Trial of High Dose Vitamin D in Patient's With Crohn's Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Trial of High Dose Vitamin D in Patient's With Crohn's Disease (NCT02208310), a randomized phase 4 study. The primary outcome is Composite Endpoint: Number of Participants With (Any of) a CD-related Hospitalization, CD-related Surgery, CD-related ER Visits and Steroid Prescriptions.

2. Clinical Question

The trial’s clinical question concerned whether high-dose vitamin D supplementation was associated with fewer Crohn’s disease-related events among patients with Crohn’s disease and vitamin D deficiency. The registry describes a composite primary endpoint that counts participants with any Crohn’s disease-related hospitalization, surgery, emergency-room visit, or steroid prescription by Day 180. The stated hypothesis also refers to hospitalizations, surgeries, and steroid use.

The record lists randomized allocation and double masking, but also labels the model as single group. It does not resolve this tension. The planned clinical comparison cannot be assessed from the posted primary outcome because only 1 subject remained in the study to Day 180, and the reported endpoint value is available for the high-dose arm alone.

3. Trial Design

The registry identifies NCT02208310 as a Phase 4 randomized controlled trial of high-dose vitamin D in Crohn’s disease, sponsored by the University of Michigan. The listed design features are randomized allocation and double masking. At the same time, the model is recorded as single group, while the registry also lists a low-dose arm and a high-dose arm. The record does not explain this inconsistency, so the design details should be read as reported rather than treated as a fully reconciled account.

The enrollment is listed as 11. The registry lists cholecalciferol 10,000 IU for the high-dose arm and cholecalciferol 400 IU for the low-dose arm. The high-dose description specifies daily dosing for 30 days, with a possible repeat course if vitamin D levels remained below 50 ng/ml. The low-dose description specifies daily dosing for 30 days. Both descriptions contain additional text about maintaining masking and summer enrollment, but the text is truncated in the registry record; the complete dosing schedule is therefore not reported.

The study start is listed as 2015-04, and primary completion as 2016-04. Its status is terminated. The record does not report why it was terminated. The primary endpoint was originally planned for Day 180 and Day 360, but the description says only 1 subject remained in the study to Day 180, and that data are presented. The primary endpoint values and denominators show why the posted result cannot support a comparison between the treatment arms.

Thirteen outcome measures are listed, including the primary composite and secondary outcomes related to hospitalizations, steroid prescriptions, surgeries, disease activity, inflammatory markers, therapy escalation, and quality of life. Ten secondary results are posted, while the analyses count is recorded as 0. The record does not report a detailed statistical analysis plan or explain how the listed outcomes were prioritized beyond identifying the primary endpoint.

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 Composite Endpoint: Number of Participants With (Any of) a CD-related Hospitalization, CD-related Surgery, CD-related ER Visits and Steroid Prescriptions, measured over Day 180.

The primary endpoint is the number of participants with any of a set of Crohn’s disease-related events by Day 180. The composite includes hospitalization, surgery, an emergency-room visit, or a steroid prescription. A participant is counted if any one or more of those events occurs; the endpoint does not report each component separately in the posted primary result.

Composite endpoints are used in clinical research to capture a broader set of events under one outcome. In general, this can make an endpoint reflect several ways a condition may lead to healthcare use or treatment escalation. Interpretation depends on the components being clinically meaningful and sufficiently clear, and on understanding whether one component contributes much more than the others. Those component-specific results are not reported in the posted primary endpoint.

The endpoint is reported as a count of participants, not as a time-to-event measure or a rate. The registry identifies Day 180 as the presented timeframe and says the original plan also included Day 360. However, it states that only 1 subject remained in the study to Day 180. The reported high-dose value is 0.0 participants, while the low-dose endpoint count is 0.0 and its value is missing. As a result, the posted data do not provide a two-arm comparison of the composite endpoint.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is binary at the participant level: each participant either had at least one listed event or did not. The registry reports the number of participants with an event, rather than an event rate or a continuous measurement. In general, a binary endpoint can be compared between randomized arms by estimating a difference in event proportions or by using a model suited to binary data. Such analyses require usable outcome information for both arms. The posted primary outcome does not provide that information for this comparison.

What does the reported count describe?

The high-dose primary result has a participant count of 1.0 and a value of 0.0. The low-dose result has a participant count of 0.0 and no outcome value. The registry’s skip note states that values are missing or not estimable for a two-arm comparison of the binary endpoint. It would not be appropriate to infer a treatment contrast from the available entries, or to treat the missing low-dose value as an observed outcome.

In general, an estimated effect is a comparison between groups, while an arm-specific count describes only that arm’s observed data. A comparative estimate needs data from each group and a defined statistical method. No comparative estimate, confidence interval, or p-value is reported for this primary endpoint. The statistical analysis used by the sponsor, if any, is not reported in the registry record.

Why do confidence intervals matter?

