Estimation of healthcare expenditure per capita of Turkey using artificial intelligence techniques with genetic algorithm-based feature selection

被引:14
作者
Ceylan, Zeynep [1 ]
Atalan, Abdulkadir [2 ]
机构
[1] Samsun Univ, Fac Engn, Dept Ind Engn, TR-55420 Samsun, Turkey
[2] Gaziantep Islam Sci & Technol Univ, Fac Engn & Nat Sci, Dept Ind Engn, Gaziantep, Turkey
关键词
artificial intelligence; genetic algorithm‐ based feature selection; healthcare expenditure per capita; optimization; prediction; VECTOR MACHINE; CLASSIFICATION; DIAGNOSIS; GROWTH;
D O I
10.1002/for.2747
中图分类号
F [经济];
学科分类号
02 ;
摘要
This study presents a comprehensive analysis of artificial intelligence (AI) techniques to predict healthcare expenditure per capita (pcHCE) in Turkey. Well-known AI techniques such as random forest (RF), artificial neural network (ANN), multiple linear regression (MLR), support vector regression (SVR), and relevance vector machine (RVM) were used to forecast pcHCE. Twenty-nine years of historical data from 1990 to 2018 were used in the training and testing phases of the models. Gross domestic product per capita, life expectancy at birth, unemployment rate, crude birth rate, and the number of physicians and hospitals were used as input variables for the analysis. A genetic algorithm-based feature selection (GAFS) method was applied to all models to select the relevant and optimal feature subset in the prediction of pcHCE. The comparative results showed that the GAFS method improved the overall performance of all base AI models. The hybrid GAFS-RF model performed best among all AI-based prediction methods, with a 99.86% correlation of determination (R-2) value at the testing stage.
引用
收藏
页码:279 / 290
页数:12
相关论文
共 44 条
[1]   Determinants of health expenditure in OECD countries: A decision tree model [J].
Akca, Nesrin ;
Sonmez, Seda ;
Yilmaz, Ali .
PAKISTAN JOURNAL OF MEDICAL SCIENCES, 2017, 33 (06) :1490-1494
[2]  
[Anonymous], 2017, GENETIC ALGORITHMS F
[3]   Empirical characterization of random forest variable importance measures [J].
Archer, Kelfie J. ;
Kirnes, Ryan V. .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2008, 52 (04) :2249-2260
[4]   Informing policy makers about future health spending: A comparative analysis of forecasting methods in OECD countries [J].
Astolfi, Roberto ;
Lorenzoni, Luca ;
Oderkirk, Jillian .
HEALTH POLICY, 2012, 107 (01) :1-10
[5]  
Atalan A., 2019, PONTE, V75, P12, DOI DOI 10.21506/J.P0NTE.2019.6.10
[6]   Factors underlying the growth of hospital expenditure in Spain in a period of unexpected economic shocks: A dynamic analysis on administrative data [J].
Bernal-Delgado, Enrique ;
Comendeiro-Maaloe, Micaela ;
Ridao-Lopez, Manuel ;
Sanso Rossello, Andreu .
HEALTH POLICY, 2020, 124 (04) :389-396
[7]  
Boachie M., 2014, J BEHAV EC FINANCE E, V2, P35, DOI DOI 10.12691/JBE-2-2-1
[8]   What drives public health care expenditure growth? Evidence from Swiss cantons, 1970-2012 [J].
Braendle, Thomas ;
Colombier, Carsten .
HEALTH POLICY, 2016, 120 (09) :1051-1060
[9]   Forecasting PM10 levels using ANN and MLR: A case study for Sakarya City [J].
Ceylan, Z. ;
Bulkan, S. .
GLOBAL NEST JOURNAL, 2018, 20 (02) :281-290
[10]  
Ceylan Z., 2020, J ENV HLTH SCI ENG, P1