Colonoscopy Check-up in People With Lynch Syndrome: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Colonoscopy Check-up in People With Lynch Syndrome (NCT06126120), a registered phase not stated study. The primary outcome is Participant Non-adherence to 2-yearly Colonoscopy Check-up..

2. Clinical Question

3. Trial Design

This was a completed, questionnaire-based study, not a randomized treatment trial. Imperial College London sponsored the study. The registry lists enrollment of 231 and study dates from 2024-01-17 to primary completion on 2024-04-04. Completion status describes the study’s registry status; it does not by itself establish that every planned analysis or result is available in the record.

Participants came from the Lynch syndrome research registry pilot in England. The pilot included adults with Lynch syndrome who had previously participated in the Cancer Prevention Programme 3 trial. To be included in the present study, people had to have participated in the pilot, consented to be contacted about future research, and been aged 25 years or older. People who had undergone surgery to remove their rectum were excluded.

The research question concerned adherence to UK guidance recommending colonoscopy check-ups every 2 years after reaching a certain age. The questionnaire was used to investigate the percentage meeting the recommendation, factors associated with being more or less likely to meet it, and views, experiences, and challenges. The registry identifies the four most important challenges as a secondary outcome, but does not report the challenge findings.

For the primary outcome, the investigators used colonoscopy information from the national Hospital Episode Statistics database. The described assessment considered intervals between participants’ two or three most recent check-up colonoscopies, depending on data availability, and the interval from the most recent check-up to questionnaire completion. The record gives the data window as December 1995 through April 2024. The primary analysis was restricted to participants with a past or current cancer recorded in national cancer registry data. The record does not report the size of that analysis population.

No randomized allocation, treatment assignment, or like-for-like control comparison is described. The registry record does not report a statistical analysis plan, a sample-size justification for the study, or the details of analyses of factors associated with adherence.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: Of the 257 people in the registry pilot, seven were excluded at the initial participant eligibility assessment. The remaining 250 people were invited to take part in the present study, of whom 19 were subsequently excluded, either because the investigators were informed after invite that they met the exclusion criteria or because they did not respond to the questionnaire. This left 231 participants (92% of invitees). Participants were not assigned to any group or intervention.

Overall Study

Analysis population for the primary outcome, as defined in the registry: The number here differs from the total number of participants because only those who had a past/current cancer recorded in national cancer registry data were included in the analysis of non-adherence with 2-yearly colonoscopy check-up; data on check-up colonoscopies from the HES database were available only for these participants. Additionally, participants had to have had at least 2 recorded check-up colonoscopies to be included in this analysis.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Participant Non-adherence to 2-yearly Colonoscopy Check-up., measured over Up to approximately 13 years (median 5 years), based on the interval(s) between participants' 2 or 3 most recent check-up colonoscopies and the interval between participants' most recent check-up colonoscopy and questionnaire completion..

The primary endpoint is participant non-adherence to 2-yearly colonoscopy check-up, expressed as a count and described as a percentage. It is based on recorded timing rather than a clinical event such as cancer diagnosis. The assessment uses national Hospital Episode Statistics data on check-up colonoscopies, including intervals between recent check-ups and the interval from the latest check-up to completion of the questionnaire.

The stated timeframe is up to approximately 13 years, with a median of 5 years, reflecting the periods covered by the available intervals. The record says that two or three of the most recent check-up colonoscopies were used depending on data availability. Colonoscopy data recorded between December 1995 and April 2024 were considered.

Using an interval-based endpoint is relevant to the study question because the recommendation concerns the timing of repeated check-ups. It allows the investigators to classify adherence against the 2-yearly schedule rather than relying solely on participants’ recollection. In general, administrative records can provide dates of recorded care, while a questionnaire can provide context and reported experiences; neither source alone necessarily captures every aspect of adherence.

The endpoint’s analysis population is narrower than total enrollment: only participants with a past or current cancer recorded in national cancer registry data were included in the stated non-adherence analysis. The registry record does not report the endpoint count or percentage, the number included in this analysis, or how missing or conflicting records were handled. The outcome definition is therefore described, but its result and precision are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

How is the endpoint defined?

The endpoint classifies whether a participant’s recorded colonoscopy timing met the recommended 2-yearly schedule. The registry describes using intervals between the two or three most recent check-up colonoscopies, depending on data availability, as well as the interval from the latest check-up to questionnaire completion. In general, a schedule-based outcome requires a rule for deciding which intervals count as adherent. The registry record describes the intended endpoint but does not report the detailed classification rule, including how borderline intervals were treated.

The count and percentage are different ways of expressing the same endpoint information. A count states how many participants were classified as non-adherent; a percentage relates that count to the analysis population. Interpreting the percentage requires knowing who was included in its denominator. The record says the primary analysis included only participants with a past or current cancer recorded in national cancer registry data, but does not state the denominator.

