A Study of LY3303560 in Participants With Mild Cognitive Impairment or Alzheimer's Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of LY3303560 in Participants With Mild Cognitive Impairment or Alzheimer's Disease (NCT03019536), a randomized phase 1 study. The primary outcome is Number of Participants With One or More Serious Adverse Event(s) (SAEs) Considered by the Investigator to be Related to Study Drug Administration.

2. Clinical Question

3. Trial Design

This was a completed phase 1, randomized, double-masked, parallel study of LY3303560 in participants with mild cognitive impairment due to Alzheimer’s disease or mild to moderate Alzheimer’s disease. The registry lists an enrollment of 22. Participants were assigned to intravenous placebo, 70 mg LY3303560, or 210 mg LY3303560. The registry record does not report the allocation ratio or the procedures used to generate and conceal assignments.

The scheduled treatment period was every 4 weeks for 25 weeks, with an option to continue treatment up to 49 weeks. A 16-week follow-up period followed. The study description says that the study would last up to 65 weeks, not including screening, and that screening was required within 90 days before study start. The primary endpoint was assessed from baseline up to Week 65.

The registry lists the study start as 2017-01-31 and primary completion as 2019-06-05, with status recorded as completed. These dates describe the registry record; they do not by themselves provide information about participant-level follow-up completeness or the timing of individual events.

The primary outcome was a count of participants with one or more investigator-attributed, study-drug-related serious adverse events. The registry also lists pharmacokinetic outcomes: maximum serum concentration of LY3303560 at Week 49 and area under the serum concentration-time curve during the dosing interval. Although the study description mentions pharmacodynamics, the registry record does not provide a pharmacodynamic outcome result in the reported results used for this analysis. Further information about the detailed protocol, dose escalation procedures, or statistical design 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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All randomized participants who received at least one dose of study drug.

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: All randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With One or More Serious Adverse Event(s) (SAEs) Considered by the Investigator to be Related to Study Drug Administration, measured over Baseline up to Week 65.

The primary endpoint counts participants who experienced at least one serious adverse event that the investigator considered related to study drug administration. Its stated timeframe is baseline up to Week 65, and its population is all randomized participants who received at least one dose of study drug. It is therefore a participant-level safety outcome: the count concerns whether a participant met the endpoint, not the total number of separate serious events.

Serious adverse events are used in safety monitoring because their seriousness distinguishes them from less severe events, while the investigator’s attribution records a judgment about whether the event was related to study drug administration. These are separate considerations. The endpoint does not include every adverse event, nor does it establish causation independently of the investigator’s assessment.

The endpoint is relevant to a phase 1 study whose stated aims include safety and tolerability. However, it captures only a defined part of the safety picture. The registry separately notes that other non-serious adverse events and all serious adverse events, regardless of causality, are reported in the adverse-events results. The primary endpoint should not be interpreted as a complete account of all symptoms, laboratory changes, or other safety outcomes. The registry record does not report additional detail about how seriousness or investigator attribution was operationalized.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is binary at the participant level: a participant either met the definition of at least one investigator-attributed, study-drug-related serious adverse event during the stated timeframe or did not. The reported quantity is a count of participants. This makes the outcome different from a continuous measure, such as a laboratory value, and different from a count of every event when participants can experience more than one event.

What do the counts represent?

The registry reports the endpoint counts separately for placebo, 70 mg LY3303560, and 210 mg LY3303560. Each count should be read with its corresponding listed group size and with the endpoint population definition in mind: randomized participants who received at least one dose. The counts describe what was observed in those groups. They do not show an estimated causal effect, and they should not be converted into a claim about treatment differences without an appropriate comparison and uncertainty assessment.

A binary outcome can be analyzed using group proportions, risk differences, relative measures, or regression methods, depending on the analysis plan and data structure. These methods answer related but not identical questions. An absolute contrast describes a difference in event probability, while a relative contrast compares probabilities on a ratio scale. Regression can account for specified covariates, but that requires a reported model and sufficient information. The registry record does not report an analysis model, an effect estimate, or a formal comparison for this endpoint, so none of these quantities can be described as a trial result.

Why does uncertainty matter?

A confidence interval expresses the uncertainty around an estimated quantity under the assumptions of the analysis. It helps distinguish a precise estimate from one that is compatible with a broad range of possible values. Event counts in small groups can be especially imprecise, and a zero count does not imply that the population event probability is exactly zero. Because no confidence intervals are reported for this endpoint, the precision of the observed group pattern cannot be quantified from the registry record.

A p-value, if reported, would describe how compatible the data are with a specified statistical null model, conditional on the analysis assumptions. It would not measure the probability that the treatment is effective, the probability that a finding is due to chance, or the size or importance of an effect. No p-value or tested comparison is reported for the primary endpoint. This absence means that a significance claim should not be inferred from the counts alone.

How should the comparison status be read?

