Forecasting the Number of Pneumoconiosis Inpatients: a Case of Hospital in Chiang Mai Province
Keywords:
forecasting, inpatients, pneumoconiosisAbstract
From fiscal year 2015 to September 2023, a hospital in Chiang Mai Province recorded monthly statistics of over 4,000 pneumoconiosis inpatients. The time series data revealed seasonal patterns and an upward trend. This study aimed to forecast monthly inpatient cases using three approaches: the Classical Decomposition-Multiplicative model with a seasonal index derived from the Ratio-to-Moving Average method (classical decomposition ratio to moving average: CDRMA), the Box and Jenkins method (seasonal autoregressive integrated moving average: SARIMA), and a hybrid model based on Grey System Theory. The forecasting used monthly inpatient data collected from the CMI reporting system, developed by the Chiang Mai Provincial Public Health Office, covering fiscal years 2014–2023. Among the models tested, ARIMA(1,1,1)(0,1,1)12 was the most suitable, with a 96-month mean absolute percentage error (MAPE) of 4.44%, lower than the 5.39% from the CDRMA model. The hybrid Grey model, GM(1,1) with error periodic correction (EPC), achieved a MAPE of 1.18% when annual forecasts were distributed into monthly values for 2023. For the same year, the GRMA and GSA methods yielded 9-month MAPE values of 4.88% and 4.05%, respectively. Due to the seasonal and increasing nature of the data, the GRMA model was selected. Forecast accuracy was validated using the Public Health Statistics Report of Chiang Mai Province (Report No. 178), published in early 2024, which recorded 56,937 actual cases. The GRMA method, using GM(1,1)EPC, produced results that were 2.05% higher than the actual figures.
Downloads
References
Qi XM, Luo Y, Song MY, Liu Y, Shu T, Liu Y, et al. Pneumoconiosis: current status and future prospects. Chin Med J 2021;134(8):898–907.
วิวัฒน์ เอกบูรณวัฒน์. คู่มือการลงรหัส ICD-10 สำหรับโรคจากการประกอบอาชีพ. ชลบุรี: สัมมาอาชีวะ; 2554.
ทีมพัฒนาสารสนเทศ เขตบริการสุขภาพที่ 1. รายงานอัตราในปอด 2557-2566 [อินเทอร์เน็ต]. 2567 [สืบค้นเมื่อ 30 ต.ค. 2567]. แหล่งข้อมูล: https://cmi.ciorh1.com/web/index.php?r=report%2Fpdx&co_thip_ new=178&chwcode=50&year=2023
กระทรวงสาธารณสุข HDC v4.0. อัตราป่วยโรคระบบทางเดินหายใจ เขตสุขภาพที่ 1 จังหวัดเชียงใหม่ โรงพยาบาลนครพิงค์ ปี 2556 ถึง 2566 [อินเทอร์เน็ต]. 2567 [สืบค้นเมื่อ 30 ต.ค. 2567]. แหล่งข้อมูล: https://hdcservice.moph.go.th/hdc/reports/report.php?cat_id=f16421e617aed29602f9f09d951 cce68&id=4408d6d11a1efac662b6fd9e83594cea
Lou HR, Wang X, Gao Y, Zeng Q. Comparison of ARIMA model, DNN model and LSTM model in predicting disease burden of occupational pneumoconiosis in Tianjin, China. BMC Public Health 2022;22(1):2167.
Li Z, Li Y. A comparative study on the prediction of the BP artificial neural network model and the ARIMA model in the incidence of AIDS. BMC Med Inform Decis Mak 2020;20(1):143.
Wang Y, Xu C, Yao S, Zhao Y. Forecasting the epidemiological trends of COVID-19 prevalence and mortality using the advanced alpha-Sutte Indicator. Epidemiol Infect 2020;148:e236.
Adeyinka DA, Muhajarine N. Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models. BMC Med Res Methodol 2020;20(1): 292.
Ceylan Z. Estimation of COVID-19 prevalence in Italy, Spain, and France. Sci Total Environ 2020;729:138817.
Zhang L, Hong T, Miao H. Grey system analysis in the field of medicine and health. Grey Systems 2019;9(2): 251-8.
