Efficacy and Safety of Elpipodect (MK-8189) in Participants With an Acute Episode of Schizophrenia (MK-8189-008): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety of Elpipodect (MK-8189) in Participants With an Acute Episode of Schizophrenia (MK-8189-008) (NCT04624243), a randomized phase 2 study. The primary outcome is Change From Baseline in Positive and Negative Syndrome Scale (PANSS) Total Score at Week 6.

2. Clinical Question

3. Trial Design

This was a phase 2B, randomized, double-blind, placebo- and active-controlled, parallel-group trial of elpipodect in participants experiencing an acute episode of schizophrenia. The registry lists triple masking. The study was completed and enrolled 499 participants. Its recorded start date was 2020-12-15, and its primary completion date was 2024-06-21.

The trial evaluated once-daily elpipodect at 8 mg, 16 mg, and 24 mg, alongside risperidone 6 mg and placebo. The registry describes treatment periods extending through Week 12, followed by 2 weeks of follow-up for the elpipodect arms. The risperidone arm received risperidone 6 mg once daily through the acute and extension treatment periods. The placebo comparator for the primary Week 6 assessment received placebo in Weeks 1 to 6, followed by elpipodect 24 mg in Weeks 7 to 12.

A protocol amendment changed planned enrollment to approximately 500 participants and removed the elpipodect 8 mg arm. Participants enrolled before that amendment who had been assigned to 8 mg remained on that regimen. The registry states that the 8 mg effect was not assessed for the primary endpoint. The primary hypotheses concerned superiority to placebo for the 24 mg and 16 mg doses, respectively, using Week 6 mean change from baseline in PANSS total score.

The total enrollment is not the denominator for every outcome. The primary analysis population was defined by treatment received and availability of baseline and post-baseline measurements; endpoint-specific analysis counts are reported separately. The registry record does not report further details of the randomization procedure, allocation concealment, or a sample-size justification.

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: Randomization into the MK-8189 8 mg arm ceased as of Amendment 4.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All participants who receive ≥1 dose of MK-8189 (16 mg or 24 mg), risperidone, or placebo, and have both a baseline measurement and ≥1 valid post-baseline assessment, are included. Per protocol, the effect of the 8 mg dose was not assessed.

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 Positive and Negative Syndrome Scale (PANSS) Total Score at Week 6, measured over Baseline and Week 6.

The primary endpoint was change from baseline in PANSS total score at Week 6. PANSS is a clinician-rated inventory used to assess schizophrenia symptom severity. It contains 30 items: 7 for positive symptoms, 7 for negative symptoms, and 16 for general psychopathology. Each item is rated on a 7-point scale from 1 (absent) to 7 (extreme). The total is the sum of all item ratings and ranges from 30 to 210.

The endpoint is a change score: it describes how the participant’s Week 6 score differs from the baseline score, rather than reporting the Week 6 score alone. The registry defines lower change scores as reflecting improvement and higher change scores as reflecting worsening. The primary outcome is reported as a least-squares mean, with a 95% confidence interval for each treatment arm. Sponsor comparisons use the least-squares mean difference between each elpipodect dose and the placebo comparator.

Using a standardized symptom scale allows the trial to compare average change across randomized groups rather than relying only on individual symptom descriptions. The Week 6 timing corresponds to the acute treatment period, when the comparator group received placebo. The registry identifies risperidone as the active control and placebo as the inactive control. It does not report in the registry record a rationale for selecting Week 6 or additional details about how the endpoint was chosen.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is continuous: each participant has a numerical PANSS change score, and the arm results are summarized using least-squares means. A least-squares mean is a model-based group estimate. The registry identifies ANCOVA as the method for the sponsor’s treatment comparisons, but the full model specification and the covariates included are not reported in the registry record. Therefore, the posted least-squares mean differences can be described, but the registry does not support reconstructing every detail of their adjustment.

What does a confidence interval convey?