What does the data source contribute?

Hospital Episode Statistics data were used for colonoscopy information, while questionnaire completion supplies the endpoint’s latest reference point. The record describes the data window as December 1995 through April 2024 and the timeframe as up to approximately 13 years, with a median of 5 years. In general, using recorded care data can reduce reliance on memory for dates, but administrative records may not capture every procedure or may classify procedures differently from a research definition. The registry record does not describe validation of the records, linkage completeness, or how any discrepancies between data sources were handled.

The analysis was further limited to participants whose past or current cancer was recorded in national cancer registry data. That restriction matters for interpretation: the primary result, if reported, would refer to that analysis population rather than automatically to all enrolled participants or everyone with Lynch syndrome. The record does not report why this restriction was selected, nor whether the included participants differed from those not included.

What is a confidence interval for?

As a general statistical concept, a confidence interval expresses uncertainty around an estimated quantity under a stated statistical method. It helps readers distinguish the point estimate from the range of estimates that remain compatible with the observed data and method. It does not correct bias, make a restricted population representative, or account automatically for errors in outcome classification. No confidence interval for non-adherence is reported in the registry record, so the precision of the primary estimate cannot be assessed.

Why can over-dispersion matter?

In general, over-dispersion occurs when observed variability is greater than a statistical model assumes. If a model assumes less variation than the data contain, standard errors can be too small and intervals or tests can appear more certain than warranted. This is a general consideration for count or rate analyses, not a claim about this study’s data. The registry record does not report a model for the primary endpoint, a dispersion assessment, or whether any adjustment for over-dispersion was considered.

What analysis plan is documented?

The record describes the outcome measure and its data sources but does not report the inferential method, covariate selection, model form, significance threshold for the primary analysis, or handling of repeated intervals within a participant. These details should not be inferred from the endpoint description. The record also does not state whether analyses were prespecified, whether there were interim analyses, or how any exploratory analyses were distinguished from confirmatory ones.

The sample-size material is described as a planning illustration computed from the observed effect. Its stated assumptions are a two-sided significance level of 0.05, equal allocation between two hypothetical arms, and a normal approximation; the effect to detect is a stated fraction of the observed effect. For time-to-event illustrations, the reported quantity is the total number of events, while other illustrations use participants per arm. These assumptions describe the illustration, not the design of this questionnaire-based study. It is not a randomized comparison, and the equal-allocation assumption does not create study arms. Sample-size illustrations are not observed power. The numerical illustration and the effect on which it is based are not reported in the registry record.

Because the primary outcome result and its analysis details are absent, readers cannot reproduce the endpoint estimate or independently assess its uncertainty. General statistical principles can explain what an analysis might need to address, but they cannot substitute for the missing estimate, denominator, and methods.

10. Multiplicity, Missing Data and Analysis Populations

The study had more than one stated objective: estimating non-adherence, examining factors associated with adherence, and understanding views, experiences, and challenges. The registry lists two outcome measures, including the primary non-adherence outcome and a secondary outcome concerning the four most important challenges. The record does not report results for either outcome, nor does it describe a multiplicity strategy for analyses across outcomes or factors.

Multiplicity is a general issue when several hypotheses or comparisons are examined. Considering many results can increase the chance that some appear noteworthy by chance, depending on the analysis and decision rules. Whether that concern applies, and how it was addressed, cannot be determined because the statistical plan and analysis details are not reported in the registry record. No adjustment or hierarchy should be assumed.

The record does not describe missing-data methods, imputation, exclusions beyond the stated eligibility criteria, or sensitivity analyses. It does say that two or three recent colonoscopies were used depending on data availability, which indicates that the amount of history available could differ among participants. It does not explain how incomplete histories affected endpoint classification. The eligible analysis population was restricted to participants with past or current cancer recorded in national cancer registry data; its size is not reported.

Enrollment of 231 is not the primary endpoint denominator. The record does not report how many people completed the questionnaire, how many had usable linked colonoscopy information, or how many were included in the restricted primary analysis. No comparison of included and excluded participants is reported. These omissions limit assessment of missingness, selection, and the reach of any result. They also mean that the primary estimate cannot be reconstructed from the registry record.

11. What the Result Does, and Does Not, Mean

The record identifies a clear descriptive question: how many participants in the specified analysis population did not meet a 2-yearly colonoscopy schedule, using recorded intervals. It also identifies an additional interest in factors related to adherence and the challenges participants considered most important. However, the registry record does not report the primary count or percentage, the challenge findings, or the results of any factor analyses. The content therefore supports understanding what was intended to be measured, not what the study found.

Even if the percentage were available, it would describe the people included in the analysis and the endpoint definition used. The primary population was restricted to participants with a past or current cancer recorded in national cancer registry data. It should not automatically be generalized to all people with Lynch syndrome, all participants enrolled in the study, or people in settings not represented in the registry population.

