Effects of LY450139, on the Progression of Alzheimer's Disease as Compared With Placebo: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Effects of LY450139, on the Progression of Alzheimer's Disease as Compared With Placebo (NCT00762411), a randomized phase 3 study. The primary outcome is Change From Baseline in Alzheimer's Disease Assessment Scale- Cognitive Subscale (ADAS-Cog11) at 76 Weeks.

2. Clinical Question

3. Trial Design

This was a Phase 3, randomized, quadruple-masked, parallel-group trial sponsored by Eli Lilly and Company. The registry lists Alzheimer's disease as the condition and reports enrollment of 1111 participants. The study started in 2008-09, reached primary completion in 2011-04, and is marked completed. The registry record does not report the original sample-size justification or the details of the randomization procedure beyond describing the trial as randomized.

The treatment groups followed different schedules during the period relevant to the primary endpoint. The LY450139 arm began with 60 mg orally once daily for 2 weeks, moved to 100 mg once daily for 2 weeks, and then received 140 mg once daily through Week 88. The placebo arm received placebo through Week 76, after which participants were titrated to LY450139 up to 140 mg once daily through Week 88. The registry summary also says that patients taking approved Alzheimer's disease medications could participate and continue those medications during the study.

The primary endpoint was assessed at 76 weeks, using baseline at randomization as the reference. The primary analysis population is defined as randomized participants who received at least 1 dose of study medication. The posted primary endpoint group counts are 555 for LY450139 and 553 for placebo. These counts should be read as the groups reported for that outcome, rather than treated as a reconciliation of the overall enrollment. The original protocol's handling of participants who did not contribute an endpoint measurement is not reported in the registry record.

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.

Initial Treatment

Reasons for not completing this period:

Delayed Start

Reasons for not completing this period:

Safety Follow Up (SFU)-Optional

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intent to treat (ITT) population: All randomized participants who received at least 1 dose of study medication.

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 Change From Baseline in Alzheimer's Disease Assessment Scale- Cognitive Subscale (ADAS-Cog11) at 76 Weeks, measured over Baseline (randomization), 76 weeks.

ADAS-Cog11 is the Alzheimer's Disease Assessment Scale cognitive subscale and was the trial's primary efficacy measure. The registry describes 11 items covering orientation, verbal memory, language, and praxis, which it identifies as areas commonly impaired in Alzheimer's disease. The scale ranges from 0 to 70, and higher scores indicate greater disease severity. The outcome is change from baseline at 76 weeks, so the analysis concerns how the recorded score changed over the study period, not a single end-of-study score in isolation.

The registry reports least-squares means controlled for baseline value, age, investigator, visit, and concomitant standard-of-care medication. Adjustment can account for those specified variables in the model-based group estimates. The registry record does not report the detailed model specification or the numerical adjusted treatment contrast and its confidence interval. The posted group means and the recalculated comparison offer descriptive context, but they are not a replacement for the sponsor's adjusted analysis.

ADAS-Cog11 is used as an outcome because it measures cognitive performance in domains relevant to the condition named in the record. Interpretation must still account for uncertainty in the estimated group contrast, the analysis population, and the way missing measurements were handled. The direction of a change also matters: an increase on this scale corresponds to greater disease severity according to the registry description.

7. Results Posted in the Registry

• 140 mg LY450139: mean 7.37 versus 6.77 on control; difference 0.60 (95% CI -1.49 to 2.69), standardized effect d = 0.03; z-test p = 0.575.

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.

Change From Baseline in Clinical Dementia Rating Sum of Boxes (CDR-SB) at 76 Weeks

• 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:
  • 140 mg LY450139: mean 3.05 versus 4.00 on control; difference -0.95 (95% CI -3.76 to 1.86), standardized effect d = -0.18; z-test p = 0.508.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 140 mg LY450139 and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Neuropsychiatric Inventory (NPI) at 76 Weeks

• 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:
  • 140 mg LY450139: mean 2.94 versus 3.84 on control; difference -0.90 (95% CI -3.66 to 1.86), standardized effect d = -0.04; z-test p = 0.523.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 140 mg LY450139 and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in the Resource Utilization in Dementia-Lite (RUD-Lite) up to 76 Weeks

