Safety and Quality of Life Study of Dexlansoprazole Modified Release Formulation to Treat Heartburn: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety and Quality of Life Study of Dexlansoprazole Modified Release Formulation to Treat Heartburn (NCT00255190), a randomized phase 3 study. The primary outcome is Mean Change From Baseline to Month 12 for Hemoglobin Values.

2. Clinical Question

The primary endpoint results are based on 88 participants in the 60 mg QD arm and 228 in the 90 mg QD arm. The reported mean changes were -0.29 g/dL and -0.05 g/dL, respectively. The comparison therefore describes the difference in average change between two active-dose groups among participants with the values needed for this endpoint. It does not compare treatment with no treatment, and it does not by itself describe every aspect of long-term safety.

3. Trial Design

The registry record identifies NCT00255190 as a Phase 3, randomized, open-label, parallel-group study of dexlansoprazole MR in people with gastroesophageal reflux disease. The official title describes an assessment of long-term safety for 60 mg QD and 90 mg QD. The record lists 591 enrolled participants and marks the study completed. The recorded start was 2006-01, and primary completion was 2008-06.

Both groups received dexlansoprazole MR, with the assigned daily dose distinguishing the arms. Because masking is listed as none, the study was open-label: treatment assignment was not masked. The record identifies randomization but does not report the allocation ratio, the randomization procedure, or details of how treatment assignment was implemented. Those details should not be inferred from the endpoint-specific sample sizes, which represent participants included in that particular outcome summary rather than the total enrollment.

The stated purpose was to determine the long-term safety profile of daily treatment. The primary posted outcome was mean change from baseline to Month 12 in hemoglobin. The primary endpoint summary included participants who received at least one dose, with the additional requirement of both baseline and Month 12 values for the parameter. The arm-specific endpoint counts were 88 and 228. They are smaller than the overall enrollment, but the reasons for the difference are not reported in the registry record.

The registry record lists 30 outcome measures and 28 analyses. Ten secondary outcomes are posted. These include PAGI-QOL and PAGI-SYM measures at specified follow-up times, while detailed secondary results are available for a subset of those measures. The protocol, the original sample-size justification, and the planned handling of interim analyses are not reported in the registry record. The record does not establish whether any analyses or outcomes changed after the study began.

4. Participant Flow and Accounting

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

Before assignment: At screening, subjects completed a Patient Assessment of Upper Gastrointestinal Disorders Quality-of-Life Index (PAGI-QOL) and Patient Assessment of Upper Gastrointestinal Disorders-Symptom Severity Index (PAGI-SYM) questionnaires before enrollment in Dexlansoprazole Modified Release (MR) 60 mg or 90 mg once daily (QD) treatment groups.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All subjects who received at least 1 dose of study drug are included in safety analyses. For changes from baseline, a subject had to have a baseline value and a Month 12 value to be included in the summary of a specific parameter.

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 Mean Change From Baseline to Month 12 for Hemoglobin Values, measured over Baseline and Month 12.

The primary endpoint is the mean change in hemoglobin from baseline to Month 12, measured in g/dL. A change score expresses how the measured value at follow-up differs from the participant’s baseline value; the reported arm result is the average of those changes among participants included in that endpoint summary. The study record specifies that participants needed a baseline and a Month 12 value to be included in this particular summary.

As general statistical context, hemoglobin is a laboratory measure that can be followed as part of monitoring a drug’s safety profile. A group mean can indicate the average direction and size of change, but it does not show how every participant’s value changed. The standard deviation describes the spread of individual change values around the group mean. Neither a mean nor a standard deviation identifies the clinical importance of a change without relevant clinical thresholds and additional context. Such thresholds are not reported in the registry record.

The endpoint is not a direct measure of reflux symptoms, heartburn, or quality of life. The registry lists patient-reported quality-of-life and symptom outcomes separately among the secondary outcomes. Consequently, the primary result addresses an average laboratory change between the two dose groups, not all dimensions of safety or the experience of symptoms during treatment.

7. Results Posted in the Registry

• Dexlansoprazole MR 90 mg QD: mean -0.05 versus -0.29 on control; difference 0.24 (95% CI 0.02 to 0.46), standardized effect d = 0.26; z-test p = 0.033.

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.

Mean Change From Baseline to Month 1 for PAGI-QOL 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 deviations.
• Result:
  • Dexlansoprazole MR 90 mg QD: mean 0.54 versus 0.54 on control; difference 0.00 (95% CI -0.14 to 0.14), standardized effect d = 0.00; z-test p = 1.000.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Dexlansoprazole MR 90 mg QD and the control. The interval gives the range of effects that remain compatible with the data.

