Estimating reference intervals from an IPD meta-analysis using quantile regression.
Bootstrap
Individual participant data
Meta-analysis
Quantile regression
Reference interval
Journal
BMC medical research methodology
ISSN: 1471-2288
Titre abrégé: BMC Med Res Methodol
Pays: England
ID NLM: 100968545
Informations de publication
Date de publication:
26 Oct 2024
26 Oct 2024
Historique:
received:
19
10
2023
accepted:
21
10
2024
medline:
27
10
2024
pubmed:
27
10
2024
entrez:
27
10
2024
Statut:
epublish
Résumé
Reference intervals, which define an interval in which a specific proportion of measurements from a healthy population are expected to fall, are commonly used in medical practice. Synthesizing information from multiple studies through meta-analysis can provide a more precise and representative reference interval than one derived from a single study. However, the current approaches for estimating the reference interval from a meta-analysis mainly rely on aggregate data and require parametric distributional assumptions that cannot always be checked. With the availability of individual participant data (IPD), non-parametric methods can be used to estimate reference intervals without any distributional assumptions. Furthermore, patient-level covariates can be introduced to estimate personalized reference intervals that may be more applicable to specific patients. This paper introduces quantile regression as a method to estimate the reference interval from an IPD meta-analysis under the fixed effects model. We compared several non-parametric bootstrap methods through simulation studies to account for within-study correlation. Under fixed effects model, we recommend keeping the studies fixed and only randomly sampling subjects with replacement within each study. We proposed to use the quantile regression in the IPD meta-analysis to estimate the reference interval. Based on the simulation results, we identify an optimal bootstrap strategy for estimating the uncertainty of the estimated reference interval. An example of liver stiffness measurements, a clinically important diagnostic test without explicitly established reference range in children, is provided to demonstrate the use of quantile regression in estimating both overall and subject-specific reference intervals.
Sections du résumé
BACKGROUND
BACKGROUND
Reference intervals, which define an interval in which a specific proportion of measurements from a healthy population are expected to fall, are commonly used in medical practice. Synthesizing information from multiple studies through meta-analysis can provide a more precise and representative reference interval than one derived from a single study. However, the current approaches for estimating the reference interval from a meta-analysis mainly rely on aggregate data and require parametric distributional assumptions that cannot always be checked.
METHODS
METHODS
With the availability of individual participant data (IPD), non-parametric methods can be used to estimate reference intervals without any distributional assumptions. Furthermore, patient-level covariates can be introduced to estimate personalized reference intervals that may be more applicable to specific patients. This paper introduces quantile regression as a method to estimate the reference interval from an IPD meta-analysis under the fixed effects model.
RESULTS
RESULTS
We compared several non-parametric bootstrap methods through simulation studies to account for within-study correlation. Under fixed effects model, we recommend keeping the studies fixed and only randomly sampling subjects with replacement within each study.
CONCLUSION
CONCLUSIONS
We proposed to use the quantile regression in the IPD meta-analysis to estimate the reference interval. Based on the simulation results, we identify an optimal bootstrap strategy for estimating the uncertainty of the estimated reference interval. An example of liver stiffness measurements, a clinically important diagnostic test without explicitly established reference range in children, is provided to demonstrate the use of quantile regression in estimating both overall and subject-specific reference intervals.
Identifiants
pubmed: 39462323
doi: 10.1186/s12874-024-02378-0
pii: 10.1186/s12874-024-02378-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
251Subventions
Organisme : NIH HHS
ID : R01LM012982
Pays : United States
Organisme : NIH HHS
ID : R01LM012982
Pays : United States
Organisme : NIH HHS
ID : R01LM012982
Pays : United States
Informations de copyright
© 2024. The Author(s).
