Study to Evaluate the Efficacy and Safety of Filgotinib in the Treatment of Small Bowel Crohn's Disease (SBCD): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study to Evaluate the Efficacy and Safety of Filgotinib in the Treatment of Small Bowel Crohn's Disease (SBCD) (NCT03046056), a randomized phase 2 study. The primary outcome is Percentage of Participants Who Achieved Clinical Remission at Week 24.

2. Clinical Question

3. Trial Design

The registry record describes a randomized, double-blind, placebo-controlled, parallel-group Phase 2 study of filgotinib in small bowel Crohn's disease. The three groups were filgotinib 200 mg, filgotinib 100 mg, and placebo. Enrollment was 78 participants. The primary analysis population included randomized participants who received at least one dose of study drug.

The registry record gives the study start as 2017-04-11 and primary completion as 2020-07-20, with the overall status listed as completed. Treatment was specified for up to 27 weeks in the 200 mg group, up to 26.3 weeks in the 100 mg group, and up to 28.7 weeks in the placebo group. The primary endpoint was assessed at Week 24.

The study's design was intended to compare each filgotinib dose group with placebo. This produces two treatment-versus-control comparisons, not a direct comparison between the two filgotinib doses. The registry record does not report the randomization procedure, allocation ratio, sequence-generation method, or details about how masking was maintained. The record also does not report the original sample-size justification or the assumptions used to plan enrollment.

The registry record describes an option for participants to enter a separate long-term extension study if they met its eligibility requirements. That extension is distinct from the Week 24 comparison addressed by the primary endpoint. Its outcomes and eligibility details are not reported in the registry record. As a Phase 2 trial, these results describe the evidence in this study population and are not, by themselves, a complete account of longer-term outcomes or of findings in other populations.

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: 198 participants were screened.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set included all the randomized participants who received at least one dose of the study drug.

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.

Population: Safety Analysis Set included all participants who received at least 1 dose of study drug.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Who Achieved Clinical Remission at Week 24, measured over Week 24.

The primary endpoint was the percentage of participants who achieved clinical remission at Week 24. Remission was defined by a CDAI score < 150. The CDAI is used to quantify Crohn's disease symptoms; the registry record states that its scores range from 0 to 600 and that higher scores indicate more severe disease.

This endpoint turns each participant's Week 24 CDAI status into a binary outcome: the participant either met the remission threshold or did not. The group result is therefore a percentage, rather than a mean change in CDAI. A threshold-based outcome can make a clinical state easier to describe, but it does not show how close participants who did not meet the threshold came to it, or how much individual scores changed over time.

For each group, the registry reports the percentage in remission and a 90% confidence interval. The registry reports risk differences for the treatment-versus-placebo comparisons. A risk difference expresses the difference between the two group percentages in percentage-point terms. General statistical point: the group percentages describe the observed trial participants, while the interval communicates uncertainty about the underlying difference that could be compatible with the data.

The endpoint is specific to the Week 24 assessment. It does not, on its own, describe remission at other time points, changes in each person's symptoms, or longer-term outcomes. The registry record does not report the statistical model or detailed procedures used for the sponsor's primary analysis.

7. Results Posted in the Registry

• Filgotinib 200 mg: 25.0% (7/28) versus 16.7% (3/18) on control; risk difference 8.3 percentage points (95% CI -15.2 to 31.9), risk ratio 1.50 (0.44–5.06); unadjusted two-proportion z-test p = 0.504.
• Filgotinib 100 mg: 25.0% (8/32) versus 16.7% (3/18) on control; risk difference 8.3 percentage points (95% CI -14.5 to 31.2), risk ratio 1.50 (0.45–4.95); unadjusted two-proportion z-test p = 0.495.

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.