Mean Change From Baseline to Month 3 for PAGI-QOL 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 deviations.
• Result:
  • Dexlansoprazole MR 90 mg QD: mean 0.56 versus 0.61 on control; difference -0.05 (95% CI -0.21 to 0.11), standardized effect d = -0.06; z-test p = 0.543.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Dexlansoprazole MR 90 mg QD and the control. The interval gives the range of effects that remain compatible with the data.

Mean Change From Baseline to Month 6 for PAGI-QOL 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 deviations.
• Result:
  • Dexlansoprazole MR 90 mg QD: mean 0.56 versus 0.58 on control; difference -0.02 (95% CI -0.18 to 0.14), standardized effect d = -0.03; z-test p = 0.811.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Dexlansoprazole MR 90 mg QD and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary results include PAGI-QOL mean changes at Month 1, Month 3, and Month 6. The two arms’ reported mean changes are close at those visits, with the Month 1 means equal as posted and only small numerical separations at the later visits. The reported ANCOVA p-values for these three comparisons do not indicate clear evidence of between-arm differences under those analyses. These patterns are broadly consistent with the primary result in one limited respect: the secondary summaries do not show a large numerical separation between the dose groups. The endpoints measure different outcomes, however, so they are not replications of the hemoglobin result.

The registry lists additional secondary outcomes, including PAGI-QOL at later listed time points and PAGI-SYM measures, but detailed results for those measures are not included in the posted secondary summaries. The record lists 30 outcome measures, 28 analyses, and 10 posted secondary outcomes. It is not possible to infer results for outcomes without posted estimates or analyses.

Secondary results generally warrant less weight than a prespecified primary result when many outcomes and time points are examined. As general statistical context, testing many hypotheses increases the opportunity for chance findings if multiplicity is not accounted for. The registry record does not report a multiplicity adjustment or a hierarchy for interpreting secondary outcomes. The secondary p-values should therefore be viewed as exploratory or supportive rather than as stand-alone confirmatory evidence. They also should not be used to extend conclusions from hemoglobin to symptoms, quality of life, or safety as a whole.

Differences in endpoint counts across visits also matter when comparing the secondary summaries. Participants included at one visit need not be the same set included at another. The registry does not explain these changes in counts or report how missing observations were handled for the secondary analyses. Thus, the pattern across visits is descriptive and does not establish why the results differ or whether missingness influenced them.

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

• Mean Change From Baseline to Month 1 for PAGI-QOL Total Score
• Mean Change From Baseline to Month 3 for PAGI-QOL Total Score
• Mean Change From Baseline to Month 6 for PAGI-QOL Total Score
• Mean Change From Baseline to Month 9 for PAGI-QOL Total Score
• Mean Change From Baseline to Month 12 for PAGI-QOL Total Score
• Mean Change From Baseline to Month 1 for PAGI-SYM Total Score
• Mean Change From Baseline to Month 3 for PAGI-SYM Total Score
• Mean Change From Baseline to Month 6 for PAGI-SYM Total Score

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is continuous: it is a mean change in hemoglobin measured in g/dL. For each arm, the registry reports the number of participants in the endpoint summary, the mean change, and the standard deviation. The standard deviation describes variability among participant-level change values; it is not the uncertainty in the estimated mean. The analysis population is restricted to participants who received at least one dose and, for this change measure, had both baseline and Month 12 values.

What does the recalculated difference represent?

The recalculated mean difference is the 90 mg QD group mean minus the 60 mg QD group mean. From the posted summaries, this is 0.24 g/dL. It is an unadjusted comparison: it uses the group means and their reported variability without adjustment for other variables. It is not the same as an individual participant’s change, and it should not be read as a prediction for any particular participant.

The corresponding recalculated 95% confidence interval is 0.019 to 0.461, and the recalculated unadjusted p-value is 0.033. These are simple recalculations from the posted summary statistics. The registry’s reported inferential analysis is an ANOVA with p = 0.042. Since the sponsor’s analysis is the registry’s own analysis, it takes precedence when reporting the sponsor’s result. The recalculation is useful as a transparent, unadjusted reference, not as a replacement for an analysis with fuller participant-level data or details of the sponsor’s model.

What do ANOVA and ANCOVA mean?

As general statistical explanations, analysis of variance (ANOVA) compares group means while accounting for variability within groups. Analysis of covariance (ANCOVA) compares group outcomes while adjusting for one or more covariates. The registry lists ANOVA for the primary comparison and ANCOVA for the posted PAGI-QOL analyses. It does not report the covariates, model specifications, diagnostics, or other implementation details for those analyses. Those details are therefore not reported in the registry record and should not be assumed.

