Exploration and practice of data-driven high-quality development in smart hospitals

Lijuan Li; Chuanzi Yang; Zhiyan Zhang; Qiang Wu; Xiaojun Cao; Lijuan Li; Chuanzi Yang; Zhiyan Zhang; Qiang Wu; Xiaojun Cao

doi:10.3934/publichealth.2026015

AIMS Public Health

2026, Volume 13, Issue 1: 273-288. doi: 10.3934/publichealth.2026015

Previous Article Next Article

Research article

Exploration and practice of data-driven high-quality development in smart hospitals

Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, Guangdong, 510623, China
These authors contributed equally to this work.

Received: 12 November 2025 Revised: 16 January 2026 Accepted: 27 January 2026 Published: 02 March 2026

Background
In this study, we explored a data-driven approach to smart hospital construction, addressing challenges such as data silos, fragmented processes, and delayed decision-making within healthcare systems. The proposed framework supports the high-quality development of public hospitals in China and facilitates intelligent integration among healthcare delivery, service provision, and management functions, achieving synergistic advancement of the “trinity” of hospital operations.
Method
A phased action research method was employed, comprising three stages: (1) Infrastructure construction period (2016–2018): Achieving system interconnection and data sharing based on enterprise service bus, standardized interface transformation, and the establishment of an information security system. (2) Intelligent empowerment period (2019–2021): Implementing intelligent healthcare processes, patient services, hospital management, and closed-loop management. (3) Ecological expansion period (2022–2024): Constructing a regional pediatric alliance data collaboration network and enabling internet hospital service continuity. The core pathways include global data integration, data governance standardization, closed-loop management enhancement, intelligent decision support development, and internet hospital integration.
Results
The study demonstrated four outcomes: (1) Improved data quality: Standardization, completeness, and consistency were significantly improved (p < 0.001). (2) Enhanced medical quality: The accuracy rate of AI-assisted diagnosis exceeded 90%, the completion rate of clinical pathways reached 96.03%, and the intensity of antibiotic use (defined daily doses) decreased from 28.27 to 17.14. (3) Optimized service efficiency: The appointment completion rate was 98.15%, the average length of stay in a hospital decreased by 42.06% (interrupted time series analysis showed that the post-intervention level was significantly reduced, β₂ = −0.701, p = 0.002), and the number of bed turnover increased by 128.8% (β₂ = 14.558, p < 0.001). (4) Significant regional collaboration: Established collaborations with 134 hospitals, with more than 2629 cases of remote consultation and transfer in the year 2024 and 88,900 times of mutual recognition of test results.
Conclusion
The construction of a data-driven smart hospital, through systematic integration and intelligent empowerment, demonstrated positive outcomes in improving data quality, clinical performance, operational efficiency, and regional collaboration. This provides a replicable implementation framework for the high-quality development of public hospitals in China. Since this was a single-center exploratory study, subsequent multi-center validation is necessary. Continuous improvement of data governance and comprehensive regulatory systems is required to further advance medical services toward enhanced precision, collaboration, and intelligence.
- data-driven,
- high-quality development,
- smart hospitals,
- clinical decision support system,
- intelligent management
Citation: Lijuan Li, Chuanzi Yang, Zhiyan Zhang, Qiang Wu, Xiaojun Cao. Exploration and practice of data-driven high-quality development in smart hospitals[J]. AIMS Public Health, 2026, 13(1): 273-288. doi: 10.3934/publichealth.2026015

Related Papers:

Abstract

Background

In this study, we explored a data-driven approach to smart hospital construction, addressing challenges such as data silos, fragmented processes, and delayed decision-making within healthcare systems. The proposed framework supports the high-quality development of public hospitals in China and facilitates intelligent integration among healthcare delivery, service provision, and management functions, achieving synergistic advancement of the “trinity” of hospital operations.

Method

A phased action research method was employed, comprising three stages: (1) Infrastructure construction period (2016–2018): Achieving system interconnection and data sharing based on enterprise service bus, standardized interface transformation, and the establishment of an information security system. (2) Intelligent empowerment period (2019–2021): Implementing intelligent healthcare processes, patient services, hospital management, and closed-loop management. (3) Ecological expansion period (2022–2024): Constructing a regional pediatric alliance data collaboration network and enabling internet hospital service continuity. The core pathways include global data integration, data governance standardization, closed-loop management enhancement, intelligent decision support development, and internet hospital integration.