In general, an observational study can identify patterns and associations, but an association does not establish cause. A factor linked to adherence could reflect other measured or unmeasured differences, and the registry record does not report which factors were assessed or how they were analyzed. Questionnaire accounts of experiences could add context, but the record does not report those accounts or how they were summarized.

The outcome concerns adherence to a check-up schedule, not whether colonoscopy prevents cancer or changes clinical outcomes. The registry record does not report a treatment comparison, and there is no randomized comparator. The study’s stated purpose and endpoint therefore do not establish the effect of a clinical intervention. No medical recommendation can be inferred from the missing results.

Finally, a completed status does not mean that a numerical result is present in the registry. Without an estimate, denominator, and measure of uncertainty, readers cannot judge the observed frequency or its precision. The appropriate interpretation is that the study question and data sources are described, while the primary findings are not reported in the registry record.

12. Why This Trial Matters Statistically

Adherence is a meaningful statistical target when guidance depends on repeated actions over time. For a schedule-based measure, the analysis must define which recorded events count, which intervals are considered, and what population forms the denominator. This study’s registry description makes those issues visible: it uses intervals between recent check-up colonoscopies and the time from the most recent check-up to questionnaire completion, while restricting the primary analysis to people with a past or current cancer recorded in national cancer registry data.

The study also illustrates why an enrolled sample and an analysis population are not interchangeable. Enrollment was 231, but the primary analysis population was narrower. Reporting the number analyzed, the endpoint count, and the corresponding uncertainty would be necessary for readers to understand the reach and precision of an estimate. Those results are not reported in the registry record.

Combining administrative records with questionnaire information can address different parts of a research question: recorded care history can inform timing, while participants can report views and challenges. Statistically, however, each source has its own limitations, and linkage or completeness can affect who contributes to the endpoint. The record describes the sources but does not report validation, missing-data handling, or sensitivity analyses.

Lastly, the study demonstrates the distinction between a planning calculation and an observed result. A sample-size illustration based on an effect and hypothetical allocation assumptions cannot replace the reported outcome or show observed power. For this study, the central statistical contribution readers could evaluate would be the non-adherence estimate and its uncertainty; neither is reported in the registry record.

13. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The most important limitation for interpreting the posted results is that the registry record does not report the primary endpoint count or percentage. It also does not provide a denominator for the primary analysis or a measure of precision. As a result, the main descriptive question cannot be answered from the registry record.

The primary outcome population was restricted to participants with a past or current cancer recorded in national cancer registry data. The record does not report the size of this subgroup or explain how its characteristics compare with those of enrolled participants outside the analysis. Therefore, even a reported estimate would need to be interpreted as applying to the restricted analysis population, rather than assumed to represent all participants or all people with Lynch syndrome.

The endpoint depends on recorded colonoscopy history and uses a variable number of recent intervals depending on data availability. The registry record does not describe how incomplete histories, missing questionnaire dates, unmatched records, or any discrepancies were handled. It does not report validation of the administrative data or sensitivity analyses exploring alternative endpoint definitions.

The design is observational and has no randomized comparator. The record does not provide details of the analyses of factors associated with adherence, so confounding and the possibility of exploratory comparisons cannot be assessed. Results for the secondary challenge outcome are also not reported, and the methods for summarizing those challenges are not described.

Finally, the statistical analysis plan, sample-size justification for the study, multiplicity approach, and missing-data strategy are not reported in the registry record. These gaps prevent readers from judging whether analyses followed prespecified methods or how robust results might be to alternative assumptions.

14. Related Tutorials

15. Related Statistical Calculators

16. Sources

• ClinicalTrials.gov: Colonoscopy Check-up in People With Lynch Syndrome — NCT06126120.
• Registry record last updated 2026-06-05; status last verified 2026-05.
• Results first posted 2026-06-05.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

17. Record Summary

NCT06126120 is a completed questionnaire-based study sponsored by Imperial College London. It enrolled 231 participants and ran from 2024-01-17 to primary completion on 2024-04-04. The study examined adherence to the UK recommendation for 2-yearly colonoscopy check-ups among a subset of people with Lynch syndrome in England, as well as factors associated with adherence and participants’ challenges and experiences.

Eligible participants had taken part in the Lynch syndrome research registry pilot, consented to future research contact, and were aged 25 years or older; people who had undergone surgery to remove their rectum were excluded. The primary outcome used Hospital Episode Statistics data and was restricted to participants with a past or current cancer recorded in national cancer registry data. The registry describes the outcome definition and data window but does not report the primary count, percentage, analysis denominator, or uncertainty. Results for the secondary challenge outcome and factor analyses are not reported in the registry record.