The INCREASE Study - Delaying the Onset of Alzheimer's Symptomatic Expression: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The INCREASE Study - Delaying the Onset of Alzheimer's Symptomatic Expression (NCT02849639), a randomized early/phase 1 study. The primary outcome is Medication Appropriateness Index.

2. Clinical Question

The study's stated aim was to examine whether a pharmacist-physician, patient-centered medication therapy management intervention could affect cognitive reserve by addressing inappropriate medication use identified using the Beers 2015 list. The primary outcome is medication appropriateness, rather than a direct measure of dementia onset or symptomatic Alzheimer's disease. Cognitive measures and perceived health status were listed as secondary outcomes.

The registry describes a randomized, double-masked, parallel-group study with an enrollment of 90. The primary outcome results report 41 participants in the placebo arm and 44 in the MTM arm. Those outcome denominators describe the posted measure; the registry does not explain how they relate to the enrollment figure or identify the analysis population. Eligibility details, including the clinical and cognitive characteristics required for participation, are not reported in the registry record.

3. Trial Design

The INCREASE Study is identified as a randomized, double-masked, parallel-group trial and as early phase 1. The registry lists an enrollment of 90 and marks the study completed. The recorded study period began on 2017-04-04, with primary completion on 2021-04-21. The sponsor is listed as Daniela Moga.

Participants were assigned to placebo or Medication Therapy Management (MTM). The placebo description specifies educational materials without specific recommendations to change medications. The MTM description specifies educational materials and a medication assessment, with recommendations for changes when appropriate. Both arm descriptions refer to cognitive testing at the beginning and end of the study with and without a scopolamine patch, but the descriptions are truncated in the registry record. The intervention list also includes a scopolamine patch. Further details about its role, allocation, or use are not reported in the registry record.

The primary outcome timeframe is change from baseline to the end of the study, described as an average of 1 year. The registry lists three secondary outcomes: Montreal Cognitive Assessment, California Verbal Learning Test, and Perceived Health Status, each also measured as change from baseline to the end of the study, an average of 1 year. Although randomization, masking, and parallel assignment are stated, the randomization procedure, allocation concealment, masking procedures, and any deviations from the intended assignments are not reported in the registry record.

The results list 41 participants for the placebo primary outcome and 44 for MTM. The analysis population, participant flow, and reasons for any missing outcome data are not reported in the registry record. Details of the original sample-size rationale and the trial's prespecified statistical plan are also not reported in the registry record. Consequently, the planning illustrations based on observed effects should not be read as descriptions of how the study was originally designed.

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

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 Medication Appropriateness Index, measured over change from baseline to end of study, an average of 1 year.

The primary endpoint is change in the Medication Appropriateness Index (MAI) from baseline to the end of the study, an average of 1 year. The MAI evaluates medication use using ten criteria, classifying medications as appropriate, marginally appropriate, or inappropriate. The study team assigned a medication-specific MAI to each medication reported by a participant and summed those scores to obtain the participant's total MAI.

For an individual medication, the stated scale ranges from 0, meaning appropriate, to 18, meaning inappropriate for all criteria. The total score also depends on how many medications a participant takes, so the total is not a fixed-range score independent of medication count. A decrease in MAI from baseline to the end of the study indicates improved medication appropriateness according to the outcome definition.

This endpoint is relevant to the intervention's stated purpose because MTM assesses medication use and may lead to recommendations for changes. It therefore measures a medication-related target of the intervention. It does not itself measure cognitive reserve, cognitive test performance, dementia onset, or symptomatic Alzheimer's disease. Those distinctions matter when interpreting the primary result: a difference in MAI change describes medication appropriateness as operationalized by the registry, not a direct change in a clinical diagnosis or the timing of symptom onset.

7. Results Posted in the Registry

• Medication Therapy Management (MTM): mean 9.40 versus 11.20 on control; difference -1.80 (95% CI -3.46 to -0.14), standardized effect d = -0.46; z-test p = 0.034.

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.

Cognitive Reserve: Montreal Cognitive Assessment

• 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:
  • Medication Therapy Management (MTM): mean -0.31 versus -0.15 on control; difference -0.16 (95% CI -0.51 to 0.19), standardized effect d = -0.20; z-test p = 0.366.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Medication Therapy Management (MTM) and the control. The interval gives the range of effects that remain compatible with the data.

