Safety Study of Danazol With Plasma Exchange and Steroids for the Treatment of Thrombotic Thrombocytopenic Purpura (TTP): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety Study of Danazol With Plasma Exchange and Steroids for the Treatment of Thrombotic Thrombocytopenic Purpura (TTP) (NCT00953771), a non-randomized phase 2 study. The primary outcome is Number of Plasma Exchanges.

2. Clinical Question

3. Trial Design

The registry identifies this as a phase II study of danazol with plasma exchange and steroids for TTP. Enrollment is listed as 9, allocation as non-randomized, masking as none, and the model as parallel. The listed arms are “Danazol, Plex, Steroids” and “Historic Control.” The intervention description says everyone in the intervention arm will receive danazol with plasma exchange and corticosteroids. The historic-control description is blank. These details make clear that the study is not presented as a randomized, masked comparison, and the record cautions that the arms are not a like-for-like control comparison. The study status is terminated. The record lists a start of 2008-10 and a primary completion date of 2015-11-19. Those administrative dates do not establish why the study ended or whether the planned work was completed; a reason for termination is not reported in the registry record. The record also does not report a recruitment flow, the number enrolled in each arm, or the characteristics of either group beyond the safety denominators listed for the intervention arm. The primary outcome is the mean number of plasma exchanges within a timeframe of up to 30 days. Secondary outcomes include time to remission, length of stay, complete and continuous response rate, time to relapse, participants with relapses, and number of relapses. Although the outcome-measure count is listed as 7, the record reports 0 analyses. It does not post numerical results for the primary or secondary outcomes, nor a formal comparison between arms. The design and endpoint can therefore be described, but comparative efficacy cannot be assessed from the posted results.

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: Subjects were not enrolled to the control group; data was retrospectively collected by viewing the charts of 20 patients who received Plasma Exchange

Overall Study

Reasons for not completing this period:

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: The subjects were not enrolled to the control group; outcome data was retrospectively collected by viewing the charts of 20 patients who received Plasma Exchange. Baseline data was not collected

6. Primary Endpoint

The registry lists the primary outcome as Number of Plasma Exchanges, measured over up to 30 days.

The primary endpoint is the number of plasma exchanges: the total exchanges performed after initiation of the first exchange, over a timeframe of up to 30 days. It is specified as a continuous measure summarized by a mean and standard deviation. The study’s stated purpose connects this endpoint to the number of exchanges required to control TTP when danazol is used alongside plasma exchange and corticosteroids. As general statistical context, a count of treatment procedures can represent resource use or treatment burden, while a mean describes the average count in a group. The standard deviation describes how spread out individual values are around that group mean. These summaries answer different questions: the mean gives a central value, and the standard deviation indicates variability. Neither alone shows the shape of the distribution or how much groups overlap. The registry record does not post the observed means or standard deviations, participant-level counts, or a treatment-effect estimate. It therefore does not show the number of exchanges in either arm or how precisely any difference between groups was estimated. The timeframe is stated, but further details about handling participants with fewer than 30 days of observation are not reported in the registry record. As a result, the endpoint’s definition is available, but its observed results and comparison are not.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry specifies a continuous primary outcome summarized by a mean and standard deviation. It does not report a statistical analysis of that outcome. The distinctions below explain how such summaries and comparisons are generally interpreted; they do not describe an analysis reported for this study.

What does the mean describe?

As general statistical context, the mean is the arithmetic average of the observed values in a group. For this endpoint, each value would represent a participant’s number of plasma exchanges according to the endpoint definition. The mean gives a concise description of the group’s central exchange count, but it does not show whether values are tightly clustered or widely dispersed. It can also be influenced by unusually high or low observations.

What does the standard deviation add?

As general statistical context, the standard deviation describes the spread of observations around the mean. A larger standard deviation indicates greater dispersion in the measured values, while a smaller one indicates observations are more concentrated around the mean. It is not the same as the uncertainty in the estimated mean or in a between-group effect. For that, an analysis would need to report an estimate of uncertainty, such as a confidence interval. The registry record defines the intended summary as mean and standard deviation, but does not post the observed summaries.

How would a confidence interval be read?

As general statistical context, a confidence interval presents a range of effect estimates compatible with the observed data under the assumptions of the analysis. A narrow interval indicates greater precision than a wide interval, though precision does not resolve bias in the comparison. A confidence interval for a group contrast would be needed to judge the range of differences consistent with the analysis. No such interval is reported in the registry record for the primary endpoint.

What can a p-value establish?

As general statistical context, a p-value measures how unusual data at least as incompatible with a specified null model would be if that model and the analysis assumptions held. It does not measure the probability that a treatment effect is true, nor does it convey the size or clinical importance of an effect. A p-value alone also does not address bias from non-random allocation or a historical comparator. No primary-outcome p-value is reported in the registry record.

