Study to Assess the Efficacy and Safety of Umbralisib in Participants With Non-Follicular Indolent Non-Hodgkin's Lymphoma: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study to Assess the Efficacy and Safety of Umbralisib in Participants With Non-Follicular Indolent Non-Hodgkin's Lymphoma (NCT03364231), a non-randomized phase 2 study. The primary outcome is Overall Response Rate (ORR) as Assessed by Revised Response Criteria for Non- Hodgkin's Lymphoma (Lugano Classification) and Consensus-Based 6th International Workshop on Waldenstrom's Macroglobulinemia (IWWM).

2. Clinical Question

3. Trial Design

This completed Phase 2 study evaluated umbralisib monotherapy in non-follicular indolent non-Hodgkin's lymphoma. The registry lists an enrollment of 21 participants and describes two histology groups: MZL and WM. Participants in each group received umbralisib at 800 mg orally once daily. Treatment was to continue until disease progression, unacceptable toxicity, or withdrawal from the study, whichever occurred first.

The study was non-randomized, unmasked, and single-group. It did not include a randomized control arm, and the two histology groups are not control and treatment arms. Differences between their results, if reported, could reflect differences in disease type and participant characteristics as well as other factors; they would not constitute a randomized estimate of a treatment effect.

The primary endpoint was ORR, with response criteria adapted to the diagnosis: Lugano criteria for MZL and IWWM criteria for WM. The registry specifies assessment every 3 cycles, with 1 cycle lasting 28 days, beginning on Day 1 Cycle 1 and continuing up to approximately 4.2 years. Secondary outcomes listed were complete response rate, progression-free survival, time to treatment failure, and the number of participants with at least one adverse event.

The registry lists the study start as 2017-11-30, primary completion as 2022-02-15, and status as completed. It does not report a randomized comparison, an untreated control, or an active comparator. The registry record does not report further protocol details about recruitment, follow-up after treatment, or the reasons participants stopped treatment.

4. Participant Flow and Accounting

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

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: mITT population included all participants who received at least one dose of study treatment and provided at least some post baseline efficacy assessment.

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 population included all enrolled participants who received at least one dose of study treatment.

6. Primary Endpoint

The registry lists the primary outcome as Overall Response Rate (ORR) as Assessed by Revised Response Criteria for Non- Hodgkin's Lymphoma (Lugano Classification) and Consensus-Based 6th International Workshop on Waldenstrom's Macroglobulinemia (IWWM), measured over Every 3 cycles (1 Cycle = 28 days) from Day 1 Cycle 1 up to approximately 4.2 years.

ORR is the proportion of participants meeting the study's definition of response. It combines specified response categories into a single measure of tumor response, but the categories differ across the two histology groups. For MZL, the endpoint counts complete response (CR) or partial response (PR) according to the revised Lugano Classification. For WM, it counts CR, PR, very good partial response (VGPR), or minor response (MR) according to the consensus-based 6th International Workshop on Waldenstrom's Macroglobulinemia criteria.

The criteria describe changes in disease evidence and measurements. Under Lugano criteria, CR requires disappearance of all evidence of disease and disease-related symptoms; PR requires regression of measurable disease without new disease sites. In the WM criteria, response categories are based in part on changes in serum monoclonal immunoglobulin M (IgM), alongside disease regression for PR. The endpoint is assessed every 3 cycles, with 1 cycle lasting 28 days, from Day 1 Cycle 1 up to approximately 4.2 years.

In general, a response rate can describe how frequently participants met a defined response threshold during assessment. It does not by itself describe how long responses lasted, how a group would fare without treatment, or whether a treatment caused the responses. The registry record does not report an observed ORR or its 95% confidence interval, so the magnitude and precision of the primary result cannot be assessed from the posted results.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The endpoint is a percentage of participants with an event, where the event is meeting the study's histology-specific response definition. The registry names the endpoint as ORR and specifies a 95% confidence interval as its dispersion measure. It does not report the estimate or interval itself. Without these results, the response rate's numerical value and statistical precision cannot be evaluated.

What does the response percentage represent?

In general, a percentage for a binary outcome is based on counting participants classified as having or not having the outcome within a defined analysis population. For this study, the analysis population is described as the mITT population: participants who received at least one dose and provided at least some post-baseline efficacy assessment. The registry does not report how many participants met this definition or how participants with incomplete assessments were handled. No response count or response percentage is reported.

That definition matters because the denominator determines what a response percentage describes. An analysis limited to participants with post-baseline efficacy information may not include every enrolled participant. If assessment availability is related to participants' health, treatment duration, or other characteristics, the analyzed group could differ from the full enrolled group. This is a general consideration; the registry record does not report whether such differences occurred or how they were assessed.

What does the confidence interval add?

In general, a confidence interval communicates uncertainty around an estimated response percentage. It reflects the variability expected from observing a finite group of participants, under the statistical method and assumptions used. It does not capture every source of uncertainty, such as biases from a non-randomized design, and it is not a guarantee about an individual participant's outcome. Here, the registry names a 95% confidence interval but does not report its limits. No statement about interval width, precision, or compatibility with particular response rates can therefore be made.