Cognitive Reserve: California Verbal Learning Test

• 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:
  • Medication Therapy Management (MTM): mean -0.08 versus -0.10 on control; difference 0.02 (95% CI -0.39 to 0.42), standardized effect d = 0.02; z-test p = 0.934.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Medication Therapy Management (MTM) and the control. The interval gives the range of effects that remain compatible with the data.

Perceived Health Status

• 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:
  • Medication Therapy Management (MTM): mean 41.20 versus 41.40 on control; difference -0.20 (95% CI -3.67 to 3.27), standardized effect d = -0.02; z-test p = 0.910.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Medication Therapy Management (MTM) and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes cover cognitive test performance on the Montreal Cognitive Assessment and California Verbal Learning Test, together with perceived health status. Their estimates do not form a consistent pattern of clear separation between the MTM and placebo arms. The secondary comparisons are imprecise, and each posted confidence interval includes zero. The registry lists no reported analyses for these outcomes.

These results add context to the primary MAI finding but measure different constructs. MAI assesses medication appropriateness, while the cognitive tests and perceived-health measure address other aspects of participants' outcomes. A primary contrast in medication appropriateness therefore does not imply a corresponding contrast in cognition or perceived health. Conversely, secondary comparisons that are uncertain do not negate the observed primary contrast; they show that the posted results do not establish a broad pattern across all measured outcomes.

Unadjusted secondary results carry less inferential weight when several outcomes are examined because the chance of observing an apparently notable result can increase across multiple comparisons. The registry record does not report whether the study prespecified a hierarchy among outcomes or used any multiplicity adjustment. The secondary findings should consequently be treated as exploratory or descriptive in the absence of a reported analysis plan, rather than as confirmatory evidence. This is a general statistical caution and does not determine how the investigators intended to interpret them.

The secondary results also cannot clarify whether missing outcome data or analytic choices affected the comparisons, because the relevant methods are not reported in the registry record. Their value is in describing the measured outcome pattern and the uncertainty around it, not in establishing that the intervention did or did not alter cognitive reserve or perceived health.

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

• Cognitive Reserve: Montreal Cognitive Assessment
• Cognitive Reserve: California Verbal Learning Test
• Perceived Health Status

9. Statistical Interpretation

10. Statistical Methods Explained

What does a least-squares mean represent?

A least-squares mean is a model-based estimate of a group average. It can account for variables included in the statistical model, unlike a simple arithmetic average. The registry identifies the reported arm values as least-squares means but does not report the model specification, any covariates, or how missing observations were handled. It is therefore not possible to determine from the registry record which adjustments, if any, distinguish these values from unadjusted group means.

How should the mean difference be read?

The posted comparison is MTM versus placebo. For the primary outcome, the mean difference is -1.8, based on the reported arm values of 9.4 for MTM and 11.2 for placebo. A negative contrast means the MTM value is lower than the placebo value on this reported change measure. Because the endpoint description says that a decrease in MAI indicates improved medication appropriateness, the direction is consistent with a lower MAI change in the MTM arm. This direction alone does not establish clinical importance or a benefit for outcomes that were not measured by MAI.

The comparisons are described as unadjusted recalculations from the posted summary statistics. They are not a substitute for a full trial analysis using individual participant data and the intended statistical model. The registry record does not report such a model or a sponsor-reported comparison. In particular, the posted summaries do not establish whether baseline values, stratification factors, or other variables were incorporated in an original analysis.

What does the standard error tell a reader?

The arm values are accompanied by standard errors. A standard error describes the statistical uncertainty in an estimated mean; it is not the spread of individual participants' outcomes. Smaller standard errors generally indicate more precise estimates of the group mean, while larger ones indicate greater uncertainty. Standard errors can be used in statistical procedures to construct confidence intervals, but their interpretation depends on the estimator and analysis model. Because the model details are not reported, the registry's standard errors should be read as the reported precision measures rather than as a complete description of the data distribution.

For continuous outcomes, variability among individual observations and uncertainty in an estimated mean are different concepts. Participants can vary substantially even when a group mean is estimated with some precision, and a standard error alone does not show the shape of the outcome distribution. The registry does not report individual-level distributions or diagnostics that would allow assessment of those features.

What is the role of a confidence interval?

A confidence interval gives a range of values compatible with an estimate under the statistical procedure used. It communicates uncertainty more fully than a point estimate alone. For the primary comparison, the interval is entirely negative, so zero is outside that interval. This indicates that the recalculated unadjusted interval supports a negative contrast under its assumptions. It does not mean that every plausible effect has the same magnitude, nor does it settle whether the range is important in practice. For the secondary comparisons, the reported intervals include zero, indicating that those estimates are less conclusive about the direction of a difference.