Références
Boyd JC. Defining laboratory reference values and decision limits: populations, intervals, and interpretations. Asian J Androl. 2010;12(1):83–90. https://doi.org/10.1038/aja.2009.9 .
doi: 10.1038/aja.2009.9
pubmed: 20111086
pmcid: 3739683
Horn PS, Pesce AJ, Copeland BE. A robust approach to reference interval estimation and evaluation. Clin Chem. 1998;44(3):622–31. https://doi.org/10.1093/clinchem/44.3.622 .
doi: 10.1093/clinchem/44.3.622
pubmed: 9510871
Siegel L, Murad MH, Riley RD, Bazerbachi F, Wang Z, Chu H. A guide to estimating the reference range from a Meta-analysis using aggregate or individual participant data. Am J Epidemiol. 2022. https://doi.org/10.1093/aje/kwac013 .
doi: 10.1093/aje/kwac013
pubmed: 35102410
pmcid: 9431652
Cao W, Siegel L, Zhou J, Zhu M, Tong T, Chen Y, Chu H. Estimating the reference interval from a fixed effects meta-analysis. Res Synthesis Methods. 2021;12(5):630–40. https://doi.org/10.1002/jrsm.1488 .
doi: 10.1002/jrsm.1488
Siegel L, Murad MH, Chu H. Estimating the reference range from a meta-analysis. Res Synthesis Methods. 2021;12(2):148–60. https://doi.org/10.1002/jrsm.1442 .
doi: 10.1002/jrsm.1442
Khoshdel AR, Thakkinstian A, Carney SL, Attia J. Estimation of an age-specific reference interval for pulse wave velocity: a meta-analysis. J Hypertens. 2006;24(7):1231–7.
doi: 10.1097/01.hjh.0000234098.85497.31
pubmed: 16794467
Koenker R, Bassett G, Regression Quantiles. Econometrica. 1978;46(1):33–50. https://doi.org/10.2307/1913643 .
doi: 10.2307/1913643
Yu K, Lu Z, Stander J. Quantile regression: applications and current research Areas. J Royal Stat Soc Ser D (the Statistician). 2003;52(3):331–50.
Buhai S. Quantile regression: overview and selected applications. Ad Astra. 2005;4(4):1–17.
Gannoun A, Girard S, Guinot C, Saracco J. Reference curves based on non-parametric quantile regression. Stat Med. 2002;21(20):3119–35.
doi: 10.1002/sim.1226
pubmed: 12369086
Wei Y, Pere A, Koenker R, He X. Quantile regression methods for reference growth charts. Stat Med. 2006;25(8):1369–82.
doi: 10.1002/sim.2271
pubmed: 16143984
Peng L, Wuu J, Benatar M. Developing reference data for nerve conduction studies: an application of quantile regression. Muscle Nerve: Official J Am Association Electrodiagn Med. 2009;40(5):763–71.
doi: 10.1002/mus.21489
Cheung YB, Neo SH, Yang GM, Teo I, Lee GL, Qu DL, Koh AR, Thumboo J, Wee HL. Reference values for and interpretation of the Singapore Caregiver Quality of Life Scale: a quantile regression approach. J Patient-Reported Outcomes. 2020;4(1):1–10.
doi: 10.1186/s41687-020-00201-0
Schmid CH, Stijnen T, White I. Handbook of Meta-analysis. CRC; 2020.
Higgins JP, Thompson SG, Spiegelhalter DJ. A re-evaluation of random‐effects meta‐analysis. J Royal Stat Society: Ser (Statistics Society). 2009;172(1):137–59.
doi: 10.1111/j.1467-985X.2008.00552.x
Jackson D, White IR. When should meta-analysis avoid making hidden normality assumptions? Biom J Nov. 2018;60(6):1040–58. https://doi.org/10.1002/bimj.201800071 .
doi: 10.1002/bimj.201800071
Bender R, Friede T, Koch A, Kuss O, Schlattmann P, Schwarzer G, Skipka G. Methods for evidence synthesis in the case of very few studies. Res Synth Methods Sep. 2018;9(3):382–92. https://doi.org/10.1002/jrsm.1297 .
doi: 10.1002/jrsm.1297
Borenstein M, Hedges LV, Higgins JP, Rothstein HR. A basic introduction to fixed-effect and random-effects models for meta-analysis. Res Synth Methods Apr. 2010;1(2):97–111. https://doi.org/10.1002/jrsm.12 .
doi: 10.1002/jrsm.12
Rice K, Higgins JPT, Lumley T. A re-evaluation of fixed effect(s) meta-analysis. J Royal Stat Society: Ser (Statistics Society). 2018;181(1):205–27. https://doi.org/10.1111/rssa.12275 .
doi: 10.1111/rssa.12275
Rice K, Higgins JP, Lumley T. A re-evaluation of fixed effect (s) meta‐analysis. J Royal Stat Society: Ser (Statistics Society). 2018;181(1):205–27.
doi: 10.1111/rssa.12275
Hao L, Naiman DQ, Naiman DQ. Quantile regression. Sage; 2007.
