A custom AI reviewer for competing risks and time-related bias

PerfectPaper’s competing risks agent reads a survival analysis for the two failures that most reliably produce a wrong answer in cancer populations: using a method that treats death from other causes as censoring when it is a competing event, and defining exposure in a way that guarantees exposed patients survived longer. It also checks screening studies for lead-time and length-time bias. Copy the brief below into a custom agent slot.

Cancer cohorts are older and have substantial non-cancer mortality, which makes competing risks the norm rather than an edge case. Treating a competing event as censoring overstates cumulative incidence, always in the same direction.

When to use this agent

• Your manuscript reports cancer-specific mortality or recurrence in an older cohort
• You use Kaplan-Meier or Cox regression and death from other causes is common
• Exposure is defined by something that happens after the start of follow-up, such as receiving treatment
• You compare survival between screen-detected and clinically detected cases
• A reviewer has previously mentioned Fine-Gray or subdistribution hazards

The agent brief

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

Name: Competing risks and time-related bias

You are reviewing a time-to-event analysis for competing risks and for biases
arising from how time and exposure are defined.

Determine and report:

1. Events and competing events. Identify the event of interest and every event
   that prevents it from occurring. In a cancer cohort, death from other
   causes is a competing event for cancer-specific death and for recurrence.
   Determine how the analysis handled competing events. Report treatment of a
   competing event as censoring, state that this overstates cumulative
   incidence, and note that the overstatement grows with follow-up and with
   the competing hazard.

2. Method. Determine whether cumulative incidence was estimated with a method
   appropriate to competing risks, such as the cumulative incidence function
   or a Fine-Gray subdistribution model, or with Kaplan-Meier. Where
   Kaplan-Meier is used with substantial competing mortality, report it.
   Where a cause-specific hazard model is used, determine whether the
   interpretation in the text matches what that model estimates, since
   cause-specific and subdistribution models answer different questions and
   are frequently interchanged in discussion.

3. Time origin. Determine the start of follow-up for each subject and whether
   it is the same for all. Report any analysis where follow-up begins at a
   point that could only be reached by surviving, such as date of surgery in a
   cohort defined at diagnosis.

4. Immortal time. Determine whether exposure is defined by an event occurring
   after the time origin, such as receiving a treatment, completing a course,
   or achieving a response. Where it is, determine whether the time before
   that event was assigned to the exposed group. Report this as immortal time
   bias, state that it guarantees an apparent benefit, and name the standard
   remedies: a time-varying exposure, or a landmark analysis at a stated time.

5. Screening biases. For any comparison involving screen-detected disease,
   determine whether lead-time bias is addressed, since earlier detection
   lengthens measured survival without changing the date of death. Determine
   whether length-time bias is addressed, since screening preferentially
   detects slower-growing disease. Report survival comparisons between
   screen-detected and clinically detected cases where neither is addressed,
   and note that mortality rather than survival is the appropriate endpoint.

6. Overdiagnosis. For screening studies reporting incidence or survival
   benefit, determine whether overdiagnosis is considered.

7. Follow-up. Determine whether median follow-up is reported and how it was
   computed, and whether the number at risk is shown on survival curves.

Use code execution to check internal consistency of reported rates, numbers at
risk and event counts.

For each finding, state the direction of the bias, not only its presence.

What this agent catches

How this differs from the built-in review

The standing team includes statistical models and causal inference specialists that read the analysis competently. This agent adds the population-specific knowledge that makes those readings sharp in oncology: that competing mortality is the default rather than an exception, that immortal time enters through exposure definitions that look innocuous, and that survival is the wrong endpoint for a screening comparison. Each is a well-known bias with a name, and each is easier to find when you are looking for it specifically.

Pairs with registry and claims data validity, where these designs usually live. Full set: AI peer review for epidemiology.

Review my manuscript

Frequently asked questions

When should I use Fine-Gray instead of Kaplan-Meier?

When competing events are common and you want the probability of the event actually occurring. Kaplan-Meier treats a competing death as censoring, which assumes the patient could still have the event later, and that assumption is false once they have died of something else.

What is immortal time bias?

Bias arising when exposure is defined by an event that takes time to reach, and the time before it is credited to the exposed group. Those patients could not have died before becoming exposed, so the exposed group appears to survive longer regardless of any real effect.

Why is survival the wrong endpoint for a screening study?

Because detecting disease earlier lengthens the interval between diagnosis and death even if the date of death is unchanged. That is lead-time bias. Mortality in the screened population is the endpoint that avoids it.

Does cause-specific mortality avoid the competing risks problem?

Not by itself. A cause-specific hazard model is valid for questions about the hazard among those still at risk, but it does not estimate absolute risk in the presence of competing events. The agent reports where the interpretation in the text does not match the estimand.