How should the p-values be understood?

A p-value describes how unusual the observed result, or a more extreme result, would be under a specified null model. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical value of an effect. The primary unadjusted recalculated comparison has p = 0.034. The secondary p-values are 0.366 for Montreal Cognitive Assessment, 0.934 for California Verbal Learning Test, and 0.91 for Perceived Health Status. Those values are not adjusted for the number of outcomes in the posted record. They should be interpreted alongside effect estimates and confidence intervals, rather than as standalone verdicts.

The study's original significance threshold, if any, and the procedures for multiplicity adjustment are not reported in the registry record. The planning illustration separately specifies a two-sided significance level of 0.05; that planning assumption is not evidence that the trial itself used the same threshold or analysis plan.

Why can over-dispersion matter?

General statistical explanation: over-dispersion occurs when observed variation is greater than a statistical model expects. When that happens, a model that understates variation can produce standard errors that are too small and confidence intervals that are too narrow. The MAI total depends on the number of medications taken, and the registry describes medication-specific scores summed to a participant-level total. However, the record does not report a distributional assessment, a model for the total score, or an over-dispersion evaluation. It is therefore not possible to say whether over-dispersion affected these results.

The comparisons include approximate standard deviations calculated from the posted standard errors, as indicated by the recalculation details. These are not separately reported observed standard deviations. Such approximations support planning illustrations but should not be confused with direct information about participant-level variability.

What cannot be established from the posted analysis?

The registry lists zero reported analyses for the primary outcome and no reported analyses for the secondary outcomes. It gives group estimates and recalculated contrasts, but does not report an analysis population, a missing-data method, a covariate-adjustment plan, an intention-to-treat statement, interim analyses, or a multiplicity strategy. These omissions prevent a full reconstruction of the intended inferential process. The registry record also does not report whether the listed estimates account for repeated measurements, departures from random assignment, or other features of the trial conduct.

Accordingly, the mean differences, confidence intervals, and p-values are useful descriptive and unadjusted statistical summaries of the posted results. Their interpretation should remain distinct from claims about the original protocol analysis, which is not reported in the registry record.

11. Confidence Intervals and Precision

Precision concerns how narrowly the data locate an estimated difference. The primary MAI contrast is -1.8, and the unadjusted recalculated confidence interval lies wholly below zero. Its endpoints span a range of negative differences, rather than pinpointing a single exact value. Thus, the result has a direction in this comparison, but uncertainty remains about the magnitude. The interval's exclusion of zero is a feature of this unadjusted estimate and does not address multiplicity or establish clinical importance.

The reported standard errors for the primary arm means are 0.6 in each arm. These quantify uncertainty in the estimated means, not the spread of participant-level MAI scores. The registry does not report the individual-level distribution, the analysis model, or whether the standard errors reflect any covariate adjustment. Interpretation of their precision is consequently limited to the statistical summaries as posted.

For the secondary comparisons, the confidence intervals include zero. This means the posted estimates do not precisely distinguish a difference from no difference under the unadjusted procedures used for the recalculations. An interval that includes zero is not proof of no effect; it indicates that the data and calculation leave uncertainty about the direction and size of the contrast. The secondary results are especially difficult to interpret as definitive evidence because the record reports no analyses for them and does not describe adjustments for multiple outcomes.

Confidence intervals describe uncertainty under the assumptions of the calculation. They do not account automatically for unreported design features, missing-data choices, multiplicity, or model misspecification. More complete statistical precision would require details of the prespecified analysis and the participant-level data or a fuller sponsor analysis. Neither is reported in the registry record. The estimates therefore support cautious statements about the direction and uncertainty of the posted contrasts, rather than exact conclusions about the underlying effects.

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 for 80% power and participants per arm for 90% power; they are not total participant counts or observed trial results. The planning illustration assumes a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It uses the observed effect as a starting point and considers detecting 100%, 75%, or 50% of that observed effect. These are planning assumptions for the illustration, not the original trial's design assumptions, which are not reported in the registry record.

For the primary MAI outcome, planning for 100% of the observed effect gives 75 participants per arm for 80% power and 100 participants per arm for 90% power. Planning for 75% of the observed effect gives 132 participants per arm for 80% power and 177 participants per arm for 90% power. Planning for 50% of the observed effect gives 297 participants per arm for 80% power and 398 participants per arm for 90% power. The smaller the effect a study is designed to detect, the more participants are generally needed, all else held constant. The higher power target also requires more participants in these illustrations.