What does the non-randomized comparison mean?

Random allocation is a general method for making treatment groups comparable, on average, with respect to both known and unknown characteristics. This study is listed as non-randomized, and the comparator is historical. The registry explicitly warns that the arms are not a like-for-like control comparison. A difference between groups, if reported, could therefore reflect differences in who entered each group or in the circumstances under which care was delivered, rather than the intervention alone. The record does not report an adjustment strategy or enough detail to assess comparability.

Why is the outcome distribution relevant?

As general statistical context, counts can have a skewed distribution, particularly when many observations are near the lower end and a few are much higher. In that situation, a mean and standard deviation remain interpretable summaries, but they may not fully convey the distribution. Over-dispersion is a general concern when count variability exceeds what a chosen statistical model expects; ignoring it can make uncertainty estimates unreliable. The record does not provide participant-level values or distributional summaries, so it is not possible to assess skewness or over-dispersion for this endpoint.

The record includes a general planning description for sample-size illustrations: two-sided significance level 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a stated fraction of the observed effect. Such illustrations are not observed trial results and are not the study’s own design justification. The record does not report the observed primary effect needed to interpret those illustrations, or a sample-size justification from the trial protocol. There is no basis to infer the trial’s planned power or to treat a planning calculation as observed power. For time-to-event outcomes, general methods account for both event timing and censoring; the record lists outcomes such as time to remission and time to relapse but does not report their analyses. For binary outcomes, general analyses compare event proportions or use models appropriate to the design. For count outcomes, analysts may use methods suited to the distribution and follow-up. These are possible statistical approaches in general, not methods confirmed for this study. The actual analysis plan and model choices are not reported in the registry record.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Danazol, Plex, Steroids", "Historic Control")
n   <- c(9, 20)
m   <- c(14.8, 16.1)
sp  <- c(9.64, 8.93)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Danazol, Plex, Steroids  9  14.800  9.640  7.390  22.210
CARM  Historic Control  20  16.100  8.930  11.921  20.279

11. Multiplicity, Missing Data and Analysis Populations

The registry lists several secondary outcomes alongside the primary endpoint, including time to remission, length of stay, response rate, time to relapse, participants with relapses, and number of relapses. It does not report results for these outcomes, a hierarchy for testing them, or a procedure for controlling the chance of false-positive findings across multiple tests. Whether multiplicity was addressed in a protocol or analysis plan is not reported in the registry record. As general statistical context, testing multiple outcomes can increase the chance that at least one result appears notable by chance. A prespecified primary endpoint and testing hierarchy can help clarify which findings are confirmatory and which are exploratory. Because the record does not report an analysis plan or outcome-level analyses, it is not possible to determine how the listed outcomes were prioritized or whether any adjustment was used. The record does not describe missing-data handling, reasons for missing observations, or the amount of missing outcome information. Details about analysis populations, such as whether analyses were based on all enrolled participants, participants who received treatment, or another defined group, are not reported in the registry record. The primary endpoint timeframe is up to 30 days, but rules for incomplete follow-up are not described. Without these details, readers cannot assess whether missingness could have affected estimates or whether the analyzed population matched the enrolled population. The listed enrollment is 9, but the number included in any efficacy analysis is not reported. The record lists 0 analyses, so there is no posted basis for evaluating exclusions, outcome availability, or the handling of participants who did not complete observation. These gaps do not establish that data were missing or that a particular method was used; they mean those matters cannot be assessed from the registry record.

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 serious adverse event terms

Serious events with the highest arm-level rate: pulmonary edema (11.1%), hypotension (11.1%).

For the “Danazol, Plex, Steroids” group, the registry lists 9 participants at risk for serious adverse events and 2 affected. It lists 9 at risk for other adverse events and 0 affected, and records 1 death. The top serious-adverse-event terms are pulmonary edema at 11.1% and hypotension at 11.1%. These are descriptive registry figures; they do not establish cause or a comparison with another treatment. The historic-control group has 0 participants at risk in the posted safety data, with 0 affected and 0 deaths listed. A zero denominator does not provide a usable control rate. The safety figures therefore cannot support a direct comparative interpretation between the intervention and historical-control groups. The record also does not describe the timing, severity grading, relatedness assessment, or participant overlap for the listed terms. In particular, the percentages for the terms should not be taken to mean that the terms occurred in distinct participants. As general statistical context, rare safety events are estimated imprecisely in small groups, and a percentage should be read alongside its denominator. These counts describe the recorded safety experience in the registry; they are not a complete characterization of risk and do not answer the primary question about the number of plasma exchanges.