In general, a confidence interval expresses statistical uncertainty around an estimated effect. A narrow interval indicates greater precision under the method’s assumptions, while a wide interval indicates less precision. It does not give the probability that a particular treatment effect is true. Because this record does not contain an estimable two-arm primary contrast, there is no interval with which to judge the precision of that contrast.

For a binary endpoint, uncertainty is affected by the number of participants with outcome data and by how many experience the event. When observations are sparse, estimates can be unstable and conventional approximations may perform poorly. Here, the central issue is more basic: the registry does not report a low-dose endpoint value, so a two-arm estimate is not available. No alternative method for handling this situation is reported.

What can planning calculations say?

General sample-size calculations estimate how many participants would be needed under stated assumptions to detect a specified effect with a chosen statistical procedure. They are planning illustrations, not observed power and not evidence that a completed trial was adequately powered. The record’s stated planning assumptions describe a two-sided significance level of 0.05, equal allocation between arms, a normal approximation, and effects expressed as a fraction of the observed effect. For outcomes other than time-to-event outcomes, such planning values are described as participants per arm.

Those assumptions do not establish the trial’s original design rationale. The registry record does not report the trial’s own sample-size justification or a target enrollment rationale. In addition, an observed-effect-based illustration depends on having an interpretable observed effect. The primary endpoint lacks an estimable two-arm comparison, so it cannot substantiate a planning interpretation of the treatment contrast. Any illustration should not be mistaken for the number of participants actually enrolled or followed through Day 180.

How should the design fields be understood?

Randomized allocation and double masking are listed, and the record lists both a low-dose and high-dose arm. The model is also labeled single group. These entries do not align cleanly. The registry does not explain the mismatch, so the record does not permit a more specific characterization of the design than its fields and arm descriptions support. The arm descriptions also contain truncated text about masking and repeat dosing; their full procedures are not reported.

The primary outcome combines several event types. In general, a composite can be analyzed as a binary outcome when each participant is classified according to whether any component occurred. Component-level counts are important for interpretation because the composite alone does not reveal which event type contributed to the result. The registry describes the components, but the posted primary value does not supply separate component results or a two-arm composite comparison.

No adjusted model, covariate set, handling of repeated measurements, or missing-data procedure is reported for this outcome. The registry lists 0 analyses. These omissions limit the ability to reproduce or evaluate a statistical analysis; they do not justify assuming that no analysis was conducted outside the registry. The posted data support a narrow descriptive reading, not a conclusion about comparative effectiveness or the precision of a treatment effect.

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("High Dose Vitamin D")
n      <- c(1)
events <- c(0)
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  High Dose Vitamin D  1  0  0.0  0.0  97.5  0.0  79.3  1.3  84.2

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 13 outcome measures and 10 posted secondary results. The listed secondary outcomes include Crohn’s-related hospitalizations, steroid prescriptions, surgeries, changes in the Modified Harvey-Bradshaw Index, C-reactive protein and fecal calprotectin, escalation of therapy, and quality-of-life measures. The registry does not report a multiplicity adjustment, a hierarchy for testing secondary outcomes, or a detailed statistical plan specifying how multiple outcomes would be interpreted. Without such information, the risk of chance findings across multiple analyses cannot be evaluated from the registry record.

The primary endpoint itself is not available as a complete two-arm comparison: the high-dose arm reports 1.0 endpoint participant and 0.0 participants with an event, while the low-dose arm has no endpoint value. The endpoint description says only 1 subject remained in the study to Day 180. The reasons for missing endpoint information, the handling of participants who did not remain through that assessment, and the analysis population are not reported in the registry record.

The registry does not report whether the primary analysis was intended to follow an intention-to-treat principle, a per-protocol principle, or another population definition. It also does not report imputation, sensitivity analyses, or methods for handling missing observations. These are important distinctions: in general, the analysis population and missing-data approach can affect how a randomized comparison is interpreted. No such approach can be inferred from the posted outcome entries.

12. Safety Results

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

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent non-serious adverse event terms

The safety record separates serious adverse events, other adverse events, and deaths by arm. In the low-dose group, the registry reports 0 serious adverse events among 6 participants at risk, 0 other adverse events among 6 participants at risk, and 0 deaths. In the high-dose group, it reports 0 serious adverse events among 5 participants at risk, 1 other adverse event among 5 participants at risk, and 0 deaths.

These are descriptive counts for the safety categories as recorded. The listed serious-event terms are empty. The registry does not report further details about the other adverse event in the high-dose group, such as its nature, timing, severity, or relationship to the study intervention. The record also does not explain how safety follow-up relates to the limited Day 180 primary endpoint follow-up.

Zero recorded serious adverse events does not establish that serious events could not occur, and the other-event count alone does not establish causation. With the small at-risk groups listed and limited detail, these counts should not be treated as a precise estimate of comparative safety.

