AI-based tool to improve rheumatology referrals and flare management
Research type
Research Study
Full title
RMD-Health: AI-based decision support system for early detection and flare prediction of inflammatory arthritis to improve referrals and follow-up of patients with rheumatic and musculoskeletal diseases (RMD)
IRAS ID
334608
Contact name
Weizi Li
Contact email
Sponsor organisation
University of Reading
Clinicaltrials.gov Identifier
EP/Y019393/1, Other funder's reference number
Duration of Study in the UK
2 years, 11 months, 30 days
Research summary
Over 20 million people in the UK live with rheumatic and musculoskeletal diseases (RMD). Inflammatory arthritis (IA) and non-inflammatory conditions (NIC) are the two major subdivisions of RMD, each with very different treatment and management pathways (e.g. disease-modifying drugs for IA; surgeries such as joint replacements for NIC e.g. osteoarthritis). Accurate and early detection and differentiation of IA and NIC are critical for patients to be referred to the right specialists and receive the right treatment rapidly. However early detection of IA is challenging because IA often presents with non-specific symptoms and there is currently no diagnostically definitive single biomarker for IA detection.
Furthermore, RMD flare-up are unpredictable and very heterogeneous in their manifestations between individual patients. There is no marker identified for an impending flare and there is a lack of understanding of patient heterogeneity and triggers in RMD disease flare. Sudden flares always lead to additional hospitalisations, follow-up visits and decreased quality of life in general. If early signs of flare can be spotted and early intervention is in place, it will delay disease progression and prevent the development of irreversible joint damage and functional disability caused by flare. However there is currently no risk stratification tool that can predict patient flare early and accurately in practice for RMD.
This project aims to develop and validate RMD-Health, an AI-based risk stratification decision support system, for accurate and fast referral for patients with suspected RMD, and prediction of flare of patients with inflammatory arthritis.
1) Evaluating and optimising the risk stratification tool to maximise the accuracy
2) Developing a full software prototype of a real-time decision support system that incorporates user requirements;3) Piloting the prototype in Royal Berkshire NHS Foundation Trust and Oxford University Hospitals rheumatology pathways
4) Health economics and feedback analysis of the pilots.
REC name
South Central - Berkshire B Research Ethics Committee
REC reference
25/SC/0137
Date of REC Opinion
5 Jun 2025
REC opinion
Further Information Favourable Opinion