Change From Baseline in Terminal Ileum Segmental Magnetic Resonance Index of Activity (MaRIA) Score at Week 24

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • Filgotinib 200 mg: mean -1.80 versus 0.50 on control; difference -2.30 (95% CI -6.67 to 2.07), standardized effect d = -0.30; z-test p = 0.302.
  • Filgotinib 100 mg: mean 0.70 versus 0.50 on control; difference 0.20 (95% CI -4.01 to 4.41), standardized effect d = 0.03; z-test p = 0.926.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Filgotinib 200 mg and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Filgotinib 100 mg and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Distal Ileum Segmental MaRIA Score at Week 24

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • Filgotinib 200 mg: mean -1.10 versus 0.50 on control; difference -1.60 (95% CI -4.90 to 1.70), standardized effect d = -0.28; z-test p = 0.343.
  • Filgotinib 100 mg: mean -0.50 versus 0.50 on control; difference -1.00 (95% CI -4.25 to 2.25), standardized effect d = -0.17; z-test p = 0.547.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Filgotinib 200 mg and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Filgotinib 100 mg and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Jejunum Segmental MaRIA Score at Week 24

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • Filgotinib 200 mg: mean 0.40 versus 0.50 on control; difference -0.10 (95% CI -3.04 to 2.84), standardized effect d = -0.02; z-test p = 0.947.
  • Filgotinib 100 mg: mean 0.60 versus 0.50 on control; difference 0.10 (95% CI -2.78 to 2.98), standardized effect d = 0.02; z-test p = 0.946.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Filgotinib 200 mg and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Filgotinib 100 mg and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists 14 posted secondary outcomes, including segment-specific changes in MaRIA scores and percentages achieving MaRIA remission or response. Numerical comparison details are available for the terminal ileum, distal ileum, and jejunum MaRIA change outcomes. Across these segments, the estimated treatment-versus-placebo contrasts do not show a consistent pattern across both dose groups and all locations. The estimates and their 90% confidence intervals are broad, and the intervals include zero.

These secondary outcomes address magnetic resonance measures of disease activity in different bowel segments, rather than the primary endpoint of clinical remission defined by CDAI at Week 24. They can provide complementary information about imaging outcomes, but they do not answer the same question as the primary endpoint. Their overall pattern does not remove the uncertainty in the primary remission comparisons, nor should it be read as a separate confirmation of a treatment effect.

Secondary results carry less interpretive weight when many outcomes and comparisons are examined without a reported adjustment for multiplicity. The registry record does not report whether such an adjustment was used or whether the outcomes followed a prespecified testing hierarchy. General statistical point: examining many results can increase the chance that some appear notable by chance alone. For that reason, secondary findings are best treated as supportive or exploratory unless the analysis plan establishes how they were to be interpreted.

Although the registry record lists additional secondary outcomes, their detailed numerical results are not reported in the registry record. The overall reading must therefore remain limited to the available endpoint descriptions and the segmental MaRIA comparisons. The secondary findings should be considered alongside, but not substituted for, the primary endpoint and its uncertainty.

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

• Change From Baseline in Terminal Ileum Segmental Magnetic Resonance Index of Activity (MaRIA) Score at Week 24
• Change From Baseline in Distal Ileum Segmental MaRIA Score at Week 24
• Change From Baseline in Jejunum Segmental MaRIA Score at Week 24
• Percentage of Participants Who Achieved MaRIA Remission in Terminal Ileum Segment at Week 24
• Percentage of Participants Who Achieved MaRIA Remission in Distal Ileum Segment at Week 24
• Percentage of Participants Who Achieved MaRIA Remission in Jejunum Segment at Week 24
• Percentage of Participants Who Achieved MaRIA Response in Terminal Ileum Segment at Week 24
• Percentage of Participants Who Achieved MaRIA Response in Distal Ileum Segment at Week 24

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is binary because each participant either met the CDAI remission criterion at Week 24 or did not. For a binary outcome, a group percentage is the proportion of participants with the event of interest. The primary results report the percentages for each group, along with 90% confidence intervals. Those group-level intervals describe uncertainty in each percentage; they are not the same as the confidence interval for a treatment-versus-placebo contrast.

The registry's treatment comparisons use a risk difference in proportions. In plain language, this is the percentage achieving remission in a filgotinib group minus the percentage achieving remission in the placebo group. A value above zero indicates a higher observed remission proportion in the filgotinib group; a value below zero indicates a higher observed proportion in placebo. A value of zero corresponds to equal observed proportions. The sponsor reports a risk difference of 8.3 for each comparison, with 90% confidence intervals that extend below and above zero.

