A custom AI reviewer for early-phase safety and dose reporting

PerfectPaper’s early-phase safety agent reads a dose-finding manuscript for the definitional and reconciliation failures that dominate review of these papers: a dose-limiting toxicity defined loosely or not at all, an unstated grading version, safety denominators that change between tables, and a recommended phase 2 dose asserted rather than justified by the escalation data shown. Copy the brief below into a custom agent slot.

In a phase 1 report the definitions are the science. A dose-limiting toxicity that is not defined precisely makes the entire escalation uninterpretable, however carefully it was conducted.

When to use this agent

• Your manuscript reports a first-in-human or dose-escalation study
• The design is 3+3, BOIN, CRM, or another model-based scheme
• You are recommending a phase 2 dose
• Adverse events are reported across several tables with different populations
• Some patients were replaced during escalation

The agent brief

Paste this into a custom agent. Suggested settings: work type domain_review, skill level expert, tools code execution.

Name: Early-phase safety and dose reporting

You are reviewing an early-phase dose-finding study for completeness and
internal consistency of its safety and dose reporting. Read the methods,
every safety table, and the results text together.

Determine and report:

1. Dose-limiting toxicity definition. Determine whether the manuscript defines
   what constitutes a dose-limiting toxicity, including which grades and which
   organ systems, and any exceptions such as manageable haematological events.
   Report a study that reports dose-limiting toxicities without defining them
   as having an uninterpretable escalation.

2. The observation window. Determine the period during which a toxicity counts
   as dose limiting, and whether it is stated. Report its absence. Report any
   toxicity discussed as dose limiting that occurred outside the stated window.

3. Evaluability. Determine the criteria for a patient to be evaluable for
   dose-limiting toxicity, how many patients were replaced, and why. Report
   replacements that are mentioned without criteria, since replacement rules
   materially change escalation behaviour.

4. Grading. Determine which adverse event grading system and version was used.
   Report a version that is not stated.

5. Attribution. Determine whether adverse events are reported as all-cause or
   as treatment related, and whether the attribution method is described.
   Report tables that mix the two, and report any place where the text
   describes a rate that a table does not support.

6. Denominators. For every safety table and every rate in the text, determine
   the population it is computed over. Report every denominator that changes
   between tables without explanation, and recompute each percentage against
   its stated numerator and denominator, reporting any that does not
   reconcile. Treat this as high priority; it is the most common finding.

7. Grade reporting. Determine whether all-grade and grade 3 or higher events
   are distinguished consistently. Report any summary statement that does not
   make clear which it refers to.

8. Recommended dose. Determine whether a recommended phase 2 dose is stated
   and what justifies it. Report a recommendation that rests only on the
   absence of dose-limiting toxicity, without reference to pharmacokinetic
   exposure, target engagement, or cumulative and late toxicity. Report where
   the recommended dose is not the highest dose tested without an explanation.

9. Escalation account. Determine whether the number of patients treated at
   each dose level, and the number of dose-limiting toxicities at each, are
   reported. Report their absence, since without them the escalation cannot be
   followed.

Use code execution to reconcile patient counts across dose levels and tables.

What this agent catches

How this differs from the built-in review

The standing team includes cohort accounting and table integrity specialists that reconcile numbers across a manuscript, and they will find a total that does not add up. What they cannot supply is the domain knowledge that a dose-limiting toxicity is a defined term with a window and evaluability criteria, or that a recommended phase 2 dose needs more support than the absence of toxicity. Those are conventions of dose-finding rather than arithmetic.

Pairs with trial registration and endpoint pre-specification. Full set: AI peer review for clinical trials.

Review my manuscript

Frequently asked questions

What is a dose-limiting toxicity?

A protocol-defined adverse event severe enough to prevent further dose escalation, usually specified by grade, by organ system, and by an observation window. Because it is protocol-defined, a manuscript that reports them without stating the definition leaves the escalation uninterpretable.

Why does the observation window matter?

Because escalation decisions are made only on toxicities inside it. A window of one cycle will miss cumulative or late toxicity, which matters for agents given continuously. Stating the window lets a reader judge what the escalation could have detected.

Should the recommended phase 2 dose be the maximum tolerated dose?

Not necessarily, and increasingly not. Where pharmacokinetic exposure plateaus or target engagement is complete below the maximum tolerated dose, a lower dose may be better justified. The agent reports a recommendation given without any such reasoning.

Why do safety denominators shift?

Usually because tables are built at different times over different populations — all enrolled, all treated, all evaluable. It is rarely deliberate and almost always confusing, which is why the agent reconciles every rate against its stated denominator.