Koenker R. Quantile regression. Econometric Society Monographs. Cambridge University Press; 2005.
Shao J, Tu D. The jackknife and bootstrap. Springer Science & Business Media; 2012.
Field CA, Welsh AH. Bootstrapping clustered data. J Royal Stat Society: Ser B (Statistical Methodology). 2007;69(3):369–90.
doi: 10.1111/j.1467-9868.2007.00593.x
Andersson MK, Karlsson S. Bootstrapping error component models. Comput Stat. 2001;16(2):221–31.
doi: 10.1007/s001800100061
Davison AC, Hinkley DV. Bootstrap methods and their application. Cambridge University Press; 1997.
McCullagh P. Resampling and exchangeable arrays. Bernoulli 6(2) 285 - 301, April 2000.
Ren S, Lai H, Tong W, Aminzadeh M, Hou X, Lai S. Nonparametric bootstrapping for hierarchical data. J Applied Statistics. 2010;37(9):1487–98.
doi: 10.1080/02664760903046102
Hagemann A. Cluster-robust bootstrap inference in quantile regression models. J Am Stat Assoc. 2017;112(517):446–56.
doi: 10.1080/01621459.2016.1148610
Innes H, Morling JR, Aspinall EA, Goldberg DJ, Hutchinson SJ, Guha IN. Late diagnosis of chronic liver disease in a community cohort (UK Biobank): determinants and impact on subsequent survival. Public Health. 2020;187:165–71. https://doi.org/10.1016/j.puhe.2020.07.017 . 2020/10/01/.
doi: 10.1016/j.puhe.2020.07.017
pubmed: 32992162
Mueller S, Sandrin L. Liver stiffness: a novel parameter for the diagnosis of liver disease. Hepat Med May. 2010;25:2:49–67. https://doi.org/10.2147/hmer.s7394 .
doi: 10.2147/hmer.s7394
Bravo AA, Sheth SG, Chopra S. Liver biopsy. N Engl J Med. 2001;344(7):495–500. https://doi.org/10.1056/nejm200102153440706 .
doi: 10.1056/nejm200102153440706
pubmed: 11172192
Tobkes AI, Nord J. Liver biopsy: review of methodology and complications. Dig Dis. 1995;13(5):267–74.
doi: 10.1159/000171507
pubmed: 8542662
Li DK, Khan MR, Wang Z, Chongsrisawat V, Swangsak P, Teufel-Schäfer U, Engelmann G, Goldschmidt I, Baumann U, Tokuhara D. Normal liver stiffness and influencing factors in healthy children: an individual participant data meta‐analysis. Liver Int. 2020;40(11):2602–11.
doi: 10.1111/liv.14658
pubmed: 32901449
Higgins JPT, Thompson SG, Spiegelhalter DJ. A re-evaluation of random-effects meta-analysis. J Royal Stat Society: Ser (Statistics Society). 2009;172(1):137–59. https://doi.org/10.1111/j.1467-985X.2008.00552.x .
doi: 10.1111/j.1467-985X.2008.00552.x
Alhamzawi R, Yu K, Benoit DF. Bayesian adaptive Lasso quantile regression. Stat Modelling. 2012;12(3):279–97.
doi: 10.1177/1471082X1101200304
Benoit DF, Alhamzawi R, Yu K. Bayesian lasso binary quantile regression. Comput Stat. 2013;28:2861–73.
doi: 10.1007/s00180-013-0439-0
Belloni A, Chernozhukov V. ℓ 1-penalized quantile regression in high-dimensional sparse models. 2011.
Angrist J, Chernozhukov V, Fernandez-Val I. Quantile regression under Misspecification, with an application to the U.S. wage structure. Econometrica. 2006;74(2):539–63. https://doi.org/10.1111/j.1468-0262.2006.00671.x .
doi: 10.1111/j.1468-0262.2006.00671.x