Safety and Efficacy of Donepezil in Mild to Moderate Alzheimer's Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety and Efficacy of Donepezil in Mild to Moderate Alzheimer's Disease (NCT02787746), a na phase 4 study. The primary outcome is Number of Patients With Adverse Events (AEs).

2. Clinical Question

3. Trial Design

This was a Phase 4, multi-center, single-arm study in China of donepezil for mild to moderate Alzheimer's disease. Beijing Friendship Hospital is listed as the sponsor. The registry records enrollment of 241 participants, a start date of 2016-04, primary completion in 2019-01, and a completed status.

The study had one intervention group, donepezil. Allocation is listed as NA, the model as single group, and masking as none. These design features mean the registry does not describe random assignment or a masked comparison with another treatment or control group. The record's own description says the study assessed donepezil safety and efficacy in this population.

The primary endpoint is the number of participants with adverse events over 20 weeks. Its description refers to physical examinations, including vital signs and weight, clinical laboratory tests, and electrocardiograms during that period. The listed secondary outcomes include withdrawals due to adverse events, changes from baseline in Mini-Mental State Examination and Alzheimer's Disease Cooperative Study Activities of Daily Living scores, and outcomes concerning apolipoprotein E genotype and adverse events.

The registry lists six outcome measures and seven analyses. It does not report the detailed protocol, a sample-size justification for the trial, or a statistical analysis plan. The separate sample-size illustrations use hypothetical two-arm planning assumptions; those assumptions do not change the single-arm nature of the actual study.

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.

Overall Study

Reasons for not completing this period:

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 Number of Patients With Adverse Events (AEs), measured over 20 weeks.

The primary endpoint is the number of participants with adverse events during 20 weeks. It is a count of participants, not a measure of how many separate events each participant experienced. The registry description says safety monitoring during this timeframe included physical examinations such as vital signs and weight, clinical laboratory tests, and electrocardiograms.

Counting participants with at least one event is a direct way to describe how many people in the study had an adverse event. Such counts can help characterize the observed safety experience, but they do not convey how severe each event was, how long it lasted, or whether an individual had more than one event. The primary endpoint's title does not itself specify a comparison, and this single-arm study has no concurrent control group against which to compare the count.

The posted results list 93 participants with other adverse events and 3 with serious adverse events among 241 at risk in the donepezil group. The registry does not report a separate inferential estimate or confidence interval for the primary endpoint. These counts describe the participants recorded in the study; without a control group, they do not establish what portion of events was caused by treatment.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a count of participants with an event represent?

The primary endpoint is a count of participants with adverse events during a defined 20-week period. For this kind of binary outcome, each participant is classified according to whether an event was recorded or not. The endpoint counts participants meeting that condition; it is not the total number of event episodes. A participant may have more than one event, but the registry's primary endpoint does not quantify that recurrence.

The posted results report 3 participants with serious adverse events, 93 with other adverse events, and 0 deaths in the donepezil group, with 241 at risk for each of the serious and other event results. These counts should not be combined or treated as mutually exclusive categories unless the registry provides that information. It does not report whether participants could appear in more than one outcome category.

What can a single-arm result establish?

General explanation: A single-arm study describes outcomes within the group that received the intervention. It can document the events recorded under the study's observation conditions, but it does not directly estimate a treatment-versus-control contrast. A randomized comparison is one way to balance, on average, known and unknown factors between groups; that kind of comparison is not described in this record. Therefore, a result within the donepezil group alone cannot establish how the event count would differ under another treatment or no treatment.

Allocation is listed as NA, the model is single group, and masking is none. The study therefore should not be interpreted as if its one group were a randomized control comparison. The record does not report an adjusted analysis that could address the absence of such a comparator.

How should precision be understood?

General explanation: A count is the observed number of participants meeting an outcome definition. An estimate of an underlying event frequency is subject to sampling variability: another sample from the same broader population might yield a different count. A confidence interval can express uncertainty around an estimate under an explicitly stated statistical method. The registry record does not report a confidence interval for the primary endpoint, nor does it specify a statistical test for that endpoint. No interval or test result should therefore be inferred from the counts alone.

Event counts also depend on how outcomes are defined, monitored, and recorded. The endpoint description identifies physical examinations, laboratory tests, and electrocardiograms during the 20-week period. More detailed event definitions, assessment procedures, and rules for attributing events are not reported in the registry record.

What do the planning illustrations mean?

General explanation: The registry's sample-size illustrations are planning scenarios, not analyses of observed treatment effects. Their 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 outcomes, the illustrations use a total number of events; for other outcomes, they give participants per arm.

Those assumptions describe a hypothetical two-arm planning exercise, not the design of this single-arm study. A sample-size illustration is not observed power and does not show that the trial had a particular probability of detecting an effect. No trial-specific sample-size justification is reported in the registry record. The illustrations also do not supply a treatment comparison for the observed single-arm safety counts.

What is not established by the posted results?

The registry reports six outcome measures and seven analyses, but the record does not detail the statistical methods for those analyses. It does not report model specifications, covariate adjustments, confidence intervals for the outcomes, or the handling of repeated measurements. These absences matter because different analytic choices can yield different estimates and uncertainty statements. Without those details, interpretation should remain close to the outcomes and counts explicitly recorded, rather than implying that a particular inferential method was used.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Donepezil")
n      <- c(241)
events <- c(93)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Donepezil  241  93  38.6  32.4  45.1  32.7  44.9  32.7  44.9

11. Multiplicity, Missing Data and Analysis Populations

The registry lists six outcome measures and seven analyses. The secondary outcomes include withdrawals due to adverse events; changes from baseline in Mini-Mental State Examination and Alzheimer's Disease Cooperative Study Activities of Daily Living scores; and analyses concerning apolipoprotein E genotype and adverse events. Multiple outcomes and analyses create the general possibility that some findings may appear notable by chance when many hypotheses are examined. This is the reason multiplicity is considered in statistical interpretation.

The registry record does not report a multiplicity adjustment, a hierarchy for testing outcomes, or a prespecified distinction among confirmatory and exploratory analyses. It is therefore not possible to determine from the record whether the reported analyses were adjusted for multiple testing. The existence of multiple listed outcomes alone does not show that any particular adjustment was or was not performed.

Missing-data methods and analysis populations are also not reported in the registry record. The primary population field is blank, and the record does not state how participants with incomplete follow-up were handled, whether outcomes were analyzed according to any defined population, or how missing score measurements were treated. The endpoint lists 241 at risk for the serious and other adverse-event counts, but that alone does not describe the completeness of follow-up or establish how missing observations were addressed. These omissions limit the ability to assess whether the posted results represent all enrolled participants under a specified analysis rule.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: emesis (0.4%), rhabdomyolysis (0.4%), acute kidney injury (0.4%), acute myocardial infarction (0.4%).

The serious adverse-event results list 3 participants with events among 241 at risk in the donepezil group. The registry also lists Emesis, Rhabdomyolysis, Acute kidney injury, and acute myocardial infarction as serious-event terms, each at 0.4%. These terms describe the reported event categories; the record does not provide additional participant-level detail or explain whether categories overlap.

The registry separately reports 93 participants with other adverse events among 241 at risk, and lists 0 deaths. Serious and other adverse-event counts should be read as separate posted results, not added together: the registry does not report whether the same participant could be represented in both. Nor does the count alone convey severity beyond the serious-event classification, duration, recurrence, or the timing of each event.

These results describe what was recorded in the one study group. With no comparator, they cannot establish whether the intervention caused an event or whether the frequency differs from what would have occurred under another condition. The record does not report an inferential comparison or an uncertainty interval for these safety figures.

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

The study's posted results provide a descriptive account of adverse events recorded in a group of 241 participants enrolled in a multi-center, single-arm study. The primary safety outcome is the number of participants with adverse events over 20 weeks. The results list 3 participants with serious adverse events, 93 with other adverse events, and 0 deaths. Four serious-event terms are each reported at 0.4%. These figures communicate observed counts and listed categories, not a comparison of risks across treatment groups.

The findings do not establish that donepezil caused or prevented any listed event. Without a concurrent comparator, the study cannot separate treatment-related effects from events that might occur for other reasons in the study population. The results also do not estimate how the outcomes compare with another treatment or with no treatment. This limitation follows from the single-arm design, not from the size or direction of any particular count.

The record lists secondary outcomes involving withdrawals, clinical score changes, and apolipoprotein E genotype, but detailed results for those measures are not reported in the registry record. Their listing does not indicate that a change occurred or that a relationship was observed. Nor does the study title's reference to efficacy establish an efficacy finding in the absence of reported estimates for relevant outcomes.

In general, a result is more informative when its definition, analysis population, uncertainty, and comparison are clear. The registry gives a primary endpoint and event counts, but does not report a confidence interval or detailed analysis methods for the primary outcome. The appropriate reading is therefore limited: the posted counts describe safety events recorded in this study, while causal conclusions, comparative effectiveness, and the precision of underlying event frequencies remain unresolved by these results.

14. Why This Trial Matters Statistically

This study illustrates a basic distinction in clinical statistics: describing what happened in a treated group is not the same as estimating what treatment changed. A single-arm design can document adverse events observed during a defined period, and the registry reports counts for serious and other events. But without a randomized comparator, the study cannot directly estimate a difference attributable to the intervention.

That distinction is important when reading safety counts. The number of participants with an event is understandable and clinically relevant as a description of the study experience. Statistical interpretation still depends on the denominator, outcome definition, observation period, completeness of follow-up, and uncertainty. The record gives a 20-week timeframe and reports 241 at risk for the serious and other event results, but does not report confidence intervals or detailed missing-data methods.

The record also lists several secondary outcomes, including changes from baseline in clinical scores and outcomes involving genotype. Multiple outcomes can raise questions about which analyses were prioritized and how chance findings were addressed. The registry does not report a testing hierarchy or multiplicity adjustment, so readers cannot tell from this record how those issues were handled.

Finally, the planning illustrations demonstrate why design assumptions must be kept distinct from the trial that was actually conducted. The illustrations use hypothetical two-arm assumptions, whereas this study is recorded as single group. Keeping that distinction clear prevents a planning scenario from being mistaken for an observed comparison or for evidence that the study had a particular power.

15. 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 design is single-arm, with allocation listed as NA and masking as none. There is no concurrent control group in the registry record, so the posted results do not estimate a treatment-versus-control effect. This limits causal interpretation of the adverse-event counts and prevents a direct comparative assessment.

The registry reports enrollment of 241 and adverse-event denominators of 241, but does not report the primary analysis population or detailed follow-up completeness. Missing-data rules, outcome adjudication procedures, and participant-level event overlap are not reported in the registry record. These gaps make it difficult to determine precisely how the counts relate to all enrolled participants and how event categories were applied.

The record does not report confidence intervals or detailed statistical methods for the primary endpoint. It also does not report a trial-specific sample-size justification, multiplicity procedures, or the statistical methods used for the listed secondary outcomes. The planning assumptions are illustrations based on hypothetical two-arm designs and should not be treated as the study's design or as observed power.

Although changes in clinical scores, withdrawals, and genotype-related outcomes are listed, their results are not reported in the registry record. Therefore, the available information is insufficient to assess those outcomes or the study's efficacy aims. Further details on outcome definitions, analysis populations, missing data, and analysis procedures are not reported in the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Safety and Efficacy of Donepezil in Mild to Moderate Alzheimer's Disease — NCT02787746.
• Registry record last updated 2024-08-23; status last verified 2024-03.
• Results first posted 2024-08-23.
• 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.

19. Record Summary

NCT02787746 is a completed Phase 4, multi-center, single-arm study of donepezil in mild to moderate Alzheimer's disease in China, sponsored by Beijing Friendship Hospital. The registry reports enrollment of 241, a start date of 2016-04, and primary completion in 2019-01. Allocation is listed as NA, and masking as none.

The primary endpoint is the number of participants with adverse events over 20 weeks. Posted results list 3 participants with serious adverse events and 93 with other adverse events among 241 at risk, with 0 deaths. Four serious-event terms are each reported at 0.4%. Secondary outcomes include withdrawals, changes in clinical scores, and genotype-related measures. Detailed results and methods for those analyses are not reported in the registry record.