Synergies between centralized and federated approaches to data quality: a report from the national COVID cohort collaborative.

Autor:	Pfaff ER; Department of Medicine, UNC Chapel Hill School of Medicine, Chapel Hill, North Carolina, USA., Girvin AT; Palantir Technologies, Denver, Colorado, USA., Gabriel DL; Section of Biomedical Informatics and Data Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA., Kostka K; The OHDSI Center at the Roux Institute, Northeastern University, Portland, Maine, USA., Morris M; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania, USA., Palchuk MB; TriNetX LLC, Cambridge, Massachusetts, USA., Lehmann HP; Department of Medicine, Johns Hopkins School of Medicine, Baltimore, Maryland, USA., Amor B; Palantir Technologies, Denver, Colorado, USA., Bissell M; Palantir Technologies, Denver, Colorado, USA., Bradwell KR; Palantir Technologies, Denver, Colorado, USA., Gold S; Section of Biomedical Informatics and Data Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA., Hong SS; Section of Biomedical Informatics and Data Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA., Loomba J; University of Virginia, Charlottesville, Virginia, USA., Manna A; Palantir Technologies, Denver, Colorado, USA., McMurry JA; Center for Health AI, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA., Niehaus E; Palantir Technologies, Denver, Colorado, USA., Qureshi N; Palantir Technologies, Denver, Colorado, USA., Walden A; Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, Oregon, USA., Zhang XT; Johns Hopkins University School of Medicine, Baltimore, Maryland, USA., Zhu RL; Johns Hopkins University School of Medicine, Baltimore, Maryland, USA., Moffitt RA; Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York, USA., Haendel MA; University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA., Chute CG; Schools of Medicine, Public Health, and Nursing, Johns Hopkins University, Baltimore, Maryland, USA., Adams WG, Al-Shukri S, Anzalone A, Baghal A, Bennett TD, Bernstam EV, Bernstam EV, Bissell MM, Bush B, Campion TR, Castro V, Chang J, Chaudhari DD, Chen W, Chu S, Cimino JJ, Crandall KA, Crooks M, Davies SJD, DiPalazzo J, Dorr D, Eckrich D, Eltinge SE, Fort DG, Golovko G, Gupta S, Haendel MA, Hajagos JG, Hanauer DA, Harnett BM, Horswell R, Huang N, Johnson SG, Kahn M, Khanipov K, Kieler C, Luzuriaga KR, Maidlow S, Martinez A, Mathew J, McClay JC, McMahan G, Melancon B, Meystre S, Miele L, Morizono H, Pablo R, Patel L, Phuong J, Popham DJ, Pulgarin C, Santos C, Sarkar IN, Sazo N, Setoguchi S, Soby S, Surampalli S, Suver C, Vangala UMR, Visweswaran S, Oehsen JV, Walters KM, Wiley L, Williams DA, Zai A
Jazyk:	angličtina
Zdroj:	Journal of the American Medical Informatics Association : JAMIA [J Am Med Inform Assoc] 2022 Mar 15; Vol. 29 (4), pp. 609-618.
DOI:	10.1093/jamia/ocab217
Abstrakt:	Objective: In response to COVID-19, the informatics community united to aggregate as much clinical data as possible to characterize this new disease and reduce its impact through collaborative analytics. The National COVID Cohort Collaborative (N3C) is now the largest publicly available HIPAA limited dataset in US history with over 6.4 million patients and is a testament to a partnership of over 100 organizations. Materials and Methods: We developed a pipeline for ingesting, harmonizing, and centralizing data from 56 contributing data partners using 4 federated Common Data Models. N3C data quality (DQ) review involves both automated and manual procedures. In the process, several DQ heuristics were discovered in our centralized context, both within the pipeline and during downstream project-based analysis. Feedback to the sites led to many local and centralized DQ improvements. Results: Beyond well-recognized DQ findings, we discovered 15 heuristics relating to source Common Data Model conformance, demographics, COVID tests, conditions, encounters, measurements, observations, coding completeness, and fitness for use. Of 56 sites, 37 sites (66%) demonstrated issues through these heuristics. These 37 sites demonstrated improvement after receiving feedback. Discussion: We encountered site-to-site differences in DQ which would have been challenging to discover using federated checks alone. We have demonstrated that centralized DQ benchmarking reveals unique opportunities for DQ improvement that will support improved research analytics locally and in aggregate. Conclusion: By combining rapid, continual assessment of DQ with a large volume of multisite data, it is possible to support more nuanced scientific questions with the scale and rigor that they require. (© The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu