Research Article
BibTex RIS Cite

Ağaç Tabanlı Regresyon Modelleri Kullanılarak Sağlık Göstergeleri ile İnsani Gelişme Endeksinin Tahmini

Year 2021, Volume: 11 Issue: 2, 410 - 420, 31.12.2021
https://doi.org/10.37094/adyujsci.895084

Abstract

Makine öğrenmesi, bilgisayar yardımıyla geçmişteki bilgileri kullanarak matematiksel ve istatistiksel işlemlerle çıkarımlar elde eden ve gelecekteki olaylar hakkında tahmin yürütülmesi modelleme yapılmasına imkân veren bir yapay zekâ alanıdır. Bu çalışmada 191 ülkenin 2014-2018 yıllarında sağlık göstergelerinin insani gelişim endeksi (İGE) üzerindeki etkisini belirlemek ve tahmin yapmak için makine öğrenmesi yöntemlerinden ağaç tabanlı regresyon modelleri kullanılmıştır. Ağaçlı tabanlı regresyon modelleri model performans kriterlerine göre karşılaştırıldığında en iyi modelin en yüksek R2 = 0.9962 ve en küçük RMSE = 0.0094 değeri ile gradyan artırma model olduğu bulunmuştur. Gradyan artırma model ile İGE indeksine en fazla etki eden 3 değişken sırasıyla: kişi başına cari sağlık harcaması, doktorların sayısı ve hemşireler ile ebelerin sayısı olarak bulunmuştur. İGE değeri en yüksek olan 10 ülke ve Türkiye seçilerek gradyan artırma model ile 2018-2019 yılları için İGE değerleri tahmin edilmiştir. Gradyan artırma yöntemi ile İGE değeri en iyi tahmin edilen ülkeler sırasıyla Hollanda, İsveç, Norveç, İzlanda, Danimarka, Türkiye, İrlanda, Almanya, Avustralya ve Çin şeklindedir.

References

  • [1] Alpaydın, E., Yapay öğrenme, Boğaziçi Üniversitesi Yayınevi. 2011.
  • [2] Alonso, D.H., Wernick, M.N., Yang, Y.Y., Germano, G., Berman, D.S., Slomka, P., Prediction of cardiac death after adenosine myocardial perfusion SPECT based on machine learning, Journal of Nuclear Cardiology, 26(5), 1746-1754, 2019.
  • [3] Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., and Chouvarda, I., Machine learning and data mining methods in diabetes research, Computational and Structural Biotechnology Journal, 15, 104-116, 2017.
  • [4] Yakut, E., Gündüz, M., and Demirci, A., Comparison of classification success of human development index by using ordered logistic regression analysis and artificial neural network methods, Journal of Applied Quantitative Methods, 10(3), 15-34, 2015.
  • [5] Zhang, B., Ren, J., Cheng, Y., Wang, B., Wei, Z., Health data driven on continuous blood pressure prediction based on gradient boosting decision tree algorithm, IEEE Access, 7, 32423-32433, 2019.
  • [6] Konig, H.H., Leicht, H., Bickel, H., Fuchs, A., Gensichen, J., Maier, W., Mergenthal, K., Riedel-Heller, S., Schafer, I., Schon, G., Weyerer, S., Wiese, B., van den Bussche, H., Scherer, M., Eckardt, M., Grp, M.S., Effects of multiple chronic conditions on health care costs: an analysis based on an advanced tree-based regression model, BMC Health Services Research 13(1), 1-13, 2013.
  • [7] Rençber, Ö.F., Sinan, M., Reclassification Of Countries According To Human Development Index: An Application With Ann And Anfis Methods, Business & Management Studies: An International Journal, 6(3), 228-252, 2018.
  • [8] Yakut, E., Korkmaz, A., İnsani Gelişmişlik Endeksinin Karar Ağacı Algoritmaları ile Modellenmesi: BM’de Bir Uygulama 2010-2017 Dönemi, Anadolu Üniversitesi Sosyal Bilimler Dergisi, 20(2), 65-84, 2020.
  • [9] dos Santos, C.B., Pilatti, L.A., Pedroso, B., Carvalho, D.R., Guimaraes, A.M., Forecasting the human development index and life expectancy in Latin American countries using data mining techniques, Ciência & Saúde Coletiva, 23(11), 3745-3757, 2018.
  • [10] Hu, L., Li, L., Ji, J., Sanderson, M., Identifying and understanding determinants of high healthcare costs for breast cancer: a quantile regression machine learning approach, BMC Health Services Research, 20(1), 1066, 2020.
  • [11] Saboo, A., Parakh, R., Trivedi, P., Potdar, M., A Comparative Study of Artificial Neural Networks and Multiple Linear Regression by Predicting Human Development Index, International Journal of Scientific & Engineering Research, 7(9), 424-428, 2016.
  • [12] Çoşar, K., OECD sağlık verilerinin veri madenciliği yöntemleri ile analizi, Marmara University, İstanbul, 2020.
  • [13] Breiman, L., Friedman, J., Olshen, R., Stone, C., Classification and regression trees, Chapman and Hall/CRC, 1998.
  • [14] Therneau, T.M., Atkinson, E.J., An introduction to recursive partitioning using the RPART routines, Technical report Mayo Foundation, 1997.
  • [15] Friedman, C., Sandow, S., Utility-based learning from data, Machine learning & pattern recognition series, Boca Raton: Chapman & Hall/CRC, 397 pages, 2011.
  • [16] Liaw, A., Wiener, M., Classification and regression by random Forest, R News, 2(3), 18-22, 2002.
  • [17] Chen, T., Guestrin, C., Xgboost: A scalable tree boosting system, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016.
  • [18] Friedman, J. H., Greedy function approximation: a gradient boosting machine, Annals of Statistics, 1189-1232, 2001.
  • [19] Friedman, J.H., Stochastic gradient boosting, Computational Statistics & Data Analysis, 38(4), 367-378, 2002.
  • [20] Ridgeway, G., Generalized boosted models: A guide to the gbm package, Update, 1(1), 2007, 2007.
  • [21] URL-1, https://data.worldbank.org/ Erişim tarihi 25.12.2020.
  • [22] URL-2, http://hdr.undp.org/en/content/human-development-index-hdi Erişim tarihi 25.12.2020
  • [23] Şeker, Ş.E., Eşmekaya, E., Eksik verilerin tamamlanması (imputation), YBS Ansiklopedi, 4, 10-17, 2017.
  • [24] Uğuz, S., Makine Öğrenmesi Teorik Yönleri ve Python Uygulamaları ile Bir Yapay Zeka Ekolü, Nobel, Ankara, 2019.
  • [25] Uygur, S., Yıldırım, F., Cinsiyete bağlı insani gelişme endeks yaklaşımları: Türkiye örneği, Tisk Akademi, 30-59, 2011.

