This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Vancomycin for C Difficile NAAT+/EIA- Hematology Oncology Patients (NCT03030248), a randomized phase 2 study. The primary outcome is Changes in Clostridium Difficile Bacterial Loads in the Stool.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT03030248 |
| Phase | Phase 2 |
| Condition | Clostridium Difficile Infection, Hematologic Diseases, Bone Marrow Transplant |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Triple |
| Enrollment | 9 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Medical College of Wisconsin |
| Results posted | Yes |
2. Clinical Question
Population
Hematology-oncology patients with active diarrhea and a stool result that was positive by nucleic acid amplification testing (NAAT) and negative by toxin enzyme immunoassay (EIA) were eligible for the trial described in the record. The conditions listed also include hematologic diseases, bone marrow transplant, oncologic disorders, and Clostridium difficile infection. This describes the population of interest, not evidence that every person with these conditions was eligible or enrolled.
Intervention
The active-treatment group was assigned oral vancomycin capsules, 125 mg every 6 hours for 14 days. The registry identifies the study as randomized, triple-masked, and parallel-group. The record does not specify which roles were included in the masking.
Comparator
The comparison group received placebo oral capsules every 6 hours for 14 days. Comparing treatment with placebo was intended to distinguish changes associated with assignment to vancomycin from changes observed under placebo in this selected clinical population.
Primary question
The primary endpoint was change in C. difficile bacterial load in stool, measured in CFUs using quantitative PCR. The record describes comparison of an initial pretreatment sample with each participant’s last collected stool sample, up to 90 days. The registry does not report the numerical endpoint results or an analysis comparing the assigned groups. Consequently, the posted record cannot establish the size, precision, or direction of a between-group difference in this endpoint.
3. Trial Design
This was a randomized, triple-masked, parallel-group phase 2 trial sponsored by the Medical College of Wisconsin. It compared oral vancomycin with placebo among hematology-oncology patients with active diarrhea and NAAT-positive, toxin EIA-negative C. difficile test results. The registry lists the study as completed. The recorded start date is 2018-06-01, and the primary completion date is 2020-06-30.
The vancomycin group was assigned 125 mg oral capsules every 6 hours for 14 days. The placebo group was assigned placebo capsules on the same every-6-hours schedule for 14 days. The registry identifies the study as randomized and masked but does not report the method used to generate the random allocation sequence, how assignments were concealed, or who was masked. Those design details are therefore not reported in the registry record.
The brief summary describes a planned enrollment of 30 patients, with 15 per arm. The registry reports enrollment of 9. These are different quantities: the former is the stated design target, whereas the latter is the recorded enrollment. The record does not explain the difference or give a recruitment account.
Outcome assessments were intended at several time points, including days 0, 14, 21, and 90. The primary endpoint description instead specifies the initial pretreatment stool sample and the last sample collected for each participant, up to 90 days. The registry does not report a detailed schedule of sample collection or explain how different follow-up times were handled in the primary analysis.
The record lists one outcome measure and no analyses. It gives a limited account of sample availability for the primary endpoint, but no numerical group summaries, treatment-effect estimate, confidence interval, or test result. Thus, the design can be described from the registration, while the primary outcome comparison cannot be evaluated 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.
Overall Study
| Stage | Vancomycin Treated Group | Placebo Group |
|---|---|---|
| STARTED | 5 | 4 |
| COMPLETED | 4 | 4 |
| NOT COMPLETED | 1 | 0 |
Analysis population for the primary outcome, as defined in the registry: Only 4 participants in the vancomycin group were analyzed given that one failed to give stool samples. In the placebo group all first samples were available for all 4 participants; however, only 2 participants provided a follow up sample ("last sample").
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.
| Characteristic | Unit | Vancomycin Treated Group | Placebo Group | Total |
|---|---|---|---|---|
| Participants analysed | 5 | 4 | 9 | |
| Age, Categorical: <=18 years | Participants | 0 | 0 | 0 |
| Age, Categorical: Between 18 and 65 years | Participants | 3 | 1 | 4 |
| Age, Categorical: >=65 years | Participants | 2 | 3 | 5 |
| Sex: Female, Male: Female | Participants | 1 | 2 | 3 |
| Sex: Female, Male: Male | Participants | 4 | 2 | 6 |
| Ethnicity (NIH/OMB): Hispanic or Latino | Participants | 0 | 1 | 1 |
| Ethnicity (NIH/OMB): Not Hispanic or Latino | Participants | 5 | 3 | 8 |
| Ethnicity (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): American Indian or Alaska Native | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Asian | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Native Hawaiian or Other Pacific Islander | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Black or African American | Participants | 1 | 0 | 1 |
| Race (NIH/OMB): White | Participants | 4 | 4 | 8 |
| Race (NIH/OMB): More than one race | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 0 |
| Region of Enrollment: United States | participants | 5 | 4 | 9 |
6. Primary Endpoint
The registry lists the primary outcome as Changes in Clostridium Difficile Bacterial Loads in the Stool, measured over First sample versus last stool sample collected, up to 90 days.
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | CFUs |
| Endpoint classification | Continuous Endpoint |
The primary endpoint was change in Clostridium difficile bacterial loads in stool, measured in CFUs. The record says bacterial counts were determined by quantitative polymerase chain reaction (PCR), comparing each participant’s initial, pretreatment sample with the last stool sample obtained for that participant. The last sample could be collected up to 90 days. The measure is described as a mean with standard deviation, indicating that the intended endpoint is a continuous quantity rather than a yes-or-no event.
