scholarly journals Current status of use of big data and artificial intelligence in RMDs: a systematic literature review informing EULAR recommendations

RMD Open ◽  
2019 ◽  
Vol 5 (2) ◽  
pp. e001004 ◽  
Author(s):  
Joanna Kedra ◽  
Timothy Radstake ◽  
Aridaman Pandit ◽  
Xenofon Baraliakos ◽  
Francis Berenbaum ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Musculoskeletal Diseases ◽  
Data Sources ◽  
Current Status ◽  
Eular Recommendations ◽  
European League Against Rheumatism ◽  
Data Points

ObjectiveTo assess the current use of big data and artificial intelligence (AI) in the field of rheumatic and musculoskeletal diseases (RMDs).MethodsA systematic literature review was performed in PubMed MEDLINE in November 2018, with key words referring to big data, AI and RMDs. All original reports published in English were analysed. A mirror literature review was also performed outside of RMDs on the same number of articles. The number of data analysed, data sources and statistical methods used (traditional statistics, AI or both) were collected. The analysis compared findings within and beyond the field of RMDs.ResultsOf 567 articles relating to RMDs, 55 met the inclusion criteria and were analysed, as well as 55 articles in other medical fields. 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. Both traditional and AI methods were used to analyse big data (respectively, 10 (18%) and 45 (82%) in RMDs and 8 (15%) and 47 (85%) out of RMDs). Machine learning represented 97% of AI methods in RMDs and among these methods, the most represented was artificial neural network (20/44 articles in RMDs).ConclusionsBig data sources and types are varied within the field of RMDs, and methods used to analyse big data were heterogeneous. These findings will inform a European League Against Rheumatism taskforce on big data in RMDs.

scholarly journals EULAR points to consider for the use of big data in rheumatic and musculoskeletal diseases

2019 ◽  
Vol 79 (1) ◽  
pp. 69-76 ◽  
Author(s):  
Laure Gossec ◽  
Joanna Kedra ◽  
Hervé Servy ◽  
Aridaman Pandit ◽  
Simon Stones ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Musculoskeletal Diseases ◽  
Task Force ◽  
Data Interpretation ◽  
Current Status ◽  
Privacy By Design ◽  
Design Data ◽  
European League Against Rheumatism ◽  
International Experts

BackgroundTremendous opportunities for health research have been unlocked by the recent expansion of big data and artificial intelligence. However, this is an emergent area where recommendations for optimal use and implementation are needed. The objective of these European League Against Rheumatism (EULAR) points to consider is to guide the collection, analysis and use of big data in rheumatic and musculoskeletal disorders (RMDs).MethodsA multidisciplinary task force of 14 international experts was assembled with expertise from a range of disciplines including computer science and artificial intelligence. Based on a literature review of the current status of big data in RMDs and in other fields of medicine, points to consider were formulated. Levels of evidence and strengths of recommendations were allocated and mean levels of agreement of the task force members were calculated.ResultsThree overarching principles and 10 points to consider were formulated. The overarching principles address ethical and general principles for dealing with big data in RMDs. The points to consider cover aspects of data sources and data collection, privacy by design, data platforms, data sharing and data analyses, in particular through artificial intelligence and machine learning. Furthermore, the points to consider state that big data is a moving field in need of adequate reporting of methods and benchmarking, careful data interpretation and implementation in clinical practice.ConclusionThese EULAR points to consider discuss essential issues and provide a framework for the use of big data in RMDs.

Artificial intelligence in safety-critical systems: a systematic review

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yue Wang ◽  
Sai Ho Chung
Keyword(s):  
Artificial Intelligence ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Current Status ◽  
Critical Systems ◽  
Research Directions ◽  
Content Type ◽  
Critical Domain ◽  
Safety Critical ◽  
Safety Critical Systems

PurposeThis study is a systematic literature review of the application of artificial intelligence (AI) in safety-critical systems. The authors aim to present the current application status according to different AI techniques and propose some research directions and insights to promote its wider application.Design/methodology/approachA total of 92 articles were selected for this review through a systematic literature review along with a thematic analysis.FindingsThe literature is divided into three themes: interpretable method, explain model behavior and reinforcement of safe learning. Among AI techniques, the most widely used are Bayesian networks (BNs) and deep neural networks. In addition, given the huge potential in this field, four future research directions were also proposed.Practical implicationsThis study is of vital interest to industry practitioners and regulators in safety-critical domain, as it provided a clear picture of the current status and pointed out that some AI techniques have great application potential. For those that are inherently appropriate for use in safety-critical systems, regulators can conduct in-depth studies to validate and encourage their use in the industry.Originality/valueThis is the first review of the application of AI in safety-critical systems in the literature. It marks the first step toward advancing AI in safety-critical domain. The paper has potential values to promote the use of the term “safety-critical” and to improve the phenomenon of literature fragmentation.

