Aarhus University Seal / Aarhus Universitets segl

Anders Hammerich Riis

Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence. / Collin, Lindsay J; Riis, Anders H; MacLehose, Richard F; Ahern, Thomas P; Erichsen, Rune (Editor); Thorlacius-Ussing, Ole; Lash, Timothy L.

In: Clinical epidemiology, Vol. 12, 02.2020, p. 113-121.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

Collin, LJ, Riis, AH, MacLehose, RF, Ahern, TP, Erichsen, R (ed.), Thorlacius-Ussing, O & Lash, TL 2020, 'Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence', Clinical epidemiology, vol. 12, pp. 113-121. https://doi.org/10.2147/CLEP.S230314

APA

Collin, L. J., Riis, A. H., MacLehose, R. F., Ahern, T. P., Erichsen, R. (Ed.), Thorlacius-Ussing, O., & Lash, T. L. (2020). Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence. Clinical epidemiology, 12, 113-121. https://doi.org/10.2147/CLEP.S230314

CBE

Collin LJ, Riis AH, MacLehose RF, Ahern TP, Erichsen R, Thorlacius-Ussing O, Lash TL, ed. 2020. Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence. Clinical epidemiology. 12:113-121. https://doi.org/10.2147/CLEP.S230314

MLA

Vancouver

Collin LJ, Riis AH, MacLehose RF, Ahern TP, Erichsen R, (ed.), Thorlacius-Ussing O et al. Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence. Clinical epidemiology. 2020 Feb;12:113-121. https://doi.org/10.2147/CLEP.S230314

Author

Collin, Lindsay J ; Riis, Anders H ; MacLehose, Richard F ; Ahern, Thomas P ; Erichsen, Rune (Editor) ; Thorlacius-Ussing, Ole ; Lash, Timothy L. / Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence. In: Clinical epidemiology. 2020 ; Vol. 12. pp. 113-121.

Bibtex

@article{05222e8b23814871b26e3910c09b45ef,
title = "Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence",
abstract = "Background: Among men and women diagnosed with colorectal cancer (CRC), 20-50% will develop a cancer recurrence. Cancer recurrences are not routinely captured by most population-based registries; however, linkage across Danish registries allows for the development of predictive models to detect recurrence. Successful application of such models in population-based settings requires validation against a gold standard to ensure the accuracy of recurrence identification.Objective: We apply a recently developed validation study design for prospectively collected validation data to validate predicted CRC recurrences against gold standard diagnoses from medical records in an actively followed cohort of CRC patients in Denmark.Methods: We use a Bayesian monitoring framework, traditionally used in clinical trials, to iteratively update classification parameters (positive and negative predictive values, and sensitivity and specificity) in an adaptive validation substudy design. This design allows determination of the sample size necessary to estimate the corresponding parameters and to identify when validation efforts can cease based on predefined criteria for parameter values and levels of precision.Results: Among 355 men and women diagnosed with CRC in Denmark and actively followed semi-annually, there were 63 recurrences diagnosed by active follow-up and 70 recurrences identified by a predictive algorithm. The adaptive validation design met stopping criteria for the classification parameters after 120 patients had their recurrence information validated. This stopping point yielded parameter estimates for the classification parameters similar to those obtained when the entire cohort was validated, with 66% less patients needed for the validation study.Conclusion: In this proof of concept application of the adaptive validation study design for outcome misclassification, we demonstrated the ability of the method to accurately determine when sufficient validation data have been collected. This method serves as a novel validation substudy design for prospectively collected data with simultaneous implementation of a validation study.",
author = "Collin, {Lindsay J} and Riis, {Anders H} and MacLehose, {Richard F} and Ahern, {Thomas P} and Rune Erichsen and Ole Thorlacius-Ussing and Lash, {Timothy L}",
note = "{\textcopyright} 2020 Collin et al.",
year = "2020",
month = feb,
doi = "10.2147/CLEP.S230314",
language = "English",
volume = "12",
pages = "113--121",
journal = "Clinical Epidemiology",
issn = "1179-1349",
publisher = "Dove Medical Press Ltd.(Dovepress)",

}

RIS

TY - JOUR

T1 - Application of the Adaptive Validation Substudy Design to Colorectal Cancer Recurrence

AU - Collin, Lindsay J

AU - Riis, Anders H

AU - MacLehose, Richard F

AU - Ahern, Thomas P

AU - Thorlacius-Ussing, Ole

AU - Lash, Timothy L

A2 - Erichsen, Rune

N1 - © 2020 Collin et al.