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

The record establishes that the study asked whether danazol added to plasma exchange and corticosteroids could reduce the number of plasma exchanges required to control TTP. It identifies a primary endpoint, its summary measure, and a timeframe. It also identifies a phase II, non-randomized parallel design with a historical-control arm. These details make the research question and broad design understandable. What the posted results do not establish is the observed number of exchanges, the difference between groups, or the uncertainty around any difference. There are no reported primary-outcome results and no listed statistical analyses. Consequently, the record does not show that exchange use was reduced, increased, or unchanged. The absence of a posted estimate is not evidence that the groups had equal outcomes; it means the comparison cannot be evaluated from the registry record. Even if a numerical difference were available, the non-randomized historical comparison would require cautious interpretation. The record itself warns that the arms are not a like-for-like control comparison. Without information on group comparability, the analysis, and potential differences in care or observation, an association would not by itself establish that danazol caused the observed pattern. The adverse-event counts add limited descriptive safety information for the intervention group, including 2 participants with serious adverse events among 9 at risk and 1 death. They do not establish whether events were related to treatment, and the historic-control denominator is 0. The registry also lists secondary outcomes but does not provide their results. The most defensible reading is therefore narrow: the record describes the intended question, trial structure, endpoint, and selected safety data, while leaving the central efficacy comparison and its precision unreported.

14. Why This Trial Matters Statistically

This study is statistically notable because its stated clinical question is clear while its comparative outcome evidence is not available in the registry record. The primary endpoint—number of plasma exchanges over up to 30 days—directly reflects the study’s stated aim of assessing exchange use. Yet the record posts neither group summaries nor an estimated contrast, and it lists 0 analyses. That distinction between a well-defined question and a reported answer is important when interpreting registry information. The design also illustrates why the comparator matters. The study is non-randomized and uses a historical control whose description is blank. The record explicitly warns that the arms are not a like-for-like control comparison. In general, historical comparisons may be useful for describing experience, but differences in participants, measurement, or care over time can complicate causal interpretation. A numerical contrast alone would not remove those concerns. The endpoint is a count summarized by a mean and standard deviation. As general statistical context, those summaries can describe average use and variability, but understanding the distribution and estimation uncertainty is also important. The record provides no observed values, confidence interval, or analysis method with which to assess those features. The sample-size assumptions describe planning illustrations rather than a trial-specific design justification, and no observed effect is posted to interpret such illustrations. Finally, the listed safety counts show why denominators and comparator data matter. The intervention group has safety denominators, whereas the historic-control group has none at risk. Those data can be described, but not used to estimate a comparative safety pattern. Taken together, the record is a reminder that registry design details, outcome definitions, analyses, and results answer different questions; the presence of one does not substitute for the others.

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 principal limitation for interpreting this trial record is that it reports no numerical result for the primary endpoint and lists 0 analyses. The registry specifies the endpoint as the mean number of plasma exchanges, with standard deviation, over up to 30 days, but does not post either group’s observed summaries or a treatment-effect estimate. Statistical precision therefore cannot be assessed. The comparator is historical, allocation is non-randomized, and masking is none. The registry itself cautions that the arms are not a like-for-like control comparison. The historic-control arm description is blank, and its safety denominators are 0. The record does not report enough information to assess group comparability or whether the same outcome definitions and observation conditions applied across groups. Enrollment is listed as 9, but arm-specific enrollment and the number included in efficacy analyses are not reported. Participant characteristics, missing-data handling, analysis populations, and details about incomplete follow-up are also not reported in the registry record. The reason for the terminated status is not reported. These omissions limit assessment of selection, attrition, and the applicability of any potential comparison. The record lists secondary outcomes but does not post their results or describe multiplicity handling. It also does not report the trial’s statistical analysis plan, sample-size justification, or interim analyses. The planning assumptions described in the record are illustrations based on an observed effect, but no primary observed effect is posted. These limitations do not establish that particular analyses or procedures were absent from the conduct of the study; they identify information that cannot be assessed from the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Safety Study of Danazol With Plasma Exchange and Steroids for the Treatment of Thrombotic Thrombocytopenic Purpura (TTP) — NCT00953771.
• Registry record last updated 2024-07-23; status last verified 2024-07.
• Results first posted 2023-08-04.
• 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 record describes a phase II, non-randomized, unmasked parallel study of danazol with plasma exchange and corticosteroids for TTP. Enrollment is listed as 9, and the status is terminated. The primary endpoint is the mean number of plasma exchanges performed after the first exchange, over up to 30 days. A historic-control arm is listed, but its description is blank, and the record cautions that the arms are not a like-for-like control comparison. No primary outcome values or statistical analyses are posted; the record lists 0 analyses. Secondary outcomes are named but their results are not reported. For the intervention group, the record lists 2 serious adverse events among 9 at risk, 0 other adverse events among 9 at risk, and 1 death. The historic-control safety denominator is 0. These data describe the registry entry but do not establish a comparative treatment effect or comparative safety result.