Improving Adherence to Post PCI Antiplatelet Therapy in Minority Populations: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Improving Adherence to Post PCI Antiplatelet Therapy in Minority Populations (NCT01651208), a randomized na study. The primary outcome is Number of Participants With Appropriate Adherence/ Medication Possession Ratio (MPR).

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group trial listed as completed. The registry reports enrollment of 452 participants and identifies the study as not applicable for phase. The recorded start was 2010-01, and primary completion was 2011-11. The sponsor was the University of Miami.

Participants were assigned to phone-based motivational interviewing (MINT) or a mailed educational DVD. The primary outcome comparison includes 227 participants in the MINT arm and 225 in the DVD arm. The registry describes MINT as telephone encounters with a nurse trained in motivational interviewing. Its wording mentions 4 to 7 encounters and also says participants would be contacted every 3 months to complete 4 encounters. The DVD was intended to reinforce adherence behavior and address questions and concerns after stent placement.

The design is recorded as randomized, unmasked, and parallel. The specific randomization procedure, allocation concealment, and any steps taken to limit bias in outcome assessment are not reported in the registry record. The record also does not state whether participants, clinicians, or outcome assessors were masked beyond listing masking as none.

The primary outcome was measured 12 months after stent placement. The registry lists a 4-Item Morisky Medication Adherence Scale as a secondary outcome at 12 months. Further details about the follow-up process, participant flow, adherence to the intervention, and the populations included in each analysis are not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

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 Number of Participants With Appropriate Adherence/ Medication Possession Ratio (MPR), measured over 12 months after receiving coronary stent.

The primary endpoint is the number of participants classified as having appropriate adherence to antiplatelet medication 12 months after receiving a coronary stent. The registry defines the classification using the medication possession ratio (MPR), a measure of medication availability across multiple intervals. MPR is calculated from days’ supply of medication relative to the period from the first fill through the last refill, including the days’ supply of the last refill. The registry’s stated cutpoint for appropriate adherence is MPR >= .80.

MPR is used as an estimate of adherence based on medication availability; it does not directly establish whether or when a participant took each dose. The binary endpoint converts the underlying measure into a count of participants above or below the stated cutpoint. That makes the outcome suitable for comparing the proportion classified as adherent between randomized groups, while retaining less detail than the original continuous MPR measure. The registry does not report the distribution of continuous MPR values or other cutpoints.

As a general statistical point, a binary endpoint gives a clinically interpretable count but makes results dependent on the chosen threshold: participants near either side of a cutpoint can be classified differently despite similar underlying values. The registry identifies its threshold as previously validated, but further validation details are not reported in the registry record.

7. Results Posted in the Registry

• Mailed DVD: 46.7% (105/225) versus 60.4% (137/227) on control; risk difference -13.7 percentage points (95% CI -22.8 to -4.6), risk ratio 0.77 (0.65–0.92); unadjusted two-proportion z-test p = 0.004.

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.

4-Item Morisky Medication Adherence Scale (MMAS-4)

• 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:
  • Mailed DVD: mean 3.60 versus 3.82 on control; difference -0.22 (95% CI -0.33 to -0.11), standardized effect d = -0.38; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Mailed DVD than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry posts one secondary endpoint, the 4-Item Morisky Medication Adherence Scale measured at 12 months. It adds an adherence-related measure to the primary MPR-based classification, but it does not represent an independent group of participants or an independent trial. Its interpretation depends on how the scale is scored, and the scoring direction is not explained in the registry record.

The secondary analysis should be viewed as supplementary context for the primary result, not as a separate confirmation. Both outcomes concern adherence, but they capture it differently: the primary endpoint classifies medication availability using an MPR threshold, while the secondary endpoint is a scale score. Agreement between related measures, if established, would not remove uncertainty about measurement, analysis choices, or the trial’s scope.

The registry’s reported secondary test and the direct unadjusted re-calculation both indicate a between-group difference by their respective tests, but the reported estimate is not explained in relation to the direct contrast. This makes the secondary result less straightforward to interpret than the primary count comparison. It should not be used to resolve uncertainty about the primary endpoint.

As a general statistical concern, testing multiple outcomes or making multiple comparisons increases the chance of obtaining at least one apparently unusual result by chance if each test is interpreted separately. The registry record does not report a multiplicity adjustment or a prespecified hierarchy for outcomes. Accordingly, an unadjusted secondary result carries less inferential weight than a primary result designated in advance, and should be interpreted cautiously rather than as a stand-alone conclusion.

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

• 4-Item Morisky Medication Adherence Scale (MMAS-4)

9. Statistical Interpretation

10. Statistical Methods Explained

The registry lists a chi-squared test for the primary comparison. The accompanying re-calculations are simple, unadjusted comparisons based on the posted group counts and summary statistics. They do not incorporate adjustment for other participant characteristics or other modeling choices. The registry record does not report whether the sponsor’s analysis used any adjustments beyond the named test.

