Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Medical Informatics

Date Submitted: Jan 4, 2026
Date Accepted: Mar 6, 2026

The final, peer-reviewed published version of this preprint can be found here:

An Intelligent Interactive Management Platform for Rheumatoid Arthritis Care: Real-World Observational Study

Zhang Z, Zhang X, Zhang L, Du M, Zhang L, Yang S, Cai X, Hou S

An Intelligent Interactive Management Platform for Rheumatoid Arthritis Care: Real-World Observational Study

JMIR Med Inform 2026;14:e90784

DOI: 10.2196/90784

PMID: 41926687

An Intelligent Interactive Management Platform for Rheumatoid Arthritis Care: Development and Real-World Evaluation Study

  • Ziyun Zhang; 
  • Xinyue Zhang; 
  • Li Zhang; 
  • Mingyan Du; 
  • Lijuan Zhang; 
  • Siyu Yang; 
  • Xiaoli Cai; 
  • Shengchao Hou

ABSTRACT

Background:

Effective post-discharge management is essential for maintaining disease control and improving long-term outcomes in rheumatoid arthritis (RA). Digital health technologies, particularly intelligent management platforms, provide new opportunities for continuous care and self-management in real-world settings.

Objective:

This study aimed to develop a nurse-led, artificial intelligence (AI)–assisted interactive management platform for post-discharge rheumatoid arthritis care and to examine its association with patient outcomes in a real-world clinical setting.

Methods:

A single-center, multi-campus, real-world observational study with a quasi-experimental framework was conducted at Tongji Hospital between November 2024 and October 2025. Participants were allocated to either a platform-based management group (Campus 1, n=184) or a comparison group receiving routine post-discharge care (Campus 2, n=157). The platform enabled remote monitoring through a smartphone application, which collected joint symptoms, fatigue, medication adherence, laboratory results, and emotional status, with data uploaded to a secure cloud server. The AI system analyzed data in real-time and alerted healthcare providers to abnormalities. Nurses and health coaches delivered personalized education and interventions. Primary outcomes were changes in Disease Activity Score in 28 joints (DAS28) and Health Assessment Questionnaire II (HAQ-II) scores at discharge and at six-months follow-up. Secondary outcomes included medication adherence and patient satisfaction, assessed at six months.

Results:

A total of 341 RA completed the 6-month follow-up. DAS28 scores decreased significantly in the platform-based management group at six months (mean 5.04, SD 1.38 vs mean 4.27, SD 1.20; P<.001), showing a greater reduction than in the comparison group (P=.023). HAQ-II scores improved significantly in the platform-based management group (mean 2.45, SD 0.75 vs. mean 1.67, SD 0.56, P<.001), while the comparison group showed no significant change (P=.120; between-group P<.001). Medication adherence was higher in the platform-based group (90.2% vs 79.6%, P=.006). Overall healthcare satisfaction was also higher in the platform-based group (95.7% vs 76.4%, P<.001), with a greater proportion reporting “very satisfied” (81.5% vs 37.6%).

Conclusions:

The intelligent interactive management platform markedly enhanced disease control, functional status, medication adherence, and satisfaction among RA patients post-discharge. This nurse-led, AI-assisted system represents a promising model for improving outpatient RA management. Clinical Trial: ClinicalTrials; https://clinicaltrials.gov/study/ChiCTR2500115743


 Citation

Please cite as:

Zhang Z, Zhang X, Zhang L, Du M, Zhang L, Yang S, Cai X, Hou S

An Intelligent Interactive Management Platform for Rheumatoid Arthritis Care: Real-World Observational Study

JMIR Med Inform 2026;14:e90784

DOI: 10.2196/90784

PMID: 41926687

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.