A Study of MP-101 in Dementia-Related Psychosis and/or Agitation and Aggression: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of MP-101 in Dementia-Related Psychosis and/or Agitation and Aggression (NCT03044249), a randomized phase 2 study. The primary outcome is Percentage of Participants With 30% Improvement From Baseline in the Neuropsychiatric Inventory (NPI) - Psychosis Subscale or Aggression/Agitation Subscale Score.

2. Clinical Question

This is a question about a defined behavioral-response threshold, not about every aspect of dementia-related symptoms or functioning. The registry describes a ten-week study assessing tolerability, pharmacokinetics, and efficacy. The posted primary result concerns only the specified Week 10 NPI response measure.

3. Trial Design

The registry identifies this as a phase 2, randomized, triple-masked, parallel-group study comparing MP-101 with placebo. Its brief description calls it a ten-week study. Enrollment was 81. The recorded status is terminated, and the primary completion date is 2020-01-30. The registry lists the study start as 2017-05-04 and identifies Mediti Pharma Inc. as the sponsor.

Participants assigned to MP-101 received an oral once-daily dose that escalated over the first part of treatment: 20 mg at Week 0, 40 mg at Week 1, and 60 mg from Week 2 through Week 9. Participants assigned to placebo received three capsules once daily across the same described weeks. The registry record does not report the reason for termination, so the termination status alone does not establish why the study ended or what consequences it had for the results.

The primary endpoint analysis population was narrower than the enrollment total. It was defined as randomized participants who received at least one dose, completed at least Week 4 with NPI scores, and were not withdrawn due to early termination of the study. The posted primary result includes 33 participants in the placebo group and 26 in the MP-101 group. For the posted NPI Total Score secondary result, the group sizes are 34 and 26; for the Core Total Score they are also 34 and 26. These different analysis counts reflect the denominators reported for each outcome, not the full enrolled population.

The record does not report the original sample-size justification, the planned allocation ratio, detailed randomization procedures, or the reason for termination. Those details should not be inferred from the enrollment or analysis counts.

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 who completed at least Week 4 with NPI scores but were not withdrawn due to early termination of the study.

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 who received at least one dose of study drug.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants With 30% Improvement From Baseline in the Neuropsychiatric Inventory (NPI) - Psychosis Subscale or Aggression/Agitation Subscale Score, measured over Week 10.

The primary endpoint is the percentage of participants with at least a 30% improvement from baseline in the NPI Psychosis subscale or the NPI Aggression/Agitation subscale at Week 10. Which subscale applies depends on the participant’s diagnosis: psychosis for participants with a psychosis diagnosis, or aggression/agitation for participants with an agitation/aggression diagnosis.

The NPI is described in the registry as a questionnaire for quantifying behavioral changes in dementia. Its domains include ratings of frequency and severity, a total score formed from frequency and severity, and caregiver distress. For the endpoint definition, improvement is assessed against baseline on the relevant subscale rather than by combining every NPI domain into a single response criterion.

A threshold-based endpoint turns a change score into a responder classification: each participant either meets or does not meet the stated improvement threshold. The resulting group percentage is straightforward to interpret as the fraction meeting that definition, but it does not preserve the full range of individual changes. Participants just short of the threshold and those with no change may both count as nonresponders, while the endpoint does not describe how far responders improved beyond the threshold.

The registry also describes a core total score combining delusions, hallucinations, and aggression/agitation domain scores, with lower scores indicating less severity. That score is distinct from the primary responder definition. The primary outcome asks about the percentage meeting the subscale-specific threshold at Week 10.

7. Results Posted in the Registry

• MP-101: 61.5% (16/26) versus 57.6% (19/33) on control; risk difference 4.0 percentage points (95% CI -21.2 to 29.1), risk ratio 1.07 (0.70–1.63); unadjusted two-proportion z-test p = 0.758.

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 NPI Total Score

• 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:
  • MP-101: mean -8.70 versus -3.43 on control; difference -5.27 (95% CI -12.21 to 1.67), standardized effect d = -0.39; z-test p = 0.137.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between MP-101 and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in NPI Core Total Score

• 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:
  • MP-101: mean -5.05 versus -3.46 on control; difference -1.59 (95% CI -5.01 to 1.83), standardized effect d = -0.24; z-test p = 0.362.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between MP-101 and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in NPI Domains - Anxiety

• 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 deviations.
• Result:
  • MP-101: mean -0.60 versus -0.10 on control; difference -0.50 (95% CI -2.11 to 1.11), standardized effect d = -0.16; z-test p = 0.544.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between MP-101 and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists eight secondary outcomes, including global improvement, NPI scores and domains, caregiver distress, adverse events, motor assessment, and pharmacokinetic measures. Numerical comparisons are posted for three secondary measures: NPI Total Score, NPI Core Total Score, and the NPI Anxiety domain. The remaining listed secondary outcomes do not have numerical comparisons in the results represented in these analyses.