The registry indicates that a two-arm binary comparison was unavailable because values were missing or not estimable. This means there is no posted recalculated comparison to interpret. It does not replace the group-level counts, and it does not establish that the sponsor performed no analysis outside the results recorded in the registry. The registry record does not report a sponsor analysis for this endpoint that could be compared with a recalculation.

Where a recalculation is available, it is a simple unadjusted calculation from posted summary statistics and may not match a sponsor’s prespecified or adjusted analysis. In this record, no recalculated comparison is reported, so there is no recalculated estimate to set beside a sponsor result. The registry record does not report a sample-size justification, an interim analysis plan, or a detailed statistical analysis plan.

What does a planning illustration mean?

Sample-size planning asks how much information a future study might need to detect a chosen effect under specified assumptions. Such an illustration is conditional on the selected significance level, allocation, statistical approximation, and assumed effect. It is not a measure of what the completed trial achieved and is not observed power. The stated planning approach uses a two-sided significance level of 0.05, equal allocation, a normal approximation, and an effect defined as a fraction of the observed effect. However, no usable observed comparison is reported for this binary endpoint, and no planning result is reported in the registry record. The planning assumptions therefore do not supply a basis for a numerical sample-size conclusion.

Over-dispersion is a general concern when the variability in event data exceeds what a simple model assumes. For participant-level binary data, model fit and dependence matter if observations are clustered or otherwise not independent. The registry record does not describe such a structure or report model diagnostics, so over-dispersion cannot be evaluated as a trial-specific issue from these results.

Finally, the endpoint’s attribution and follow-up definition affect the statistical interpretation. Investigator judgment determines whether an event is counted as related, and the baseline-to-Week-65 window defines the period covered. A different attribution rule or observation window could yield a different endpoint, but the registry record does not report alternative definitions or sensitivity analyses. The posted counts should therefore be understood narrowly, according to the recorded endpoint definition.

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("Placebo IV", "70 mg LY3303560", "210 mg LY3303560")
n      <- c(6, 7, 9)
events <- c(0, 0, 0)
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  Placebo IV  6  0  0.0  0.0  45.9  0.0  39.0  0.4  41.0
ARM  70 mg LY3303560  7  0  0.0  0.0  41.0  0.0  35.4  0.3  36.9
ARM  210 mg LY3303560  9  0  0.0  0.0  33.6  -0.0  29.9  0.3  30.8

11. Multiplicity, Missing Data and Analysis Populations

The registry record does not report a multiplicity strategy for the primary and secondary outcomes. Multiplicity arises when several outcomes, treatment contrasts, time points, or analyses are examined: without an analysis plan, the implications for false-positive findings cannot be assessed. The listed secondary outcomes concern pharmacokinetic measures, but their results are not reported in the data. It is not reported in the registry record whether these outcomes were tested inferentially or how any tests were prioritized.

Missing-data procedures are not reported in the registry record. The endpoint population is described as all randomized participants who received at least one dose, but that definition does not explain how participants with incomplete follow-up, missing event assessments, or withdrawal were handled. The record does not provide participant-level follow-up completeness or a sensitivity analysis for missing outcomes. Consequently, it is not possible to assess whether the posted counts account for all eligible observation time in the same way across groups.

The registry reports a primary outcome population but does not describe additional analysis populations, such as a separate per-protocol population, or specify whether any outcomes were analyzed using different populations. It also does not report a detailed statistical analysis plan, interim analyses, or adjustment for baseline characteristics. These omissions do not prove that such procedures were absent from the full study documentation; they mean that they are not reported in the registry record. Interpretation should remain anchored to the posted group counts and their stated population rather than assuming unreported handling choices.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: back pain (11.1%), metastatic neoplasm (11.1%), pneumothorax (11.1%), pulmonary mass (11.1%).

The primary safety figure counts participants with at least one serious adverse event judged by the investigator to be related to study drug administration. The registry reports 0 in the placebo group, 0 in the 70 mg LY3303560 group, and 2 in the 210 mg LY3303560 group. Their listed group sizes are 6, 7, and 9, respectively. The endpoint covers baseline up to Week 65 and uses the population of randomized participants who received at least one dose.

The separate serious adverse event summary reports 0 participants in the placebo group, 0 in the 70 mg group, and 2 in the 210 mg group, without restricting the count to events considered related. The registry also reports other non-serious adverse events in 4, 7, and 8 participants, respectively, and deaths of 0 in each group. These categories should be read separately: the primary endpoint applies an investigator-relatedness criterion, while the separate serious event summary includes events regardless of causality.

The listed serious-event terms are Back pain, Metastatic neoplasm, Pneumothorax, and Pulmonary mass, each reported at 11.1%. The registry information does not specify the treatment group for each term. These counts and terms are descriptive safety information; without a formal comparison and uncertainty estimates, they do not establish a comparative safety difference.

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

The result establishes what the registry reports for the defined primary endpoint during the stated observation window: 0 participants in the placebo group, 0 in the 70 mg group, and 2 in the 210 mg group experienced at least one serious adverse event considered by the investigator to be related to study drug administration. It is a description of observed participants, not a test of whether treatment groups differ.