Prediction of Human Development Index with Health Indicators Using Tree-Based Regression Models

Year 2021, Volume: 11 Issue: 2, 410 - 420, 31.12.2021
https://doi.org/10.37094/adyujsci.895084

Abstract

Machine learning is a field of artificial intelligence that allows computers to predict and model future events by making inferences from past information with mathematical and statistical operations. In this study, we used tree-based regression models, one of the machine learning methods, to determine and predict the effect of health indicators of 191 countries on the human development index (HDI) between 2014 and 2018 years. When tree-based regression models were compared according to model performance criteria, it was found that the best model was the gradient boosting model with the highest R2 = 0.9962 and the smallest RMSE = 0.0094. With the gradient boosting model, the three most important variables to HDI are; current health expenditure per capita, physicians and nurses, and midwives, respectively. By selecting the ten countries with the highest HDI values and Turkey, HDI values were estimated for 2018-2019 with a gradient boosting model. The countries for which HDI values are best predicted by the gradient boosting method are Netherlands, Sweden, Norway, Iceland, Denmark, Turkey, Ireland, Germany, Australia, and China.

References

  • [1] Alpaydın, E., Yapay öğrenme, Boğaziçi Üniversitesi Yayınevi. 2011.
  • [2] Alonso, D.H., Wernick, M.N., Yang, Y.Y., Germano, G., Berman, D.S., Slomka, P., Prediction of cardiac death after adenosine myocardial perfusion SPECT based on machine learning, Journal of Nuclear Cardiology, 26(5), 1746-1754, 2019.
  • [3] Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., and Chouvarda, I., Machine learning and data mining methods in diabetes research, Computational and Structural Biotechnology Journal, 15, 104-116, 2017.
  • [4] Yakut, E., Gündüz, M., and Demirci, A., Comparison of classification success of human development index by using ordered logistic regression analysis and artificial neural network methods, Journal of Applied Quantitative Methods, 10(3), 15-34, 2015.
  • [5] Zhang, B., Ren, J., Cheng, Y., Wang, B., Wei, Z., Health data driven on continuous blood pressure prediction based on gradient boosting decision tree algorithm, IEEE Access, 7, 32423-32433, 2019.
  • [6] Konig, H.H., Leicht, H., Bickel, H., Fuchs, A., Gensichen, J., Maier, W., Mergenthal, K., Riedel-Heller, S., Schafer, I., Schon, G., Weyerer, S., Wiese, B., van den Bussche, H., Scherer, M., Eckardt, M., Grp, M.S., Effects of multiple chronic conditions on health care costs: an analysis based on an advanced tree-based regression model, BMC Health Services Research 13(1), 1-13, 2013.
  • [7] Rençber, Ö.F., Sinan, M., Reclassification Of Countries According To Human Development Index: An Application With Ann And Anfis Methods, Business & Management Studies: An International Journal, 6(3), 228-252, 2018.
  • [8] Yakut, E., Korkmaz, A., İnsani Gelişmişlik Endeksinin Karar Ağacı Algoritmaları ile Modellenmesi: BM’de Bir Uygulama 2010-2017 Dönemi, Anadolu Üniversitesi Sosyal Bilimler Dergisi, 20(2), 65-84, 2020.
  • [9] dos Santos, C.B., Pilatti, L.A., Pedroso, B., Carvalho, D.R., Guimaraes, A.M., Forecasting the human development index and life expectancy in Latin American countries using data mining techniques, Ciência & Saúde Coletiva, 23(11), 3745-3757, 2018.
  • [10] Hu, L., Li, L., Ji, J., Sanderson, M., Identifying and understanding determinants of high healthcare costs for breast cancer: a quantile regression machine learning approach, BMC Health Services Research, 20(1), 1066, 2020.
  • [11] Saboo, A., Parakh, R., Trivedi, P., Potdar, M., A Comparative Study of Artificial Neural Networks and Multiple Linear Regression by Predicting Human Development Index, International Journal of Scientific & Engineering Research, 7(9), 424-428, 2016.