Across the three measures with numerical comparisons, the point estimates generally indicate larger reductions in the MP-101 group than in the placebo group. However, each unadjusted interval includes zero, and the corresponding unadjusted p-values do not establish a clear group difference. These secondary outcomes provide related context about symptom-score changes, but they are not the same as the primary threshold-based responder endpoint. They therefore cannot be used to replace or resolve the primary result.

In general, multiple outcome testing increases the chance that at least one result may look unusual by chance when many comparisons are considered. Without a reported multiplicity strategy, isolated secondary findings would warrant particular caution. Here, the posted secondary comparisons are themselves uncertain, and they should be interpreted alongside the primary result rather than as independent confirmation.

The secondary analyses also have outcome-specific denominators and measurement definitions. A score change, a responder percentage, a caregiver-distress count, and an adverse-event measure answer different questions. The registry record does not report enough information to combine them into a single overall measure of benefit or to determine how missing secondary outcome results were handled across the complete set of listed outcomes.

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

• Percentage of Participants With Improvement From Baseline in the Clinical Global Impression of Improvement (CGI-I) at Week 10
• Change From Baseline in NPI Total Score
• Change From Baseline in NPI Core Total Score
• Number of Participants With NPI Caregiver Distress
• Change From Baseline in NPI Domains - Anxiety
• Number of Participants With Any Treatment Emergent Adverse Event
• Change From Baseline in the Unified Parkinson's Disease Rating Scale (UPDRS) Part III
• Population Pharmacokinetics (PK): Plasma Levels of MP-101 and Metabolite

9. Statistical Interpretation

10. Statistical Methods Explained

What does a risk difference represent?

For a binary endpoint, each participant is classified according to whether the defined event occurred. Here, that event is meeting the NPI improvement threshold. A risk difference compares the event proportions in two groups by subtracting one group’s proportion from the other. A value at zero represents equal proportions; values on opposite sides of zero indicate opposite directions of group difference. The recalculated risk difference is 0.040, with an interval from -0.212 to 0.291. Because the interval spans zero, the posted summary statistics are compatible with no difference as well as with differences in either direction.

What do the confidence interval and p-value say?

In general, a confidence interval expresses uncertainty around an estimate under the assumptions of the analysis. It helps distinguish a tightly estimated result from one that remains compatible with a broad range of values. A p-value measures how unusual data at least as inconsistent with a specified no-difference model would be, if that model and the analysis assumptions were true. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of an effect. The recalculated unadjusted p-value is 0.758; the reported Fisher Exact analysis gives p = 0.48. Neither should be interpreted alone without considering the estimate, interval, endpoint definition, and analysis population.

Why are there two estimates?

The recalculated primary comparison is a simple unadjusted comparison derived from the posted arm summaries. The registry’s reported analysis names Fisher Exact and reports a Response Ratio value of 4, with a 90% interval from -18 to 25. The recalculation and the reported analysis need not match exactly because they use different stated analysis approaches and the sponsor’s result is the analysis recorded in the registry. The record does not give enough detail to reconstruct all analytical choices behind the reported result. The reported p-value and interval should therefore be presented as recorded, not reverse-engineered from the recalculation.

What do the secondary mean differences represent?

For the NPI Total Score, Core Total Score, and Anxiety domain, the posted group summaries are mean changes from baseline. A mean difference compares the average change in the MP-101 group with the average change in the placebo group. Negative changes indicate improvement for the NPI measures as described in the record; interpretation of the contrast depends on the outcome’s direction. The recalculated mean differences and intervals are unadjusted. In general, a mean difference summarizes the average contrast, but it does not show the distribution of individual responses or whether changes were similar across participants.

The NPI Total Score and Core Total Score summaries report standard errors alongside the group means. A standard error describes uncertainty in an estimated mean, not the spread of participant scores themselves. The Anxiety domain summary instead reports standard deviations, which describe variability among observations. These are different quantities and should not be treated as interchangeable measures of dispersion.

Why does over-dispersion matter in general?