• 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:
  • 140 mg LY450139: mean 0.72 versus 0.82 on control; difference -0.10 (95% CI -0.52 to 0.32), standardized effect d = -0.03; z-test p = 0.638.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 140 mg LY450139 and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists a broad set of secondary outcomes, including measures of dementia severity, neuropsychiatric symptoms, resource use, quality of life, cognition, plasma amyloid beta, and brain imaging. Of those outcomes with numerical results included in the record, the posted group contrasts do not show a consistent strong statistical signal across the reported measures. The registry gives sponsor-analysis p-values of 0.294 for the CDR-SB outcome, 0.477 for NPI, and 0.673 for RUD-Lite. Their recalculated intervals include zero, so these summaries also do not establish a clear group difference.

The available secondary results do not overturn or replace the primary ADAS-Cog11 result. Secondary measures address related but distinct aspects of disease, functioning, and resource use, so concordance can be informative, but a secondary measure is not an alternative primary endpoint. The posted record contains 29 outcome measures and 22 analyses, while 25 secondary outcomes are listed as posted; detailed numerical findings for every listed secondary outcome are not reported in the registry record.

When numerous outcomes are tested, the possibility of chance findings rises unless the analysis plan addresses multiplicity. Unadjusted secondary results therefore carry less weight than a prespecified primary analysis, especially when the registry does not report whether a multiplicity strategy was used. The pattern should be treated as exploratory context, not as a set of independent confirmations. The original hierarchy among secondary outcomes and any planned interpretation rules are not reported in the registry record.

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

• Change From Baseline in Clinical Dementia Rating Sum of Boxes (CDR-SB) at 76 Weeks
• Change From Baseline in Neuropsychiatric Inventory (NPI) at 76 Weeks
• Change From Baseline in the Resource Utilization in Dementia-Lite (RUD-Lite) up to 76 Weeks
• Change From Baseline in the EuroQol 5-Dimensional Health-Related Quality of Life Scale Proxy Version (EQ-5D Proxy) Visual Analog Scale (VAS) at 76 Weeks
• Change From Baseline in Quality of Life in Alzheimer's Disease (QoL-AD) at 76 Weeks
• Change From Baseline in Mini Mental State Examination (MMSE) at 76 Weeks
• Percent Change From Baseline in Amyloid Beta (Aβ) 1-42 Plasma Concentration at 52 Weeks
• Change From Baseline in Positron Emission Tomography (PET) Using Fluorine-18 Fluorodeoxyglucose (18F-FDG) at 76 Weeks

9. Statistical Interpretation

10. Statistical Methods Explained

The registry's primary outcome is continuous: it is a change in ADAS-Cog11 score. For a continuous outcome, an analysis can compare group means, while accounting for specified covariates or repeated measurements through a statistical model. The registry reports least-squares means controlled for baseline value, age, investigator, visit, and concomitant standard-of-care medication. Least-squares means are model-based group estimates adjusted for the included variables; they need not equal simple arithmetic means of individual observations.

What is the sponsor's analysis?

The reported primary analysis method is Mixed Models Analysis, and the registry gives p = 0.560. A mixed model is a general statistical approach that can represent outcome measurements associated within participants or with other grouping structures, depending on the model specification. That is a general explanation, not a claim about the exact structure used in this trial. The registry record does not report the detailed model formula, covariance assumptions, estimation method, or the numerical adjusted treatment contrast. It does state which covariates controlled the reported least-squares mean value.

What is the recalculated comparison?

The recalculated difference of 0.6 units is obtained from the posted group means, and the accompanying interval is a simple unadjusted recalculation from posted summary statistics. This calculation does not reproduce the sponsor's mixed models analysis. The reported group spreads are standard errors, not standard deviations. The recalculation estimates a pooled standard deviation from those standard errors and group sizes, so that standard deviation is approximate. This distinction matters because a standard error describes uncertainty in a mean estimate, whereas a standard deviation describes variability among individual observations.

A p-value measures how incompatible the observed data are with a specified null model, under the assumptions of the statistical analysis. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of an effect. The sponsor's p-value comes from the reported mixed models analysis. The recalculated p-value of 0.575 is based on the unadjusted summary-statistic comparison and should not be treated as another version of the sponsor's result.

Why does adjustment matter?