Randomization is intended to make groups comparable on average at the point of assignment, but it does not guarantee that every measured or unmeasured characteristic is balanced in the realized study. An adjusted analysis may account for specified baseline variables, but the registry’s outcome summary does not identify which variables, if any, were included in the primary ANOVA. No adjustment details can be inferred from the reported p-value alone.

Why does the analysis population matter?

The registry states that all participants who received at least one dose were included in safety analyses. It also states that a participant needed both a baseline value and a Month 12 value to be included in the summary for a change-from-baseline parameter. Thus, the stated general safety population and the population contributing to this particular endpoint are not necessarily identical. The endpoint-specific counts, 88 and 228, identify the numbers included in the reported summaries; the record does not give a full account of participant flow or explain the missing endpoint values.

As general statistical context, excluding participants without a follow-up measurement can affect a comparison if the availability of that measurement is related to treatment assignment or to the outcome. A complete-case summary is straightforward to describe, but it does not automatically correct for missing outcomes. The registry record does not report imputation, sensitivity analyses, or another strategy for handling missing Month 12 values. The consequences of missing data therefore cannot be evaluated from the posted information alone.

How should p-values be read?

A p-value describes how compatible the observed data are with a specified null model, conditional on the statistical assumptions used for the test. It does not give the probability that a treatment effect is real, the size of an effect, or the probability that a result will recur. A smaller p-value is not automatically evidence of greater clinical importance. In this case, the sponsor-reported p-value and the unadjusted recalculated p-value come from different reported procedures, so they should be identified separately rather than treated as interchangeable.

The primary endpoint comparison has a single posted sponsor analysis in the registry summary. The registry record does not describe whether an analysis plan was finalized before unblinding, whether any interim analyses were performed, or what decision rules were prespecified. The record also does not report a multiplicity strategy for interpreting multiple outcomes and analyses. Those omissions limit assessment of how the reported inferential results fit into a broader prespecified statistical plan.

Why can over-dispersion matter?

As general context, over-dispersion refers to variability that is greater than a statistical model expects. When variability is underestimated, standard errors may be too small and confidence intervals too narrow; when it is modeled appropriately, uncertainty estimates can better reflect observed variation. The primary outcome is continuous, and the registry reports standard deviations for the two arms. It does not report an over-dispersion assessment or a model-specific variance adjustment. This general issue should not be taken to mean that over-dispersion occurred in this analysis.

Overall, the available methods information supports describing the arm means and the reported ANOVA result, while the recalculated comparison provides a simple unadjusted check. Further judgments about model adequacy, covariate adjustment, missingness, and prespecification require details not reported in the registry record.

11. Confidence Intervals and Precision

The recalculated 95% confidence interval for the mean difference, defined as the 90 mg QD arm minus the 60 mg QD arm, extends from 0.019 to 0.461 g/dL. It quantifies uncertainty in the unadjusted difference estimated from the posted group summaries. Under the assumptions of this calculation, values throughout that interval are compatible with the observed data at the stated confidence level.

A confidence interval is not a guarantee that the true difference lies in the interval, nor does it describe the spread of individual participants’ changes. The arm-specific standard deviations, 0.873 and 0.959, describe participant-level variation; the confidence interval describes uncertainty in the estimated between-arm mean difference. These answer different questions.

The lower end of the recalculated interval is close to zero, while the upper end is farther from zero. This indicates that the unadjusted estimate is more precise about the direction than about the exact magnitude: the interval does not identify one exact mean difference. The registry-reported ANOVA p-value is 0.042, while the recalculated unadjusted p-value is 0.033. The confidence interval and recalculated p-value belong to the simple unadjusted recalculation; they should not be presented as the sponsor’s model-based interval or test result.

The registry does not provide a sponsor-reported confidence interval for the primary comparison, a clinical threshold for a meaningful hemoglobin change, or a detailed account of missing follow-up values. Consequently, the statistical precision of the unadjusted estimate can be described, but its clinical importance and its sensitivity to missing data cannot be resolved from the registry record.

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 sample-size figures are planning illustrations based on the observed effect, not the trial’s original design calculations. For the primary endpoint, the planning figures are participants per arm. They are not total participants across both arms and are not total event counts. Time-to-event planning results, when applicable, are expressed as total events, but the primary continuous outcome uses participants per arm.

The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. The 80% power column describes the number of participants per arm that the planning calculation estimates would give an 80% chance of detecting an effect of that size under those assumptions, if the effect and model assumptions hold. The 90% power column uses a higher target chance of detecting the effect and therefore generally requires more participants per arm.

