The Current State of Big Data Use and Artificial Intelligence in RMDs: A Systematic Literature Review Informing EULAR Recommendations

Joanna Kedra¹, Timothy R.D. Radstake ², Aridaman Pandit ³, Xenofon Baraliakos ⁴, Francis Berenbaum ⁵, Axel Finckh ⁶, Bruno Fautrel ⁷, Tanja Stamm ⁸, David Gomez-Cabrero ⁹, Christian Pristipino ¹⁰, Remy Choquet ¹¹, Hervé Servy ¹², Simon Stones ¹³, Gerd Burmester ¹⁴ and Laure Gossec ¹⁵, ¹Sorbonne Université, Institut Pierre Louis d'Epidémiologie et de Santé Publique (iPLESP), UMR S1136, Paris France, Paris, France, ²Department of Rheumatology/Clinical Immunology, University Medical Center Utrecht, Utrecht, The Netherlands., Utrecht, Netherlands, ³Dept. of Rheumatology, Clinical Immunology and Laboratory for Translational Immunology, University Medical Center Utrecht, The Netherlands, Utrecht, Netherlands, ⁴Rheumazentrum Ruhrgebiet-Ruhr-University Bochum, Herne, Germany, Herne, Germany, ⁵Sorbonne Université-Inserm CDR Saint-Antoine, AP-HP, Paris, France, ⁶Division of Rheumatology, Geneva University Hospital, Switzerland, Geneva, Switzerland, ⁷Pitié-Salpêtrière Hospital, Department of Rheumatology, AP-HP, Sorbonne University, UPMC university, Paris, Ile-de-France, France, ⁸Medical University of Vienna, Vienna, Austria, ⁹Translational Bioinformatics Unit, Navarra Biomed, Departamento de Salud-Universidad Pública de Navarra, Pamplona, Navarra, Spain, Pamplona, Spain, ¹⁰Ospedale San Filippo Neri, Rome, Italy., Rome, Italy, ¹¹INSERM U1142, Orange Healthcare, France, Paris, France, ¹²Sanoia e-health services, France, Paris, France, ¹³School of Healthcare, University of Leeds, Leeds, UK, Leeds, United Kingdom, ¹⁴Charité—University Medicine Berlin, Berlin, Germany, ¹⁵Sorbonne Université and Hôpital Pitié-Salpêtrière, Paris, France

Meeting: 2019 ACR/ARP Annual Meeting

Keywords: Big data, rheumatic disease and artificial intelligence

Session Information

Date: Tuesday, November 12, 2019

Title: Epidemiology & Public Health Poster III: OA, Gout, & Other Diseases

Session Type: Poster Session (Tuesday)

Session Time: 9:00AM-11:00AM

Background/Purpose: Big data are defined as data sets that are too large or complex for traditional data-processing application software to adequately deal with. Artificial Intelligence (AI) includes various statistical techniques which can deal with big data. The current use of these concepts in publications related to rheumatic and musculoskeletal diseases (RMDs) is unknown. Therefore, the aim of this literature review was to assess the current use of big data and AI in the field of RMDs.

Methods: A systematic literature review was performed in PubMed MEDLINE in November 2018, with key words referring to big data, artificial intelligence and RMDs. All original reports published in English were analyzed. A mirror literature review was also performed outside of RMDs on the same number of articles. The number of data analyzed, data sources and statistical methods used (traditional statistics, AI or both) were collected. The analysis compared findings within and beyond the field of RMDs.

Results: Of 567 articles relating to RMDs, 55 met the inclusion criteria and were analyzed, as well as 55 articles in other medical fields. The mean year of publication was 2014 for the RMDs SLR, with 72% of the articles published between 2013 and 2018; whereas the articles included in the mirror non-RMD review were all published in 2018 or 2019. Among RMDs, the most represented fields were inflammatory joint diseases (N=22, 40%) and osteoarthritis (N=16, 29%). The 3 most represented diseases were: knee osteoarthritis (N=13, 24%), rheumatoid arthritis (N=12, 22%) and post-menopausal osteoporosis (N=6, 11%). Outside of RMDs, the most represented medical fields were: oncology (N=14, 25%), neurology (N=8, 15%), infectious diseases (N=6, 11%), ophtalmology (N=5, 9%) and psychiatry (N=5, 9%).

Only two articles in the field of RMDs (4%) and seven articles out of the field of RMDs (13%) mentioned a clear definition of big data. The mean number of data points was 746 million [range 2000–5 billion] in RMDs, and 9.1 billion [range 100,000 – 200 billion] outside of RMDs.

Data sources were varied: in RMDs, 26 (47%) were clinical, 8 (15%) biological and 16 (29%) radiological; whereas outside of RMDs, the distribution was quite homogenous between clinical, biological and imaging sources (respectively 31%, 31% and 29%).

