Related Experiment Video
Updated: Feb 18, 2026
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
Published on: January 5, 2024
Use of artificial intelligence and machine learning for the management of fibromyalgia: a scoping review
Ana Laura Clempi Almeida E Silva1, Victor Hugo Palhares Flávio Reis1, Antonieta Santos Andrade Lamoglia1
1Laboratory of Immunology and Omic Sciences - LImCOm. Institute of Natural and Biological Sciences, Federal University of Triângulo Mineiro, Research Building Prof. Aluízio Rosa Prata, Uberaba, Brazil.
Background:
Fibromyalgia (FM) is a complex and multifactorial syndrome characterized by widespread pain, fatigue, cognitive impairment, and other systemic symptoms. The absence of specific biomarkers and the heterogeneous clinical presentation pose significant diagnostic challenges.
Objective:
This scoping review aims to explore the current applications of artificial intelligence (AI) and machine learning (ML) in the diagnosis and clinical management of FM.
Methods:
A systematic search was conducted in PubMed, EMBASE, and the Cochrane Library using defined keywords related to FM and AI/ML. Studies were included if they addressed ML applications in FM patients. Following PRISMA-ScR guidelines, 43 studies published between 2011 and 2024 were included and analyzed for ML techniques used, diagnostic targets, data types, and clinical relevance.
Results:
As expected, the majority of studies done so far focused on improving diagnostic accuracy through supervised algorithms such as support vector machines, neural networks, and ensemble models, as well as unsupervised clustering and dimensionality reduction techniques. Notable findings include the identification of neurophysiological signatures via fMRI, gene expression patterns, retinal imaging changes, and metabolomic biomarkers that distinguish FM patients from controls. For instance, one study investigating circulating microRNAs used a Random Forest model to identify 11 microRNAs (e.g. hsa-miR-28-5p, hsa-miR-29a-3p, hsa-miR-150-5p) capable of differentiating patients with FM, ME/CFS, and healthy controls, suggesting their potential as biomarkers for more accurate diagnoses. Reported model accuracies ranged from 82% to 100%, although most studies were pilot-based with small and imbalanced samples, limiting generalizability.
Conclusion:
AI and ML offer promising tools to overcome longstanding limitations in FM diagnosis and treatment. While current findings demonstrate significant potential, larger, multicenter studies with rigorous validation protocols are essential to finally establish these approaches as clinically reliable solutions.
