Streamlining Anomaly Detection for Rheumatology: A Systematic Literature Review
Loading...
Files
Size: 1.57 MB, File format: Adobe PDF
Date
Authors
Ijadi Maghsoodi, Abtin
Quincey, Vicki
Rasouli Panah, Hamidreza
Parsons, Matthew
Wood, Lincoln C
Walker, Cameron
O’Sullivan, Michael
Madanian, Samaneh
Supervisor
Item type
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Science and Business Media LLC
Abstract
This study investigated the effectiveness of Artificial Intelligence (AI) and Machine Learning (ML) approaches for anomaly detection in rheumatology, focusing on their potential to improve clinical insights and identify deviations in disease patterns and diagnostics. This systematic review adhered to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive search was conducted across PubMed, Cochrane Library, Web of Science, Scopus, and EBSCO databases to identify cohort studies that developed and/or validated AI and ML models for anomaly detection in rheumatology. Data were extracted and studies were critically evaluated using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines and the Prediction Model Risk of Bias Assessment Tool (PROBAST), with the search last updated on January 28, 2025. The systematic search yielded 2,089 unique citations, from which 40 studies met the inclusion criteria. AI and ML models included demonstrated high performance measures. Most studies focused on rheumatoid arthritis, utilising imaging data, biomarkers, and electronic health records. The quality assessment revealed that 72.5% of the studies had a low risk of bias; however, 25% exhibited high risk due to methodological limitations such as insufficient validation and unclear outcome definitions. Reporting standards were generally well adhered to, although critical gaps such as blinding and risk stratification were frequently overlooked. This study identified a predominance of unclear and high risks of bias across many models, highlighting the need for transparency improvements and addressing such limitations. Key areas for enhancement include incorporating robust calibration measures to improve models and performance measures.Graphical abstract
Description
Keywords
4605 Data Management and Data Science, 46 Information and Computing Sciences, Data Science, Arthritis, Bioengineering, Networking and Information Technology R&D (NITRD), Machine Learning and Artificial Intelligence, 4.1 Discovery and preclinical testing of markers and technologies, 3 Good Health and Well Being, 0801 Artificial Intelligence and Image Processing, 4605 Data management and data science
Source
International Journal of Data Science and Analytics, ISSN: 2364-415X (Print); 2364-4168 (Online), Springer Science and Business Media LLC, 22(1), 249-. doi: 10.1007/s41060-026-01191-w
Publisher's version
Rights statement
Creative Commons Attribution 4.0
Permanent link
Endorsement
Review
Supplemented By
Referenced By
Creative Commons license
Except where otherwise noted, this item's license is described as Creative Commons Attribution 4.0