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

The posted primary outcome supports a limited descriptive statement: among the 1.0 participant with a reported high-dose Day 180 endpoint, the recorded number with any qualifying event was 0.0. The low-dose arm has no reported endpoint value. The registry therefore does not provide the central information needed to compare the randomized arms on the primary composite.

This result does not establish that high-dose vitamin D reduces, increases, or has the same effect on Crohn’s disease-related hospitalizations, surgeries, emergency-room visits, or steroid prescriptions relative to low-dose vitamin D. It also does not answer whether the intervention affects each composite component separately. No comparative effect estimate, confidence interval, or p-value is reported, so neither the direction nor the precision of a group difference can be assessed.

The registry’s status is terminated, and it states that only 1 subject remained in the study to Day 180. The reason for termination and the reasons participants did not contribute Day 180 endpoint data are not reported in the registry record. Those missing details prevent an assessment of whether endpoint availability was related to treatment, outcome, or other factors. They should not be replaced with assumptions.

More broadly, the record contains design and reporting uncertainties: the randomized, double-masked descriptors appear alongside a single-group model designation, and the arm descriptions are truncated. The safety counts are descriptive and do not supply additional evidence about the primary comparative question. The appropriate statistical conclusion is therefore about limitations of the posted evidence: the primary endpoint result is incomplete for the randomized comparison, and the record does not establish a comparative treatment effect.

14. Why This Trial Matters Statistically

This trial illustrates how a registry result can be difficult to interpret even when a primary endpoint and intervention arms are identified. A randomized comparison depends on outcome information from the groups being compared. Here, only the high-dose arm has a reported Day 180 primary endpoint value, and the record says only 1 subject remained to that assessment. Without a low-dose endpoint value, a comparative estimate cannot be formed from the posted results.

The example also shows why an endpoint’s definition and its observed data must be considered together. The composite groups several clinically relevant event types, but the result does not provide separate component counts or a complete comparison of the composite between arms. Even a clearly defined endpoint cannot answer the comparative question when the underlying outcome data are incomplete in the registry.

Statistical interpretation also depends on transparent reporting of design and analysis decisions. Randomized allocation and double masking are listed, but the single-group model designation is not reconciled. The record does not report the analysis population, missing-data procedure, multiplicity approach, or detailed statistical analysis plan. These gaps constrain reproducibility and make it difficult to distinguish planned analyses from descriptive reporting.

Finally, the safety counts demonstrate the difference between reporting a count and establishing a precise safety comparison. The registry records no serious adverse events in either group and one other adverse event in the high-dose group, but the at-risk groups are limited and event details are sparse. These observations are useful as registry entries, not as a definitive comparative safety assessment. The statistical lesson is to separate what was recorded from what the data can support.

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 important trial-specific limitation is the incomplete Day 180 primary endpoint information. The endpoint description states that only 1 subject remained in the study to Day 180. The posted primary result reports 1.0 participant and 0.0 events for the high-dose arm, while no endpoint value is reported for the low-dose arm. This prevents the intended arm comparison from being evaluated. A Day 360 result is not reported in the posted primary data, although the endpoint description says that Day 360 had originally been planned.

The registry lists an enrollment of 11 and a terminated status, but does not explain the termination or participant follow-up. It does not report why endpoint data are missing, whether missingness differed by arm, or how missing outcomes were handled. The analysis population and statistical procedure are also not reported. Consequently, the relationship between the enrolled population, the safety groups, and the single Day 180 endpoint observation cannot be fully assessed from the record.

There are further reporting limitations. The design is described as randomized and double-masked, yet the model is labeled single group. The record does not reconcile those descriptions. The treatment-arm descriptions are truncated, so the full dosing and masking procedures are not available. The registry does not report a sample-size justification, a detailed analysis plan, or a multiplicity approach. Component-level primary outcome results and details of the single other adverse event are also not reported.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Trial of High Dose Vitamin D in Patient's With Crohn's Disease — NCT02208310.
• Registry record last updated 2017-10-06; status last verified 2017-08.
• Results first posted 2017-10-06.
• 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

NCT02208310 is a University of Michigan Phase 4 randomized controlled trial of vitamin D supplementation in Crohn’s disease, listed as terminated. The registry describes double masking and randomized allocation, while also labeling the model single group. The listed arms are Low Dose Vitamin D, using cholecalciferol 400 IU, and High Dose Vitamin D, using cholecalciferol 10,000 IU.

The primary endpoint is the number of participants with any Crohn’s disease-related hospitalization, surgery, emergency-room visit, or steroid prescription by Day 180. The high-dose arm has a reported endpoint count of 1.0 and a value of 0.0; the low-dose arm has no endpoint value. The record says only 1 subject remained to Day 180. No two-arm primary comparison is estimable from the posted outcome entries.

The record lists 13 outcome measures and 10 posted secondary results. It does not report the reason for termination, detailed statistical methods, or the handling of missing endpoint data.