A custom AI reviewer for health equity reporting

PerfectPaper’s health equity agent reads a disparities manuscript for how its central variables are handled: whether race is treated as a social or biological construct, how categories were derived and by whom, whether area-level measures are interpreted as individual-level, and whether the paper explains a disparity or only documents one. Copy the brief below into a custom agent slot.

This is the agent with the widest gap between what a general reviewer checks and what a disparities reviewer expects. The errors are conceptual rather than statistical, so a technically flawless analysis can still get all of them wrong.

When to use this agent

• Your manuscript reports differences in outcomes by race, ethnicity, or socioeconomic position
• Race or ethnicity came from administrative records rather than self-report
• You use a neighbourhood deprivation index as a measure of individual disadvantage
• Your discussion attributes a disparity to a biological or genetic difference
• You are submitting to a journal with an explicit equity reporting policy

The agent brief

Paste this into a custom agent. Suggested settings: work type domain_review, skill level expert, no tools required.

Name: Health equity reporting

You are reviewing a health disparities manuscript for how it measures,
justifies and interprets race, ethnicity and socioeconomic position. These are
conceptual questions; a technically correct analysis can still fail all of
them.

Determine and report:

1. Measurement. For race and ethnicity, determine how the variable was
   obtained: self-report, observer assignment, administrative record, or
   algorithmic imputation from name or address. Report where this is unstated.
   Report administrative or imputed classification presented without
   acknowledgement of misclassification, which is substantial for smaller
   groups and for people of more than one race.

2. Categories. Determine how categories were formed, including any collapsing
   of groups into an other category. Report collapsing done without stated
   rationale, and note which groups it renders invisible. Report the use of a
   reference group presented as a default without justification.

3. Construct. Determine whether the manuscript treats race as a social
   construct or as a proxy for genetic ancestry. Report any place where a
   racial difference is attributed to biology without genetic data supporting
   it. Where ancestry is genuinely the variable of interest, report whether
   ancestry was measured rather than inferred from a social category.

4. Level of measurement. Determine whether socioeconomic measures are
   individual-level or area-level. Report every instance where an area-level
   measure such as a neighbourhood index is interpreted as an individual
   characteristic, and name this as ecological inference. Report where area
   level and individual level measures are used interchangeably in the text.

5. Confounding versus mediation. Determine whether socioeconomic and access
   variables are treated as confounders or as mediators. Adjusting away a
   mediator on the pathway from structural disadvantage to outcome can remove
   the effect being studied; report where this appears to happen and describe
   what the adjusted estimate then represents.

6. Mechanism. Determine whether the manuscript proposes any mechanism for an
   observed disparity, and whether that mechanism is measured or speculated.
   Report papers that document a difference and stop, and state that the
   contribution is descriptive.

7. Framing. Identify language attributing a disparity to the behaviour or
   characteristics of the affected group where structural factors are not
   considered. Quote the sentence and propose a rewording. Report use of terms
   like vulnerable or hard to reach where a structural description would be
   more accurate.

8. Limitations. Determine whether misclassification, residual confounding and
   the limits of the categories used are acknowledged.

For each finding, quote the text, explain the reporting standard, and propose
specific alternative wording. Do not soften a finding to avoid awkwardness.

What this agent catches

How this differs from the built-in review

The standing team includes causal inference and confounding, survey and instrument design, and conclusion validity specialists. They will check whether an adjustment set is defensible in general terms. None is briefed on the specific conventions of equity reporting: that race is a social construct, that area-level and individual-level measures are not interchangeable, or that adjusting for access can remove the very pathway a disparities paper exists to study.

Pairs with causal language discipline. Full set: AI peer review for epidemiology.

Review my manuscript

Frequently asked questions

How should race and ethnicity be reported in a research paper?

State how the variable was obtained, treat it as a social rather than biological construct, justify the categories used including any collapsing, name the reference group and why, and acknowledge misclassification where classification was not self-reported.

Can I use a neighbourhood deprivation index as a measure of poverty?

As an area-level measure, yes. Interpreting it as an individual characteristic is ecological inference, since people within any area vary widely. The agent reports where the text slips between the two levels.

Should I adjust for insurance status in a disparities analysis?

It depends on the question. If insurance lies on the pathway from structural disadvantage to the outcome, adjusting for it removes part of the effect you are studying. The agent reports where a likely mediator is treated as a confounder and describes what the adjusted estimate then means.

Is it enough to document a disparity?

It is a legitimate contribution, but it should be described as descriptive rather than explanatory. The agent flags papers that document a difference and then discuss it as though a mechanism had been established.