Adjustment can change a group contrast when the included covariates are associated with the outcome or differ in their distribution across groups. The registry says the primary least-squares means were controlled for baseline value, age, investigator, visit, and concomitant standard-of-care medication. The record does not provide enough detail to independently reproduce those model-adjusted estimates. Therefore, descriptive group means and unadjusted calculations should be interpreted alongside, not in place of, the sponsor's analysis.

In general, over-dispersion means that outcome variability is greater than a particular statistical model expects. It can affect standard errors and the reliability of uncertainty estimates if the model does not account for it. This is a general statistical concept; the registry does not report whether over-dispersion was assessed or relevant to the primary continuous endpoint. Likewise, the registry record does not report an interim analysis plan or whether any interim analyses were conducted.

Confidence intervals express uncertainty about an estimated effect under the analysis assumptions. A 95% confidence interval is generated by a procedure that, across repeated samples under its assumptions, would contain the target parameter in 95% of such intervals. It does not mean there is a 95% probability that a particular fixed effect lies in the observed interval. The interval attached to the recalculated estimate reflects that unadjusted calculation, not the sponsor's mixed-model estimate.

The registry reports 29 outcome measures and 22 analyses, and lists 25 secondary outcomes as posted. When many outcomes are examined, the chance of observing apparently notable results by chance can increase. Methods to address this include prespecifying a testing hierarchy or adjusting for multiple comparisons. Whether such procedures were planned or used is not reported in the registry record, so secondary p-values require cautious interpretation.

11. Confidence Intervals and Precision

The recalculated mean difference for the primary endpoint is 0.6 units, with a 95% confidence interval from -1.495 to 2.695 units. The interval includes zero and also includes negative and positive contrasts. Thus, the posted summary-statistic calculation does not identify a precise direction of the underlying difference. The interval's span indicates substantial uncertainty around the point estimate, relative to the estimate itself.

This interval is an unadjusted recalculation based on posted group summary statistics. It is not the confidence interval from the sponsor's mixed models analysis. Although the registry reports that the primary least-squares means were adjusted for baseline value, age, investigator, visit, and concomitant standard-of-care medication, it does not report the adjusted contrast or its confidence interval. The sponsor's p-value is available, but a p-value alone does not convey the range of effect sizes compatible with the adjusted analysis.

In general, a confidence interval combines information about the estimated effect and its statistical uncertainty. A narrow interval indicates greater precision than a wide interval, given the model and data; neither width nor inclusion of zero alone establishes clinical importance. The registry does not report a threshold for a clinically important ADAS-Cog11 difference, so the clinical meaning of particular values within the interval cannot be determined from the record. The interval should be interpreted with the endpoint definition, analysis method, and population in view.

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 for two-group continuous-outcome comparisons and report participants per arm, not total events. They use the observed effect as a starting point and show planning for 100%, 75%, and 50% of that observed effect. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. These are planning assumptions for the illustration; the trial's original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column describes the number of participants per arm that the stated planning calculation estimates would be needed for an 80% chance of detecting the chosen effect under its assumptions. The 90% power column gives the corresponding planning estimate for a 90% chance. These are not counts of participants observed in this trial, and they do not show what power the completed trial actually had.

For a given endpoint, the illustration requires more participants per arm when the effect to be detected is smaller: planning for 75% or 50% of the observed effect requires more participants than planning for the full observed effect. This reflects a general statistical principle: smaller group differences are harder to distinguish from random variation, all else being equal. The figures are planning illustrations based on the observed effect, not observed power.

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 = 0.600; pooled standard deviation σ = 17.793.
2. n = 2 × (1.96 + 0.842)² × 17.793² / 0.600² = 13,804.4, rounded up to 13,805 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 <- 0.600000000000001                      # observed difference in means
sigma <- 17.7926762621992                     # 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(762411)
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 = 13,805 (80% power), 18,481 (90% power)
 75% of observed effect: n per arm = 24,542 (80% power), 32,854 (90% power)
 50% of observed effect: n per arm = 55,218 (80% power), 73,921 (90% power)
power.t.test: 13805.4 
Simulated power at n = 13,805 per arm: 0.800 (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 a Mixed Models Analysis for the primary outcome, with p = 0.560. It does not report the sponsor's adjusted treatment-effect estimate or confidence interval. The sponsor's analysis is the trial's reported inferential analysis and takes precedence over the simple unadjusted recalculation from summary statistics.

