Single and multi-objective optimal designs for group testing experiments with a focus on screening for an infectious disease

Chi-Kuang Yeh; Julie Zhou; Weng Kee Wong

arxiv: 2508.08445 · v2 · submitted 2025-08-11 · 📊 stat.ME

Single and multi-objective optimal designs for group testing experiments with a focus on screening for an infectious disease

Chi-Kuang Yeh , Weng Kee Wong , Julie Zhou This is my paper

Pith reviewed 2026-05-18 23:06 UTC · model grok-4.3

classification 📊 stat.ME

keywords group testingoptimal designA-optimalitymulti-objective designinfectious disease screeningChlamydiabudget constraintsexact designs

0 comments

The pith

Optimal designs for group testing in disease screening extend beyond D-optimality to A-, c-, and E-criteria while supporting multi-objective goals under budget constraints.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Group testing pools samples to screen for infectious diseases such as Chlamydia when testing resources are limited. The paper develops methods to construct optimal designs that estimate model parameters accurately according to user-chosen criteria including A-, c-, and E-optimality in addition to the usual D-optimality. It also provides ways to balance several objectives at once. For large studies general theory produces optimal approximate designs, while two new algorithms generate highly efficient exact designs when sample sizes must stay small due to realistic budgets. The resulting designs are tested for robustness under operational uncertainties, and a Shiny app is supplied to apply them in practice, with concrete gains shown for Chlamydia screening that uses imperfect assays.

Core claim

The paper establishes that optimal designs for group testing experiments can be constructed under a range of optimality criteria including A-, c-, and E-optimality in addition to D-optimality, and for multiple objectives simultaneously. For large studies, optimal approximate designs are derived using general theory, and for small samples, two algorithms are proposed to find highly efficient exact designs subject to budget constraints. These designs are applied to a Chlamydia screening trial accounting for imperfect assays, showing advantages over current methods, with further investigation into properties under operational uncertainties.

What carries the argument

Extension of standard optimal design theory to the group testing statistical model with imperfect assays and user-specified cost structures, used to derive single- and multi-objective optimal approximate and exact designs.

If this is right

More efficient use of limited testing resources in large-scale infectious-disease screening programs.
Ability to optimize designs simultaneously for multiple goals such as estimation accuracy and total cost.
Practical construction of exact designs that respect realistic budget constraints for smaller studies.
Web-based tools that let practitioners implement the designs directly in trial planning.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same design framework could be adapted to other resource-limited testing settings such as blood safety or DNA library screening.
Combining these optimal designs with adaptive or sequential testing rules might yield further efficiency gains.
Public-health agencies could apply the approach to improve cost-effectiveness of routine disease surveillance.
Field validation studies would be needed to check performance when unmodeled operational factors arise.

Load-bearing premise

The statistical model for group testing with imperfect assays and the user-specified cost structure accurately capture the real testing process and costs without substantial operational uncertainties or model misspecification.

What would settle it

A real Chlamydia screening trial in which the proposed optimal designs fail to produce lower total costs or higher parameter estimation precision than standard group testing methods under identical budget limits and assay error rates.

read the original abstract

Group testing techniques are widely used in resource-constrained settings, such as infectious-disease screening, blood safety, DNA library screening, and industrial inspection, where the efficient use of limited testing resources depends critically on how the initial study is designed. This paper discusses various ways that group testing experiments can be designed more efficiently and flexibly, under a user-specified optimality criterion and cost structure. We construct optimal designs to estimate model parameters beyond the \(D\)-optimality criterion to include the \(A\)-, \(c\)-, \(E\)-optimality, and extend the framework for finding optimal designs with multiple objectives. For large studies, we use a general theory and obtain various types of optimal approximate designs. When sample sizes are small, we propose two algorithms to construct highly efficient exact designs under realistic budget constraints. Additionally, we investigate properties of the proposed designs under various operational uncertainties and create a Shiny app to facilitate implementation of the proposed designs. To fix ideas, we focus on finding highly efficient group testing designs for a Chlamydia screening trial with imperfect assays under budget constraints and show the advantages of our optimal designs over current methods.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This paper adapts standard optimal design methods to group testing with costs and imperfect assays, adding multi-objective criteria and exact-design algorithms that are practical for screening work.

read the letter

The key point is that this paper adapts optimal design theory to group testing for infectious disease screening, incorporating imperfect tests and budget constraints while extending to A-, c-, E-optimality and multi-objective criteria. They provide algorithms for exact designs in small samples and approximate ones for large studies, plus a Shiny app. What stands out as new is the multi-objective extension and the handling of realistic budget limits in the group testing context. The Chlamydia example illustrates efficiency improvements over standard approaches. They also examine properties under uncertainties like parameter variations. The paper does a good job making the methods accessible with the app and concrete comparisons. The derivations build on standard information matrix approaches, which is fine since the application is the focus. On the soft side, the model relies on known assay sensitivity and specificity, and although robustness is checked, greater emphasis on how to handle uncertainty in those values would strengthen it for real deployment. The algorithms appear to be adaptations of existing exchange or optimization techniques rather than entirely novel ones. These are not deal-breakers but worth noting for users. This work suits statisticians and public health researchers designing screening studies with limited resources. A reader looking for practical optimal design tools in nonlinear or constrained settings will find value here. It is worth sending to a serious referee because the methodology is sound, the example is relevant, and the implementation details are provided. I recommend engaging with it in peer review. The central constructions hold up and the output is usable.

Referee Report

0 major / 3 minor

Summary. The manuscript develops a framework for single- and multi-objective optimal designs in group testing experiments focused on infectious-disease screening (e.g., Chlamydia). It extends beyond D-optimality to A-, c-, and E-optimality criteria, derives approximate designs for large studies via general theory, and proposes two algorithms for efficient exact designs under realistic budget constraints for small samples. The approach incorporates imperfect assays and linear cost structures, examines robustness under operational uncertainties, and includes a Shiny app for implementation.

Significance. If the derivations and algorithms hold, the work provides a practical extension of optimal-design methods to a setting with clear resource constraints and imperfect testing. The multi-objective and exact-design components, together with the software tool and uncertainty analysis, address needs that standard D-optimal approaches do not fully cover. This could improve efficiency in public-health screening trials.

minor comments (3)

The abstract states that the designs are investigated 'under various operational uncertainties,' but the introduction or methods section should list the specific uncertainties (e.g., prevalence misspecification, cost variability) considered in the robustness checks.
Notation for the information matrix and the multi-objective weighting scheme should be introduced with explicit definitions before the first numerical example to improve readability for readers unfamiliar with the group-testing model.
The description of the two exact-design algorithms would benefit from a short pseudocode or step-by-step outline in the main text rather than relegating all algorithmic details to an appendix.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive summary of the manuscript and for recommending minor revision. The assessment correctly identifies the extensions beyond D-optimality, the use of approximate and exact designs under budget constraints, and the inclusion of the Shiny app and robustness analysis. We are pleased that the practical relevance for infectious-disease screening is recognized.

Circularity Check

0 steps flagged

No significant circularity; standard theory applied to new domain

full rationale

The derivation begins from a standard logistic-type group testing model that incorporates assay sensitivity/specificity and a linear cost function, then computes the Fisher information matrix and applies the usual equivalence theorems for D-, A-, c-, and E-optimality as well as multi-objective combinations. Exact-design construction uses known exchange or integer-programming algorithms adapted only to the budget constraint. All steps follow directly from established optimal-design results once the information matrix is written down; no parameter is fitted to a subset and then renamed a prediction, no optimality criterion is defined in terms of itself, and no load-bearing uniqueness theorem or ansatz is imported via self-citation. The Chlamydia-screening example is a direct numerical illustration rather than a redefinition of the criteria.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claims rest on the applicability of standard optimal-design theory to the group-testing likelihood and on the accuracy of the stated cost and uncertainty models; no new physical entities are introduced.

free parameters (1)

budget constraints
Realistic budget limits are imposed when constructing exact designs for small studies.

axioms (1)

domain assumption Standard optimal design theory applies directly to the group testing model with imperfect assays.
The paper invokes general theory for approximate designs and extends it to the specific setting.

pith-pipeline@v0.9.0 · 5736 in / 1322 out tokens · 51137 ms · 2026-05-18T23:06:22.086142+00:00 · methodology

Single and multi-objective optimal designs for group testing experiments with a focus on screening for an infectious disease

Core claim

What carries the argument

If this is right

Where Pith is reading between the lines

Load-bearing premise

What would settle it

discussion (0)