Computable phenotype for real-world, data-driven retrospective identification of relapse in ANCA-associated vasculitis.

Autor:	Scott J; Trinity Kidney Centre, Trinity Translational Medicine Institute, Trinity College Dublin, Dublin, Ireland JESCOTT@tcd.ie., White A; School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland.; ADAPT SFI centre, Trinity College Dublin, Dublin, Ireland., Walsh C; Department of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland.; National Centre for Pharmacoeconomics, St James's Hospital, Dublin, Ireland., Aslett L; Department of Mathematical Science, University of Durham, Durham, UK., Rutherford MA; School of Infection & Immunity, University of Glasgow, Glasgow, UK., Ng J; School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland., Judge C; School of Medicine, College of Medicine, Nursing and Health Science, University of Galway, Galway, Ireland., Sebastian K; Trinity Kidney Centre, Trinity Translational Medicine Institute, Trinity College Dublin, Dublin, Ireland., O'Brien S; Trinity Kidney Centre, Trinity Translational Medicine Institute, Trinity College Dublin, Dublin, Ireland., Kelleher J; Department of Statistics, Dublin Institute of Technology, Dublin, Ireland., Power J; Vasculitis Ireland Awareness, Dublin, Ireland., Conlon N; Department of Immunology, St James's Hospital, Dublin, Ireland., Moran SM; Trinity Kidney Centre, Trinity Translational Medicine Institute, Trinity College Dublin, Dublin, Ireland.; Department of Nephrology, Cork University Hospital, Cork, Ireland., Luqmani RA; Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Science (NDORMs), University of Oxford, Oxford, UK., Merkel PA; Division of Rheumatology, Department of Medicine, Division of Epidemiology, Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA., Tesar V; Department of Nephrology, General University Hospital, Prague, Czech Republic.; 1st Faculty of Medicine, Charles University, Prague, Czech Republic., Hruskova Z; 1st Faculty of Medicine, Charles University, Prague, Czech Republic.; General University Hospital, Prague, Czech Republic., Little MA; Trinity Kidney Centre, Trinity Translational Medicine Institute, Trinity College Dublin, Dublin, Ireland.; ADAPT SFI centre, Trinity College Dublin, Dublin, Ireland.
Jazyk:	angličtina
Zdroj:	RMD open [RMD Open] 2024 Apr 30; Vol. 10 (2). Date of Electronic Publication: 2024 Apr 30.
DOI:	10.1136/rmdopen-2023-003962
Abstrakt:	Objective: ANCA-associated vasculitis (AAV) is a relapsing-remitting disease, resulting in incremental tissue injury. The gold-standard relapse definition (Birmingham Vasculitis Activity Score, BVAS>0) is often missing or inaccurate in registry settings, leading to errors in ascertainment of this key outcome. We sought to create a computable phenotype (CP) to automate retrospective identification of relapse using real-world data in the research setting. Methods: We studied 536 patients with AAV and >6 months follow-up recruited to the Rare Kidney Disease registry (a national longitudinal, multicentre cohort study). We followed five steps: (1) independent encounter adjudication using primary medical records to assign the ground truth, (2) selection of data elements (DEs), (3) CP development using multilevel regression modelling, (4) internal validation and (5) development of additional models to handle missingness. Cut-points were determined by maximising the F1-score. We developed a web application for CP implementation, which outputs an individualised probability of relapse. Results: Development and validation datasets comprised 1209 and 377 encounters, respectively. After classifying encounters with diagnostic histopathology as relapse, we identified five key DEs; DE1: change in ANCA level, DE2: suggestive blood/urine tests, DE3: suggestive imaging, DE4: immunosuppression status, DE5: immunosuppression change. F1-score, sensitivity and specificity were 0.85 (95% CI 0.77 to 0.92), 0.89 (95% CI 0.80 to 0.99) and 0.96 (95% CI 0.93 to 0.99), respectively. Where DE5 was missing, DE2 plus either DE1/DE3 were required to match the accuracy of BVAS. Conclusions: This CP accurately quantifies the individualised probability of relapse in AAV retrospectively, using objective, readily accessible registry data. This framework could be leveraged for other outcomes and relapsing diseases. Competing Interests: Competing interests: PAM declares the following disclosures: Consulting and Research Support: AbbVie, AstraZeneca, Boeringher-Ingelheim, Bristol-Myers Squibb, ChemoCentryx, Forbius, Genentech/Roche, Genzyme/Sanofi, GlaxoSmithKline, InflaRx, Neutrolis, Takeda. Consulting only: Cabaletta, CSL Behring, Dynacure, EMDSerono, Immagene, Jannsen, Jubilant, Kiniksa, Kyverna, Magenta, MiroBio, Mitsubishi, Novartis, Pfizer, Q32, Regeneron, Sparrow, Vistera. Research Support only: Eicos, Electra, Sanofi, Star. Stock options: Kyverna. Royalties: UpToDate. All other authors declare that they have no competing interests. (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY. Published by BMJ.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu