ARIMA model for predicting chronic kidney disease and estimating its economic burden in China.

BACKGROUND: Chronic kidney disease (CKD) is an important global public health issue. In China, CKD affects a large number of patients and causes a huge economic burden. This study provided a new way to predict the number of patients with CKD and estimate its economic burden in China based on the autoregressive integrated moving average (ARIMA) model. METHODS: Data of the number of patients with CKD in China from 2000 to 2019 were obtained from the Global Burden of Disease. The ARIMA model was used to fit and predict the number of patients with CKD. The direct and indirect economic burden of CKD were estimated by the bottom-up approach and the human capital approach respectively. RESULTS: The results of coefficient of determination (0.99), mean absolute percentage error (0.26%), mean absolute error (343,193.8) and root mean squared error (628,230.3) showed that the ARIMA (1,1,1) model fitted well. Akaike information criterion (543.13) and Bayesian information criterion (546.69) indicated the ARIMA (1,1,1) model was reliable when analyzing our data. The result of relative error of prediction (0.23%) also suggested that the model predicted well. The number of patients with CKD in 2020 to 2025 was predicted to be about 153 million, 155 million, 157 million, 160 million, 163 million and 165 million respectively, accounting for more than 10% of the Chinese population. The total economic burden of CKD from 2019 to 2025 was estimated to be $179 billion, $182 billion, $185 billion, $188 billion, $191 billion, $194 billion and $198 billion respectively. CONCLUSION: The number of patients with CKD and the economic burden of CKD will continue to rise in China. The number of patients with CKD in China would increase by 2.6 million (1.6%) per year on average from 2020 to 2025. Meanwhile, the total economic burden of CKD in China would increase by an average of $3.1 billion per year. The ARIMA model is applicable to predict the number of patients with CKD. This study provides a new perspective for more comprehensive understanding of the future risk of CKD.

Exploration of Three Incidence Trend Prediction Models Based on the Number of Diagnosed Pneumoconiosis Cases in China From 2000 to 2019.

OBJECTIVE: To predict the future incidence trend of pneumoconiosis in China, and to evaluate three predictive models. METHODS: We selected pneumoconiosis cases (2000-2019) to fit Generalized Additive Model (GAM), Curve Fitting Method, and GM (1,1) Model, chosen average fitting relative error, relative error of prediction, and coefficient of determination to evaluate models. RESULTS: Chinese incidence trend of pneumoconiosis would decrease in the future. Predicted value of GAM (14,566) and Curve Fitting Method (15,781) in 2019 was close to the actual value (15,898). Relative error of prediction of GAM and Curve Fitting Method was -8.38% and -0.73%, respectively. CONCLUSIONS: The government needs to strengthen prevention and control since pneumoconiosis cases might remain huge in the future. Besides, we advise that GAM and Curve Fitting Method can be used to predict Chinese incidence trend of pneumoconiosis.

Predicting Diabetes and Estimating Its Economic Burden in China Using Autoregressive Integrated Moving Average Model.

Objectives: To predict the number of people with diabetes and estimate the economic burden in China. Methods: Data from natural logarithmic transformation of the number of people with diabetes in China from 2000 to 2018 were selected to fit the autoregressive integrated moving average (ARIMA) model, and 2019 data were used to test it. The bottom-up and human capital approaches were chosen to estimate the direct and indirect economic burden of diabetes respectively. Results: The number of people with diabetes in China would increase in the future. The ARIMA model fitted and predicted well. The number of people with diabetes from 2020 to 2025 would be about 94, 96, 97, 98, 99 and 100 m respectively. The economic burden of diabetes from 2019 to 2025 would be about $156b, $160b, $163b, $165b, $167b, $169b and $170b respectively. Conclusion: The situation of diabetes in China is serious. The ARIMA model can be used to predict the number of people with diabetes. We should allocate health resources in a rational manner to improve the prevention and control of diabetes.