Zhou D, Zhu D, Li N, Han B. Exploration of Three Incidence Trend Prediction Models Based on the Number of Diagnosed Pneumoconiosis Cases in China From 2000 to 2019. J Occup Environ Med 2021;63(7):e440-44.
Liu S, Lin Y. Grey systems theory and application. Berlin: Springer; 2010.
โรงพยาบาลนครพิงค์. ประวัติโรงพยาบาล [อินเทอร์เน็ต]. 2567 [สืบค้นเมื่อ 30 ต.ค. 2567]. แหล่งข้อมูล: https://www.nkp-hospital.go.th/th/history.php
Microsoft. Support >> Excel functions (by category) [Internet]. 2023 [cited 2023 Oct 20]. Available from: https://support.microsoft.com/en-us/office/excel-functions-by-category-5f91f4e9-7b42-46d2-9bd1-63f26a86c0eb
Excel Easy. Line chart [Internet]. 2023 [cited 2023 Oct 20]. Available from: https://www.exceleasy.com/examples/trendline.html
The R Foundation. The R project for statistical computing [Internet]. 2023 [cited 2023 Oct 20]. Available from: https://www.r-project.org/
Hyndman R, Athanasopoulos G, Bergmeir C, Caceres G, Chhay L, Kuroptev K, et al. Methods and tools for displaying and analysing univariate time series forecasts including exponential smoothing via state space models and automatic ARIMA modelling [Internet]. 2023 [cited 2023 Oct 20]. Available from: https://cran.rproject.org/web/packages/forecast/index.html
Vision Academy. Measurement of seasonal indices using ratio to moving average method for monthly data [Internet]. 2021 [cited 2023 Oct 20]. Available from: https://www.youtube.com /watch?v=dqGUvOWT_14
Srivastava M. University of Lucknow - methods of time series [Internet]. 2023 [cited 2023 Oct 20]. Available from: https://www.lkouniv.ac.in/site/writereaddata/siteContent/ 202003291612342405mukeshsrivastava_businessstastics3.pdf
Shweta. Towards data science - part 1: average and smoothing models [Internet]. 2021 [cited 2023 Oct 20]. Available from: https://towardsdatasci ence.com/introduction-to-time-series-forecasting-part-1-average-and-smoothing-models-a739d832315
Hyndman RJ, Athanasopoulos G. Forecasting: principles and practice. 2nd edition. Melbourne: OTexts; 2018.
Shweta. Towards data science - introduction to time series forecasting — part 2 (ARIMA Models) [Internet]. 2021[cited 2023 Oct 20]. Available from: https://towardsdatascience.com/ introduction-to-time-series-forecasting-part-2-arima-models-9f47bf0f476b
CRAN. Package forecast. forecast: forecasting functions for time series and linear models [Internet]. 2023 [cited 2023 Oct 20]. Available from: https://cran.r-project.org/web/packages/ forecast/index.html
Cobb B. Deseasonalized data with a centered moving average [Internet]. 2020 [cited 2023 Oct 20]. Available from: https://www.youtube.com/watch?v=lCGw53-tlRw
Emmanuel J. Calculating seasonal indexes (without trend) in Excel | Forecasting [Internet]. 2021 [cited 2023 Oct 20]. Available from: https://www.youtube.com/watch?v=5foKJgA7mWw
Andrés D. Machine learning pills: error metrics for time series forecasting [Internet]. 2023 [cited 2023 Oct 20]. Available from: https://mlpills.dev/time-series/error-metrics-for-time-series-forecasting/
Lewis CD. Industrial and business forecasting methods. London: Butterworths; 1982.
Indeed Editorial Team. Quantitative forecasting vs. qualitative forecasting [Internet]. 2022 [cited 2023 Oct 20]. Available from: https://www.indeed.com/career-advice/career-development/quantitative-vs-qualitative-forecasting-pros-and-cons
Lou J, Li Y, Wang H, Zhang X, Chen Y. Forecasting the burden of pneumoconiosis using ARIMA, deep neural networks and LSTM models in China. BMC Public Health 2022;22:1456.
Indeed Editorial Team. Quantitative forecasting vs. qualitative forecasting [Internet]. 2022 [cited 2023 Oct 20]. Available from: https://www.indeed.com/career-advice/career-development/quantitative-vs-qualitative-forecasting-pros-and-cons
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ministry of Public Health
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