Power is the probability, under specified assumptions and a particular true effect, that a planned test will detect an effect by meeting its statistical criterion. The 80% and 90% columns represent different planning targets, not guarantees about a future result. These calculations are not observed power: they do not measure how likely the completed trial was to find its result after the data were collected. The original sample-size justification, including its target effect and other design assumptions, is not reported in the registry record.

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 = -1.800; pooled standard deviation σ = 3.914.
2. n = 2 × (1.96 + 0.842)² × 3.914² / -1.800² = 74.2, rounded up to 75 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 <- -1.8                      # observed difference in means
sigma <- 3.91401559428283                     # 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(2849639)
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 = 75 (80% power), 100 (90% power)
 75% of observed effect: n per arm = 132 (80% power), 177 (90% power)
 50% of observed effect: n per arm = 297 (80% power), 398 (90% power)
power.t.test: 75.2 
Simulated power at n = 75 per arm: 0.797 (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. Multiplicity, Missing Data and Analysis Populations

The registry record lists three secondary outcomes in addition to the primary MAI endpoint. It does not report a multiplicity strategy, such as a procedure to control the chance of false-positive conclusions across several outcomes, nor does it report a hierarchy or gatekeeping plan. The posted p-values are unadjusted recalculations. Without the prespecified analysis plan, it is not possible to determine how the investigators intended to interpret multiple outcome tests or whether any adjustment was conducted outside the registry record.

The record lists zero reported analyses for the primary outcome and no reported analyses for the secondary outcomes. The summaries include group estimates and comparisons, but do not identify whether the analysis was intention-to-treat, per-protocol, or based on another analysis population. The registry record does not report participant flow by arm, the number with missing outcomes, reasons for missingness, or methods used to handle missing data. The reported outcome denominators should therefore not be assumed to represent all randomized participants or a particular prespecified population.

Likewise, the registry does not report whether analyses adjusted for baseline values or other factors, how protocol deviations were handled, or whether repeated measurements were modeled. Interim analyses and any associated stopping rules are not reported in the registry record. These omissions are not evidence that such methods were absent; they mean the registry record does not document them.

These uncertainties affect how confidently the posted comparisons can be linked to a planned confirmatory analysis. A complete interpretation would require the analysis plan and additional details on outcome availability, populations, and model choices. In their absence, the recalculated comparisons should be understood as unadjusted summaries based on the posted arm statistics, with no assumption that unreported methods were or were not used.

15. 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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: infections (8.7%), major cardiac event (4.5%), gi emergencies (4.5%), injurious fall (2.3%), stroke (2.3%).

The registry reports serious adverse events among 44 participants at risk in the placebo group and 46 in the MTM group. Serious adverse events affected 9 participants in the placebo group and 7 in the MTM group. Other adverse events were reported among 42 participants at risk in the placebo group and 41 in the MTM group. The record lists 2 deaths in the placebo group and 0 in the MTM group.

The serious-event terms listed include Infections at 8.7%, Major cardiac event at 4.5%, GI emergencies at 4.5%, Injurious fall at 2.3%, Stroke at 2.3%, and Cancer at 2.3%. The registry does not clarify the denominator or whether participants could contribute to more than one term, so these percentages should be read as reported, not converted into counts or summed.

These figures are descriptive safety summaries. The safety denominators differ from the primary outcome denominators, and the record does not report a statistical comparison of adverse events or establish attribution to the intervention. The counts alone do not support causal conclusions about group differences.

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

The primary posted comparison describes a lower MAI change value in the MTM arm than in the placebo arm. Because the MAI definition treats a decrease as improved medication appropriateness, the direction of the estimate is consistent with a lower MAI change for MTM. The unadjusted recalculated confidence interval lies below zero, while its range still leaves uncertainty about the magnitude of the contrast.

This finding concerns the medication-appropriateness outcome measured over the stated average 1-year timeframe. It does not directly show a change in cognitive reserve, cognitive test performance, dementia onset, symptomatic Alzheimer's disease, or healthcare costs. Those broader goals appear in the study rationale, but the primary endpoint is MAI and the registry does not report a direct measure of delaying symptom onset.

The secondary outcomes do not establish a consistent pattern of differences across cognition and perceived health. Their comparisons are unadjusted, their intervals include zero, and the registry does not report analyses or a multiplicity plan for them. This uncertainty should not be recast as proof of no effect, just as the primary estimate should not be extended to outcomes it does not measure.