Results

The study demonstrated four outcomes: (1) Improved data quality: Standardization, completeness, and consistency were significantly improved (p < 0.001). (2) Enhanced medical quality: The accuracy rate of AI-assisted diagnosis exceeded 90%, the completion rate of clinical pathways reached 96.03%, and the intensity of antibiotic use (defined daily doses) decreased from 28.27 to 17.14. (3) Optimized service efficiency: The appointment completion rate was 98.15%, the average length of stay in a hospital decreased by 42.06% (interrupted time series analysis showed that the post-intervention level was significantly reduced, β₂ = −0.701, p = 0.002), and the number of bed turnover increased by 128.8% (β₂ = 14.558, p < 0.001). (4) Significant regional collaboration: Established collaborations with 134 hospitals, with more than 2629 cases of remote consultation and transfer in the year 2024 and 88,900 times of mutual recognition of test results.

Conclusion

The construction of a data-driven smart hospital, through systematic integration and intelligent empowerment, demonstrated positive outcomes in improving data quality, clinical performance, operational efficiency, and regional collaboration. This provides a replicable implementation framework for the high-quality development of public hospitals in China. Since this was a single-center exploratory study, subsequent multi-center validation is necessary. Continuous improvement of data governance and comprehensive regulatory systems is required to further advance medical services toward enhanced precision, collaboration, and intelligence.

Authors' contributions

LL and CY analyzed the data, prepared the figures/tables, and drafted the manuscript. QW, XC and ZZ collaborated to edit and revised the manuscript. All authors completed a review process and approved the final version of the work.

Conflict of interest

The authors declare no conflict of interest.

