Use of machine learning in osteoarthritis research: a systematic literature review
Francis Berenbaum,
Jérémie Sellam,
David Klatzmann,
Atul J Butte,
Karine Louati,
Encarnita Mariotti-Ferrandiz,
Marie Binvignat,
Valentina Pedoia
Affiliations
Francis Berenbaum
15 Institut national de la santé et de la recherche médicale, Sorbonne Université, Paris, France
Jérémie Sellam
Rheumatology Department, Saint-Antoine Teaching Hospital, DHU i2B, Univ Paris 06, Paris and Inserm UMRS_938, Paris, France
David Klatzmann
Biotherapy (CIC-BTi) and Inflammation Immunopathology-Biotherapy Department (i2B), Hôpital Pitié-Salpêtrière, AP-HP, Paris, France
Atul J Butte
Department of Pediatrics, University of California, San Francsico, CA, United States
Karine Louati
Department of Rheumatology, Hôpital Saint-Antoine, Assistance Publique – Hôpitaux de Paris (AP-HP), Centre de Recherche Saint-Antoine, Inserm UMRS_938, Assistance Publique – Hôpitaux de Paris (AP-HP), Sorbonne Universite, Paris, France
Encarnita Mariotti-Ferrandiz
Clinical Investigation Center for Biotherapies (CIC-BTi) and Immunology-Inflammation-Infectiology and Dermatology Department (3iD), Assistance Publique–Hôpitaux de Paris, Hôpital Pitié-Salpêtrière–Charles Foix Hospital, Paris, France
Marie Binvignat
INSERM UMRS 959, Immunology-Immunopathology-Immunotherapy (i3), Sorbonne Université, Paris, France
Valentina Pedoia
4University of California San Francisco, Radiology and Biomedical Imaging, Musculoskeletal Quantitative Imaging Research, San Francisco, United States of America
Objective The aim of this systematic literature review was to provide a comprehensive and exhaustive overview of the use of machine learning (ML) in the clinical care of osteoarthritis (OA).Methods A systematic literature review was performed in July 2021 using MEDLINE PubMed with key words and MeSH terms. For each selected article, the number of patients, ML algorithms used, type of data analysed, validation methods and data availability were collected.Results From 1148 screened articles, 46 were selected and analysed; most were published after 2017. Twelve articles were related to diagnosis, 7 to prediction, 4 to phenotyping, 12 to severity and 11 to progression. The number of patients included ranged from 18 to 5749. Overall, 35% of the articles described the use of deep learning And 74% imaging analyses. A total of 85% of the articles involved knee OA and 15% hip OA. No study investigated hand OA. Most of the studies involved the same cohort, with data from the OA initiative described in 46% of the articles and the MOST and Cohort Hip and Cohort Knee cohorts in 11% and 7%. Data and source codes were described as publicly available respectively in 54% and 22% of the articles. External validation was provided in only 7% of the articles.Conclusion This review proposes an up-to-date overview of ML approaches used in clinical OA research and will help to enhance its application in this field.