The recalculated contrasts use the posted event counts and group sizes. They are simple, unadjusted re-calculations from summary data, not reconstructions of the sponsor's full analysis. The corresponding unadjusted p-values are 0.504 and 0.495. A p-value is a measure of how compatible the observed data are with a specified null hypothesis under the assumptions of a statistical test; it is not the probability that the null hypothesis is true. These recalculated p-values are not reported as the sponsor's own p-values, and the registry record does not give sponsor p-values for the primary contrasts.

General statistical point: a confidence interval is a range of estimates compatible with the data under the method used to construct it. Wider intervals indicate less precision. For a difference, an interval spanning zero includes no observed group difference among the values compatible with the data. It can also include differences in either direction, so it does not show that the groups are equivalent. The specific interval method used by the sponsor is not reported in the registry record.

The primary comparison is between each dose group and placebo. The registry also reports many secondary outcomes, including change in MaRIA scores by small-bowel segment and percentages meeting segment-specific MaRIA response or remission criteria. The continuous MaRIA comparisons are reported as least-squares mean differences, with 90% confidence intervals. A least-squares mean is an adjusted mean from a statistical model, but the model and the covariates used for these estimates are not reported in the registry record. The values should therefore be interpreted as registry-reported model-based estimates, without assuming particular adjustment details.

For the recalculated continuous comparisons, the standard deviations are approximated from the posted standard errors and group sizes. General statistical point: over-dispersion means that outcomes vary more than a simpler statistical model expects. If a binary outcome is more variable than the model assumes, standard errors and confidence intervals can be too small unless the analysis accounts for that extra variability. The registry record does not report whether or how over-dispersion was assessed for the primary binary endpoint, so no conclusion about that issue can be drawn for this trial.

The analysis population is described as the Full Analysis Set, defined as all randomized participants who received at least one dose of study drug. That definition excludes randomized participants who did not receive any study drug. The registry record does not report the number of participants excluded under that definition, details of how missing Week 24 outcomes were handled, or whether any sensitivity analyses were performed. These omissions matter because the interpretation of a binary endpoint can depend on how missing outcomes are treated.

The registry record does not report the sponsor's statistical analysis method for the primary endpoint, its exact confidence-interval procedure, prespecified covariates, interim analyses, or the original sample-size calculation. The posted re-calculations and planning illustrations should not be mistaken for those missing protocol details. General statistical point: the method used to calculate an interval or test affects its properties, especially in small samples. Where the method is unreported, the posted estimates can be described, but the analysis procedure cannot be independently reconstructed from summary statistics alone.

There are two treatment-versus-placebo comparisons for the primary outcome, and the record lists 15 outcome measures and 29 analyses. The registry record does not report a multiplicity adjustment or a prespecified hierarchy for interpreting the outcomes. When many outcomes or contrasts are examined, the chance of at least one apparently notable result can increase. This is one reason to give the prespecified primary endpoint greater interpretive weight than the secondary findings, while recognizing that the registry record does not give the full analysis plan needed to verify all prespecification details.

11. Confidence Intervals and Precision

The primary endpoint estimates are imprecise. The 90% confidence intervals for the remission percentages are broad: 12.4 to 41.9 for filgotinib 200 mg, 13.1 to 40.6 for filgotinib 100 mg, and 4.7 to 37.7 for placebo. This width reflects substantial uncertainty about the underlying group percentages, beyond the percentages observed among trial participants.

The treatment-versus-placebo risk-difference intervals are also broad. For the sponsor-reported analyses, the 200 mg comparison has a 90% confidence interval from -16.5 to 32.1, and the 100 mg comparison has a 90% confidence interval from -15.9 to 32.0. Each interval contains zero and includes values on both sides of zero. The data are therefore compatible with a range of possible differences, including no difference and differences favoring either group. The estimates do not locate the treatment contrast precisely.