The rows for 100%, 75%, and 50% of the observed effect represent progressively smaller target effects. Smaller effects are harder to distinguish from random variation, so the planning calculation requires more participants per arm to maintain the same target power. This relationship is visible in both the numerical planning values and the associated curve.

These figures do not describe the study’s observed ability to detect an effect and are not observed power. They are retrospective planning illustrations calculated from the observed effect, not evidence about how the original study was designed. The original sample-size justification and its assumptions are 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 = 0.240; pooled standard deviation σ = 0.936.
2. n = 2 × (1.96 + 0.842)² × 0.936² / 0.240² = 238.7, rounded up to 239 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 <- 0.24                      # observed difference in means
sigma <- 0.935963705132224                     # 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(255190)
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 = 239 (80% power), 320 (90% power)
 75% of observed effect: n per arm = 425 (80% power), 569 (90% power)
 50% of observed effect: n per arm = 955 (80% power), 1,279 (90% power)
power.t.test: 239.7 
Simulated power at n = 239 per arm: 0.796 (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. Analyses Reported by the Sponsor

The registry reports an ANOVA for the primary comparison of the two dose groups, with p = 0.042. This is the sponsor’s posted inferential result and takes precedence when describing the sponsor’s analysis. The registry summary does not provide a sponsor-reported effect estimate or confidence interval for that ANOVA.

A separate unadjusted recalculation from the posted arm means and standard deviations gives a mean difference of 0.24 g/dL for 90 mg QD minus 60 mg QD, with a recalculated 95% confidence interval of 0.019 to 0.461 and an unadjusted p-value of 0.033. It is a simple summary-statistic comparison and does not reproduce the sponsor’s ANOVA. The differing p-values should therefore be reported with their methods identified, not treated as contradictory estimates of an identical calculation.

The registry does not report enough detail about the sponsor’s model to establish whether it incorporated covariates or other features unavailable to the recalculation. The sponsor result is the relevant reported analysis; the recalculation offers a transparent, unadjusted comparison and a measure of its uncertainty based on the posted summaries.

15. Multiplicity, Missing Data and Analysis Populations

The registry lists multiple outcome measures and analyses, including a primary hemoglobin endpoint and secondary quality-of-life and symptom measures at different follow-up times. It does not report a multiplicity adjustment, a formal hierarchy among secondary endpoints, or a strategy specifying which comparisons would be treated as confirmatory. As general statistical context, making many comparisons creates more opportunities for chance findings. Without the planned approach to multiplicity, isolated secondary p-values should be interpreted cautiously and should not be treated as equivalent to a single prespecified primary test.

The record reports a primary safety-analysis population consisting of participants who received at least one dose. For the change-from-baseline endpoint, a participant also needed a baseline value and a Month 12 value to be included. The primary outcome counts are 88 in the 60 mg QD arm and 228 in the 90 mg QD arm, compared with total enrollment of 591. The registry record does not provide the reasons participants lack endpoint values or a complete account of the participant flow into each analysis.

The record does not report whether missing outcomes were imputed, whether participants with incomplete follow-up were included in another analysis, or whether sensitivity analyses examined alternative missing-data assumptions. As general context, a comparison limited to participants with observed values may be affected if missingness is related to treatment or outcome. The available summaries do not establish whether that happened, and no particular missing-data mechanism should be assumed.

The registry also does not report an intention-to-treat analysis population for this endpoint, the handling of protocol deviations, or a detailed statistical analysis plan. Although the record identifies randomization and open-label masking, these labels alone do not settle how participants were analyzed or whether all randomized participants were retained in the outcome analysis. These missing details constrain assessment of the robustness and prespecification of the reported results.

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

The posted primary summaries show mean hemoglobin changes of -0.29 g/dL in the 60 mg QD arm and -0.05 g/dL in the 90 mg QD arm among participants included in the endpoint analysis. The sponsor-reported ANOVA has p = 0.042. The unadjusted recalculation estimates a mean difference of 0.24 g/dL, with a 95% confidence interval from 0.019 to 0.461 and p = 0.033. These statistics describe a between-arm difference in average change over the stated follow-up.

They do not establish the clinical importance of that difference. The registry record does not report a threshold for a meaningful hemoglobin change or provide other clinical context for interpreting these values. A difference between group means does not show that every participant changed in the same direction, and it does not reveal the distribution of individual outcomes beyond the reported standard deviations.

The primary endpoint also does not answer whether symptoms or quality of life differed, whether every aspect of safety was similar, or how outcomes would compare with placebo or no treatment. Both arms received dexlansoprazole MR, and the available primary comparison is between the two daily doses. The posted secondary results address some patient-reported outcomes, but they do not turn the primary laboratory endpoint into a comprehensive measure of experience or safety.

