Crossmark

Development of a risk assessment model for multimorbidity of diabetes, hypertension, and coronary heart disease with XGBoost in primary care in Shanghai, China: a retrospective study

Crossref DOI link: https://doi.org/10.1186/s12872-025-05479-w

Published Online: 2026-01-05

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Chen, Ning

Zhang, Peipei

Fan, Feng

Jin, Hua

Chen, Yanying

Liu, Jing

Chen, Lin

Wan, Xiaoguang

Guo, Jing

Yang, Zaijia

Sun, Lei

Shan, Houqian

Yu, Dehua

Wang, Zhaoxin

Shi, Jianwei
Funding

Funding for this research was provided by:

National Natural Science Foundation of China (72104183)

Discipline Leader Climbing Program (Ye2202103)

Shanghai Leading Talents Program (YDH-20170627)

National Key Research and Development Program of China (2022YFC3601505)

Project of Chinese Engineering S&T Strategy for Development (46000023T000000923833)

Hainan Province Clinical Medical Center, The Excellent Talent Team of Hainan Province (No.QRCBT202121)

Hainan Provincial Key Research and Development Program (ZDYF2020147)

soft science project of Shanghai Science and Technology Commission (22692107200)
License Information

Text and Data Mining valid from 2026-01-05

Version of Record valid from 2026-02-03
More Information

Article History

Received: 19 July 2025

Accepted: 23 December 2025

First Online: 5 January 2026

Declarations

:

: All methods were carried out in accordance with relevant guidelines and regulations. The research was conducted in accordance with the Declaration of Helsinki, with a continuous concern to protect the dignity, integrity and privacy of the participants, including the confidentiality of their data.The studies involving human participants were reviewed and approved by the Ethics Committee of Tongji University (ref: LL-2016-ZRKX-017). The projects adopted a centralised, project-level consent model. Under the premise of adhering to the initially agreed research scope, it was able to conduct large-scale participant recruitment in an ethical and efficient manner without the need to repeat the single consent process. All the patient data used in this study were strictly anonymized before analysis. Given the large scale and centralized nature of the data processing, it was really impossible to re-identify individuals. Participants provided their written informed consent before participating in this study.

: Not applicable.

: The authors declare no competing interests.

Document is current

Any future updates will be listed below