Study of Dose Adjustment From Levothyroxine to a New Levothyroxine Sodium Test Formulation: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Dose Adjustment From Levothyroxine to a New Levothyroxine Sodium Test Formulation (NCT01916304), a na phase 2 study. The primary outcome is Percentage of Participants That Do Not Need a Change of Dose.

2. Clinical Question

In statistical terms, the question is descriptive: among the participants with available primary-endpoint data, how often was the dose left unchanged at the specified assessment? It is not a comparison of outcomes between separately assigned treatment groups. The registry lists secondary outcomes concerning the magnitude of dose change, whether thyroid stimulating hormone (TSH) was between 0.4-2.5 mU/L, absolute serum TSH values, and relative percent change in serum TSH. These outcomes offer additional ways to describe dose and laboratory measurements, but their results are not reported in the registry record.

3. Trial Design

The registry describes a completed Phase 2 study with enrollment of 101 and a single-group model. Its official title characterizes it as a multicentre, open-label switch study in (near) total thyroidectomised patients. The masking field is NONE, and allocation is NA. These features indicate that the registry does not describe randomized allocation or a blinded comparison. The study began in 2013-07, reached primary completion in 2014-06, and is recorded as COMPLETED.

Participants switched from L-thyroxine Christiaens® to the new levothyroxine sodium test formulation. The intervention is listed as a drug. The description specifies once-daily oral tablets, with a dose of 25-225 μg determined according to the thyroid stimulating hormone level, for up to 12 to 20 weeks. The registry record does not report more detailed dose-adjustment rules or the schedule of measurements beyond the primary endpoint timeframe.

A single-group switch design can describe what happened after the change in formulation in the enrolled study population. It does not, by itself, separate the effect of the new formulation from other influences over time. Without a concurrent control group, there is no randomized contrast to show what would have happened to similar participants who continued the previous formulation under otherwise comparable conditions. Open-label treatment also means the record does not describe masking of participants or study personnel.

The enrollment figure is not necessarily the number contributing data to every outcome. The primary endpoint specifies an intent-to-treat population with data available for analysis, but the number with usable endpoint data is not reported in the registry record. The record lists five outcome measures and zero analyses. It does not report a statistical analysis plan, a sample-size justification for the trial, interim analyses, or details of how participants were followed when outcome data were unavailable.

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: Participants with a diagnosis of Primary Hypothyroidism were switched from treatment with L-Thyroxine Christiaens® to treatment with new levothyroxine sodium 25-225 μg.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Participants from the intent-to-treat population, with data available for analysis.

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 Percentage of Participants That Do Not Need a Change of Dose, measured over 2 months (± 2 weeks) after switch to sodium formulation..

The primary endpoint is the percentage of participants who did not need a dose change. It is assessed 2 months (± 2 weeks) after switching to the sodium formulation. A physician determined dose change according to clinical judgement. The endpoint is therefore a binary classification at the participant level: the dose either needed a change or did not, as judged by the physician for the assessment.

A percentage is used to express the frequency of participants meeting the “no dose change” definition in the endpoint population. This can make the result easier to interpret than a raw count alone, particularly when the number with available data differs from enrollment. The registry specifies the intent-to-treat population with data available for analysis, but does not report the number included in the primary analysis. It also does not report the observed percentage or its 95% confidence interval.

The endpoint addresses dose stability after a switch, not the full range of clinical outcomes that could matter to participants. The registry lists secondary outcomes on dose changes and TSH, including the percentage with TSH between 0.4-2.5 mU/L, but those measures do not replace the primary endpoint. The clinical-judgement component also means that the endpoint depends on how physicians decided whether a dose change was needed. The registry record does not report a more standardized decision rule.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The main statistical quantity in the primary endpoint is a proportion: the share of the analysis population classified as not needing a dose change. The registry gives the endpoint unit as a percentage of participants and identifies the parameter as a number. In general, a binary outcome assigns each participant to one of two categories. For this study, the categories concern whether a dose change was judged necessary at the endpoint assessment. The registry does not report the count in either category or the analysis denominator.

What does a confidence interval describe?

The endpoint specifies a 95% confidence interval. In general, a confidence interval conveys the statistical uncertainty around an estimate, taking account of the observed data and the method used to calculate the interval. It is not a guarantee that the true value lies within the particular interval. The interval can be read alongside the estimated percentage: the estimate describes the observed proportion, while the interval gives a range of values compatible with the data under the method’s assumptions.

The registry record does not report the primary percentage, the interval limits, or the method used to calculate the interval. Consequently, the interval’s width and the precision of the estimate cannot be assessed. The registry also does not report the endpoint analysis denominator, which is needed to understand how many available observations informed the proportion. Enrollment alone cannot establish that denominator because the endpoint population is described as participants with data available for analysis.

Why does the single-group design matter?

The study model is single-group, and allocation is listed as NA. There is no concurrent randomized control group. Statistical estimation of a proportion after the switch remains possible in principle, but the design does not estimate a randomized difference between switching and continuing the previous treatment. A within-study observation after a switch may describe the participants’ experience, yet it cannot distinguish the switch from other time-related or clinical influences without additional design or analysis information.