General statistical point: a confidence interval is about uncertainty in an estimate, not a range containing a fixed proportion of individual participants' outcomes. A narrower interval generally indicates greater precision, while a wider interval indicates less precision. Precision depends on factors such as the amount of information in the data and the variability of the outcome. In this trial, the group sizes were 28, 32, and 18, and the primary endpoint is a percentage based on whether each participant crossed a threshold.

The recalculated intervals differ somewhat from the sponsor-reported intervals. The recalculated interval for the 200 mg risk difference is -0.152 to 0.319, and for the 100 mg risk difference it is -0.145 to 0.312. The registry record does not identify the sponsor's interval method, so the reason for the difference cannot be specified from the record. Both sets of intervals communicate substantial uncertainty and include zero; neither supports a precise estimate of the contrast.

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 observed effects, not the trial's original enrollment plan. For this binary primary outcome, the figures are participants per arm, not total events. Each row uses a different fraction of the observed effect: 100%, 75%, or 50%. The primary comparison's illustrations show that planning for 100% of the observed effect gives 372 participants per arm for 80% power and 498 participants per arm for 90% power. For 75% of the observed effect, the figures are 637 and 852 participants per arm; for 50%, they are 1,377 and 1,842 participants per arm.

The listed calculation 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 the stated fraction of the observed effect. These assumptions describe the planning illustration; the trial's own design assumptions and original sample-size justification are not reported in the registry record. Figures for continuous secondary outcomes are also reported as participants per arm. Time-to-event sample-size displays, if present, use total events, but the primary endpoint is binary rather than time-to-event.

The 80% power column gives the estimated participants per arm under the stated assumptions for a design with an 80% chance of detecting the specified effect if that effect is the true one. The 90% power column describes the corresponding planning target for a 90% chance. Higher power generally requires more participants under otherwise unchanged assumptions. The curve should be read as a visual representation of how the planning requirement changes with the effect size being targeted; the numerical assumptions and values, rather than a visual estimate, are the basis for interpreting the calculation.

Smaller effects require more participants to detect with the same power, which is why the figures rise as the assumed effect fraction declines. These calculations are not observed power: they do not measure the probability that the completed trial detected a real effect. They are conditional planning illustrations, and their large figures relative to the enrolled groups emphasize how uncertain small-study estimates can be.

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 = 0.167; treatment proportion p₁ = 0.250; average p̄ = 0.208.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5743 = 1.1257.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5713 = 0.4808.
4. n = (1.1257 + 0.4808)² / (0.0833)² = 371.6, rounded up to 372 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 <- 0.166666666666667                          # control proportion
p1 <- 0.25                          # 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(3046056)
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 = 372 (80% power), 498 (90% power)
 75% of observed effect: n per arm = 637 (80% power), 852 (90% power)
 50% of observed effect: n per arm = 1,377 (80% power), 1,842 (90% power)
power.prop.test: 371.6 
Simulated power at n = 372 per arm: 0.805 (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

The registry's own primary analyses report risk differences of 8.3 percentage points for filgotinib 200 mg versus placebo and 8.3 percentage points for filgotinib 100 mg versus placebo. Their 90% confidence intervals are -16.5 to 32.1 and -15.9 to 32.0, respectively. The sponsor's reported analyses do not include p-values in the registry record.

The re-calculations use the posted remission counts and group sizes to produce simple, unadjusted estimates. They give risk differences of 0.083 for both comparisons, with unadjusted p-values of 0.504 and 0.495. Their intervals are -0.152 to 0.319 for the 200 mg comparison and -0.145 to 0.312 for the 100 mg comparison. These intervals are not identical to the registry-reported intervals.

The registry record does not identify the sponsor's statistical method, so the differences between the intervals cannot be attributed to a particular method from the record. There is no stated discrepancy flag for the primary results. The re-calculation is useful as a check based on summary counts, but it does not replace the sponsor's reported analysis or reproduce an analysis that may have used participant-level data or model details not reported in the record. The sponsor's analysis is the relevant registry-reported result; the recalculation is an additional, unadjusted reading of the posted summaries.