Both traditional and AI methods were used to analyze big data (respectively 10 (18%) and 45 (82%) in RMDs and 8 (15%) and 47 (85%) out of RMDs). Machine learning was used in almost all AI papers (44/45 in RMDs and 47/47 outside of RMDs), and among machine learning methods, the most represented was artificial neural network (20/44 in RMDs, and 24/47 out of RMDs). More details are provided in Figure 1.

Conclusion: Big data sources and types are varied within the field of RMDs, and methods used to analyze big data were heterogeneous. These findings informed a EULAR taskforce developing recommendations for big data in RMDs.

Figure 1: Distribution of machine learning methods in RMDs and outside of RMDs

Disclosure: J. Kedra, None; T. Radstake, None; A. Pandit, None; X. Baraliakos, AbbVie, 2, 5, 8, Abbvie, 2, 5, 8, BMS, 2, 5, 8, 9, Bristol-Myers Squibb, 2, 5, 8, Celgene, 2, 5, 8, 9, Chugai, 2, 5, 8, 9, Janssen, 2, 5, 8, 9, Lilly, 2, 8, 9, Merck, 2, 5, 8, MSD, 2, 5, 8, 9, Novartis, 2, 5, 8, 9, Novatis, 2, 5, 8, Pfizer, 2, 5, 8, 9, UCB, 2, 5, 8, 9, UCB Pharma, 2, 5, 8, Werfen, 2, 5, 8; F. Berenbaum, 4P Pharma, 2; A. Finckh, Eli-Lilly, 5, 8, Pfizer, 2, 5, 8; B. Fautrel, AbbVie, 2, 5, 8, Biogen, 5, 8, BMS, 5, 8, Boehringer Ingelheim, 8, Celgene, 5, 8, Eli Lilly and Company, 2, 5, Janssen, 5, 8, Lilly, 8, Medac, 5, 8, MSD, 2, 5, 8, NORDIC Pharma, 5, 8, Novartis, 5, 8, Pfizer, 2, 5, 8, Roche, 5, 8, Sanofi-Aventis, 5, SOBI, 5, 8, UCB, 5, 8; T. Stamm, Janssen, 8, MSD, 8, Novartis, 8, Roche, 2, 8; D. Gomez-Cabrero, None; C. Pristipino, None; R. Choquet, Orange Healthcare, 3; H. Servy, Sanoïa e-health Services, 3; S. Stones, None; G. Burmester, AbbVie, 5, 8, Abbvie, 5, 8, AbbVie Inc, Eli Lilly, Gilead, Janssen, Merck, Roche, Pfizer, and UCB Pharma., 5, 8, AbbVie Inc., 5, 8, BMS, 5, 8, Eli Lilly, 5, 8, Eli Lilly and Company, 5, Gilead, 5, 8, Gilead Sciences, Inc., 5, 8, Janssen, 5, 8, Lilly, 5, 8, Merck, 5, 8, Merck Shar & Dohme, 5, 8, MSD, 5, 8, Pfizer, 2, 5, 8, Roche, 2, 5, 8, Roche, Sanofi-Genzyme, 5, 8, Sanofi, 5, 8, UCB, 5, 8, Union Chimique Belge, 2, 5, 8; L. Gossec, Abbvie, 5, AbbVie, 5, Abbvie, Biogen, BMS, Celgene, Lilly, Novartis, Pfizer, SAnofi-Aventis, UCB, 5, Amgen, 5, Biogen, 5, BMS, 2, 5, Celgene, 5, Celgene Corporation, 2, Janssen, 5, Lilly, 2, 5, MSD, 5, Nordic Pharma, 5, Novartis, 5, Pfizer, 2, 5, Sanofi, 5, Sanofi-Aventis, 5, UCB, 5.

To cite this abstract in AMA style:

Kedra J, Radstake T, Pandit A, Baraliakos X, Berenbaum F, Finckh A, Fautrel B, Stamm T, Gomez-Cabrero D, Pristipino C, Choquet R, Servy H, Stones S, Burmester G, Gossec L. The Current State of Big Data Use and Artificial Intelligence in RMDs: A Systematic Literature Review Informing EULAR Recommendations [abstract]. Arthritis Rheumatol. 2019; 71 (suppl 10). https://acrabstracts.org/abstract/the-current-state-of-big-data-use-and-artificial-intelligence-in-rmds-a-systematic-literature-review-informing-eular-recommendations/. Accessed .

« Back to 2019 ACR/ARP Annual Meeting

ACR Meeting Abstracts - https://acrabstracts.org/abstract/the-current-state-of-big-data-use-and-artificial-intelligence-in-rmds-a-systematic-literature-review-informing-eular-recommendations/