基于指南的人工智能系统在基层高血压管理中的应用:单臂前后对照研究
A guideline-based artificial intelligence system for hypertension in primary care: a single-arm pre–post study
研究团队评估了基于指南的数字系统在基层高血压管理中的效果,结果显示12个月后收缩压下降8.86 mmHg,舒张压下降3.42 mmHg,控制率从60.39%提高到76.70%,依从性评分提高。研究支持AI系统在资源有限的基层医疗中的潜在可扩展性,但未设对照组,存在选择偏差。
- Article
- Open access
- Published: 19 November 2026
- Yan Yang ORCID: orcid.org/0009-0007-6042-04521 na1,
- Yubin Liu1 na1,
- Zhilin Gou1,
- Ying Xiao1,
- Xinyu Zhang1 &
- …
- Bo Zhou2
Scientific Reports (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Hypertension control remains suboptimal in primary care, particularly in resource-constrained settings lacking clinical decision support. This retrospective cohort study evaluated the real-world changes associated with a Guideline-based Digital System (GDS) implemented in a primary care network in Chengdu, China. Data from 515 hypertensive patients with complete baseline and 12-month follow-up data were analyzed. The primary outcome was office blood pressure control rate (< 140/90 mmHg, or < 130/80 mmHg for patients with diabetes); secondary outcomes included changes in systolic/diastolic blood pressure, fasting blood glucose, lipid profiles, and medication adherence (MMAS-8). After 12 months, systolic blood pressure decreased by 8.86 mmHg (95% CI: -10.67~-7.04; P < 0.001) and diastolic by 3.42 mmHg (95% CI: -4.60~-2.26; P < 0.001). The control rate increased from 60.39% to 76.70% (+ 16.31% points; P < 0.001). MMAS-8 score changed from 4.98 to 6.18 (P < 0.001). Significant changes were also observed in fasting blood glucose and lipid profiles (all P < 0.05). Implementation of the GDS system was associated with pre-post changes in blood pressure control, cardiovascular risk factors, and medication adherence, supporting the potential scalability of AI-based guideline-digitalized systems in resource-constrained primary care settings. However, due to the lack of a control group, high exclusion rate, and potential selection bias, these findings cannot establish causality and should be presented as preliminary associations.
Abbreviations
- GDS:
-
Guideline‑based Digital System
- MMAS-8:
-
8-item Morisky Medication Adherence Scale
- SBP:
-
Systolic Blood Pressure
- DBP:
-
Diastolic Blood Pressure
- HIS:
-
Hospital Information System
- FBG:
-
Fasting Blood Glucose
- LDL-C:
-
Low-density Lipoprotein Cholesterol
- HDL-C:
-
High-density Lipoprotein Cholesterol
- TC:
-
Total Cholesterol
- TG:
-
Triglycerides
- MCID:
-
Minimal Clinically Important Difference
- NCDs:
-
Non-communicable diseases
- STROBE:
-
Strengthening the Reporting of Observational Studies in Epidemiology
Acknowledgements
The authors thank all patients and healthcare professionals who contributed to this study.
Funding
This work was supported by the grant from the Chengdu Municipal Medical Research Project (Grant No. 2025531).
Author information
Author notes
Yan Yang and Yubin Liu have contributed equally to this work.
Authors and Affiliations
Department of Pharmacy, Chengdu Xinjin District Hospital of Traditional Chinese Medicine, Chengdu, China
Yan Yang, Yubin Liu, Zhilin Gou, Ying Xiao & Xinyu Zhang
Department of Information Technology, Chengdu Xinjin District Hospital of Traditional Chinese Medicine, Chengdu, China
Bo Zhou
Authors
- Yan Yang
- Yubin Liu
- Zhilin Gou
- Ying Xiao
- Xinyu Zhang
- Bo Zhou
Corresponding author
Correspondence to Yan Yang.
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethics approval and consent to participate
This retrospective study was approved by the Chengdu Xinjin District Hospital of Traditional Chinese Medicine Ethics Committee (approval number: KY202502). The requirement for written informed consent was waived by the Chengdu Xinjin District Hospital of Traditional Chinese Medicine Ethics Committee because the study involved retrospective analysis of de-identified, routinely collected clinical data, and no active intervention or additional patient contact was performed. All data were anonymized before analysis. The study adhered to the principles of the Declaration of Helsinki and relevant Chinese data protection regulations. The MMAS-8 was used in this study. On June 25, 2025, the U.S. District Court for the District of Nevada ruled in Adherence v. CVS Health Corporation (Case No. 2:24-cv-01590) that the MMAS-4 and MMAS-8 are not protected by copyright. Based on this binding judicial precedent, no license or permission is legally required for the use of this scale. We have fully disclosed this to the editorial office.
Clinical trial number
Not applicable.
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
Yang, Y., Liu, Y., Gou, Z. et al. A guideline-based artificial intelligence system for hypertension in primary care: a single-arm pre–post study. Sci Rep (2026). https://doi.org/10.1038/s41598-026-81038-3
Received: 21 August 2026
Accepted: 12 November 2026
Published: 19 November 2026
DOI: https://doi.org/10.1038/s41598-026-81038-3
Keywords
来源:Nature 健康护理主题 · nature.com