Study Evaluating Intepirdine (RVT-101) in Subjects With Mild to Moderate Alzheimer's Disease on Donepezil: MINDSET Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study Evaluating Intepirdine (RVT-101) in Subjects With Mild to Moderate Alzheimer's Disease on Donepezil: MINDSET Study (NCT02585934), a randomized phase 3 study. The primary outcome is Alzheimer's Disease Assessment Scale - Cognitive Subscale 11 Items (ADAS-Cog-11) Score Change From Baseline to Week 24.

2. Clinical Question

The endpoint assesses cognitive abilities including memory, comprehension, orientation in time and place, and spontaneous speech. Its total score ranges from 0 to 70, with higher scores indicating more severe cognitive impairment. The reported analysis compares the least-squares mean change for RVT-101 with the corresponding mean change for placebo, with both groups continuing donepezil.

The statistical question is whether the observed group contrast is sufficiently distinct from no difference to be supported by the analysis, and how precisely the contrast is estimated. The registry identifies the primary analysis as a superiority comparison. It does not establish from the contrast alone how meaningful any difference would be to participants, and no threshold for clinical importance is reported in the registry record.

3. Trial Design

The registry describes MINDSET as a phase 3, randomized, quadruple-masked, parallel-group study. It enrolled 1315 participants and is marked completed. The listed condition is Alzheimer’s disease. The study began in 2015-10, and primary completion is recorded as 2017-09.

Participants were assigned to RVT-101 or placebo as an adjunct to existing stable donepezil treatment. Both arms allowed 5 mg or 10 mg donepezil. Thus, the comparison concerns adding RVT-101 rather than replacing donepezil with a different background treatment. The registry’s brief summary describes the study as seeking to confirm a demonstrated treatment effect of intepirdine as adjunctive therapy; that statement is the study’s stated aim, not a conclusion about the results.

The primary outcome was change in ADAS-Cog-11 score from baseline to Week 24. The primary endpoint population is described as the ITT population with data at both timepoints. The record also lists secondary outcomes covering global change assessed with caregiver interview, dependence, neuropsychiatric symptoms, ADAS-Cog-13, and plasma concentrations of RVT-101.

The original protocol’s target sample size, the assumptions used to select it, the detailed randomization procedure, and the exact masking roles are not reported in the registry record. The registry record also does not describe the allocation ratio, planned interim analyses, or whether any changes were made to the planned design. The sample-size illustrations associated with the observed results are not the trial’s original design calculations.

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: 2173 participants signed consent and were screened for participation. Of these, 1470 entered a 3-week single-blind placebo run-in period with treatment with placebo qd + stable dose of donepezil 5 or 10 mg qd. There was an overlap between the participants from the run-in period and the participants that were randomized during the treatment period.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: ITT Population with data at both timepoints.

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.

Population: ITT population

6. Primary Endpoint

The registry lists the primary outcome as Alzheimer's Disease Assessment Scale - Cognitive Subscale 11 Items (ADAS-Cog-11) Score Change From Baseline to Week 24, measured over Baseline, 24 weeks.

The primary endpoint is change from baseline to Week 24 on the ADAS-Cog-11, an 11-item measure of cognitive performance. The registry description says it assesses memory, comprehension, orientation in time and place, and spontaneous speech. Scores range from 0 to 70, and a higher total indicates more severe cognitive impairment.

A change score compares a participant’s score at follow-up with the baseline score. Comparing average changes between randomized groups provides an estimate of how the groups differed over the study period, while retaining the same background donepezil treatment in both arms. The registry reports least-squares mean changes, which are model-based group estimates, and their standard errors.

General: a cognitive scale can offer a structured way to assess a domain targeted by a trial, and a prespecified primary endpoint gives the main confirmatory comparison a defined focus. The score is not a complete account of a person’s condition or daily experience. The registry record does not report a threshold for a clinically important ADAS-Cog-11 change, so the numerical contrast cannot by itself be translated into a judgment about importance to participants.

7. Results Posted in the Registry

• RVT-101: mean 0.39 versus 0.75 on control; difference -0.36 (95% CI -0.95 to 0.23), standardized effect d = -0.07; z-test p = 0.230.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Clinical Global Impression of Change - Plus Caregiver Interview (CIBIC+) Score at Week 24

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • RVT-101: mean 4.18 versus 4.30 on control; difference -0.12 (95% CI -0.22 to -0.02), standardized effect d = -0.14; z-test p = 0.022.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for RVT-101 than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The Dependence Scale (DS) Score Change From Baseline to Week 24

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • RVT-101: mean 0.30 versus 0.17 on control; difference 0.13 (95% CI -0.07 to 0.33), standardized effect d = 0.08; z-test p = 0.192.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between RVT-101 and the control. The interval gives the range of effects that remain compatible with the data.

Neuropsychiatric Inventory (NPI) Score Change From Baseline to Week 24

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • RVT-101: mean -0.08 versus 0.06 on control; difference -0.14 (95% CI -1.09 to 0.81), standardized effect d = -0.02; z-test p = 0.772.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between RVT-101 and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists five secondary outcomes, while numerical results are included for three of them: CIBIC+ at Week 24, change in Dependence Scale score, and change in NPI score. Their estimates and sponsor analyses are displayed with the other outcome results. Considered together, they do not show a uniform pattern of precise between-group differences: the reported estimates vary in direction and their uncertainty differs across measures.

The CIBIC+ result is the secondary comparison with a sponsor-reported interval that does not include zero and a nominal p-value below 0.05. The dependence and NPI sponsor intervals include zero. This contrasts with the primary ADAS-Cog-11 result, whose interval also includes zero. The secondary findings should therefore be read as additional, not as a replacement for the primary endpoint. The numerical values for ADAS-Cog-13 and plasma concentrations are not reported in the registry record.

General: when a trial examines multiple outcomes, the chance of finding at least one apparently notable result by chance can increase if each is assessed separately. A multiplicity adjustment or a clearly defined hierarchy can help control how those results are interpreted. The registry record does not report a multiplicity procedure or a hierarchy for the secondary outcomes. Consequently, a nominal secondary p-value carries less confirmatory weight than a result from a prespecified primary analysis, especially when several outcomes are assessed.

The registry does not give scale-direction information for every secondary measure or a threshold for clinical importance. For that reason, the contrast signs and statistical significance should not be turned into broad claims about patient benefit. The overall secondary pattern adds context, but it does not resolve the primary endpoint’s uncertainty.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Clinical Global Impression of Change - Plus Caregiver Interview (CIBIC+) Score at Week 24
• The Dependence Scale (DS) Score Change From Baseline to Week 24
• Neuropsychiatric Inventory (NPI) Score Change From Baseline to Week 24
• ADAS-Cog-13 Score Change From Baseline to Week 24
• Measurement of Concentrations of RVT-101 (Intepirdine) in Plasma

9. Statistical Interpretation

10. Statistical Methods Explained

What does a mean difference describe?

The primary result is a difference between the two groups’ least-squares mean changes on ADAS-Cog-11. A negative estimate means the reported change estimate for RVT-101 is lower than the placebo estimate on this scale. Since higher ADAS-Cog-11 scores indicate more severe cognitive impairment, the direction of the estimate can be described numerically, but the confidence interval and study context are necessary for interpretation. The estimate is not a count of participants who improved, nor does it describe every participant’s outcome.

What is a least-squares mean?

General: a least-squares mean is a model-based estimate of a group mean. It can account for the terms included in the model, unlike a simple arithmetic average. The registry identifies the reported primary method as Mixed Models Analysis and describes its parameter as a least-square mean difference. The model specification, covariates, covariance structure, and handling of observations after dropout are not reported in the registry record. Therefore, the exact adjustments behind the sponsor’s model result cannot be reconstructed from the summary alone.

What does a standard error tell us?

The arm estimates are accompanied by standard errors. General: a standard error describes the sampling uncertainty of an estimated mean, rather than the spread of individual participant measurements. Smaller standard errors usually indicate a more precisely estimated mean, all else equal. The reported arm standard errors are 0.211 for RVT-101 and 0.213 for placebo. They are not standard deviations and should not be read as describing the range of individual ADAS-Cog-11 changes.

How should the confidence interval be read?

General: a confidence interval gives a range of estimates compatible with the data and the assumptions of the analysis at its stated confidence level. The sponsor’s 95% interval for the primary contrast is -0.95 to 0.22. Because this range includes zero, the results are compatible with no difference as well as with contrasts on either side of zero. The interval does not mean that 95% of participant outcomes lie within its endpoints, and it does not assign a 95% probability to a fixed effect after the data have been observed.

What does the p-value address?

General: a p-value measures how unusual data at least as incompatible with a specified null hypothesis would be if that null hypothesis and the analysis assumptions were true. It is not the probability that the null hypothesis is true, and it is not a measure of clinical importance. The primary sponsor-reported p-value is 0.225. The registry identifies the test as a superiority analysis, but details of the test implementation beyond the mixed models method are not reported.

Why distinguish the model result from a recalculation?

The sponsor’s primary analysis is a mixed-model comparison. The accompanying recalculation is an unadjusted comparison based on posted arm summary statistics. It reproduces the contrast as -0.36 and yields p = 0.23, with an interval that rounds to -0.95 to 0.23. The sponsor reports -0.36, p = 0.225, and an interval from -0.95 to 0.22. Small differences can arise because a simple summary-statistic calculation does not reproduce the model, its assumptions, or its exact estimation procedure. The recalculation is useful as a check on scale and broad interpretation, but it is not an independent analysis of participant-level data.

Why can over-dispersion matter?

General: in count outcomes, over-dispersion means that variability exceeds what a basic count model would expect. It can make standard errors too small if ignored. The primary ADAS-Cog-11 endpoint is continuous, not a count outcome, so count-model over-dispersion is not the central issue for this comparison. The registry record does not identify the primary endpoint as a count or report an over-dispersion assessment.

What analysis details remain unknown?

The primary outcome population is described as the ITT population with data at both timepoints. That wording does not explain how missing follow-up measurements were handled, whether additional imputation was used, or whether participants were analyzed according to assigned group in every circumstance. The registry record does not report the model’s covariates, assumptions checks, treatment of protocol deviations, or sensitivity analyses. It also does not report a prespecified multiplicity adjustment across outcomes. These omissions limit how fully the analysis can be independently reproduced from registry summaries.

11. Confidence Intervals and Precision

The sponsor’s primary estimate is -0.36 units, with a 95% confidence interval from -0.95 to 0.22. The estimate is the center of the reported contrast, while the interval communicates uncertainty around it under the model and its assumptions. Since the interval crosses zero, the record does not rule out no difference at the stated confidence level. It also spans values on both sides of zero, so the direction of the underlying contrast is not pinned down with high precision.

The point estimate is more limited than the interval as a description of uncertainty. Reporting only -0.36 would obscure that the range of estimates compatible with the analysis includes a small positive contrast as well as negative contrasts. Conversely, the interval does not mean that all values within it are equally likely, or that values outside it are impossible. It is a statistical uncertainty range, not a range for individual participants.

The unadjusted recalculation gives a 95% interval from -0.95 to 0.23, close to the sponsor’s reported interval. Its p-value is 0.23, compared with the sponsor-reported p = 0.225. These small differences reflect that the recalculation uses summary statistics and does not recreate the sponsor’s mixed model. The sponsor analysis is the reported trial analysis.

Precision is also distinct from clinical importance. The registry record does not state a minimally important difference for ADAS-Cog-11. Without that benchmark, the interval can describe statistical uncertainty but cannot show whether its values correspond to changes that participants or clinicians would regard as important. The posted standard errors for each arm further describe uncertainty in the mean estimates; they are not measures of individual variability.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning illustrations are participants per arm, not total events. They use a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to a stated fraction of the observed effect. These are planning illustrations based on the observed estimate, not the trial’s original design assumptions; those original assumptions are not reported in the registry record. The figures are not observed power.

The 80% power column gives the illustrative number of participants per arm needed for an 80% chance of detecting the selected effect under the stated assumptions, if that effect were the true effect and the analysis assumptions held. The 90% power column uses a higher target chance of detection and therefore calls for more participants per arm for the same effect size. These are prospective planning quantities, not evidence that the completed trial had a particular probability of success.

The rows consider planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. For the primary ADAS-Cog-11 estimate, the display gives 3,160 participants per arm for 80% power and 4,231 for 90% power when planning for 100% of the observed effect. Planning for 75% gives 5,618 per arm for 80% power and 7,521 for 90% power. Planning for 50% gives 12,640 per arm for 80% power and 16,922 for 90% power.

The pattern illustrates a general planning principle: smaller effects are harder to distinguish from random variation, so detecting them requires more participants. These figures depend on the assumptions stated above and on the observed effect used as a starting point. They should not be interpreted as the trial’s achieved power or as a reconstruction of the sponsor’s original sample-size calculation.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -0.360; pooled standard deviation σ = 5.108.
2. n = 2 × (1.96 + 0.842)² × 5.108² / -0.360² = 3,160.0, rounded up to 3,160 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -0.36                      # observed difference in means
sigma <- 5.10769537341549                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(2585934)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 3,160 (80% power), 4,231 (90% power)
 75% of observed effect: n per arm = 5,618 (80% power), 7,521 (90% power)
 50% of observed effect: n per arm = 12,640 (80% power), 16,922 (90% power)
power.t.test: 3160.9 
Simulated power at n = 3,160 per arm: 0.802 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The registry reports the sponsor’s primary analysis as a Mixed Models Analysis, with a least-square mean difference of -0.36, a 95% confidence interval from -0.95 to 0.22, and p = 0.225. This is the principal reported analysis for the primary endpoint.

The simple unadjusted recalculation from posted summary statistics gives the same mean difference, -0.36, and a p-value of 0.23. Its interval, when stated to no more than three decimal places, is -0.95 to 0.23. The slight endpoint and p-value differences are consistent with using a summary-statistic calculation rather than reproducing the mixed model. The recalculation does not use participant-level observations or establish the model’s assumptions.

For the secondary outcomes with sponsor analyses included, the registry also reports mixed-model estimates and p-values. The unadjusted recalculations are separate checks and can differ slightly from those sponsor results for the same reason. They should not be treated as replacements for the sponsor’s model-based analyses. In particular, the registry record does not provide enough detail to independently reproduce all model choices or missing-data handling.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when several statistical hypotheses are tested. General: even when each test uses the same nominal significance threshold, conducting multiple tests increases the chance that at least one result appears statistically notable by chance. Trials may address this through adjustments, a prespecified testing hierarchy, or other strategies. The registry record does not report an adjustment or hierarchy for the listed secondary outcomes, nor does it describe how multiplicity was handled across analyses.

The primary outcome is identified separately, which helps define the main confirmatory question. The sponsor reports a mixed-model superiority analysis for that endpoint. The secondary outcomes cover distinct domains and measures, but the record does not say whether they were intended as confirmatory hypotheses or exploratory assessments. Accordingly, secondary p-values should not be interpreted as though each were an isolated primary test.

Missing-data handling also affects interpretation. The primary endpoint population is described as the ITT population with data at both timepoints. The registry record does not report the number of participants missing endpoint data, reasons for missingness, any imputation method, or sensitivity analyses for missing outcomes. It is therefore not possible from the record to assess whether missingness could have affected the estimated contrast or how robust the result was to alternative assumptions.

The mixed models method is named, but the model specification and the assumptions used to handle incomplete repeated measurements are not reported. The record also does not describe protocol-deviation exclusions or sensitivity analyses comparing analysis populations. These details matter because an analysis’s interpretation depends not only on its point estimate but also on how the study planned and handled multiple questions, incomplete observations, and departures from the intended analysis.

16. 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 2% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: cerebrovascular accident (0.5%), basal cell carcinoma (0.5%), fall (0.5%), hip fracture (0.5%), seizure (0.3%).

The registry records serious adverse events for 40 of 656 at risk in the RVT-101 treatment group and 44 of 651 at risk in the placebo treatment group. These are counts of participants recorded as affected within the registry’s stated groups, not a comparison adjusted for exposure time or differences in follow-up. The record also reports 191 other adverse events among 656 at risk in the RVT-101 group and 166 among 651 at risk in the placebo group.

Deaths recorded during the treatment period were 3 for RVT-101 and 2 for placebo. Separate entries report deaths in screening, run-in, and post-treatment periods. Those periods should not be combined with treatment-period figures without a defined analysis and exposure framework. The most frequently listed serious adverse event terms include Cerebrovascular Accident, Basal cell carcinoma, Fall, Hip fracture, Seizure, and Myocardial infarction, with the percentages displayed in the registry.

These descriptive safety counts do not establish causation, comparative risk, or a safety profile on their own. The registry record does not give event timing, exposure-adjusted rates, statistical comparisons, or detailed event-level context.

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

The primary result describes an estimated difference between randomized groups in mean ADAS-Cog-11 change over the 24-week endpoint period. The sponsor reports a contrast of -0.36, with a 95% confidence interval from -0.95 to 0.22 and p = 0.225. The interval includes zero, so the analysis does not establish a statistically clear difference between groups under the reported model. Its range also shows that the estimate is uncertain in direction and magnitude.

This result does not prove that the groups were identical. A non-significant result can reflect a small underlying difference, uncertainty in the estimate, or both. The interval is more informative than a binary significant-or-not label because it displays a range of effects compatible with the analysis. But without a clinical-importance threshold, it does not identify whether any value in that range would matter to participants.

The comparison is specifically RVT-101 added to stable donepezil versus placebo added to stable donepezil, not RVT-101 versus no treatment or a comparison of donepezil with another therapy. It concerns the endpoint and time frame reported in the registry; it should not be extended to outcomes or time periods not reported.

The secondary results add observations across other measures, but the registry does not report numerical results for all listed secondary outcomes, and a multiplicity procedure is not described. Those findings therefore do not change the interpretation of the primary analysis. Likewise, the adverse-event counts are descriptive registry entries and do not alone establish whether an event was caused by treatment or quantify comparative risk.

Overall, the record documents a randomized, masked comparison and reports an uncertain primary estimate. It does not establish a definitive difference in the primary cognitive outcome, nor does it demonstrate equivalence. The statistical summaries also do not replace a complete assessment of study conduct, missing data, clinical importance, and safety context.

18. Why This Trial Matters Statistically

Statistically, MINDSET is informative because it places the primary question in a randomized, quadruple-masked, parallel-group phase 3 design with 1315 enrolled participants. Randomization and masking are design features intended to support a fair comparison and reduce some sources of bias. The registry record does not provide enough detail to assess every implementation feature, but these design labels help define the nature of the evidence being reported.

The endpoint is a continuous cognitive score, and the primary result is expressed as a model-based mean difference with a confidence interval and p-value. This makes it possible to distinguish the estimated direction and magnitude from the uncertainty around that estimate. The primary interval includes zero, which is an important qualification that would be lost if attention were confined to the point estimate.

The trial also illustrates why supporting statistics need context. The sponsor’s mixed-model analysis and the simple recalculation are broadly aligned, but the recalculation cannot reproduce the full model. Secondary outcomes cover multiple domains, yet numerical results are not available for all listed outcomes and multiplicity handling is not reported. These gaps limit how much confirmatory weight can be assigned to isolated secondary findings.

Finally, planning illustrations based on the observed effect show how required sample size depends on the effect size targeted and the desired power. They are not a record of the original design rationale or achieved power. Separating those planning calculations from the actual randomized trial results is essential to reading the evidence accurately.

19. 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 registry record gives a concise account rather than a full statistical analysis plan. The target sample-size rationale and original design assumptions are not reported, so the planning illustrations based on the observed effect cannot be used to infer what the sponsor planned before the trial. Interim analyses and any changes to the planned analysis are also not described.

The primary population is identified as ITT participants with data at both timepoints, but the record does not explain missing-data methods, the number of participants without endpoint data, or sensitivity analyses. This leaves uncertainty about the robustness of the estimate to incomplete follow-up. The mixed models method is named, but its model terms and assumptions are not reported, limiting independent reproduction of the sponsor’s result.

Although five secondary outcomes are listed, numerical results are not reported for ADAS-Cog-13 and plasma concentrations in the registry record. Multiplicity handling is not described, which limits the confirmatory interpretation of secondary tests. The registry also does not state a clinically important threshold for the primary score or all secondary measures.

Safety entries are presented as affected counts and numbers at risk across treatment and other study periods. The record does not provide exposure-adjusted comparisons, event-level context, or causal assessments. These limitations mean that the reported summaries support a bounded statistical reading, rather than a complete reconstruction of the trial’s conduct or a comprehensive evaluation of every outcome.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study Evaluating Intepirdine (RVT-101) in Subjects With Mild to Moderate Alzheimer's Disease on Donepezil: MINDSET Study — NCT02585934.
• Registry record last updated 2018-12-05; status last verified 2018-11.
• Results first posted 2018-12-05.
• 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.

23. Record Summary

NCT02585934 is the completed phase 3 MINDSET study of RVT-101 added to existing stable donepezil compared with placebo added to donepezil in mild to moderate Alzheimer’s disease. The registry describes a randomized, quadruple-masked, parallel-group design and records 1315 participants enrolled.

The primary endpoint was change from baseline to Week 24 on ADAS-Cog-11. The sponsor’s mixed models analysis reports a least-square mean difference of -0.36, a 95% confidence interval from -0.95 to 0.22, and p = 0.225. The interval includes zero, leaving uncertainty about the direction and magnitude of the group contrast.

The record lists five secondary outcomes, with numerical results included for three. It reports adverse-event counts across treatment and other study periods. Original sample-size assumptions, detailed missing-data methods, and multiplicity procedures are not reported in the registry record.