Early detection of inflammatory arthritis to improve referrals using multimodal machine learning from blood testing, semi-structured and unstructured patient records - Proceedings

Aug 6, 2026

Upload by Logic

Early detection of inflammatory arthritis (IA) supports efficient, accurate hospital referral triage, enabling timely treatment and helping prevent deterioration of disease course under constrained healthcare resources. Manual assessment remains labor-intensive and inefficient, requiring evaluation of extensive clinical information for every referral from General Practice to hospitals. Although machine learning can automate repetitive assessments, many IA models depend mainly on blood test results, which are often unavailable at referral time. This study introduces an ensemble learning method integrating multimodal semi-structured and unstructured patient records to assist decision-making, achieving precision 0.89, recall 0.85, F1 0.86, accuracy 0.85, and G-Mean 0.88.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

1. Introduction

Early detection of inflammatory arthritis to improve referrals using multimodal machine learning from blood testing, semistructured and unstructured patient records Conference or Workshop Item Published Version Creative Commons: Attribution-Noncommercial-No Derivative Works 4.0 Open Access Wang, B. ORCID: [https://orcid.org/0000-0003-1403-1847](https://orcid.org/0000-0003-1403-1847) , Li, W. ORCID: [https://orcid.org/0000-0003-2878-3185](https://orcid.org/0000-0003-2878-3185) , Bradlow, A. , Chan, A. T. Y. and Bazuaye, E. (2024) Early detection of inflammatory arthritis to improve referrals using multimodal machine learning from blood testing, semi-structured and unstructured patient records. In: The 57th Hawaii International Conference on System Sciences, 3-6 Jan 2024, Hawaii, pp. 3416-3424. Available at [https://centaur. reading.ac. uk/1](https://centaur. reading.ac. uk/1) 13221/ It is advisable to refer to the publisher’s version if you intend to cite from the work. See Guidance on citing. Published version at: [https://hdl. handle. net/10125/106796](https://hdl. handle. net/10125/106796) All outputs in CentAUR are protected by Intellectual Property Rights law, including copyright law. Copyright and IPR is retained by the creators or other copyright holders . Terms and conditions for use of this material are defined in the End User Agreement . [www. reading.ac. uk/centaur](www. reading.ac. uk/centaur) CentAUR Central Archive at the University of Reading Reading’s research outputs online Proceedings of the 57th Hawaii International Conference on System Sciences | 2024 Early detection of inflammatory arthritis to improve referrals using multimodal machine learning from blood testing, semi-structured and unstructured patient records Bing Wang Informatics Research Centre, Henley Business School, University of Reading, UK [bing.wang@pgr.reading.ac.uk](bing.wang@pgr.reading.ac.uk) Weizi Li Informatics Research Centre, Henley Business School, University of Reading, UK [weizi.li@henley.ac.uk](weizi.li@henley.ac.uk) Anthony Bradlow Rheumatology Department, Royal Berkshire NHS Foundation Trust, UK [anthony.bradlow@royalberkshire.nhs.uk](anthony.bradlow@royalberkshire.nhs.uk) Antoni T.Y. Chan Rheumatology Department, Royal Berkshire NHS Foundation Trust, UK [antoni.chan@royalberkshire.nhs.uk](antoni.chan@royalberkshire.nhs.uk) Eghosa Bazuaye Informatics Department, Royal Berkshire NHS Foundation Trust, UK [eghosa.bazuaye@royalberkshire.nhs.uk](eghosa.bazuaye@royalberkshire.nhs.uk) Abstract Early detection of inflammatory arthritis (IA) is critical to efficient and accurate hospital referral triage for timely treatment and preventing the deterioration of the IA disease course, especially under limited healthcare resources. The manual assessment process is the most common approach in practice for the early detection of IA, but it is extremely labor-intensive and inefficient. A large amount of clinical information needs to be assessed for every referral from General Practice (GP) to the hospitals. Machine learning shows great potential in automating repetitive assessment tasks and providing decision support for the early detection of IA. However, most machine learning-based methods for IA detection rely on blood testing results. But in practice, blood testing data is not always available atthe point of referrals, so we need methods to leverage multimodal data such as semi-structured and unstructured data for early detection of IA. In this research, we present an ensemble learning-based method using multimodal data to assist decisionmaking in the early detection of IA. Experimental results show the precision, recall, F1-Score, accuracy, and G-Mean of 0.89, 0.85, 0.86, 0.85, and 0.88. To the best of our knowledge, our study is the first attempt to utilize multimodal data to support the early detection of IA from GP referrals. Keywords: Early detection of inflammatory arthritis;

FAQs

Why is early detection of inflammatory arthritis important for referrals?

Early detection enables efficient and accurate hospital referral triage for timely treatment and helps prevent deterioration of the IA disease course, especially when healthcare resources are limited.

What limitation affects many machine learning methods for IA detection?

Most methods rely on blood testing results, but blood testing data is not always available at the point when referrals are made.

How does the proposed approach address missing blood test data?

The study uses an ensemble learning method with multimodal data, leveraging semi-structured and unstructured patient records to support early IA detection from GP referrals.

Aug 6, 2026

Upload by Logic