General statistical explanation: a confidence interval expresses uncertainty around an estimate under the assumptions of the analysis. A narrower interval indicates greater precision than a wider interval, while an interval that includes zero for a difference is compatible with no difference under the interval procedure. The sponsor-reported 97.5% intervals for both primary dose comparisons include zero. Their endpoints also include effects in either direction, so the point estimate alone should not be treated as a precise description of the treatment contrast.

A p-value measures how compatible the observed data are with a specified null hypothesis under the statistical model; it is not the probability that the null hypothesis is true, nor does it measure clinical importance. The sponsor reported p = 0.241 for 16 mg versus placebo and p = 0.784 for 24 mg versus placebo. Those values accompany the estimates and intervals; they do not replace consideration of the estimated effect, its uncertainty, or the analysis population.

How do the recalculated secondary comparisons differ?

The posted body-weight re-calculations are simple, unadjusted comparisons of group summary statistics. They are not the sponsor’s reported ANCOVA results. They compare each listed elpipodect arm with the comparator using the displayed means and standard deviations, and give an unadjusted estimate, interval, and p-value. These calculations can help describe the posted summaries, but they do not account for any covariate adjustment or multiplicity procedure that may have been used in an analysis not reported in the registry record. The registry lists no sponsor-reported analyses for these body-weight endpoints.

General statistical explanation: an unadjusted comparison does not control the probability of false-positive findings across multiple tests. That matters when several endpoints, time points, or dose comparisons are examined. An unadjusted p-value is therefore evidence about a single comparison under its assumptions, not a confirmatory conclusion across a family of outcomes. The registry record does not report a multiplicity plan for the secondary outcomes.

How should the planning illustrations be read?

The planning illustrations use the observed effect as a reference and show participants per arm for 80% power and participants per arm for 90% power at a two-sided significance level of 0.05, assuming equal allocation and a normal approximation. The examples scale the effect to 100%, 75%, or 50% of the observed effect. These are planning illustrations, not the trial’s design justification, and not observed power. The registry record does not report the trial’s own sample-size assumptions or justification.

General statistical explanation: planning estimates depend on assumptions about the effect to detect, variability, allocation, and significance threshold. If the effect used for planning is smaller, more participants are generally needed to detect it with the same target power, all else equal. The figures are not a guarantee that a future study will achieve its target, and they do not explain the precision of the completed trial by themselves. For time-to-event outcomes, a planning quantity may refer to events; these body-weight outcomes are continuous and the illustrations are expressed as participants per arm.

What limits interpretation of the methods?

The registry describes the primary endpoint population as participants receiving at least one dose of MK-8189 16 mg or 24 mg, risperidone, or placebo, with baseline and at least one valid post-baseline assessment. It does not report the detailed missing-data method, treatment of intercurrent events, assumptions for model fitting, or sensitivity analyses. These details matter because model-based comparisons can depend on how incomplete observations and departures from the planned treatment course are handled. The posted summary supports interpretation of the reported estimates, but not an independent reconstruction of the sponsor’s full analysis.

10. Analyses Reported by the Sponsor

The sponsor’s own primary analysis used ANCOVA and reported least-squares mean differences for each elpipodect dose against the placebo comparator. For 16 mg, the reported difference was -2.8, with a 97.5% confidence interval from -8.3 to 2.6 and p = 0.241. For 24 mg, the reported difference was -0.7, with a 97.5% confidence interval from -6.3 to 4.9 and p = 0.784. The registry record identifies both as superiority analyses. The record does not report a sponsor analysis for the primary 8 mg dose comparison.

The sponsor-reported estimates take precedence over a simple re-calculation from arm summaries when both are available, because the ANCOVA results are the reported trial analyses and may reflect model-based adjustment. The body-weight re-calculations are distinct: they are unadjusted comparisons from summary means and standard deviations, and the registry lists no sponsor-reported analyses for those endpoints. No discrepancy is flagged between the available primary summaries and sponsor analyses. The registry does not provide enough detail to reproduce the ANCOVA model or determine the reason for the 97.5% confidence level.

