Abstract
Forecasting inpatient mortality (IM) and discharges against medical advice (DAMA) provides essential insights for healthcare quality monitoring and hospital management. This study compared six time-series forecasting methods—ARIMA, Grey Model, NNETAR, LSTM, Prophet, and Chronos, a pretrained probabilistic model—to predict monthly IM and DAMA in two tertiary hospitals in China from January 2018 to December 2024. Model performance was evaluated using RMSE, MAE, MAPE. Chronos demonstrated the best predictive accuracy for IM across both hospitals, achieving the lowest MAPE values (26.96–33.37%) and outperforming traditional and deep learning approaches (Diebold–Mariano test, p < 0.05). For DAMA forecasting, Chronos performed optimally (MAPE = 5.52%) in the hospital with higher and more stable DAMA volumes, whereas NNETAR yielded relatively superior results (MAPE = 11.29%) in the hospital with smaller and more irregular time series. LSTM consistently showed limited generalizability, likely due to small sample sizes and model complexity. These findings indicate that pretrained models such as Chronos can deliver robust and scalable forecasting performance even with limited data, while simpler neural networks like NNETAR may better handle low-volume, noisy data. Implementing these models in hospital management systems could enhance the timeliness and precision of quality monitoring, enabling proactive responses to adverse clinical and operational trends.
Data availability
The original contributions presented in the study are included in the article, further inquiries can be directed to the corresponding author.
References
Barbazza, E., Klazinga, N. S. & Kringos, D. S. Exploring the actionability of healthcare performance indicators for quality of care: a qualitative analysis of the literature, expert opinion and user experience. BMJ Qual. Saf. 30, 1010–1020 (2021).
Alfandre, D. J. I’m Going Home: Discharges Against Medical Advice. Mayo Clin. Proc. 84, 255–260 (2009).
Saia, M. et al. Hospital readmissions and mortality following discharge against medical advice: a five-year retrospective, population-based cohort study in Veneto region, Northeast Italy. BMJ Open. 13, e069775 (2023).
Ni, J. et al. Discharge against medical advice after hospitalization for sepsis: Predictors, 30-Day Readmissions, and outcomes. J. Emerg. Med. 65, e383–e392 (2023).
Ambasta, A., Santana, M., Ghali, W. A. & Tang, K. Discharge against medical advice: ‘deviant’ behaviour or a health system quality gap? BMJ Qual. Saf. 29, 348–352 (2020).
Kumah, A. Poor quality care in healthcare settings: an overlooked epidemic. Front. Public. Health. 13, 1504172 (2025).
Dalili, H., Shariat, M. & Sahebi, L. Time series analysis for forecasting neonatal intensive care unit census and neonatal mortality. BMC Pediatr. 25, 339 (2025).
Rodea-Montero, E. R. et al. Trends, structural changes, and assessment of time series models for forecasting hospital discharge due to death at a Mexican tertiary care hospital. PLOS ONE. 16, e0248277 (2021).
Cho, N. Y. et al. Discharge against medical advice in trauma patients: Trends, risk factors, and implications for health care management strategies. Surgery 176, 942–948 (2024).
Gao, R., Cheng, W. X., Suganthan, P. N. & Yuen, K. F. Inpatient discharges forecasting for Singapore hospitals by machine learning. IEEE J. Biomed. Health Inf. 26, 4966–4975 (2022).
Avinash, G., Pachori, H., Sharma, A. & Mishra, S. Time series forecasting of bed occupancy in mental health facilities in India using machine learning. Sci. Rep. 15, 2686 (2025).
Besong, A. E. et al. Significance of the ARIMA epidemiological modeling to predict the rate of HIV and AIDS in the Kumba health district of Cameroon. Front. Public. Health. 13, 1526454 (2025).
Tan, X. et al. Grey modelling and real-time forecasting for the approximate non-homogeneous white exponential law BDS clock bias sequences. Sci. Rep. 14, 17897 (2024).