The registry record does not report the original sample-size justification, a complete statistical plan, analysis populations, or missing-data methods. Those gaps limit the ability to assess whether the posted comparisons correspond to the intended trial analysis and how robust they are to analytic choices. The available results are thus most appropriately read as summaries of the posted outcomes, not as a complete causal or clinical assessment.

No medical conclusion follows from these statistics alone. The data describe an unadjusted contrast in a medication-appropriateness measure and uncertain secondary comparisons. They do not establish that the intervention delays Alzheimer's symptoms or determine what action any individual should take.

17. Why This Trial Matters Statistically

Statistically, the study brings together an intervention aimed at medication use and an outcome that quantifies medication appropriateness. That alignment makes the MAI an interpretable endpoint for the intervention's immediate target. The registry's definition also makes a lower change meaningful in a specific direction: decreases indicate improved medication appropriateness. This helps readers distinguish the numerical sign of the contrast from its outcome-specific meaning.

The study also illustrates why a point estimate, uncertainty interval, and analysis context should be considered together. The primary contrast is negative and its unadjusted interval excludes zero, but the interval does not identify a uniquely precise magnitude. The record does not provide the original statistical plan or a reported sponsor analysis, so the recalculated result should not be mistaken for a fully documented confirmatory analysis.

A further statistical issue is the gap between the primary endpoint and the broader study motivation. Medication appropriateness may be relevant to the intervention's stated cognitive-reserve rationale, but it is not a direct measure of cognitive reserve or delayed symptom onset. The secondary cognitive outcomes are therefore important context, yet their estimates are uncertain and the registry does not report a multiplicity approach. The distinction between an intervention's intended pathway and the outcomes actually measured is essential to avoid overinterpreting a result.

Finally, the registry reports planning illustrations based on observed effects, while the original sample-size rationale is not reported. This makes it possible to discuss how assumptions about detectable effect size relate to required participants, but not to reconstruct the trial's original design choices. Together, these features make the study a useful example of how endpoint choice, uncertainty, multiplicity, and incomplete analysis reporting shape interpretation.

18. 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 leaves important trial-specific details unreported. Eligibility criteria, baseline participant characteristics, randomization procedures, allocation concealment, and the practical implementation of masking are not described. The arm descriptions are truncated, including the text about cognitive testing with and without a scopolamine patch. Although the patch is listed as an intervention, its role in the study cannot be reconstructed fully from the record.

The primary endpoint is an MAI total that depends on the number of medications taken, as well as the medication-specific scores. The registry does not report how medication counts varied, whether the measurement properties or scoring were assessed in this population, or how baseline medication burden was handled in the analysis. The reported least-squares means and standard errors are not accompanied by a model specification.

The outcome denominators are 41 for placebo and 44 for MTM, while enrollment is listed as 90. Safety denominators are different again. The registry does not report participant flow, missingness, reasons for incomplete outcome data, or the populations used for each analysis. These figures should not be used to infer attrition or explain why denominators differ.

Other limitations include the absence of reported sponsor analyses, analysis plans, multiplicity methods, interim-analysis details, and the original sample-size justification. The recalculated comparisons are based on summary statistics and do not reproduce a documented individual-level model. The listed outcomes and timeframe also do not directly establish longer-term dementia outcomes or symptom onset. These limitations restrict interpretation to the outcomes and summaries recorded, without implying that unreported procedures were necessarily absent.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: The INCREASE Study - Delaying the Onset of Alzheimer's Symptomatic Expression — NCT02849639.
• Registry record last updated 2023-07-19; status last verified 2023-06.
• Results first posted 2022-08-22.
• 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.

22. Record Summary

The INCREASE Study (NCT02849639) is recorded as a completed, randomized, double-masked, parallel-group, early phase 1 study with enrollment of 90. It compared Medication Therapy Management with placebo in a study concerning cognitive reserve and Alzheimer's symptomatic expression.

The primary outcome was change in the Medication Appropriateness Index from baseline to the end of the study, an average of 1 year. The posted least-squares means were 11.2 for placebo and 9.4 for MTM, with a recalculated unadjusted mean difference of -1.8 and p = 0.034. Secondary outcomes were Montreal Cognitive Assessment, California Verbal Learning Test, and Perceived Health Status; their unadjusted comparisons were uncertain.

The registry record does not report the original sample-size justification, a full statistical plan, analysis populations, or missing-data methods. The results describe medication appropriateness and other posted outcomes; they do not directly establish delayed Alzheimer's symptom onset.