Artificial intelligence and big data in tourism: a systematic literature review

2020 ◽  
Vol 11 (2) ◽  
pp. 343-367 ◽  
Author(s):  
Dimitra Samara ◽  
Ioannis Magnisalis ◽  
Vassilios Peristeras
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Literature Review ◽  
Systematic Literature Review ◽  
New Technologies ◽  
Recent Literature ◽  
Content Type ◽  
Analysis Methodology ◽  
Tourism Sector

Purpose This paper aims to research, identify and discuss the benefits and overall role of big data and artificial intelligence (BDAI) in the tourism sector, as this is depicted in recent literature. Design/methodology/approach A systematic literature review was conducted under the McKinsey’s Global Institute (Talwar and Koury, 2017) methodological perspective that identifies the four ways (i.e. project, produce, promote and provide) in which BDAI creates value. The authors enhanced this analysis methodology by depicting relevant challenges as well. Findings The findings imply that BDAI create value for the tourism sector through appropriately identified disseminations. The benefits of adopting BDAI strategies include increased efficiency, productivity and profitability for tourism suppliers combined with an extremely rich and personalized experience for travellers. The authors conclude that challenges can be bypassed by adopting a BDAI strategy. Such an adoption will stand critical for the competitiveness and resilience of existing established and new players in the tourism sector. Originality/value Besides identifying the benefits that BDAI brings in the tourism sector, the research proposes a guidebook to overcome challenges when introducing such new technologies. The exploration of the BDAI literature brings important implication for managers, academicians and consumers. This is the first systematic review in an area and contributes to the broader e-commerce marketing, retailing and e-tourism research.

scholarly journals SAT0052 THERAPEUTIC STRATEGIES IN DIFFICULT-TO-TREAT RHEUMATOID ARTHRITIS: PRELIMINARY RESULTS OF A SYSTEMATIC LITERATURE REVIEW INFORMING THE 2020 EULAR RECOMMENDATIONS FOR THE MANAGEMENT OF DIFFICULT-TO-TREAT RHEUMATOID ARTHRITIS

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 957-957
Author(s):  
N. M. T. Roodenrijs ◽  
A. Hamar ◽  
M. Kedves ◽  
G. Nagy ◽  
J. M. Van Laar ◽  
...  
Keyword(s):  
Rheumatoid Arthritis ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Therapeutic Strategies ◽  
Eular Recommendations ◽  
Management Interventions ◽  
Fatigue Exercise ◽  
Factor Inhibitor ◽  
Management Recommendations ◽  
Sat 1

Background:Rheumatoid arthritis (RA) patients treated according to European League Against Rheumatism (EULAR) recommendations failing ≥2 biological or targeted synthetic disease-modifying antirheumatic drugs (b/tsDMARDs) with a different mode of action who still have complaints which may be suggestive of active disease may be defined as suffering from ‘difficult-to-treat RA’. Management recommendations for RA focus predominantly on the earlier phases of the disease and specific recommendations for difficult-to-treat RA patients are currently lacking.1Objectives:To systematically summarise evidence in the literature on pharmacological and non-pharmacological therapeutic strategies for difficult-to-treat RA patients, informing the 2020 EULAR recommendations for the management of difficult-to-treat RA.Methods:A systematic literature review (SLR) was performed: PubMed, Embase and Cochrane databases were searched up to December 2019. Relevant papers were selected and appraised.Results:Thirty articles were selected for therapeutic strategies in patients with limited DMARD options due to contraindications, 73 for patients in whom previous b/tsDMARDs were not effective (‘true refractory RA’), and 51 for patients with predominantly non-inflammatory complaints. For patients with limited DMARD options, limited evidence was found on effective DMARD options for patients with concomitant obesity, and on safe DMARD options for patients with concomitant hepatitis B and C. In patients who failed ≥2 bDMARDs, tocilizumab, tofacitinib, baricitinib, upadacitinib and filgotinib were found to be more effective than placebo, but evidence was insufficient to prioritise. In patients who failed ≥1 bDMARD, there was a tendency of non-tumour necrosis factor inhibitor (TNFi) bDMARDs to be more effective than TNFi (Figure 1). Generally, b/tsDMARDs become less effective when patients failed more bDMARDs, this tendency was not clear for upadacitinib and filgotinib (Figure 2). In patients with predominantly non-inflammatory complaints (mainly function, pain and fatigue), exercise, education, psychological and self-management interventions were found to be of additional benefit.Conclusion:This SLR underscores the scarcity of evidence on the optimal treatment of difficult-to-treat RA patients. As difficult-to-treat RA is a newly defined disease state, all evidence is to an extent indirect. Several b/tsDMARDs were found to be effective in patients who failed ≥2 bDMARDs and generally effectiveness decreased with a higher number of failed bDMARDs. Additionally, a beneficial effect of non-pharmacological interventions was found on non-inflammatory complaints.References:[1] Smolen JSet al. Ann Rheum Dis2020. Epub ahead of print.Disclosure of Interests:Nadia M. T. Roodenrijs: None declared, Attila Hamar: None declared, Melinda Kedves: None declared, György Nagy: None declared, Jacob M. van Laar Grant/research support from: MSD, Genentech, Consultant of: MSD, Roche, Pfizer, Eli Lilly, BMS, Désirée van der Heijde Consultant of: AbbVie, Amgen, Astellas, AstraZeneca, BMS, Boehringer Ingelheim, Celgene, Cyxone, Daiichi, Eisai, Eli-Lilly, Galapagos, Gilead Sciences, Inc., Glaxo-Smith-Kline, Janssen, Merck, Novartis, Pfizer, Regeneron, Roche, Sanofi, Takeda, UCB Pharma; Director of Imaging Rheumatology BV, Paco Welsing: None declared

Sign in / Sign up

Export Citation Format

Share Document