What does the risk difference describe?

The risk difference is the difference between the proportions meeting the binary endpoint in two groups. In this comparison, the contrast is DVD minus MINT. A negative estimate therefore corresponds to a smaller observed proportion meeting the adherence definition in the DVD arm. The confidence interval describes uncertainty around that contrast under the calculation’s assumptions. The estimate is reported as -0.137, with interval limits of -0.228 and -0.046.

Risk differences use the outcome’s original probability scale. They can be easier to relate to a difference in group proportions than relative measures, but their values depend on the baseline event frequency as well as the contrast between groups. The registry also reports a risk ratio and an odds ratio. A risk ratio compares the two probabilities as a ratio; an odds ratio compares the odds of the outcome. These relative measures use different scales, and their numerical values should not be read as interchangeable with the risk difference.

What do the chi-squared test and p-value mean?

A chi-squared test is a general method for assessing whether categorical outcome counts differ between groups. For a two-group binary outcome, it compares the observed pattern of counts with the pattern expected under a null hypothesis of no group association. The registry reports p < 0.01 for its primary analysis; the unadjusted re-calculation reports p = 0.004.

As a general explanation, a p-value is the probability, under the null hypothesis and the test’s assumptions, of obtaining a result at least as incompatible with that null as the observed result. It is not the probability that the null hypothesis is true, nor does it measure the size or practical importance of a difference. A small p-value does not resolve questions about outcome completeness, analysis choices, bias, or how broadly a result applies.

How should the secondary mean comparison be read?

The registry reports a two-sided t-test for the 4-Item Morisky Medication Adherence Scale. A t-test is a general method for comparing group means while accounting for variability within the groups. The posted group means are accompanied by standard deviations, which describe spread among participant scores rather than uncertainty in the group mean. The re-calculated mean difference is an unadjusted DVD-minus-MINT contrast.

The registry’s reported secondary test gives a value of 0.29 and p < 0.01, while the direct summary-statistic re-calculation gives a mean difference of -0.22 and p < 0.001. The registry record does not explain how the reported value relates to the direct contrast, including its direction or scale. The two results should not be treated as though their estimates are directly interchangeable.

What is the role of the confidence interval?

A confidence interval gives a range of estimates compatible with the observed data under a specified statistical procedure. It conveys uncertainty about an estimated contrast, rather than a range containing a stated proportion of individual participant outcomes. The re-calculated intervals are unadjusted and are based on the posted summary statistics. General statistical interpretation also depends on the calculation’s assumptions; the record does not report additional modeling details for the sponsor’s analyses.

The registry’s tests and the re-calculations answer related but not identical reporting questions. The former are the analyses posted in the registry. The latter provide direct, unadjusted contrasts from the posted group summaries. The re-calculations do not establish that the trial’s original analysis plan used those methods or that the sponsor’s results should be replaced by them.

11. Confidence Intervals and Precision

For the primary binary outcome, the re-calculated risk difference for DVD compared with MINT is -0.137, with a 95% confidence interval from -0.228 to -0.046. The interval lies on the negative side of zero, consistent with a lower observed proportion meeting the adherence definition in the DVD group for this coding of the contrast. Its width also indicates uncertainty about the size of the group difference; the estimate should not be treated as exact.

The relative measures have 95% confidence intervals of 0.649 to 0.921 for the risk ratio and 0.396 to 0.835 for the odds ratio. These intervals are on different scales from the risk-difference interval. As a general principle, confidence intervals describe statistical uncertainty under the method used; they do not capture every possible source of uncertainty, such as bias from missing outcomes or limitations in measurement.

For the secondary mean comparison, the re-calculated difference is -0.22, with a 95% confidence interval from -0.328 to -0.113. This interval also lies below zero for the stated DVD-minus-MINT contrast. However, the registry’s own reported value for this analysis is 0.29, and the record does not explain the relation between that value and the re-calculated contrast. That reporting ambiguity limits straightforward interpretation of the secondary estimate.

The intervals are unadjusted. The registry record does not report whether confidence intervals were adjusted for multiple outcomes or analyses. Confidence intervals should therefore be read alongside the outcome definitions, coding of group contrasts, sponsor-reported tests, and unreported analysis details, rather than as a complete account of all uncertainty.

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 expressed as participants per arm, not total events. The primary outcome is a binary participant count, and the secondary outcome is a continuous score; neither is a time-to-event outcome. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect defined as a stated fraction of the observed effect. The trial’s original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the estimated number of participants per arm under which the planning method would have an 80% chance of detecting the specified effect if that effect and the other assumptions held. The 90% column uses a higher chance of detection and consequently requires more participants per arm for each listed effect. These are planning illustrations computed from the observed effect, not a statement about the trial’s original planning or its achieved ability to detect an effect.