The recalculated mean difference is 0.6 units, with a 95% confidence interval from -1.495 to 2.695 units and p = 0.575. This calculation uses the posted group means, group sizes, and standard errors; it does not adjust for the covariates listed for the least-squares means and relies on an approximate pooled standard deviation. The two p-values arise from different analyses, so their small numerical difference should not be interpreted as a conflict or as evidence that one analysis corrects the other.

Both reported analyses fail to provide a statistically clear indication of a difference at the conventional level often used in research, but the registry does not state the trial's prespecified significance threshold for this outcome. The sponsor's p-value should be understood in the context of its mixed models method, while the recalculation is a transparent descriptive check based on aggregate summaries. Neither p-value by itself communicates the likely size or clinical importance of a difference.

15. Multiplicity, Missing Data and Analysis Populations

The registry record does not report whether the analysis plan adjusted for multiple comparisons, specified a testing hierarchy, or otherwise controlled the overall chance of false-positive findings across outcomes. This matters because the record lists 29 outcome measures and 22 analyses, and multiple outcome testing can produce apparently notable results by chance. The primary endpoint has a reported sponsor analysis, but the registry does not provide enough information to reconstruct the full prespecified statistical plan.

The record defines the primary analysis population as the ITT population: all randomized participants who received at least 1 dose of study medication. This definition is more specific than simply referring to everyone randomized, because it explicitly includes a dose requirement. The primary endpoint group counts are 555 and 553. The registry record does not report whether all participants in this stated population had a 76-week measurement available or how missing endpoint observations were handled.

Missing-data methods can affect estimated group differences when observations are unavailable, particularly if the reasons for missingness differ across groups or relate to outcomes. In general, statistical approaches may use model-based assumptions, imputation, or other procedures, but none should be attributed to this trial without a registry report. The handling of treatment discontinuation, incomplete follow-up, and deviations from assigned treatment is not reported in the registry record.

The registry summary describes the placebo group switching to LY450139 after Week 76, but it does not report whether interim analyses were conducted. Details of monitoring, stopping rules, missing-data sensitivity analyses, and prespecified decision criteria are also not reported in the registry record. These omissions limit independent assessment of how robust the results are to alternative assumptions, but they do not establish that any particular procedure was absent from the full trial documentation.

16. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: abdominal pain upper (4.5%), bile duct stone (4.5%), diarrhoea (2.9%), diverticulum intestinal (2.9%), vomiting (2.9%).

The registry reports serious adverse event figures separately for the initial treatment period, delayed-start period, and safety follow-up period. For the initial treatment period, serious adverse events affected 60 of 555 participants in the placebo group and 92 of 556 in the 140 mg LY450139 group. The delayed-start entries report 7 of 34 and 1 of 22, respectively. In safety follow-up, the entries report 22 of 430 and 20 of 312. These are counts of participants affected and the corresponding numbers at risk as reported for each period; they should not be added together because the registry presents distinct periods and groupings.

The registry lists serious adverse event terms including abdominal pain upper, bile duct stone, diarrhoea, diverticulum intestinal, vomiting, and urinary tract infection, with the displayed percentages ranging from 2.9% to 4.5%. The record does not provide enough information in these entries to assign those term percentages to a particular treatment period or to infer causality. Death counts are not reported in the registry record. Safety counts alone do not establish whether an event was caused by study treatment.

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

The primary endpoint result is a comparison of changes in ADAS-Cog11 scores over 76 weeks among the reported analysis groups. The sponsor's mixed models analysis gives p = 0.560, while the unadjusted recalculation yields a mean difference of 0.6 units and a confidence interval that includes values in both directions. These results do not provide a statistically clear distinction between the groups on this endpoint, but they also do not establish that the groups were identical.

A non-significant p-value is not proof of no effect. It indicates that the reported analysis did not produce a result that is statistically distinguishable from the null under its assumptions and decision framework. The confidence interval is useful because it shows that a range of positive and negative contrasts remains compatible with the recalculated summary. The adjusted confidence interval from the sponsor's model is not reported, so precision for the model-based contrast cannot be assessed from the registry entry.