11. Multiplicity, Missing Data and Analysis Populations

The study had two stated primary hypotheses: elpipodect 24 mg versus placebo and elpipodect 16 mg versus placebo on Week 6 change in PANSS total score. The sponsor reports a separate ANCOVA result for each comparison. The registry gives 97.5% confidence intervals, but does not explain why this confidence level was selected or state how the two primary hypotheses were handled together. Whether a formal multiplicity adjustment was applied is not reported in the registry record. The reported p-values should therefore be read as posted, without assuming an unreported family-wise procedure.

The registry lists multiple secondary outcomes, including symptom subscales, clinician-rated severity, and body-weight change at different times. It does not report a hierarchy, gatekeeping strategy, or other multiplicity plan for these endpoints. Repeated testing across outcomes and time points can increase the chance of false-positive findings. This concern is particularly relevant to the unadjusted body-weight re-calculations, which are descriptive and do not establish a confirmatory secondary result.

The primary analysis population required at least one dose of an eligible treatment and both a baseline measurement and at least one valid post-baseline assessment. This defines who contributed to the primary endpoint analysis, but it does not explain how participants without those measurements were handled in other analyses. The registry record does not report the extent or pattern of missing primary outcome data, the method used to address missing values, or sensitivity analyses assessing alternative assumptions. Detailed rules for handling treatment discontinuation, rescue treatment, or other events are also not reported in the registry record.

These omissions do not invalidate the posted estimates, but they limit the ability to evaluate their robustness independently. The available record supports reading the sponsor’s estimates and intervals as reported; it does not support claims about an unreported missing-data strategy, interim monitoring, or statistical analysis plan.

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: schizophrenia (11.8%), suicidal ideation (5.9%), toxicity to various agents (1.7%), psychotic disorder (1.7%), chronic obstructive pulmonary disease (1.5%).

The registry reports serious adverse events, other adverse events, and deaths in treatment-period groups. For the acute Weeks 1 to 6 period, serious adverse events were reported for 8 participants in the 16 mg group, 6 in the 24 mg group, 2 in the risperidone group, and 0 in the placebo group; the corresponding groups at risk were 132, 132, 65, and 129. The 8 mg group had 1 serious adverse event among 41 participants at risk. Deaths were reported as 0 in each of these groups for that period.

For Weeks 7 to 12, the registry reports 4 serious adverse events among 75 participants at risk in the 16 mg group, 3 among 60 in the 24 mg group, 0 among 39 in the risperidone group, and 2 among 85 in the group that received placebo during Weeks 1 to 6 and MK-8189 24 mg afterward. The 8 mg group had 3 among 17 participants at risk. One death was reported in the 16 mg Weeks 7 to 12 group; the other listed groups had 0 deaths.

The registry also lists serious-event terms with percentages, including schizophrenia at 11.8% and suicidal ideation at 5.9%. The term-level denominator and further detail are not reported in the registry record. These figures describe reported events and exposure groups; they do not by themselves establish comparative risk or causation. The registry record does not provide enough information to assess event severity beyond the serious-event classification, duration, or individual clinical circumstances.

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

The primary results describe estimated average symptom-score changes for the defined analysis population and the sponsor’s comparisons of two elpipodect doses with the placebo comparator at Week 6. The point estimates for both dose comparisons are negative, but the reported confidence intervals include zero, and the reported p-values are 0.241 and 0.784. Thus, the posted analyses do not establish a statistically distinguishable difference from the comparator at the reported levels. The intervals also indicate uncertainty about the size and direction of the underlying contrast.

This interpretation is about the group-level PANSS total-score endpoint at one assessment time. It does not state that every participant’s symptoms changed in the same way, and it does not describe all possible clinical outcomes. A group mean can conceal variation between participants. The endpoint also captures a particular clinician-rated symptom scale rather than every aspect of illness or daily functioning. Other outcomes and safety information are separate considerations.

The findings do not establish that elpipodect is effective or ineffective for an individual, nor do they answer questions about use outside the trial’s eligibility and treatment conditions. The registry record describes adult participants with an acute episode of schizophrenia, specific dose regimens, and a Week 6 primary assessment. It does not report longer-term comparative results beyond the listed trial periods in the results.

