Yang, Deliang, Tang, Yiyi, Chan, Vivien Kin Yi, Fang, Qiwen, Chan, Sandra Sau Man, Luo, Hao, Wong, Ian Chi Kei, Ou, Huang-Tz, Chan, Esther Wai Yin, Bishai, David Makram, Chen, Yingyao, Knapp, Martin 
ORCID: 0000-0003-1427-0215, Jit, Mark, Craig, Dawn and Li, Xue
(2025)
Population-wide depression incidence forecasting comparing ARIMA/vector-ARIMA to temporal fusion transformers.
Journal of Medical Internet Research.
ISSN 1438-8871
(In Press)
Abstract
Background Accurate prediction of population-wide depression incidence is vital for effective public mental health management. However, this incidence is often influenced by socio-economic factors, such as abrupt events or changes, including pandemics, economic crises, and social unrest, creating complex structural break scenarios in the time-series data. These structural breaks can affect the performance of forecasting methods in various ways. Therefore, understanding and comparing different models across these scenarios is essential. Objective To develop depression incidence forecasting models and compare the performance of ARIMA/vector-ARIMA(VARIMA) and Temporal Fusion Transformers (TFT) under different structural break scenarios. Methods We developed population-wide depression incidence forecasting models and compared the performance of ARIMA/ VARIMA-based methods to TFT-based methods. Using monthly depression incidence from 2002 to 2022 in Hong Kong, we applied sliding windows to segment the whole time series into 72 ten-year sub-samples. The forecasting models were trained, validated and tested on each sub-sample. Within each ten-year subset, the first seven years were used for training, with the eighth year for setting hold-out validation, and the ninth and tenth years for testing. The accuracy on testing set within each ten-year sub-sample was measured by symmetric mean absolute percentage error (SMAPE). Results We found that in sub-samples without significant slope or trend change (structural break), multivariate TFT significantly outperformed univariate TFT, vector-ARIMA (VARIMA), and ARIMA, with an average SMAPE of 11.6% compared to 13.2% (P=.011) for univariate TFT, 16.4% (P=.002) for VARIMA, and 14.8% (P=.003) for ARIMA. Adjusting for the unemployment rate improved TFT performance more effectively than VARIMA. When fluctuating outbreaks happened, TFT was more robust to sharp interruptions, whereas VARIMA/ARIMA performed better when incidence surged and remained high. Conclusions This study provides a comparative evaluation of TFT and ARIMA/VARIMA models for forecasting depression incidence under various structural break scenarios, offering insights into predicting disease burden during both stable and unstable periods. The findings support a decision-making framework for model selection based on the nature of disruptions and data characteristics. For public health policymaking, the results suggest that TFT may be a more suitable tool for disease burden forecasting during periods of stable burden level or when sudden temporary interruption, such as pandemics or socio-political events, impact disease occurrence.
| Item Type: | Article |
|---|---|
| Additional Information: | © 2025 The Author(s) |
| Divisions: | Care Policy and Evaluation Centre Health Policy |
| Subjects: | R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine R Medicine Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Date Deposited: | 27 Mar 2025 11:21 |
| Last Modified: | 27 Mar 2025 11:21 |
| URI: | http://eprints.lse.ac.uk/id/eprint/127658 |
Actions (login required)
 |
View Item |