The endpoint is a cognitive scale with higher values indicating greater disease severity. Its result is not a direct measure of every aspect of Alzheimer's disease, and it does not by itself answer questions about imaging, quality of life, resource use, or longer-term outcomes. The registry lists those kinds of secondary outcomes, but the complete numerical evidence for all listed outcomes is not reported in the registry record.

These findings describe the trial comparison, population, endpoint, and follow-up period reported in the registry. They do not demonstrate a mechanism, establish a treatment effect outside the measured outcomes, or settle what would happen under a different study design or population. No medical recommendation follows from the statistical result alone.

18. Why This Trial Matters Statistically

This trial is statistically informative because its primary outcome is a clearly defined continuous measure assessed at a specified follow-up point, and the registry reports both a sponsor analysis and group summary statistics. That makes it possible to distinguish the model-based analysis from a simple unadjusted recalculation. The difference between these analyses is not merely numerical: they use different information and answer the comparison through different statistical procedures.

The result also illustrates why effect estimates and uncertainty intervals matter alongside p-values. The sponsor's p-value summarizes evidence under its mixed models analysis, while the recalculated contrast and interval show that the aggregate data do not precisely settle the direction or size of the difference. Neither a non-significant p-value nor a confidence interval spanning zero proves equivalence.

The trial's design included a placebo period through Week 76 followed by a switch to LY450139 for the placebo group. That timing is relevant to interpreting the primary comparison: the endpoint is at the end of the described initial treatment contrast, not a continued placebo comparison through Week 88. Statistical interpretation depends on recognizing the actual timing and group definitions, rather than treating all follow-up as one unchanging comparison.

Finally, the record's extensive outcome list underscores the importance of prespecification and multiplicity. A primary endpoint can anchor interpretation, while secondary findings may add context, but many tests require careful control and cautious reading. The registry does not report whether such controls were planned, making transparency about that uncertainty part of the statistical interpretation.

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.

Several trial-specific limitations arise from what the registry reports. The sponsor's adjusted treatment-effect estimate and confidence interval for ADAS-Cog11 are not reported in the registry record. The available unadjusted recalculation is based on posted means, sample sizes, and standard errors, with an approximate pooled standard deviation; it cannot reproduce the listed covariate-adjusted mixed models analysis.

The registry describes the primary population as randomized participants who received at least 1 dose, but does not report missing-data handling, the number with observed 76-week outcomes, or sensitivity analyses. The original sample-size justification, detailed statistical analysis plan, interim analysis procedures, and multiplicity strategy are also not reported. These gaps constrain assessment of precision, robustness, and how secondary findings were interpreted.

The placebo arm switched to LY450139 after Week 76, so later follow-up does not represent the same placebo-versus-drug contrast as the primary endpoint. The registry summary says participation could last approximately 2 years, but detailed results beyond the specified endpoint and the implications of the switch are not fully reported in the record. The secondary outcome list is broad, but complete numerical findings for every listed outcome are not included in the available record.

Safety reporting is segmented by periods and includes counts of affected participants and participants at risk. Deaths are not reported in the registry record, and the listed serious-event terms do not establish treatment causality. These limits call for restraint in interpreting either efficacy or safety from the registry entries alone.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Effects of LY450139, on the Progression of Alzheimer's Disease as Compared With Placebo — NCT00762411.
• Registry record last updated 2015-02-16; status last verified 2015-01.
• Results first posted 2014-09-25.
• 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

NCT00762411 is a completed Phase 3 randomized, quadruple-masked, parallel-group trial sponsored by Eli Lilly and Company. It enrolled 1111 participants with Alzheimer's disease and compared LY450139 with placebo. The primary endpoint was change from baseline in ADAS-Cog11 at 76 weeks, with higher scores indicating greater disease severity.

The registry reports a mixed models analysis with p = 0.560. Posted means were 7.37 for LY450139 and 6.77 for placebo; the unadjusted recalculated difference is 0.6 units, with a 95% confidence interval from -1.495 to 2.695. The adjusted sponsor estimate and confidence interval are not reported in the registry record. Secondary outcomes and period-specific serious adverse event counts provide additional context, while multiplicity and missing-data procedures are not reported.