The study is also unmasked. For the primary outcome, a physician used clinical judgement to determine whether a dose change was needed. In general, a decision-based outcome can be affected by differences in how clinicians apply judgement. Masking can sometimes limit the influence of treatment knowledge on assessment, but masking is recorded as NONE in this study. The registry record does not describe whether judgement was standardized across sites or whether assessments were independently reviewed.

How should a planning calculation be read?

Any sample-size illustration associated with the posted results is distinct from the trial’s observed findings. The stated illustration assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is expressed as a fraction of the observed effect. Those assumptions describe a planning exercise, not the design used in this single-group switch study. The registry record does not report the trial’s own sample-size justification, and the planning calculation should not be described as observed power.

In general, planning sample sizes depend on the chosen effect to detect, the error-rate threshold, the allocation, and the statistical method. If the target effect is set as a fraction of an observed effect, that is a hypothetical planning choice rather than proof that the effect is real or clinically important. The sample-size assumptions also specify that time-to-event calculations give total events under a Schoenfeld approach, while other calculations give participants per arm. Those conventions do not change the interpretation of this trial’s single-group design. No numerical planning results are reported in the registry record.

What can secondary outcomes add?

The listed secondary outcomes address complementary questions. The magnitude of dose change describes the scale of adjustments, while the TSH outcomes concern whether values fall in a specified range, absolute values, or relative percent change from baseline. In general, continuous measurements and binary thresholds can reveal different features of the data. A threshold result depends on the selected range, while a continuous measure retains information about values across its scale. The registry record does not report the results, analysis methods, or missing-data handling for these outcomes.

The registry lists five outcome measures and zero analyses. This does not provide an account of which statistical procedures were planned or applied. The record does not report a model, covariate adjustment, distributional assumptions for secondary outcomes, or a method for handling repeated measurements. Those details should not be inferred from the endpoint names or from the intervention schedule.

Why does over-dispersion matter in general?

For count outcomes, over-dispersion means that the observed variability is greater than a statistical model expects. Ignoring it can make uncertainty appear too small and can lead to confidence intervals or tests that are too optimistic. This is a general consideration for count data, not a reported feature of this trial. The primary endpoint is described as a percentage, and the registry record does not report an over-dispersion assessment or a model for counts.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Levothyroxine Sodium New Formulation")
n      <- c(82)
events <- c(27)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Levothyroxine Sodium New Formulation  82  27  32.9  22.9  44.2  23.7  43.7  23.7  43.7

11. Multiplicity, Missing Data and Analysis Populations

The registry lists five outcome measures, including the primary endpoint and secondary outcomes on dose changes and TSH. It lists zero analyses. A multiplicity strategy—such as a hierarchy among outcomes, an adjustment to account for testing several outcomes, or a distinction between confirmatory and exploratory analyses—is not reported in the registry record. Without that information and without reported outcome results, it is not possible to assess how multiple outcomes were handled or how any reported statistical evidence should be interpreted across outcomes.

The primary population is described as participants from the intent-to-treat population with data available for analysis. This does not specify how missing measurements were handled or whether participants with missing endpoint data were included through any imputation or other method. The number with available primary-endpoint data, the reasons for unavailable data, and the extent to which missingness differed across participants are not reported in the registry record. The enrollment figure should therefore not be substituted for the primary analysis denominator.

In general, missing data can affect both the size and interpretation of an estimated percentage. If the availability of an outcome is related to the outcome itself or to factors associated with it, an analysis restricted to available cases may not represent all enrolled participants. This is a general statistical concern, not a claim about what occurred in this study. The registry record does not provide enough information to characterize missingness or evaluate sensitivity to alternative assumptions.

The record also does not report interim analyses, prespecified statistical methods, or a protocol-level approach to outcome prioritization. These omissions limit assessment of analysis choices and the scope of conclusions, independently of the fact that numerical results are unavailable.

12. 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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: cardiac failure (1.0%), post procedural haematoma (1.0%), catheterisation cardiac (1.0%), skin lesion (1.0%), bladder catheterisation (1.0%).

The safety record lists 101 at risk for the levothyroxine sodium new formulation group and records 7 under serious adverse events and 7 under other adverse events. These entries should be read as registry-recorded group figures; the record does not explain further whether the counts refer to participants, events, or both. Deaths are listed as null. The registry also identifies the following top serious adverse event terms, each with a recorded value of 1.0%: Cardiac failure, Post procedural haematoma, Catheterisation cardiac, Skin lesion, Bladder catheterisation, and Hysterectomy.

These terms are not evidence by themselves that the formulation caused the events. The record does not report a control group, a causal assessment, event timing, severity details beyond the serious-event classification, or the method used to select the listed terms. In a single-group study, the figures describe reports recorded during the study context and do not provide a randomized safety comparison. The listed percentages should be interpreted as registry entries, not as a basis for attributing causation. The registry record does not report additional details needed to evaluate individual events or compare safety between treatments.