A zero count in a group is not evidence that the true risk is zero. The listed group sizes are 6 for placebo, 7 for 70 mg, and 9 for 210 mg, so the observed counts come from limited group-level experience. The registry does not provide confidence intervals that would express the uncertainty around the event experience. Nor does it provide a formal comparison to determine whether the pattern is compatible with a treatment-related difference.

The endpoint also reflects investigator attribution. The serious adverse event summary includes events regardless of causality, which is why it must not be treated as interchangeable with the primary endpoint. The reported non-serious adverse event counts and death counts provide additional descriptive context, but they do not change the definition of the primary result. The registry does not provide enough detail to assess event timing, duration, resolution, or how the attribution judgments were made.

The study was designed to assess safety, tolerability, pharmacokinetics, and pharmacodynamics. The reported primary endpoint addresses only a particular safety outcome. Although pharmacokinetic measures are listed, their results are not reported in the data; the safety counts cannot establish how LY3303560 was handled by the body. The primary endpoint also does not measure cognition or clinical progression. Therefore, these results do not establish clinical benefit, lack of benefit, or a definitive comparative safety profile. They describe a limited set of posted outcomes in the registry record.

14. Why This Trial Matters Statistically

This trial illustrates why the endpoint definition matters as much as the event count. The primary result is not a count of every adverse event or even every serious adverse event: it is a count of participants with at least one serious event that the investigator considered related to study drug administration. A different seriousness rule, attribution judgment, or follow-up window would describe a different outcome.

It also shows why descriptive counts should not be mistaken for comparative evidence. The posted counts distinguish the observed experience across placebo and the two LY3303560 dose groups, but the registry does not report a formal comparison or uncertainty estimates. Without those, it is not possible to quantify the precision of the pattern or to make a statistical claim about differences between groups. This is particularly important when group sizes are limited.

The separation between the primary related-event endpoint and the adverse-event summary is statistically and clinically important. The latter includes serious events regardless of causality and also reports non-serious events and deaths. Each measure answers a different descriptive question. Combining them would obscure the endpoint definition and could lead to an inaccurate interpretation.

Finally, the record demonstrates a common limit of registry results: listing an outcome does not ensure that a numerical result or analysis is available. Pharmacokinetic outcomes are named, while their results are not reported in the data. Statistical interpretation must therefore stay within the evidence actually recorded. That discipline prevents descriptive safety data from being stretched into conclusions about efficacy, mechanism, or certainty that the registry does not support.

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 registry record has several limitations for interpreting this particular trial. The primary outcome is based on investigator judgment about relatedness, but the record does not report the criteria or process used for that judgment. The outcome covers baseline up to Week 65, yet participant-level follow-up completeness and handling of incomplete observation are not reported. The endpoint population is specified as randomized participants who received at least one dose, but the registry does not provide details about exclusions or missing endpoint assessments.

The reported counts are not accompanied by confidence intervals, p-values, adjusted estimates, or a formal between-group analysis. The registry marks a binary comparison unavailable because values were missing or not estimable. Therefore, the observed difference in counts cannot be treated as a statistically established treatment effect. Further, the listed group sizes are limited, which constrains how much can be inferred from the event pattern.

The primary endpoint does not represent all safety outcomes. The registry separately reports serious adverse events regardless of causality, other non-serious adverse events, and deaths, but the information presented does not provide event-level details, timing, or treatment assignment for the listed serious-event terms. The registry lists pharmacokinetic outcomes, but their results are not included. The study description also names pharmacodynamics as an aim without a corresponding result in the reported data.

Design and analysis details are limited. The registry does not report the allocation ratio, randomization procedures, a detailed statistical analysis plan, sample-size justification, multiplicity handling, or missing-data methods. It also does not report interim analyses. These details may exist elsewhere, but they are not reported in the registry record and cannot be assumed when interpreting the posted results.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study of LY3303560 in Participants With Mild Cognitive Impairment or Alzheimer's Disease — NCT03019536.
• Registry record last updated 2023-10-10; status last verified 2023-10-01.
• Results first posted 2023-10-10.
• 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

NCT03019536 is a completed phase 1 randomized, double-masked, parallel study of LY3303560 in participants with mild cognitive impairment due to Alzheimer’s disease or mild to moderate Alzheimer’s disease. The registry lists enrollment of 22 and three treatment groups: placebo, 70 mg LY3303560, and 210 mg LY3303560. Treatment was administered intravenously every 4 weeks, with an option to continue up to 49 weeks, followed by a 16-week follow-up period.

The primary endpoint was the number of participants with at least one serious adverse event considered by the investigator to be related to study drug administration, from baseline up to Week 65. The registry reports counts of 0, 0, and 2 across placebo, 70 mg, and 210 mg, with listed group sizes of 6, 7, and 9. It does not report a formal comparison or uncertainty estimates for this endpoint. Pharmacokinetic outcomes are listed, but their results are not reported in the data.