Why are there different response rules?

The registry specifies the revised Lugano Classification for MZL and IWWM criteria for WM. These rules define which clinical and measurement changes count as CR, PR, VGPR, or MR. For example, Lugano CR refers to disappearance of all evidence of disease and disease-related symptoms; WM CR includes disappearance of serum monoclonal IgM protein by immunofixation with a normal serum IgM level. The endpoint combines response categories differently across histology groups. As a result, an ORR in one group is not necessarily a directly interchangeable measure with an ORR in the other.

In general, standard response rules help make outcome classification more consistent, but they do not remove judgment or measurement variability. The registry identifies the criteria and assessment timing but does not report assessor blinding, central review, or procedures for resolving disagreements. The study itself is listed as unmasked.

What can the single-group design estimate?

In general, an uncontrolled single-group study can describe outcomes observed among participants receiving the study treatment. It cannot, on its own, distinguish treatment effects from the natural course of disease, participant selection, changes in supportive care, or other influences. Random allocation to a comparator can help balance prognostic factors across groups; this study was non-randomized and has no control group. Its MZL and WM groups are disease subgroups, not randomized comparisons.

The registry lists a planning illustration based on a stated fraction of the observed effect, using a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. Such an illustration is a hypothetical planning calculation, not observed power and not evidence that the trial had a particular probability of finding an effect. Its equal-allocation assumption describes the calculation, not the actual single-group study design. The sample-size justification for the trial itself is not reported in the registry record.

What does the analysis record leave uncertain?

The registry lists no analyses. It does not report a test statistic, p-value, adjusted estimate, or model-based analysis for ORR. It also does not report the statistical method used to construct the stated confidence interval. General methods for a response percentage can rely on different interval procedures, with different behavior in small samples; the appropriate interpretation depends on the method actually used. Since that method and the interval are absent, they should not be inferred.

For outcomes such as progression-free survival and time to treatment failure, general analyses often depend on follow-up duration and event timing. The registry lists those outcomes but provides no numerical results, event counts, censoring details, or analysis methods. It is therefore not possible to assess their estimates or precision. Likewise, the adverse-event counts can be described as counts, but they do not supply a complete account of event severity, timing, duration, or attribution.

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("MZL: Umbralisib", "WM: Umbralisib")
n      <- c(8, 10)
events <- c(3, 3)
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  MZL: Umbralisib  8  3  37.5  8.5  75.5  13.7  69.4  13.7  70.1
ARM  WM: Umbralisib  10  3  30.0  6.7  65.2  10.8  60.3  10.9  61.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists several outcomes: ORR as primary, and CR rate, progression-free survival, time to treatment failure, and participants with at least one adverse event as secondary outcomes. It does not report how statistical testing across multiple outcomes or response categories was handled. In general, testing several hypotheses can increase the chance of at least one apparently unusual result by chance. Procedures such as prespecifying a primary test or adjusting for multiple comparisons can address different aspects of this issue, but the registry record does not say whether such procedures were used. No multiplicity adjustment should be assumed.

The primary endpoint description identifies an mITT population as participants who received at least one dose and had at least some post-baseline efficacy assessment. The size of that population, the number without post-baseline assessments, and the handling of missing or unevaluable response data are not reported in the registry record. In general, missing outcome data can affect an estimate if the probability of missingness is associated with response or prognosis. Methods can include specified rules for unevaluable participants or sensitivity analyses, but the record does not report these details.

The registry lists no analyses and does not report an analysis plan, a statistical analysis plan, or an approach to missing data. It also does not describe interim analyses or stopping rules. These omissions mean readers cannot determine from the registry record whether these issues were addressed elsewhere or how they might influence the posted findings. The listed mITT definition is useful, but it does not resolve the unreported denominator and missing-data questions.

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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: colitis (12.5%).

The registry reports serious adverse event counts separately by histology group. In the MZL group, 1 participant among 8 at risk had a serious adverse event; in the WM group, 0 participants among 13 at risk had one. The registry also lists colitis at 12.5% among the top serious event terms. That term-level percentage should be read as a reported safety detail, not as a complete description of all serious events or as evidence about cause.

These counts describe participants with at least one serious adverse event, rather than the total number of individual events. A participant may experience more than one event, and the counts alone do not show event timing, duration, severity beyond the serious classification, or whether investigators considered an event related to umbralisib. The registry record does not report those details in the information summarized for these counts.

Zero recorded participants with a serious adverse event in the WM group does not establish that serious events are impossible or that the risk is zero. In general, safety estimates from small groups can be imprecise, and the observed count is not a direct measure of risk in a broader population. The MZL and WM figures also should not be treated as a randomized comparison. The registry separately reports deaths as 1 in MZL and 0 in WM; these counts alone do not establish cause or relationship to study treatment.

