EUVIMEDEUVIMED entdecken
Open Access

Electronic Health Record-Based Machine Learning Model for Predicting Disease Activity in Patients with Rheumatoid Arthritis

Xiaoying Zhang iD, Chun Li, Zelin Yun, Yi Zhao, Shengguang Li, Wenqiang Fan, Limin Ma, Xiangheng Meng, Ru Li, Fangmin Xu, Jing Yang, Zhanguo Li

Health Data Science · 01.01.2026 · 6

DOI: 10.34133/hds.0461 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Health Data Science, online erschienen am 08.06.2026. Verfasst von Xiaoying Zhang und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Rheumatology & Immunology, Peking University People's Hospital, Beijing, China. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Beijing Municipal Science and Technology Projects, Beijing Natural Science Foundation, China International Medical Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The use of initial clinical assessments to predict therapeutic outcomes via machine learning (ML) is a promising frontier in precision medicine. The study aims to construct ML models capable of predicting disease activity in patients with rheumatoid arthritis (RA), thereby optimizing clinical decision-making and treatment selection.

Methods

This multicenter retrospective study analyzed electronic health records (EHRs) from 1,864 patients with RA across 5 tertiary hospitals in China between 2017 and 2022. The dataset from Peking University People’s Hospital (PKUPH) was employed as the training and internal validation cohort, whereas data from 4 other centers were used for external validation. Longitudinal variables, including demographics, laboratory indices, and medication regimens, at baseline, 3-month, and 6-month follow-up were integrated to capture dynamic disease patterns. Four ML models were trained to predict disease status 6 months post-treatment, with the primary outcome defined as clinical remission (disease activity score in 28 joints with erythrocyte sedimentation rate ≤ 2.6).

Results

The final analysis included 1,629 patients from PKUPH and 235 from 4 other tertiary hospitals. In the internal validation phase, the optimal model achieved an accuracy of 95.3% and an area under the receiver operating characteristic curve (AUROC) of 0.971, with sensitivity, specificity, positive predictive, and negative predictive values of 98.1%, 84.2%, 96.1%, and 91.8%, respectively. The model exhibited generalizability in external validation, presenting an accuracy of 87.3% and an AUROC of 0.922. Furthermore, in the multiclass task of stratifying patients into remission, low, moderate, or high disease activity, the deep neural network model showed an accuracy of 68.6% and AUROC of 0.860.

Conclusions

Longitudinal clinical data extracted from EHRs can be effectively leveraged to develop prognostic models. This study confirms that deep learning approaches trained on large-scale multicenter cohorts can accurately predict disease trajectories in RA, offering a valuable tool for personalized patient management.

Autor:innen und Institutionen

  • Department of Rheumatology & Immunology, Peking University People's Hospital, Beijing, China.
  • Department of Rheumatology and Immunology, Peking University Third Hospital, Beijing, China.
  • Beijing Key Laboratory for Rheumatism Mechanism and Immune Diagnosis (BZ0135), Beijing, China.
  • Department of Rheumatology and Immunology, Xuanwu Hospital Capital Medical University, Beijing, China.
  • Department of Rheumatology and Immunology, Peking University International Hospital, Beijing, China.
  • Department of Rheumatology and Immunology, Xinxiang Central Hospital, Henan, China.

ORCID-Profile: Xiaoying Zhang

Förderung

  • Beijing Municipal Science and Technology Projects
  • Beijing Natural Science Foundation
  • China International Medical Foundation
  • Sichuan Science and Technology Program

Zitieren

APA

Zhang, X., Li, C., Yun, Z., Zhao, Y., Li, S., Fan, W., Ma, L., Meng, X., Li, R., Xu, F., Yang, J., & Li, Z. (2026). Electronic Health Record-Based Machine Learning Model for Predicting Disease Activity in Patients with Rheumatoid Arthritis. Health Data Science, 6. https://doi.org/10.34133/hds.0461

Vancouver

Zhang X, Li C, Yun Z, Zhao Y, Li S, Fan W, et al. Electronic Health Record-Based Machine Learning Model for Predicting Disease Activity in Patients with Rheumatoid Arthritis. Health Data Science. 2026;6. doi:10.34133/hds.0461

BibTeX
@article{Zhang2026,
  author = {Zhang, Xiaoying and Li, Chun and Yun, Zelin and Zhao, Yi and Li, Shengguang and Fan, Wenqiang and Ma, Limin and Meng, Xiangheng and Li, Ru and Xu, Fangmin and Yang, Jing and Li, Zhanguo},
  title = {Electronic Health Record-Based Machine Learning Model for Predicting Disease Activity in Patients with Rheumatoid Arthritis},
  journal = {Health Data Science},
  year = {2026},
  volume = {6},
  doi = {10.34133/hds.0461}
}
Kostenlos starten →