Talkhi, N., Fatemi, A., Ataei, N., Jabbari Nooghabi, M. & Z. & Modeling and forecasting number of confirmed and death caused COVID-19 in IRAN: A comparison of time series forecasting methods. Biomed. Signal. Process. Control. 66, 102494 (2021).
Saranya, M. S. & Vinish, V. N. A comparative evaluation of streamflow prediction using the SWAT and NNAR models in the meenachil river basin of central Kerala, India. Water Sci. Technol. 88, 2002–2018 (2023).
Guo, Y. et al. Deep learning models for hepatitis E incidence prediction leveraging Baidu index. BMC Public. Health. 24, 3014 (2024).
Sembiring, I., Wahyuni, S. N. & Sediyono, E. LSTM algorithm optimization for COVID-19 prediction model. Heliyon 10, e26158 (2024).
Ansari, A. F. et al. Chronos: Learning the Language of Time Series. Preprint at (2024). https://doi.org/10.48550/ARXIV.2403.07815
Al-qaness, M. A. A., Ewees, A. A. & Fan, H. Abd El Aziz, M. Optimization method for forecasting confirmed cases of COVID-19 in China. J. Clin. Med. 9, 674 (2020).
Gaur, A., Gilham, E., Machin, L. & Warriner, D. Discharge against medical advice: the Causes, consequences and possible corrective measures. Br. J. Hosp. Med. 85, 1–14 (2024).
Cecil, E., Bottle, A., Esmail, A., Vincent, C. & Aylin, P. What is the relationship between mortality alerts and other indicators of quality of care? A National cross-sectional study. J. Health Serv. Res. Policy. 25, 13–21 (2020).
Lim, B. & Zohren, S. Time-series forecasting with deep learning: a survey. Philos. Trans. R Soc. Math. Phys. Eng. Sci. 379, 20200209 (2021).
Brigato, L. et al. Position: There are no Champions in Long-Term Time Series Forecasting. Preprint at (2025). https://doi.org/10.48550/ARXIV.2502.14045
Liu, X. & Wang, W. Deep time series forecasting models: A comprehensive survey. Mathematics 12, 1504 (2024).
Youssef, A. et al. External validation of AI models in health should be replaced with recurring local validation. Nat. Med. 29, 2686–2687 (2023).
Andric, M. & Dragoni, M. Machine learning and statistical insights into hospital stay durations: the Italian EHR case. Preprint at (2025). https://doi.org/10.48550/ARXIV.2504.18393
Sakib, M. & Siddiqui, T. Multi-Network-Based ensemble deep learning model to forecast Ross river virus outbreak in Australia. Int. J. Pattern Recognit. Artif. Intell. 37, 2352015 (2023).
Acknowledgements
We are grateful to the referees and the editors for their valuable comments.
Funding
The study was supported by the Non-profit Central Research Institute Fund of Chinese Academy of Medical Sciences (2024-RW630-01) and the Natural Science Foundation of Xizang Autonomous Region (XZZR202402111(W)). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Author information
Authors and Affiliations
Contributions
Cheng Pang: Conceptualization, Methodology, Formal analysis, Mainly Writing, Funding acquisition; Dexi Jiayong: Data curation, Writing – review & editing, Revising; Dandan Jiang: Data curation, Writing – review & editing; Yi Wang: Investigation, Writing – review & editing; Naishi Li: Methodology, Investigation, Writing – review & editing; Dan Ren: Conceptualization, Funding acquisition, project administration, Writing – review & editing.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval and consent to participate
The studies were approved by the Ethics Committee of Peking Union Medical College Hospital (approval number I-25PJ1221) and the Ethics Committee of People’s Hospital of Xizang Autonomous Region (approval number ME-TBHP-24-067). The study was conducted in accordance with the local legislation and institutional requirements. Written informed consent for participation was not required from the participants or the participants’ legal guardians/next of kin because the study used a retrospective study design.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Pang, C., Jiayong, D., Jiang, D. et al. A comparative evaluation of time-series models for forecasting inpatient deaths and discharges against medical advice. Sci Rep (2026). https://doi.org/10.1038/s41598-026-37913-0
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-37913-0
