Forecasting the health expenditures in Iran by Using Time Series Analysis as Machine Learning Model in Python

Abstract

Background: Forecasting the future trend of health expenditures is an important step to achieve universal health coverage (UHC) by 2030. This study aimed to examine the two decades underlying historical trends in Iran’s health expenditures and explore these data as the grounds for forecasting its health expenditures. Methods: Iran’s health spending data spanning 2001–2019 were extracted from the National Health Account 2020 database. Total health expenditure, government, prepaid private, and out-of-pocket spending per capita were forecasted for 2020–2030. The Autoregressive integrated moving average (ARIMA) model was used to obtain future projections based on time series analysis. Python programming language has been used for prediction. Results: The model of total health expenditure (THE), government health expenditure (GHE), social health expenditure (SHE), prepaid private health expenditure (PPHE), and out-of-pocket health expenditure (OOP) are ARIMA (0,2,2), ARIMA (1,2,3), ARIMA (1,2,2), ARIMA (1,1,2), and ARIMA (1,2,0). According to the simulation results, in 2030, Iran’s THE is expected to reach 16,555,761,416 billion IRR, and the constituent ratios in GHE, SHE, PPHE, and OOP will be 29%, 28%, 11%, and 32%, respectively. Conclusions: Forecasting health expenditures is important in ensuring sustainable financing for the health sector, which is a critical aspect of achieving UHC. Our result would help policymakers to make sufficient data available in order to plan the future of resources and estimate the amount of the budget allocated to Healthcare. Iran should take effective measures to control the excessive growth of THE, keep decreasing the OOP percentage, and improve the efficiency and fairness of the use of health funds.