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

The study is a completed, single-group switch study of a new levothyroxine sodium formulation. Its stated primary question concerns the percentage of participants who did not need a dose change at the assessment 2 months (± 2 weeks) after the switch. The endpoint is clinically interpretable as a description of physician-assessed dose stability in participants with available data. However, the registry record does not report the observed percentage or its 95% confidence interval. The primary result and its precision therefore remain unknown from this record.

The design does not include a concurrent randomized control group. It can describe outcomes after the switch, but it cannot establish a causal contrast against continued use of L-thyroxine Christiaens®. The dose was determined according to TSH level and the physician used clinical judgement to decide whether a change was needed. These features are important context for interpreting the endpoint and do not establish a uniform dose-adjustment rule.

The registry lists additional outcomes involving dose-change magnitude and TSH, but their results are not reported. It also does not report the number of participants with primary endpoint data, the missing-data approach, or the statistical analysis methods. Consequently, neither the primary endpoint nor the broader pattern of outcomes can be assessed for magnitude or uncertainty from the registry record.

These limitations do not mean the study contains no useful information. Its design and endpoint identify a practical question about dose adjustment after a formulation switch, and its record describes how the outcome was defined. But a defined question is not itself a reported result. No claim about the size, direction, or precision of the outcome—or about whether one formulation is preferable—can be supported by the outcome information recorded.

14. Why This Trial Matters Statistically

This trial raises a statistical question that is distinct from a conventional treatment-versus-control comparison. The primary endpoint asks how often dose adjustment was judged necessary after a switch. A proportion can be a direct way to describe that experience, but its interpretation depends on the endpoint definition, the denominator, and the uncertainty around the estimate. The registry record specifies the endpoint and its timeframe, yet does not report the percentage, the confidence interval, or the number contributing data.

The design also illustrates the difference between describing a post-switch outcome and estimating a treatment effect. A single-group study can document what occurred in the participants studied, but it lacks the concurrent randomized comparison needed to separate the switch from other changes over time. This distinction is central when readers encounter outcome descriptions that sound comparative even though the design is not a comparative trial.

Clinical judgement is part of the primary endpoint. That makes it important to understand how the judgment was applied, whether it was consistent across settings, and whether assessment could be influenced by knowledge of the treatment. The record states that the study was open-label and that physicians made dose-change decisions according to clinical judgement, but does not report further standardization or assessment procedures.

Finally, the gap between a complete outcome definition and a missing outcome estimate is consequential. The listed secondary outcomes and safety terms provide context, but they cannot substitute for the absent primary result or resolve uncertainty about missing data and analysis methods. Statistically careful interpretation distinguishes what the design set out to measure from what the registry actually reports.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The most direct limitation for interpreting the primary endpoint is that its result is not reported in the registry record. The record provides neither the percentage of participants who did not need a dose change nor the 95% confidence interval. It also does not give the number of participants with available primary-endpoint data, so the analysis denominator cannot be established from the enrollment figure.

The design is single-group, with allocation listed as NA and masking listed as NONE. There is no concurrent randomized comparator. Therefore, the study description does not support a randomized estimate of the difference between switching to the new formulation and continuing the previous formulation. Changes observed after switching could reflect other influences that are not characterized in the registry record.

The primary classification depended on a physician’s clinical judgement. The registry does not report a more detailed decision rule, methods for standardizing decisions, or whether assessments were reviewed. Open-label assessment is relevant context for a judgement-based endpoint. The record does not report whether any procedures were used to assess or limit possible effects of treatment knowledge.

The registry lists secondary outcomes but does not report their results or analysis methods. It also does not describe multiplicity handling, missing-data methods, the trial’s sample-size justification, or interim analyses. These gaps limit evaluation of the precision, robustness, and scope of the planned or reported analyses. The safety entries likewise lack reported event timing and causal assessment, and no control group is available for a randomized safety comparison. These are limitations of what the registry record reports; they do not establish that unreported procedures or analyses were not performed.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Study of Dose Adjustment From Levothyroxine to a New Levothyroxine Sodium Test Formulation — NCT01916304.
• Registry record last updated 2015-07-20; status last verified 2015-06.
• Results first posted 2015-07-20.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

19. Record Summary

NCT01916304 is recorded as a completed Phase 2, single-group, open-label switch study sponsored by Takeda. It enrolled 101 participants and investigated switching from L-thyroxine Christiaens® to a new levothyroxine sodium formulation in (near) total thyroidectomised patients with hypothyroidism. The intervention was an oral, once-daily tablet at 25-225 μg, with dose determined according to TSH level and treatment for up to 12 to 20 weeks.

The primary endpoint was the percentage of participants who did not need a dose change, assessed 2 months (± 2 weeks) after the switch. A physician determined dose change according to clinical judgement. The primary population was described as the intent-to-treat population with data available for analysis. The registry record does not report the primary estimate, its 95% confidence interval, the analysis denominator, or the statistical analysis methods.

Secondary outcomes concerned dose change and TSH. The safety record lists 7 under serious adverse events and 7 under other adverse events, with 101 at risk in the formulation group. The study has no concurrent randomized comparator.