15. Multiplicity, Missing Data and Analysis Populations

The registry record lists 15 outcome measures and 29 analyses. The primary outcome has two planned treatment-versus-placebo comparisons in the posted results, and the secondary outcomes include several segmental imaging measures and response or remission percentages. When a study examines multiple outcomes or comparisons, the chance of observing a seemingly notable result by chance can rise. This issue is called multiplicity.

The registry record does not report whether the sponsor adjusted for multiplicity, set a hierarchy for testing endpoints, or designated which secondary analyses were confirmatory versus exploratory. It also does not report enough of the statistical analysis plan to determine how the testing strategy was prespecified. The sponsor's reported primary confidence intervals should therefore be described as posted, without assuming that they account for other outcomes or comparisons. The recalculated p-values are explicitly unadjusted and should not be interpreted as multiplicity-controlled evidence.

The primary outcome population is defined as randomized participants who received at least one dose of study drug. The registry record does not report the number of randomized participants who did not receive a dose, if any, or how missing Week 24 CDAI assessments were handled. It also does not report the number of participants with missing endpoint data, the assumptions used for any imputation, or sensitivity analyses addressing missingness. Missing outcome data can affect both the estimated percentages and the confidence intervals, particularly when the endpoint is classified according to a threshold.

The registry record does not report the full analysis populations for each secondary endpoint, the handling of missing imaging assessments, or whether participants with incomplete segment data were analyzed differently. Those details would be useful for assessing how much information contributed to each secondary comparison. Without them, the posted results can be described, but the robustness of the analyses to missing data or alternative analysis decisions cannot be evaluated from the registry record.

These omissions do not prove that an adjustment or missing-data procedure was not used; they mean that the procedure is not reported in the registry record. Interpretation should distinguish reported estimates from assumptions about how they were generated.

16. 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 serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: crohn's disease (12.5%), small intestinal obstruction (7.1%), ileus (3.1%), anal abscess (3.1%), pneumonia (3.1%).

The registry reports serious adverse events among 4 participants in the filgotinib 200 mg group, 7 participants in the filgotinib 100 mg group, and 0 participants in the placebo group. The corresponding numbers at risk were 28, 32, and 18. These are counts of participants affected, not counts of all individual serious-event episodes. The registry also lists serious adverse event terms, including Crohn's disease, small intestinal obstruction, ileus, anal abscess, and pneumonia, with percentages recorded for those terms.

One death is recorded in the filgotinib 200 mg group; zero deaths are recorded in the filgotinib 100 mg and placebo groups. For other adverse events, the registry reports 20 participants affected in the 200 mg group, 24 in the 100 mg group, and 13 in the placebo group. The serious adverse event and death figures are descriptive counts from groups of different sizes. They do not establish why an event occurred or whether it was caused by study treatment.

These group sizes and counts are not sufficient to support strong comparative conclusions about safety. The registry record does not provide further detail about event timing, severity categories beyond seriousness, relatedness assessments, or the statistical methods for safety comparisons. The findings should be read as the adverse-event information recorded for this trial, not as a complete estimate of risk in other populations or over longer follow-up.

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

The primary results describe the percentage of participants in each trial group who met the Week 24 CDAI remission threshold. The observed remission percentages were 25.0% in both filgotinib dose groups and 16.7% in the placebo group. The sponsor-reported risk differences were 8.3 percentage points for each filgotinib group compared with placebo, but both 90% confidence intervals include zero and span differences in either direction.

That pattern means the observed percentages were numerically higher in the filgotinib groups, while the estimates remain too imprecise to establish a clear difference from placebo. It does not establish that the treatments are equivalent, nor does it establish that a difference is absent. The trial's enrolled groups were limited in size, and the confidence intervals allow a broad range of underlying contrasts.

The endpoint captures whether a participant crossed a CDAI threshold at Week 24. It does not convey the full distribution of CDAI scores, the degree of change for participants who did not reach remission, or the persistence of remission at later times. The imaging outcomes address a different aspect of disease activity and should be interpreted as secondary evidence, with the additional caution that multiplicity handling is not reported in the registry record.

