Matthew S. Harkey , Kerry E. Costello , Bella Mehta , Chunyi Wen , Anne-Marie Malfait , Henning Madry , Brooke Patterson
{"title":"Artificial intelligence in osteoarthritis research: summary of the 2025 OARSI pre-congress workshop","authors":"Matthew S. Harkey , Kerry E. Costello , Bella Mehta , Chunyi Wen , Anne-Marie Malfait , Henning Madry , Brooke Patterson","doi":"10.1016/j.ocarto.2025.100687","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>Artificial intelligence (AI) is transforming musculoskeletal research, offering new approaches to diagnosis, prognosis, and patient management in osteoarthritis (OA). However, implementation and ethical challenges persist. This manuscript summarizes insights from the OARSI 2025 Pre-Congress Workshop on Artificial Intelligence in Osteoarthritis Research, highlighting opportunities and challenges in applying AI across biomechanics, imaging, and clinical research domains.</div></div><div><h3>Design</h3><div>The workshop, organized by the OARSI Early Career Investigator Committee and co-chaired by Drs. Matthew Harkey and Brooke Patterson, convened experts to discuss the use of AI in real-world biomechanics data collection, radiomics for imaging-based biomarkers, and large language models (LLMs) for clinical and research applications. Emphasis was placed on the need for interdisciplinary collaboration and ethical oversight.</div></div><div><h3>Results</h3><div>In biomechanics, AI-driven markerless motion capture and wearable sensors enable scalable, ecologically valid data collection, though issues such as class imbalance, data privacy, and model interpretability remain. In imaging, radiomics and deep learning models show promise for early OA detection and progression prediction but face challenges in domain adaptation and external validation. In clinical research, LLMs can streamline documentation and thematic analysis but must address concerns around bias, data security, and transparency. Across domains, transparency, reproducibility, and ethical use of AI were emphasized as critical for maintaining scientific rigor.</div></div><div><h3>Conclusions</h3><div>Cross-disciplinary collaboration and AI literacy are essential to responsibly advance AI integration in OA research. The workshop's collective insights call for ethical, patient-centered approaches that leverage AI's strengths while preserving research integrity and trust.</div></div>","PeriodicalId":74377,"journal":{"name":"Osteoarthritis and cartilage open","volume":"7 4","pages":"Article 100687"},"PeriodicalIF":2.8000,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Osteoarthritis and cartilage open","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2665913125001232","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Objective
Artificial intelligence (AI) is transforming musculoskeletal research, offering new approaches to diagnosis, prognosis, and patient management in osteoarthritis (OA). However, implementation and ethical challenges persist. This manuscript summarizes insights from the OARSI 2025 Pre-Congress Workshop on Artificial Intelligence in Osteoarthritis Research, highlighting opportunities and challenges in applying AI across biomechanics, imaging, and clinical research domains.
Design
The workshop, organized by the OARSI Early Career Investigator Committee and co-chaired by Drs. Matthew Harkey and Brooke Patterson, convened experts to discuss the use of AI in real-world biomechanics data collection, radiomics for imaging-based biomarkers, and large language models (LLMs) for clinical and research applications. Emphasis was placed on the need for interdisciplinary collaboration and ethical oversight.
Results
In biomechanics, AI-driven markerless motion capture and wearable sensors enable scalable, ecologically valid data collection, though issues such as class imbalance, data privacy, and model interpretability remain. In imaging, radiomics and deep learning models show promise for early OA detection and progression prediction but face challenges in domain adaptation and external validation. In clinical research, LLMs can streamline documentation and thematic analysis but must address concerns around bias, data security, and transparency. Across domains, transparency, reproducibility, and ethical use of AI were emphasized as critical for maintaining scientific rigor.
Conclusions
Cross-disciplinary collaboration and AI literacy are essential to responsibly advance AI integration in OA research. The workshop's collective insights call for ethical, patient-centered approaches that leverage AI's strengths while preserving research integrity and trust.