Using Capture–Recapture Methodology to Enhance Precision of Representative Sampling-Based Case Count Estimates

Chen

et al. 2022

Preprint

Self Cite

Capture-recapture methods are widely applied in estimating the number (N) of prevalent or cumulatively incident cases in disease surveillance. Here, we focus the bulk of our attention on the common case in which there are two data streams. We propose a sensitivity and uncertainty analysis framework grounded in multinomial distribution-based maximum likelihood, hinging on a key dependence parameter that is typically non-identifiable but is epidemiologically interpretable. Focusing on the epidemiologically meaningful parameter unlocks appealing data visualizations for sensitivity analysis and provides an intuitively accessible framework for uncertainty analysis designed to leverage the practicing epidemiologist's understanding of the implementation of the surveillance streams as the basis for assumptions driving estimation of N. By illustrating the proposed sensitivity analysis using publicly available HIV surveillance data, we emphasize both the need to admit the lack of information in the observed data and the appeal of incorporating expert opinion about the key dependence parameter. The proposed uncertainty analysis is an empirical Bayes-like approach designed to more realistically acknowledge variability in the estimated N associated with uncertainty in an expert's opinion about the non-identifiable parameter, together with the statistical uncertainty. We demonstrate how such an approach can also facilitate an appealing general interval estimation procedure to accompany capture-recapture methods. Simulation studies illustrate the reliable performance of the proposed approach for quantifying uncertainties in estimating N in various contexts. Finally, we demonstrate how the recommended paradigm has the potential to be directly extended for application to data from more than two surveillance streams.

Section: Conclusion and Discussionmentioning

confidence: 99%

“…As Figure 1 illustrates, specifying a known value for Ψ leads to an exceedingly precise estimator. However, this estimator can very seldom be unlocked for direct use outside of sensitivity analysis, except under a unique study design 33 . In the typical CRC scenario, we propose an uncertainty analysis anchored on the ratio parameter ϕ .…”

Section: Methodsmentioning

confidence: 99%

Sensitivity and Uncertainty Analysis for Two-Stream Capture-Recapture Methods in Disease Surveillance

Chen

et al. 2022

Preprint

Self Cite

“…However, this estimator can very seldom be unlocked for direct use outside of sensitivity analysis, except under a unique study design. 39 In the typical scenario, we propose an uncertainty analysis anchored on the parameter falseϕ. Specifically, an assumed distribution (akin to a prior) for falseϕ is specified beforehand.…”

Section: Methodsmentioning

confidence: 99%

Sensitivity and Uncertainty Analysis for Two-stream Capture–Recapture Methods in Disease Surveillance

Chen

et al. 2023

Epidemiology

Self Cite

Capture–recapture methods are widely applied in estimating the number (falseN) of prevalent or cumulatively incident cases in disease surveillance. Here, we focus the bulk of our attention on the common case in which there are 2 data streams. We propose a sensitivity and uncertainty analysis framework grounded in multinomial distribution-based maximum likelihood, hinging on a key dependence parameter that is typically nonidentifiable but is epidemiologically interpretable. Focusing on the epidemiologically meaningful parameter unlocks appealing data visualizations for sensitivity analysis and provides an intuitively accessible framework for uncertainty analysis designed to leverage the practicing epidemiologist’s understanding of the implementation of the surveillance streams as the basis for assumptions driving estimation of falseN. By illustrating the proposed sensitivity analysis using publicly available HIV surveillance data, we emphasize both the need to admit the lack of information in the observed data and the appeal of incorporating expert opinion about the key dependence parameter. The proposed uncertainty analysis is a simulation-based approach designed to more realistically acknowledge variability in the estimated falseN associated with uncertainty in an expert’s opinion about the nonidentifiable parameter, together with the statistical uncertainty. We demonstrate how such an approach can also facilitate an appealing general interval estimation procedure to accompany capture–recapture methods. Simulation studies illustrate the reliable performance of the proposed approach for quantifying uncertainties in estimating falseN in various contexts. Finally, we demonstrate how the recommended paradigm has the potential to be directly extended for application to data from >2 surveillance streams.

“…On May 1, 2022, we drew an anchor stream random sample of 200 breast cancer patients from the subset of the GCR, and CRISP abstractors conducted the necessary medical records review to ascertain whether each of those patients had experienced a true recurrence since their initial treatment date. Assuming the CoC recurrence reports were fully accurate, this design would unlock the original version of the anchor stream‐based CRC estimator 31 …”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we develop CRC methods to estimate epidemiological disease case counts accounting for misclassified diagnostic disease status. We utilize the anchor stream design, 31 for the dual purpose of ensuring independence between the two data streams and for estimating the unknown positive predictive value (PPV) associated with error‐prone signals from the existing non‐anchor stream. These key objectives are accomplished by virtue of the fact that, to date, the anchor stream uses an arguably perfect (or “gold standard”) diagnostic approach, and consists of a random or representative sample of the population obtained subsequent to the signals from the existing stream.…”

Section: Introductionmentioning

confidence: 99%

Tailoring capture‐recapture methods to estimate registry‐based case counts based on error‐prone diagnostic signals

Ward

et al. 2023

Statistics in Medicine

Self Cite

Summary Surveillance research is of great importance for effective and efficient epidemiological monitoring of case counts and disease prevalence. Taking specific motivation from ongoing efforts to identify recurrent cases based on the Georgia Cancer Registry, we extend recently proposed “anchor stream” sampling design and estimation methodology. Our approach offers a more efficient and defensible alternative to traditional capture‐recapture (CRC) methods by leveraging a relatively small random sample of participants whose recurrence status is obtained through a principled application of medical records abstraction. This sample is combined with one or more existing signaling data streams, which may yield data based on arbitrarily non‐representative subsets of the full registry population. The key extension developed here accounts for the common problem of false positive or negative diagnostic signals from the existing data stream(s). In particular, we show that the design only requires documentation of positive signals in these non‐anchor surveillance streams, and permits valid estimation of the true case count based on an estimable positive predictive value (PPV) parameter. We borrow ideas from the multiple imputation paradigm to provide accompanying standard errors, and develop an adapted Bayesian credible interval approach that yields favorable frequentist coverage properties. We demonstrate the benefits of the proposed methods through simulation studies, and provide a data example targeting estimation of the breast cancer recurrence case count among Metro Atlanta area patients from the Georgia Cancer Registry‐based Cancer Recurrence Information and Surveillance Program (CRISP) database.