  • [12] Çoşar, K., OECD sağlık verilerinin veri madenciliği yöntemleri ile analizi, Marmara University, İstanbul, 2020.
  • [13] Breiman, L., Friedman, J., Olshen, R., Stone, C., Classification and regression trees, Chapman and Hall/CRC, 1998.
  • [14] Therneau, T.M., Atkinson, E.J., An introduction to recursive partitioning using the RPART routines, Technical report Mayo Foundation, 1997.
  • [15] Friedman, C., Sandow, S., Utility-based learning from data, Machine learning & pattern recognition series, Boca Raton: Chapman & Hall/CRC, 397 pages, 2011.
  • [16] Liaw, A., Wiener, M., Classification and regression by random Forest, R News, 2(3), 18-22, 2002.
  • [17] Chen, T., Guestrin, C., Xgboost: A scalable tree boosting system, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016.
  • [18] Friedman, J. H., Greedy function approximation: a gradient boosting machine, Annals of Statistics, 1189-1232, 2001.
  • [19] Friedman, J.H., Stochastic gradient boosting, Computational Statistics & Data Analysis, 38(4), 367-378, 2002.
  • [20] Ridgeway, G., Generalized boosted models: A guide to the gbm package, Update, 1(1), 2007, 2007.
  • [21] URL-1, https://data.worldbank.org/ Erişim tarihi 25.12.2020.
  • [22] URL-2, http://hdr.undp.org/en/content/human-development-index-hdi Erişim tarihi 25.12.2020
  • [23] Şeker, Ş.E., Eşmekaya, E., Eksik verilerin tamamlanması (imputation), YBS Ansiklopedi, 4, 10-17, 2017.
  • [24] Uğuz, S., Makine Öğrenmesi Teorik Yönleri ve Python Uygulamaları ile Bir Yapay Zeka Ekolü, Nobel, Ankara, 2019.
  • [25] Uygur, S., Yıldırım, F., Cinsiyete bağlı insani gelişme endeks yaklaşımları: Türkiye örneği, Tisk Akademi, 30-59, 2011.
There are 25 citations in total.

Details

Primary Language English
Subjects Applied Mathematics
Journal Section Mathematics
Authors

Pelin Akın 0000-0003-3798-4827

Tuba Koc 0000-0001-5204-0846

Publication Date December 31, 2021
Submission Date March 11, 2021
Acceptance Date November 19, 2021
Published in Issue Year 2021 Volume: 11 Issue: 2

Cite

APA Akın, P., & Koc, T. (2021). Prediction of Human Development Index with Health Indicators Using Tree-Based Regression Models. Adıyaman University Journal of Science, 11(2), 410-420. https://doi.org/10.37094/adyujsci.895084
AMA Akın P, Koc T. Prediction of Human Development Index with Health Indicators Using Tree-Based Regression Models. ADYU J SCI. December 2021;11(2):410-420. doi:10.37094/adyujsci.895084
Chicago Akın, Pelin, and Tuba Koc. “Prediction of Human Development Index With Health Indicators Using Tree-Based Regression Models”. Adıyaman University Journal of Science 11, no. 2 (December 2021): 410-20. https://doi.org/10.37094/adyujsci.895084.
EndNote Akın P, Koc T (December 1, 2021) Prediction of Human Development Index with Health Indicators Using Tree-Based Regression Models. Adıyaman University Journal of Science 11 2 410–420.
IEEE P. Akın and T. Koc, “Prediction of Human Development Index with Health Indicators Using Tree-Based Regression Models”, ADYU J SCI, vol. 11, no. 2, pp. 410–420, 2021, doi: 10.37094/adyujsci.895084.
ISNAD Akın, Pelin - Koc, Tuba. “Prediction of Human Development Index With Health Indicators Using Tree-Based Regression Models”. Adıyaman University Journal of Science 11/2 (December 2021), 410-420. https://doi.org/10.37094/adyujsci.895084.
JAMA Akın P, Koc T. Prediction of Human Development Index with Health Indicators Using Tree-Based Regression Models. ADYU J SCI. 2021;11:410–420.
MLA Akın, Pelin and Tuba Koc. “Prediction of Human Development Index With Health Indicators Using Tree-Based Regression Models”. Adıyaman University Journal of Science, vol. 11, no. 2, 2021, pp. 410-2, doi:10.37094/adyujsci.895084.
Vancouver Akın P, Koc T. Prediction of Human Development Index with Health Indicators Using Tree-Based Regression Models. ADYU J SCI. 2021;11(2):410-2.

...