The safety counts provide a record of serious adverse events and deaths observed in the study groups, but they cannot establish causality or characterize uncommon or longer-term risks with precision. The trial's design and follow-up do not, from the registry information alone, answer every question about longer-term outcomes. The possible separate extension study is noted in the record, but its results are not reported in the registry record.

Overall, the registry supports a cautious description: remission percentages were observed in all three groups, and the treatment-versus-placebo estimates were uncertain. The results are not a basis for medical advice, and they should not be generalized beyond the study's participants without additional evidence.

18. Why This Trial Matters Statistically

This trial illustrates how a binary endpoint can be easy to state while still producing substantial uncertainty. Clinical remission was defined by a CDAI threshold, and the results can be expressed as percentages and risk differences. Yet the number of participants in each group was limited, and the confidence intervals for the differences are wide. A concise point estimate should therefore not be mistaken for a precise estimate.

It also demonstrates the value of distinguishing group percentages from between-group contrasts. A higher observed percentage in a treatment group is not, by itself, evidence of a precise treatment-placebo difference. The contrast and its interval directly address the comparative question. Here, the sponsor-reported intervals include zero, so the posted estimates remain compatible with no difference as well as differences in either direction.

The record further shows why analysis plans matter. The study includes multiple secondary outcomes and analyses, but multiplicity procedures, missing-data handling, and several primary-analysis details are not reported. Those omissions constrain how far readers can interpret secondary findings and how fully they can reproduce the sponsor's analysis from the registry.

Finally, planning illustrations based on observed effects reveal a general design challenge: smaller target effects require larger samples for the same power under the stated assumptions. Such illustrations can help researchers think about precision and future study planning, but they do not substitute for an original, prospectively justified sample-size calculation. The distinction between planning calculations and observed trial evidence is central to sound interpretation.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

Several limitations specific to this trial affect interpretation of the posted results. The primary outcome is based on a threshold, CDAI < 150, so the remission percentage does not show the distribution of scores or the size of changes among participants who did not meet that criterion. The primary assessment is at Week 24; the record does not provide a longer-term result for this endpoint.

The groups were relatively small: the primary endpoint analysis includes 28 participants in the filgotinib 200 mg group, 32 in the filgotinib 100 mg group, and 18 in the placebo group. As reflected in the broad confidence intervals, the treatment-placebo contrasts are not estimated precisely. The trial's original sample-size assumptions and justification are not reported in the registry record, so the planned precision or power cannot be assessed from the posted information.

The registry does not report the sponsor's detailed primary analysis method, the procedure used to construct its confidence intervals, or whether any covariate adjustment was made. It also does not report the missing-outcome counts, the handling of missing Week 24 assessments, or sensitivity analyses. These gaps limit independent evaluation of the analysis choices and their effects.

Multiplicity handling is not reported despite the many outcomes and analyses. Some secondary endpoint results are not reported in the registry record, and the available imaging measures do not substitute for the primary clinical endpoint. Safety event counts are descriptive and come from small groups; the registry information does not establish event causality or provide a precise comparison of risks. These limitations call for careful interpretation, not assumptions about procedures that the record does not describe.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study to Evaluate the Efficacy and Safety of Filgotinib in the Treatment of Small Bowel Crohn's Disease (SBCD) — NCT03046056.
• Registry record last updated 2021-08-23; status last verified 2021-08.
• Results first posted 2021-08-09.
• 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

NCT03046056 is a completed, randomized, double-blind, placebo-controlled, parallel-group Phase 2 study of filgotinib in small bowel Crohn's disease. The registry reports enrollment of 78 participants and a primary endpoint of clinical remission at Week 24, defined as CDAI < 150. Participants were assigned to filgotinib 200 mg, filgotinib 100 mg, or placebo.

The observed remission percentages were 25.0% in each filgotinib group and 16.7% with placebo. The sponsor-reported risk differences were 8.3 percentage points for both dose comparisons, with 90% confidence intervals spanning zero. The primary estimates are therefore uncertain. Segmental MaRIA measures and adverse events were also recorded, but multiplicity procedures, missing-data handling, and several details of the statistical plan are not reported in the registry record.