PY - 2020/2

Y1 - 2020/2

N2 - Background: Among men and women diagnosed with colorectal cancer (CRC), 20-50% will develop a cancer recurrence. Cancer recurrences are not routinely captured by most population-based registries; however, linkage across Danish registries allows for the development of predictive models to detect recurrence. Successful application of such models in population-based settings requires validation against a gold standard to ensure the accuracy of recurrence identification.Objective: We apply a recently developed validation study design for prospectively collected validation data to validate predicted CRC recurrences against gold standard diagnoses from medical records in an actively followed cohort of CRC patients in Denmark.Methods: We use a Bayesian monitoring framework, traditionally used in clinical trials, to iteratively update classification parameters (positive and negative predictive values, and sensitivity and specificity) in an adaptive validation substudy design. This design allows determination of the sample size necessary to estimate the corresponding parameters and to identify when validation efforts can cease based on predefined criteria for parameter values and levels of precision.Results: Among 355 men and women diagnosed with CRC in Denmark and actively followed semi-annually, there were 63 recurrences diagnosed by active follow-up and 70 recurrences identified by a predictive algorithm. The adaptive validation design met stopping criteria for the classification parameters after 120 patients had their recurrence information validated. This stopping point yielded parameter estimates for the classification parameters similar to those obtained when the entire cohort was validated, with 66% less patients needed for the validation study.Conclusion: In this proof of concept application of the adaptive validation study design for outcome misclassification, we demonstrated the ability of the method to accurately determine when sufficient validation data have been collected. This method serves as a novel validation substudy design for prospectively collected data with simultaneous implementation of a validation study.

AB - Background: Among men and women diagnosed with colorectal cancer (CRC), 20-50% will develop a cancer recurrence. Cancer recurrences are not routinely captured by most population-based registries; however, linkage across Danish registries allows for the development of predictive models to detect recurrence. Successful application of such models in population-based settings requires validation against a gold standard to ensure the accuracy of recurrence identification.Objective: We apply a recently developed validation study design for prospectively collected validation data to validate predicted CRC recurrences against gold standard diagnoses from medical records in an actively followed cohort of CRC patients in Denmark.Methods: We use a Bayesian monitoring framework, traditionally used in clinical trials, to iteratively update classification parameters (positive and negative predictive values, and sensitivity and specificity) in an adaptive validation substudy design. This design allows determination of the sample size necessary to estimate the corresponding parameters and to identify when validation efforts can cease based on predefined criteria for parameter values and levels of precision.Results: Among 355 men and women diagnosed with CRC in Denmark and actively followed semi-annually, there were 63 recurrences diagnosed by active follow-up and 70 recurrences identified by a predictive algorithm. The adaptive validation design met stopping criteria for the classification parameters after 120 patients had their recurrence information validated. This stopping point yielded parameter estimates for the classification parameters similar to those obtained when the entire cohort was validated, with 66% less patients needed for the validation study.Conclusion: In this proof of concept application of the adaptive validation study design for outcome misclassification, we demonstrated the ability of the method to accurately determine when sufficient validation data have been collected. This method serves as a novel validation substudy design for prospectively collected data with simultaneous implementation of a validation study.

U2 - 10.2147/CLEP.S230314

DO - 10.2147/CLEP.S230314

M3 - Journal article

C2 - 32099477

VL - 12

SP - 113

EP - 121

JO - Clinical Epidemiology

JF - Clinical Epidemiology

SN - 1179-1349

ER -