Enhancing the identification of rheumatoid arthritis-associated interstitial lung disease through text mining of chest computerized tomography reports

Luedders, Brent A.; Cope, Brendan J.; Hershberger, Daniel; Devries, Matthew; Campbell, W. Scott; Campbell, James; Roul, Punyasha; Yang, Yangyuna; Rojas, Jorge; Cannon, Grant W.; Sauer, Brian C.; Baker, Joshua F.; Curtis, Jeffrey R.; Mikuls, Ted R.; England, Bryant R.

doi:10.1016/j.semarthrit.2023.152204

Cited by 5 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ultimately, 16 studies were chosen for inclusion based on their relevance and adherence to our criteria. One additional study was identified and included through reference screening (11)(12)(13)(14)(18)(19)(20)(21)(22)(23)(24)(25)(26)(27)(28)(29)(30). Therefore, the review culminated in a total of 17 studies.…”

Section: Search Results and Study Selectionmentioning

confidence: 99%

Advancing Rheumatology Practice: Systematic Review of Natural Language Processing Applications

Omar,

Glicksberg,

Reuveni

et al. 2024

Preprint

View full text Add to dashboard Cite

BackgroundWith the advent of large language models (LLM), such as ChatGPT, natural language processing (NLP) is revolutionizing healthcare. We systematically reviewed NLP’s role in rheumatology and assessed its impact on diagnostics, disease monitoring, and treatment strategies.MethodsFollowing PRISMA guidelines, we conducted a systematic search to identify original research articles exploring NLP applications in rheumatology. This search was performed in PubMed, Embase, Web of Science, and Scopus until January 2024.ResultsOur search produced 17 studies that showcased diverse applications of NLP in rheumatology, addressing disease diagnosis, data handling, and monitoring.Notably, GPT-4 demonstrated strong performance in diagnosing and managing rheumatic diseases. Performance metrics indicated high accuracy and reliability in various tasks. However, challenges like data dependency and limited generalizability were noted.ConclusionNLP, and especially LLM, show promise in advancing rheumatology practice, enhancing diagnostic precision, data handling, and patient care. Future research should address current limitations, focusing on data integrity and model generalizability.

show abstract

Section: Search Results and Study Selectionmentioning

confidence: 99%

Advancing Rheumatology Practice: Systematic Review of Natural Language Processing Applications

Omar,

Glicksberg,

Reuveni

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…RA is a systemic autoimmune disease that dominantly involves joints, causing erosive bone loss and chronic deformities. 89 Although RA particularly involves the joints, morbidity has been linked to secondary interstitial lung disease (ILD) 90 and cardiovascular disease (CVD). 89 Oxidative stress has been attributed to deficiency of PON1 in patients with RA and ILD 91 and CVD.…”

Section: Ramentioning

confidence: 99%

“… 89 Although RA particularly involves the joints, morbidity has been linked to secondary interstitial lung disease (ILD) 90 and cardiovascular disease (CVD). 89 Oxidative stress has been attributed to deficiency of PON1 in patients with RA and ILD 91 and CVD. 92 Unlike SLE, 48 the mechanism of RA is not based on distorted mitochondrial metabolism and oxidative stress but a curious enhancement of PPP activity and greater antioxidant capacity of T cells.…”

Section: Ramentioning

confidence: 99%

Redox Pathogenesis in Rheumatic Diseases

Laniak,

Winans,

Patel

et al. 2024

ACR Open Rheumatology

View full text Add to dashboard Cite

Despite being some of the most anecdotally well‐known roads to pathogenesis, the mechanisms governing autoimmune rheumatic diseases are not yet fully understood. The overactivation of the cellular immune system and the characteristic development of autoantibodies have been linked to oxidative stress. Typical clinical manifestations, such as joint swelling and deformities and inflammation of the skin and internal organs, have also been connected directly or indirectly to redox mechanisms. The differences in generation and restraint of oxidative stress provide compelling evidence for the broad variety in pathology among rheumatic diseases and explain some of the common triggers and discordant manifestations in these diseases. Growing evidence of redox mechanisms in pathogenesis has provided a broad array of new potential therapeutic targets. Here, we explore the mechanisms by which oxidative stress is generated, explore its roles in autoimmunity and end‐organ damage, and discuss how individual rheumatic diseases exhibit unique features that offer targets for therapeutic interventions.

show abstract

Generating Real‐World Evidence From the Excellence Network in Rheumatology

Beukelman,

Mudano,

Stewart

et al. 2024

Pharmacoepidemiology and Drug

View full text Add to dashboard Cite

PurposeThe Excellence Network in RheumatoloGY (ENRGY) was founded in 2021 and encompasses data from more than 700 private practice rheumatology providers throughout the United States, forming a practice‐based research network (PBRN).MethodsElectronic health record (EHR) data from participating practices are aggregated, including structured data (e.g., clinical assessments) and unstructured data from two different EHR platforms. Targeted data quality efforts ensure capture of high‐quality clinical data and reduce missingness. ENRGY network membership also provides participating sites access to technology services that enhance patient care. Centralized ethics approval and pre‐existing legal agreements along with electronic tools to curate data and contact eligible study participants improves efficiency of multi‐center prospective studies.ResultsThe ENRGY data warehouse includes linked administrative claims data for commercial and government‐provided insurance (31% of patients linked to commercial claims) and patient‐generated health data from both in‐office and out‐of‐office settings via a smartphone app as well as biosensor data. ENRGY data and infrastructure can be employed to identify the highest yield sites for prospective studies; identify patients meeting study eligibility criteria; pre‐screen individual patient's willingness to participate in specific studies; centralize study data monitoring; and assist in the conduct of prospective studies.ConclusionENRGY data have been used to generate a growing number of scientific publications and may serve as a model for PBRNs in other specialties seeking to harness the potential of data linkages, patient‐generated data capture, and centralized study infrastructure for observational and interventional research.

show abstract

Enhancing the identification of rheumatoid arthritis-associated interstitial lung disease through text mining of chest computerized tomography reports

Cited by 5 publications

References 19 publications

Advancing Rheumatology Practice: Systematic Review of Natural Language Processing Applications

Advancing Rheumatology Practice: Systematic Review of Natural Language Processing Applications

Redox Pathogenesis in Rheumatic Diseases

Generating Real‐World Evidence From the Excellence Network in Rheumatology

Contact Info

Product

Resources

About