References

[1]	Central Committee of the Communist Party of China, State CouncilOutline of the “Healthy China 2030” Plan (2016). [cited 2025 November 10]. Available from: https://www.gov.cn/zhengce/2016-10/25/content_5124174.htm
[2]	General Office of the State CouncilOpinions on promoting high-quality development of public hospitals (2021). [cited 2025 November 10]. Available from: https://www.gov.cn/gongbao/content/2021/content_5618942.htm
[3]	General Office of the State CouncilGuidelines on promoting and standardizing the application and development of health and medical big data (2016). [cited 2025 November 10]. Available from: https://www.gov.cn/zhengce/content/2016-06/24/content_5085091.htm
[4]	Rani S, Kumar R, Panda B, et al. (2025) Machine learning-powered smart healthcare systems in the era of big data: Applications, diagnostic insights, challenges, and ethical implications. Diagnostics 15: 1914. https://doi.org/10.3390/diagnostics15151914
[5]	Cai Q, Wang H, Li Z, et al. (2019) A survey on multimodal data-driven smart healthcare systems: Approaches and applications. IEEE Access 7: 133583-133599. https://doi.org/10.1109/ACCESS.2019.2941419
[6]	Rahman A, Debnath T, Kundu D, et al. (2024) Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities. AIMS Public Health 11: 58-109. https://doi.org/10.3934/publichealth.2024004
[7]	Mathkor D, Mathkor N, Bassfar Z, et al. (2024) Multirole of the internet of medical things (IoMT) in biomedical systems for managing smart healthcare systems: An overview of current and future innovative trends. J Infect Public Health 17: 559-572. https://doi.org/10.1016/j.jiph.2024.01.013
[8]	Manickam P, Mariappan S, Murugesan S, et al. (2022) Artificial Intelligence (AI) and Internet of Medical Things (IoMT) assisted biomedical systems for intelligent healthcare. Biosensors 12: 562. https://doi.org/10.3390/bios12080562
[9]	Izonin I, Kutucu H, Singh KK (2023) Smart systems and data-driven services in healthcare. Comput Biol Med 158: 106074. https://doi.org/10.1016/j.compbiomed.2022.106074
[10]	Yang CY (2023) Research on the phased action strategy of platform selection of small and medium-sized E-commerce enterprises: Taking L E-commerce company as an example. Lanzhou, P. R. China: Lanzhou University. [cited 2025 November 10]. Available from: https://d.wanfangdata.com.cn/thesis/D03089805.
[11]	Hu H, Su J, Ma J (2022) Editorial: Smart hospital innovation: Technology, service, and policy. Front Public Health 10: 845577. https://doi.org/10.3389/fpubh.2022.845577
[12]	National Health Commission Statistical Information CenterNational healthcare information interoperability and standardization maturity assessment scheme for hospitals (2020). [cited 2025 November 10]. Available from: https://www.nhc.gov.cn/mohwsbwstjxxzx/s8553/202008/bdd0d4fcb1c747dda000e0adec3c17b9/files/1740035892364_40918.pdf
[13]	Zhi L, Yin P, Ren J, et al. (2021) Running an internet hospital in China: Perspective based on a case study. J Med Internet Res 23: e18307. https://doi.org/10.2196/18307
[14]	Gao S (2022) Network security problems and countermeasures of hospital information system after going to the cloud. Comput Math Methods Med 2022: 9725741. https://doi.org/10.1155/2022/9725741
[15]	Cheng W, Lian W, Tian J (2022) Building the hospital intelligent twins for all-scenario intelligence health care. Digit Health 8: 20552076221107894. https://doi.org/10.1177/20552076221107894
[16]	Wu T, Li P, Xu J, et al. (2013) Enterprise service bus and standard based hospital integration platform and its application research. Chin Med J (Engl) 126: 3978-3981. https://doi.org/10.3760/cma.j.issn.0366-6999.20130857
[17]	Health Level Seven (HL7) InternationalFHIR Release 4 (2019). [cited 2025 November 10]. Available from: https://www.hl7.org/fhir/R4/
[18]	(2017) Dama InternationalThe DAMA data management body of knowledge. Denville: Technics Publications.
[19]	Babar M, Qureshi B, Koubaa A (2024) Review on federated learning for digital transformation in healthcare through big data analytics. Future Gener Comput Syst 160: 14-28. https://doi.org/10.1016/j.future.2024.05.046
[20]	Chen Y, Zhang X, Tang X, et al. (2023) How do inpatients' costs, length of stay, and quality of care vary across age groups after a new case-based payment reform in China? An interrupted time series analysis. BMC Health Serv Res 23: 160. https://doi.org/10.1186/s12913-023-09109-z
[21]	Kermany D, Goldbaum M, Cai W, et al. (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172: 1122-1131.e9. https://doi.org/10.1016/j.cell.2018.02.010
[22]	Li L, Cao X, Chen F, et al. (2023) Research on risk prediction of in-hospital death in sepsis patients based on random forest algorithm. China Med Devices 38: 29-34.
[23]	Kandeel M (2024) Revolutionizing healthcare: Harnessing the power of artificial intelligence for enhanced diagnostics, treatment and drug discovery. Int J Pharmacol 20: 1-10. https://doi.org/10.3923/ijp.2024.1.10
[24]	Xu G, Fan X, Xu S, et al. (2025) Anonymity-enhanced sequential multi-signer ring signature for secure medical data sharing in IoMT. IEEE Trans Inf Forensics Secur 20: 5647-5662. https://doi.org/10.1109/TIFS.2025.3574959
[25]	Li R, Niu Y, Scott SR, et al. (2021) Using electronic medical record data for research in a healthcare information and management systems society (HIMSS) analytics electronic medical record adoption model (EMRAM) stage 7 hospital in Beijing: cross-sectional study. JMIR Med Inform 9: e24405. https://doi.org/10.2196/24405
[26]	Douglas AO, Senkaiahliyan S, Bulstra CA, et al. (2025) Global adoption of value-based health care initiatives within health systems: A scoping review. JAMA Health Forum 6: e250746. https://doi.org/10.1001/jamahealthforum.2025.0746
[27]	Liu X, Du C, Hu F, et al. (2022) Management of acute exacerbation of chronic obstructive pulmonary disease under atiered medical system in China. Ther Adv Respir Dis 16: 17534666221075499. https://doi.org/10.1177/17534666221075499
[28]	Zhang GW, Gong M, Li HJ, et al. (2023) The “Trinity” smart hospital construction policy promotes the development of hospitals and health management in China. Front Public Health 11: 1219407. https://doi.org/10.3389/fpubh.2023.1219407

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)