The effect scenarios use the full observed effect, 75% of the observed effect, and 50% of the observed effect. Smaller effects are harder to distinguish from random variation under the same assumptions, so they require more participants. The displayed estimates are conditional on the stated method and effect scenario; they do not account for any design features or analysis choices not included in those assumptions.

These figures are not observed power. Observed power is not a substitute for interpreting the estimated effect and its confidence interval; the planning numbers instead illustrate how sample requirements change with the assumed effect size and target power.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.604; treatment proportion p₁ = 0.467; average p̄ = 0.535.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.7054 = 1.3825.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6987 = 0.5880.
4. n = (1.3825 + 0.5880)² / (-0.1369)² = 207.3, rounded up to 208 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 <- 0.60352422907489                          # control proportion
p1 <- 0.466666666666667                          # 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(1651208)
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 = 208 (80% power), 278 (90% power)
 75% of observed effect: n per arm = 368 (80% power), 492 (90% power)
 50% of observed effect: n per arm = 821 (80% power), 1,099 (90% power)
power.prop.test: 207.3 
Simulated power at n = 208 per arm: 0.814 (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

For the primary outcome, the registry reports a chi-squared analysis with p < 0.01 but does not post a sponsor-derived effect estimate or confidence interval. The direct unadjusted re-calculation from the arm counts gives a risk difference of -0.137, a 95% confidence interval from -0.228 to -0.046, and p = 0.004. These results are broadly consistent in indicating a difference between the groups, but the re-calculated estimate and interval are not values reported by the sponsor’s analysis.

For the secondary scale outcome, the registry reports a two-sided t-test, a value of 0.29, and p < 0.01. The direct re-calculation from the posted group means gives a DVD-minus-MINT difference of -0.22, with a 95% confidence interval from -0.328 to -0.113 and p < 0.001. The registry record does not clarify how its reported value is defined or how it corresponds to the direct contrast. Its scale and direction therefore cannot be reconciled from the record alone.

Re-calculations are simple unadjusted checks using the posted summaries. They do not reproduce undisclosed modeling, analysis-population, or missing-data decisions. The sponsor’s reported analyses and the direct re-calculations should be recognized as distinct analyses, particularly for the secondary outcome where the reported contrast is not explained.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies a primary adherence outcome and one secondary scale outcome, and reports analyses for both. It does not report a multiplicity strategy, such as an adjustment to account for testing more than one outcome, or a hierarchy specifying how the secondary analysis should affect interpretation. The posted p-values are therefore best read as individual test results, not as evidence that a family of analyses has been controlled for a stated overall error rate.

Missing-data methods are not reported in the registry record. The arm counts for the primary outcome match the listed arm sizes, but this alone does not establish how missing or unavailable measurements were handled, whether every enrolled participant contributed data, or how participants with incomplete follow-up were classified. The corresponding details for the secondary score are also not reported in the registry record.

The analysis population is not reported in the registry record. In particular, the record does not specify whether analyses followed all randomized participants in their assigned groups, included only participants with outcome measurements, or used another population definition. It also does not report how protocol deviations or intervention non-adherence were handled.

Interim analyses, stopping rules, and the trial’s original statistical analysis plan are not reported in the registry record. Nor are the randomization procedure, allocation concealment, or detailed methods for handling covariates reported. These omissions do not change the posted counts or tests, but they limit assessment of whether analyses followed a prespecified plan and how missingness or multiple testing may affect uncertainty.

As a general statistical point, missing outcomes and multiple testing can affect interpretation in different ways. Missing-data decisions can alter which participants contribute to an estimate, while multiplicity concerns arise when several tests are considered together. The registry record does not provide enough detail to assess either issue fully.

16. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The registry records zero serious adverse events among 227 participants in the MINT arm and zero among 225 participants in the mailed DVD arm. It also records zero other adverse events in each arm. Death counts are not reported in the registry record. No serious adverse event terms are listed.

These entries describe the event counts posted for the listed groups. They do not establish that no events occurred outside the recorded categories or reporting period, and the record does not provide further detail about event definitions, collection procedures, or completeness of safety follow-up. Zero recorded events should not be interpreted as proof of zero risk.

The interventions are behavioral, but the registry’s adverse-event entries alone do not permit a broad safety comparison. They do not include enough information to assess event severity beyond the serious-event category, timing, attribution, or differences in ascertainment between groups. The posted figures should be read as registry-reported counts rather than as a complete account of safety.