The findings apply to the participants included in the reported summaries and should be interpreted with the endpoint-specific counts and missing-data limitations in mind. The registry record does not explain why the primary analysis counts are smaller than total enrollment, report a clinical threshold, or describe sensitivity analyses for missing Month 12 values. These limitations do not erase the reported estimates, but they restrict how broadly or causally they can be interpreted.

Statistical evidence in the sponsor’s analysis is not, on its own, a treatment recommendation or a determination that a change is beneficial or harmful. The record supports describing the observed averages, the sponsor’s test, and the uncertainty in a simple recalculation. Broader conclusions require information and clinical context not reported in the registry record.

17. Why This Trial Matters Statistically

This trial is statistically informative as a comparison between two active doses with a continuous laboratory endpoint and a stated follow-up time. The mean-change outcome makes the target contrast interpretable: the average change in one dose group relative to the other. The reported standard deviations also make it possible to describe variability, while the recalculated confidence interval conveys uncertainty in the unadjusted difference.

The record illustrates why a sponsor-reported analysis and an unadjusted recalculation should be distinguished. The sponsor reports an ANOVA p-value of 0.042; the simple recalculation gives p = 0.033 and a confidence interval for the difference. The distinction matters because the recalculation is limited to posted summary statistics and does not establish that it reproduces the sponsor’s analytical choices. Reporting both with clear attribution makes the inferential basis easier to assess.

It also demonstrates how endpoint-specific populations shape interpretation. Total enrollment is 591, while fewer participants contribute to the Month 12 hemoglobin summaries. The stated requirement for both baseline and Month 12 values is transparent, but the reasons for missing values and their handling are not reported. Such details are important when a result is presented as part of a long-term safety assessment.

Finally, the record includes multiple secondary outcomes and analyses, but does not report a multiplicity plan or complete detailed results for every listed outcome. This highlights the importance of distinguishing a primary result from secondary patterns and avoiding stronger conclusions than the available analysis supports. The case is useful for reading effect estimates, p-values, confidence intervals, analysis populations, and planning illustrations as related but different statistical information.

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.

Several limitations are specific to the posted record for this study. The design is open-label, and the registry does not report whether laboratory assessment or other parts of outcome evaluation were masked. The endpoint is a laboratory measure, but the record does not describe procedures for standardized collection, timing, or central review.

Although total enrollment is 591, the primary Month 12 hemoglobin summaries include 88 participants in the 60 mg QD arm and 228 in the 90 mg QD arm. The record states that baseline and Month 12 values were required, but it does not explain why these endpoint counts differ from enrollment, provide participant flow, or report the extent and reasons for missing values. No imputation or missing-data sensitivity analysis is reported.

The registry gives the sponsor’s ANOVA p-value but does not report a sponsor effect estimate, confidence interval, model details, covariates, or diagnostic checks for the primary endpoint. The unadjusted recalculation cannot fill those gaps. The original sample-size justification, planned analysis assumptions, and any interim-analysis procedures are not reported in the registry record.

Multiplicity procedures are not reported despite numerous listed outcomes and analyses. Detailed posted secondary results cover only a subset of the listed outcomes, and missing secondary results cannot be interpreted as showing no difference. Finally, no clinical threshold is given for the hemoglobin change, limiting interpretation of the magnitude beyond its statistical description. These limitations call for a bounded reading of the posted summaries rather than assumptions about unreported procedures or results.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Safety and Quality of Life Study of Dexlansoprazole Modified Release Formulation to Treat Heartburn — NCT00255190.
• Registry record last updated 2016-07-27; status last verified 2011-04.
• Results first posted 2009-08-12.
• 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

NCT00255190 is a completed Phase 3, randomized, open-label, parallel study of dexlansoprazole MR 60 mg QD and 90 mg QD in participants with gastroesophageal reflux disease. The registry reports total enrollment of 591 and identifies the study purpose as assessing long-term safety.

The primary outcome is mean change from baseline to Month 12 in hemoglobin. The posted means are -0.29 g/dL among 88 participants in the 60 mg QD arm and -0.05 g/dL among 228 participants in the 90 mg QD arm. The sponsor-reported ANOVA has p = 0.042. An unadjusted recalculation gives a mean difference of 0.24 g/dL, a 95% confidence interval of 0.019 to 0.461, and p = 0.033.

Detailed secondary results include PAGI-QOL at Month 1, Month 3, and Month 6. The registry does not report the original sample-size justification, multiplicity plan, or missing-data sensitivity analyses. The primary summaries therefore describe the posted analysis population and should be interpreted with these reporting limitations in mind.