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

The registry record establishes that a completed Phase 2, non-randomized, single-group study evaluated umbralisib monotherapy in participants with MZL or WM. It specifies the primary outcome, response criteria, assessment schedule, and an mITT population definition. It also reports safety counts for serious adverse events by histology group. These details help readers understand what the study was designed to assess and which participant groups were described.

The record does not report the observed ORR, its 95% confidence interval, or numerical results for the listed secondary outcomes. It therefore does not reveal how many participants met the response criteria, the estimated response frequency, or how precise that estimate was. The absence of an efficacy result in the registry record should not be interpreted as evidence that no responses occurred; it means the result is not reported there.

Nor does this design establish how outcomes compare with another treatment or with no study treatment. There was no randomized control group, and MZL and WM are distinct histology groups rather than control and intervention groups. Any observed outcome in a single treated group could reflect influences beyond treatment. This design cannot isolate those influences through a randomized comparison.

In general, an outcome's statistical significance, precision, and clinical importance are different questions. A confidence interval can characterize sampling uncertainty, while the study design affects whether an association can be attributed to treatment. The registry does not report the primary estimate or interval, and the non-randomized design limits causal interpretation regardless of the observed response count.

The serious adverse event counts offer a limited description of events in the study groups. They do not establish comparative safety, event causality, or the full range of harms. The findings should therefore be read as a partial registry account of study design and safety, not as a complete quantitative assessment of efficacy or safety.

14. Why This Trial Matters Statistically

This study illustrates why statistical interpretation begins with the design and the outcome definition, not only with a percentage. ORR depends on which response categories count and which criteria classify a participant as a responder. Here, the criteria differ between MZL and WM, so the diagnosis-specific definitions are essential context for interpreting any response estimate.

It also demonstrates the distinction between a single-group description and a comparative treatment effect. A non-randomized, single-group study can record outcomes after treatment, but it does not create a concurrent randomized estimate of outcomes under an alternative. Subgroups defined by histology do not serve as substitutes for such a comparator. This distinction is important whenever results are used to discuss whether an outcome can be attributed to treatment.

Precision is another central statistical issue. The registry specifies a 95% confidence interval for the primary endpoint, but does not report the estimate or interval. Without them, a reader cannot judge the response rate's statistical uncertainty. The registry's enrollment and safety denominators do not replace the efficacy result or reveal its precision.

Finally, a defined analysis population and a list of secondary outcomes are not enough to reconstruct the analysis. The record does not report the mITT population size, missing-data handling, multiplicity approach, or statistical methods used for the endpoint. These details matter because they affect the interpretation of estimates and the confidence readers can place in them. In this case, recognizing what is documented—and what remains unreported—is part of the statistical result.

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 of the registry record is that it does not report the primary ORR estimate or its 95% confidence interval. No observed efficacy result can be quantified from the information reported. Numerical results for the listed secondary outcomes are also not reported in the registry record, so those outcomes cannot add further detail about response durability, disease progression, treatment failure, or overall adverse-event frequency.

The design is non-randomized, unmasked, and single-group, with no concurrent control. Accordingly, the study does not provide a randomized comparison for estimating a treatment effect. The MZL and WM groups represent different histologies and use different response rules; comparisons between them would not remove confounding or establish a treatment contrast.

The registry defines an mITT efficacy population but does not report its size or explain how missing, incomplete, or unevaluable assessments were treated. It also does not report the method used to construct the confidence interval, multiplicity procedures, interim analyses, or the trial's own sample-size justification. These omissions limit assessment of analysis choices and their influence on results.

Safety interpretation is limited by the reported counts and event-term information. Counts do not give the timing, duration, detailed severity, or treatment attribution of events. They also do not provide a randomized safety comparison. The listed deaths cannot be interpreted as caused by treatment based on these counts alone. Overall, the available record supports a description of the design and select safety observations, but leaves key efficacy, analysis, and safety details unreported.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Study to Assess the Efficacy and Safety of Umbralisib in Participants With Non-Follicular Indolent Non-Hodgkin's Lymphoma — NCT03364231.
• Registry record last updated 2023-06-23; status last verified 2023-05.
• Results first posted 2023-06-23.
• 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

The registry describes a completed Phase 2, non-randomized, unmasked, single-group study of umbralisib monotherapy in non-follicular indolent non-Hodgkin's lymphoma. The listed enrollment is 21. Participants with MZL or WM received umbralisib, 800 mg orally once daily, until disease progression, unacceptable toxicity, or withdrawal.

The primary outcome was ORR under histology-specific response criteria, assessed every 3 cycles, with 1 cycle lasting 28 days, up to approximately 4.2 years. The registry record does not report the ORR estimate or its 95% confidence interval. It lists secondary outcomes but does not report their numerical results.

Serious adverse events were reported for 1 participant among 8 at risk in MZL and 0 participants among 13 at risk in WM; colitis was listed at 12.5% among the top serious event terms. The record does not provide a randomized comparator or enough analysis detail to establish comparative effects.