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

The primary result describes a difference in the observed proportion of participants meeting the registry’s MPR-based adherence threshold at 12 months. The MINT group had more participants classified as appropriately adherent than the mailed DVD group, and the unadjusted contrast has a confidence interval that does not include zero. The registry also reports a chi-squared test with p < 0.01. These statements characterize the posted outcome data and statistical comparison.

The result does not establish that every participant in one group had better adherence than every participant in the other. The endpoint is a thresholded measure of medication availability, not direct observation of dose-taking. Nor does a difference in this endpoint identify the specific mechanism responsible for the group contrast. The registry record does not report enough information about intervention delivery, missing outcomes, or the analysis population to resolve those issues.

The results also do not establish that the same contrast would occur in other settings or populations. The registry identifies the target population as minority participants who recently received a coronary stent, but detailed participant characteristics and eligibility criteria are not reported in the registry record. Generalizability beyond the enrolled participants cannot be determined from the posted results alone.

A p-value is not a measure of the probability that an intervention is effective, and a confidence interval does not include every source of uncertainty. The posted analyses do not, by themselves, answer questions about long-term outcomes, medication-taking behavior beyond the measured period, or effects not included among the registered outcomes. No medical recommendation follows from these statistical comparisons.

18. Why This Trial Matters Statistically

This trial illustrates how endpoint definition shapes a statistical comparison. The primary outcome turns a medication availability measure into a binary classification using an MPR cutpoint of .80. That produces an interpretable count of participants meeting the stated definition, while concealing variation within each category and among participants’ underlying MPR values.

It also illustrates why effect estimates, confidence intervals, and tests should be read together. The risk difference gives the group contrast on the probability scale; risk ratio and odds ratio express it on relative scales; and the p-value addresses compatibility with a null comparison under the test assumptions. None of these measures alone describes every aspect of the result.

The registry’s sponsor-reported tests and the direct unadjusted re-calculations are not interchangeable. The primary reported test and re-calculation are directionally consistent, while the secondary reported value is not explained in relation to its direct contrast. This is a practical reminder that transparent definitions of contrasts, scales, and analysis populations matter for interpreting trial results.

Finally, the posted planning illustrations show how assumptions about the effect to detect and the target probability of detection influence participant requirements. They are distinct from the trial’s original design justification, which is not reported in the registry record. Separating planning calculations from observed outcomes prevents sample-size illustrations from being mistaken for evidence about what the trial was designed to establish.

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.

Important participant details are absent. The registry identifies minority populations and coronary artery disease but does not report detailed eligibility criteria, participant characteristics, or representation across specific groups. The results therefore cannot be assessed across demographic subgroups from the posted information.

The MINT arm description is not fully consistent in its encounter count: it refers to 4 to 7 telephone encounters and also to four encounters at intervals of every 3 months. The registry record does not explain this wording or report actual intervention exposure, completion, or fidelity. Details of DVD delivery and participant use are likewise not reported.

The primary endpoint is based on medication availability and a binary threshold. The registry does not post the underlying continuous MPR distribution, so the effect of the cutpoint on classification cannot be assessed. The secondary scale’s scoring direction is also not explained. In addition, the registry’s secondary reported value is not reconciled with the direct unadjusted contrast.

Missing-data handling, analysis-population definitions, multiplicity methods, interim analyses, and the original sample-size justification are not reported in the registry record. These omissions limit evaluation of the analysis plan and the robustness of the inferential results. The absence of reported details should not be taken as evidence that a particular method was or was not used.

The study is listed as unmasked, and the registry does not report further protections against bias in outcome ascertainment. The posted adverse-event counts also lack detail about collection and follow-up. These limitations constrain what can be concluded from the registry record without invalidating the reported counts and tests themselves.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Improving Adherence to Post PCI Antiplatelet Therapy in Minority Populations — NCT01651208.
• Registry record last updated 2024-01-23; status last verified 2024-01.
• Results first posted 2014-08-22.
• 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.

23. Record Summary

The registry lists a completed randomized, unmasked, parallel-group trial sponsored by the University of Miami, with enrollment of 452. It compared phone-based motivational interviewing with a mailed educational DVD among minority participants who recently received a coronary stent.

The primary outcome was the number meeting an MPR-based definition of appropriate adherence 12 months after stent placement. The posted counts were 137 of 227 in the MINT arm and 105 of 225 in the DVD arm. The registry reports a chi-squared test with p < 0.01; the direct unadjusted re-calculation gives a risk difference of -0.137 for DVD compared with MINT, with a 95% confidence interval from -0.228 to -0.046.

One secondary adherence-scale outcome is posted. Its sponsor-reported contrast is not explained in relation to the direct unadjusted re-calculation. Further details about missing data, analysis populations, multiplicity, and the trial’s original sample-size justification are not reported in the registry record.