optimization, Applied Mathematical Modelling, 37 (6), 4399-4406, 2013.
• 31. Chen P.Y. and Yu H.M., Foundation settlement prediction based on a novel NGM model, Mathematical Problems in Engineering, 2014.
• 32. Xie N.M. and Liu S.F., Discrete grey forecasting model and its optimization, Applied Mathematical Modelling, 33 (2), 1173-1186, 2009.
• 33. Xie N.M., Liu S.F., Yang Y.J. and Yuan C.Q., On novel grey forecasting model based on non-homogeneous index sequence, Applied Mathematical Modelling, 37 (7), 5059-5068, 2013.
• 34. Zang K. and Liu S.F., Linear time-varying parameters discrete grey forecasting model, Sytems Engineering-Theory & Practice, 30 (9), 1650-1657, 2010.
• 35. Wu L.Y., Wu Z.P. and Li M., Quadratic time-varying parameters discrete grey model, Sytems Engineering-Theory & Practice, 33 (11), 2887-2893, 2013.
• 36. Jiang S.Q., Liu S., Li Z.X. and Fang Z.G., Cubic time-varying parameters discrete grey forecasting model and its properties, Control and Decision, 31 (2), 279-286, 2016.
• 37. Saeid M., Zeinoddini-Meymand H., Kamel S. and Khan B., Interaction of transformer oil parameters on each other and on transformer health index using curve estimation regression method, International Transactions on Electrical Energy Systems, 2022.
• 38. Aydin G., Forecasting natural gas production using various regression models, Petroleum Science and Technology, 33 (15-16), 1486-1492, 2015.
• 39. Mutlu Gülüm N., Altuntaş S., Monitoring technological changes with statistical control charts based on patent data, Journal of the Faculty of Engineering and Architecture of Gazi University, 36 (4), 1875-1892, 2021.
• 40. Hyndman R.J., Koehler A.B., Ord J.K. and Snyder R.D., Forecasting with exponential smoothing: the state space approach., Springer, ISBN: 978-3-540-71918-2, Berlin, Germany, 2008.