For count outcomes, over-dispersion means that observed variability exceeds what a simple count model assumes. If it is ignored, standard errors can be too small and intervals too narrow. This is a general statistical consideration; the primary endpoint is binary, and the posted secondary results are mean changes rather than count outcomes. The registry record does not report an over-dispersion assessment or a count-model analysis for the primary endpoint.

What should be inferred from the p-values?

The listed p-values are not proof that an effect exists or is absent. A large p-value can reflect a small effect, limited information, or both. In this study, the primary analysis population is considerably smaller than the enrollment total, and the primary interval is broad. The data therefore leave substantial uncertainty about the size and direction of the group difference. Statistical significance is not a measure of importance, and failure to reach a conventional threshold would not demonstrate equivalence.

The registry record does not report a full statistical analysis plan, a multiplicity adjustment strategy, interim analyses, or the original sample-size justification. Without those details, it is not possible to determine from the record whether the reported analyses were prespecified in their posted form, how all outcome comparisons were handled, or whether any interim decisions affected the final analysis. Those omissions limit how far the analyses can be interpreted beyond the results as posted.

11. Confidence Intervals and Precision

The primary risk-difference interval extends from -0.212 to 0.291 around an estimate of 0.040. Its width signals substantial uncertainty: values below zero and values above zero remain compatible with the recalculated comparison. The interval does not narrow the result to a single direction or a small range of plausible effects. The registry record does not specify the confidence level for this recalculated interval, so it should not be assigned a confidence percentage that is not recorded.

The sponsor’s reported primary result is a Response Ratio value of 4, with a 90% confidence interval from -18 to 25. That interval also spans no difference. It is the reported analysis, while the risk-difference interval is a separate unadjusted recalculation from the posted group summaries; the estimates and intervals are not interchangeable.

In general, a confidence interval gives a range of estimates reasonably compatible with the data and the model used to calculate it. A wide interval indicates limited precision, often because the available information is limited or variable. A narrow interval would indicate greater precision, but precision alone would not show that an effect is important. Here, the primary interval is broad enough to leave meaningful uncertainty in both directions.

The secondary mean-difference intervals also include zero: -12.21 to 1.674 for NPI Total Score, -5.007 to 1.827 for NPI Core Total Score, and -2.115 to 1.115 for NPI Anxiety. These intervals indicate that the posted data do not precisely establish a difference for those comparisons either. Their interpretation is constrained by the different endpoint definitions, analysis counts, and unadjusted nature of the recalculations.

The primary endpoint’s group counts are 33 and 26, whereas the overall enrollment was 81. The endpoint-specific analysis criteria and smaller denominators limit the information available for estimating the response difference. The results are best read as uncertain estimates rather than precise measurements of a stable treatment contrast.

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 figures are participants per arm, not total participants or total events. The sample-size assumptions recorded for these illustrations are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is the stated fraction of the observed effect. For time-to-event outcomes, the display would give total events, but that convention does not apply to these outcomes.

The 80% power column describes the planned number of participants per arm for a design that would have an 80% chance of detecting the specified effect under the stated assumptions, if that effect and those assumptions were true. The 90% power column uses a higher target probability of detection and consequently requires more participants per arm. These are planning illustrations calculated from observed effects, not the original trial’s design requirements.

Each line uses a different fraction of the observed effect: 100%, 75%, or 50%. A smaller effect is harder to distinguish from random variation, so more participants are needed to reach the same target power. The resulting values are particularly sensitive to the observed effect estimates, which can be unstable in a small study. The registry record does not report the trial’s own original sample-size justification or design assumptions.

These planning calculations are not observed power. They do not tell how much power the completed trial actually had after its results were known, and they do not establish that a result is true or clinically meaningful. Their role is to illustrate how sample-size requirements change under specified assumptions.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.576; treatment proportion p₁ = 0.615; average p̄ = 0.596.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6941 = 1.3604.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6935 = 0.5837.
4. n = (1.3604 + 0.5837)² / (0.0396)² = 2,406.7, rounded up to 2,407 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
p0 <- 0.575757575757576                          # control proportion
p1 <- 0.615384615384615                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(3044249)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 2,407 (80% power), 3,222 (90% power)
 75% of observed effect: n per arm = 4,296 (80% power), 5,751 (90% power)
 50% of observed effect: n per arm = 9,703 (80% power), 12,988 (90% power)
power.prop.test: 2406.7 
Simulated power at n = 2,407 per arm: 0.804 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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’s reported primary analysis uses Fisher Exact and gives a Response Ratio value of 4, a 90% confidence interval from -18 to 25, and p = 0.48. The unadjusted recalculation from the posted group summaries gives a risk difference of 0.040, an interval from -0.212 to 0.291, and p = 0.758. These are not identical estimates or inferential results. The record does not identify a discrepancy between them, and the reported sponsor analysis should be read as the registry’s own analysis rather than treated as a recalculation.