Secondary body-weight comparisons are based on unadjusted recalculations and should be interpreted with less confirmatory weight, especially because a multiplicity plan is not reported. The safety counts are descriptive reports by treatment period and do not establish causality. Taken together, the posted findings define what was estimated and how uncertain those estimates are; they do not support conclusions beyond the measured outcomes, analysis population, and follow-up described in the registry.

14. Why This Trial Matters Statistically

This trial illustrates why arm-level change and between-group treatment contrast answer different statistical questions. The reported arm means show the average change within each group, while the primary hypothesis concerns whether that change differs between elpipodect and the placebo comparator. The sponsor’s ANCOVA contrasts, confidence intervals, and p-values are therefore more directly relevant to the stated primary hypotheses than visual comparison of the arm means alone.

It also demonstrates the importance of uncertainty. A point estimate gives one summary of the observed contrast, but a confidence interval shows how imprecisely that contrast is estimated. Here, both primary intervals include zero and extend in both directions. Reporting the estimate together with its interval avoids treating a single number as definitive and helps distinguish a measured difference from the precision of evidence about that difference.

The amendment and analysis-population definition matter for interpretation as well. The 8 mg arm remained for some participants after its removal from enrollment, yet its effect was not assessed for the primary endpoint. The overall enrollment count therefore should not be substituted for the number contributing to each endpoint or comparison. Different endpoints also have different reported group counts.

Finally, the record demonstrates why secondary analyses and planning illustrations need clear labels. Unadjusted secondary re-calculations are not sponsor-confirmatory tests, and planning illustrations based on observed effects are not evidence of achieved power or the original sample-size rationale. Statistical interpretation depends not only on numerical estimates but also on knowing which analysis generated them, which participants were included, and what remains unreported.

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 does not report the full ANCOVA specification, including the covariates used, model assumptions, or diagnostic checks. It also does not report details of the randomization process beyond stating that the trial was randomized, or explain the basis for triple masking. These omissions limit independent assessment of the primary analysis and trial conduct.

The primary analysis population required treatment exposure and at least one valid post-baseline assessment, in addition to baseline measurement. The record does not provide the number of participants excluded from that population or the reasons for missing measurements. The missing-data method, sensitivity analyses, and handling of treatment discontinuation are not reported in the registry record. Endpoint-specific sample sizes also vary, which means the overall enrollment should not be taken as the denominator for each result.

The 8 mg arm was removed from enrollment after an amendment, but participants already assigned to that regimen remained on it. Its primary endpoint effect was not assessed, so the primary results do not provide an estimate for that dose. The placebo comparator changed to elpipodect 24 mg after Week 6; consequently, the Week 6 comparison is against placebo during the acute period, not a placebo group that remained on placebo throughout follow-up.

The registry record does not explain the 97.5% confidence level or report how multiplicity was addressed across the two primary hypotheses. It also does not report a multiplicity strategy for the numerous secondary outcomes. The body-weight comparisons discussed are unadjusted recalculations, not sponsor analyses. Finally, the available serious adverse-event summaries do not provide detailed event timing, participant-level context, or an explicit causal assessment. These limits warrant keeping conclusions close to the outcomes and analyses actually reported.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Efficacy and Safety of Elpipodect (MK-8189) in Participants With an Acute Episode of Schizophrenia (MK-8189-008) — NCT04624243.
• Registry record last updated 2026-04-29; status last verified 2026-04.
• Results first posted 2025-08-22.
• 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

NCT04624243 is a completed phase 2B randomized, double-blind, placebo- and active-controlled, parallel-group trial of elpipodect in participants experiencing an acute episode of schizophrenia. The registry lists triple masking and enrollment of 499. The primary outcome was Week 6 change from baseline in PANSS total score, with stated superiority hypotheses for elpipodect 16 mg and 24 mg versus placebo.

The sponsor reported ANCOVA comparisons for both primary hypotheses. Their 97.5% confidence intervals include zero, and the reported p-values are 0.241 for 16 mg and 0.784 for 24 mg. The registry also reports secondary outcomes and adverse-event counts, while key details of multiplicity, missing-data handling, and the full analysis model are not reported in the registry record.