Differences between the posted results and a simple recalculation can arise because the estimands, statistical methods, analysis populations, or rounding differ. The registry records the reported method and numbers but does not provide enough detail to reproduce every step. In particular, the interval for the recalculation has no confidence level stated in the record, while the sponsor’s interval is explicitly 90%.

Both presentations leave the primary comparison uncertain: each reported interval spans no difference, and neither result establishes a clear separation between groups. The recalculation is useful as a transparent, unadjusted check based on arm summaries; it is not a substitute for the sponsor’s stated analysis. The registry record does not report additional detail that would explain the numerical distinction more fully.

15. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary endpoint and multiple secondary outcomes, but the registry record does not report a multiplicity adjustment strategy. In general, when several hypotheses are tested, the chance of at least one apparently unusual result can increase. Adjustment methods can control that issue, but they may also change the precision or threshold used for interpretation. With no strategy reported, the secondary p-values should be regarded as unadjusted and exploratory in their evidential weight; the record does not establish whether any other adjustment was used.

The record also does not report a complete statistical analysis plan, interim analyses, or the original sample-size justification. It is therefore not possible to determine from the registry record whether outcome definitions, analysis populations, or statistical procedures were finalized before results were examined, or whether interim monitoring was part of the study. No particular protocol or plan should be inferred from the design labels or posted results.

Missing-data handling is not described in sufficient detail to assess how unavailable observations were treated. The primary endpoint population is defined by receipt of at least one dose, completion of at least Week 4 with NPI scores, and not being withdrawn due to early termination. This definition excludes some randomized participants from the primary analysis, but the record does not report reasons for every exclusion, missingness patterns, or sensitivity analyses assessing the effect of missing outcomes.

The enrollment total and outcome-specific denominators are not the same. That difference is important when judging precision and possible selection effects, but it does not by itself show why data are absent or whether their absence biased the comparison. The registry record does not report enough detail to determine whether the analyzed participants remained comparable after exclusions. These limitations mean the posted estimates should be interpreted as applying to the stated analysis populations, not automatically to every randomized or enrolled participant.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: pneumonia (4.8%), fall (2.6%), hip fracture (2.6%), dementia (2.6%), unresponsive to stimuli (2.6%).

The registry reports serious adverse events among 42 participants at risk in the placebo group and 39 at risk in the MP-101 group. Four participants in each group were reported as affected by a serious adverse event. The record also reports zero deaths in the placebo group and one in the MP-101 group. These are counts and at-risk denominators, not estimates adjusted for duration of exposure or differences in participant characteristics.

For other adverse events, the registry reports 12 affected participants among 42 at risk in the placebo group and 22 among 39 at risk in the MP-101 group. These figures are descriptive. They do not, on their own, establish a treatment-related cause or quantify comparative risk with uncertainty. The registry lists pneumonia at 4.8% among the top serious-event terms, alongside other listed terms, but the record does not provide enough detail in this summary to attribute an event to a particular treatment or explain individual event courses.

Adverse-event counts can be affected by the number of participants observed, duration of exposure, event definitions, and reporting procedures. The record does not provide a detailed safety analysis or comparative uncertainty estimates in the registry record. The counts should therefore be read as what was recorded in the study, not as proof of causation or a complete assessment of safety.

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

The primary result describes the percentage meeting a specific NPI improvement threshold at Week 10 among the defined analysis population. The posted arm percentages are 58.0 for placebo and 62.0 for MP-101. The unadjusted estimate points toward a higher response percentage in the MP-101 group, but its interval includes values on both sides of no difference. The sponsor’s reported interval also includes no difference. The posted results therefore leave substantial uncertainty about the size and direction of the comparison.

This does not establish equivalence. Demonstrating equivalence or non-inferiority requires a prespecified margin and an analysis designed to assess that question; such a margin is not reported in the registry record. Nor does an uncertain result prove that there is no effect. It means the posted data, under the analyses recorded, do not precisely determine the contrast.

The primary endpoint is a threshold-based response on one diagnosis-relevant NPI subscale. It does not measure every behavioral symptom, overall dementia progression, daily function, caregiver experience, or long-term outcome. The registry describes a ten-week study, and the primary endpoint is assessed at Week 10. Results at that time point should not be generalized to unreported durations or outcomes.

The secondary score changes and adverse-event counts provide additional descriptive information but do not erase the limitations of the primary comparison. Multiple outcomes, differing analysis counts, and unreported missing-data and multiplicity procedures further constrain interpretation. The results concern the specific study groups and analysis populations recorded, not all people with dementia-related psychosis or agitation and aggression.

No medical recommendation follows from these statistics. They describe the estimates, uncertainty, and recorded event counts in this terminated study. The registry record does not report the reason for termination, detailed protocol decisions, or the full statistical plan, so those matters cannot be used to explain the pattern of results.

18. Why This Trial Matters Statistically

This trial illustrates why a point estimate alone is not enough to interpret a clinical comparison. The primary estimate points in one direction, but the interval remains compatible with a range that includes no difference and values in the opposite direction. Precision, analysis population, and endpoint definition all matter alongside the observed percentages.

It also demonstrates the distinction between enrollment and endpoint-specific analysis. The enrollment total is 81, while fewer participants contribute to the posted primary endpoint comparison under the stated analysis criteria. Denominators determine how much information supports an estimate, and exclusion or unavailable outcome data can affect both precision and interpretation.

The study is also a useful example of keeping sponsor-reported results separate from a simple unadjusted recalculation. The registry records a Fisher Exact analysis and a distinct result based on the posted arm summaries can be recalculated. Neither should be presented as if it were the other. Clear labeling helps readers see which result is the sponsor’s reported analysis and which is a supplementary statistical check.

Finally, the registry lists multiple secondary outcomes, but not every listed outcome has numerical results represented in the posted comparisons. Multiple outcomes complicate interpretation, especially when the multiplicity approach and analysis plan are not reported. Statistical reading therefore requires attention not only to observed values, but also to what was analyzed, what remains uncertain, and what the registry record does not document.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The trial is recorded as terminated, but the registry record does not report the reason. That missing context limits interpretation of whether the termination affected recruitment, follow-up, outcome availability, or the timing of analysis; none of those explanations can be assumed. The record identifies enrollment of 81, while the primary analysis includes smaller group denominators under its stated completion and treatment criteria.

The registry record does not report the original sample-size justification, so it is not possible to assess the planned precision or power target for the trial from the registry entries. The planning illustrations based on observed effects are not substitutes for that design information. The record also does not report the full statistical analysis plan, interim analyses, a multiplicity strategy, or detailed missing-data methods.

The primary measure is a responder threshold based on different NPI subscales according to diagnosis. That makes the outcome clinically specific to the endpoint definition, but it does not convey the full distribution of changes or how close nonresponders were to the threshold. The posted primary analysis population also excludes participants who did not meet its stated criteria, and the reasons and consequences of missing endpoint data are not fully described.

The registry lists eight secondary outcomes, but numerical analyses represented in the posted comparisons cover only three secondary measures. This limits the breadth of conclusions that can be drawn from secondary results. The analyzed secondary outcomes have varying denominators and measurement scales, and the record does not report an approach for accounting for the multiplicity of outcomes.

Finally, the efficacy comparison is based on limited endpoint-specific counts and broad uncertainty. The safety counts are descriptive and do not include comparative uncertainty estimates in the record. These limitations favor cautious interpretation of the results as recorded rather than broad conclusions about efficacy or safety.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study of MP-101 in Dementia-Related Psychosis and/or Agitation and Aggression — NCT03044249.
• Registry record last updated 2021-04-01; status last verified 2021-03.
• Results first posted 2021-04-01.
• 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

The registry describes a phase 2, randomized, triple-masked, parallel-group study of MP-101 versus placebo in dementia-related psychosis and/or agitation and aggression. The brief description calls it a ten-week study, enrollment was 81, and the recorded status is terminated.

The primary endpoint was the percentage with at least a 30% improvement from baseline in the relevant NPI psychosis or aggression/agitation subscale at Week 10. The posted percentages were 58.0 for placebo and 62.0 for MP-101. The recalculated interval spans no difference, as does the sponsor-reported 90% interval. The registry also includes selected secondary score changes and descriptive adverse-event counts.

The record does not report the termination reason, original sample-size justification, full statistical analysis plan, multiplicity strategy, or detailed missing-data procedures. The posted estimates therefore require cautious interpretation, with attention to their uncertainty and outcome-specific analysis populations.