In general, measuring pathogen load can describe the amount of detectable bacterial material in a sample, while a change measure compares the observed quantity at different collection points. Such measurements can help characterize biological patterns over time. They do not, on their own, establish a clinical benefit or explain whether an observed change is attributable to treatment; interpretation depends on the comparison between randomized groups, the measurement process, and the uncertainty around the results.
The registry gives no actual mean changes, standard deviations, participant-level results, or between-group estimate for this endpoint. It therefore does not show whether measured loads changed, how variable measurements were, or how precisely any treatment contrast was estimated.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The central statistical issue is that the registry describes a primary endpoint but does not post its numerical results or an analysis of that endpoint. There is no reported mean change for either group, no estimate of the difference between groups, and no confidence interval or p-value. Without those quantities, readers cannot determine the direction or magnitude of the primary comparison or assess its precision. The absence of a reported comparison is not evidence that the groups were equivalent, nor does it establish that a difference was present.
The enrollment recorded in the registry is 9, while the brief summary states a design target of 30 patients, with 15 per arm. The record does not explain why recorded enrollment was below that target. A small enrollment can make estimates less precise in general, but no trial-specific estimate of precision can be derived from enrollment alone. The actual primary endpoint data are especially limited: the record says 4 participants in the vancomycin group were analyzed, with one failing to give stool samples. In the placebo group, initial samples were available for all 4 participants, but only 2 provided a follow-up sample. These registry entries describe missing endpoint observations; they do not supply an outcome estimate.
Time of measurement also matters. The primary endpoint uses a baseline sample and the last sample obtained, which could occur at different times up to 90 days. The record does not state the exact collection times for analyzed participants or how differences in follow-up timing were addressed. If measurements vary over time, an analysis should account for the timing and pattern of observation; the registry does not report such an approach.
The record lists safety counts separately from the primary endpoint. Those counts describe reported adverse events in the two groups, but do not fill the gap in the primary efficacy analysis. In particular, event counts cannot be used to infer the change in stool bacterial load or to determine a treatment effect on that endpoint.
Overall, the registry permits a description of the planned comparison, the recorded enrollment, and the limitations in endpoint availability. It does not permit a quantitative assessment of the primary treatment contrast. Any conclusion about the magnitude, direction, or statistical uncertainty of that contrast would require results not reported in the registry record.
9. Statistical Methods Explained
The registry identifies a randomized, triple-masked, parallel-group design. In general, random assignment is intended to make treatment groups comparable with respect to both measured and unmeasured characteristics, on average. Masking is intended to reduce the influence of treatment knowledge on care, assessment, or reporting. These are general purposes of the design features; the registry does not detail how allocation was generated or concealed, or which people were masked.
What does a continuous endpoint mean?
The primary measure is bacterial load in stool, expressed in CFUs, and the record describes it as a mean with standard deviation. A continuous measure can take a range of values rather than representing only whether an event occurred. A mean describes the center of observed measurements, while a standard deviation describes their spread around that mean. In general, reporting both helps readers understand the observed level and variability. The registry does not report either statistic for this endpoint.
The endpoint is defined as a change from an initial pretreatment sample to the last stool sample collected for each participant, up to 90 days. A change score can be analyzed by comparing changes between randomized groups, or by using an analysis that accounts for baseline values. These approaches answer related but not identical statistical questions. The registry does not report which method was used. It also does not report the numerical change scores or an estimate contrasting the assigned groups.
Why does follow-up timing matter?
The initial sample and the last available sample may be separated by different periods for different participants. In general, when outcomes can change over time, an analysis needs to make clear whether it compares measurements at a fixed visit, uses each participant’s last observation, or models the measurements over time. Those choices affect what the estimate represents. The description says the last sample could be collected up to 90 days and lists intended assessments including days 0, 14, 21, and 90, but does not report the actual sample dates or a statistical method for handling variable timing.
What can a confidence interval tell a reader?
In general, a confidence interval expresses the uncertainty around an estimated effect under the assumptions of the analysis. A narrower interval indicates greater precision, while a wider interval indicates more uncertainty. It is not a guarantee that the true effect lies within the particular interval. The registry record does not report a confidence interval for the primary endpoint, so its precision cannot be assessed from the posted results.
How should a p-value be interpreted?
In general, a p-value describes how compatible the observed data are with a specified null model, given the analysis assumptions. It does not measure the size or clinical importance of an effect, and a larger p-value does not demonstrate equivalence. No p-value or primary endpoint analysis is reported in this record. Therefore, there is no posted hypothesis-test result to interpret.
What does over-dispersion mean?
As a general statistical concept, over-dispersion occurs when variability in the observed data is greater than a model assumes. It can make standard errors and test results unreliable if the model does not account for the extra variability. This concept may matter for outcomes with highly variable distributions, but the record does not report a distributional assessment or model for the bacterial-load endpoint. It would be speculative to claim that over-dispersion was observed or that a particular correction was used.
Are the planning calculations trial results?
The registry describes a planning illustration based on a stated fraction of an observed effect, using a two-sided significance level of 0.05, equal allocation, and a normal approximation. Such calculations are hypothetical planning aids: they estimate the number of participants that might be needed under specified assumptions. They are not observed treatment effects and must not be described as observed power. The record does not report the trial’s own sample-size justification, and the primary outcome is not reduced to a single comparison in the available analysis information. Consequently, a single planning contrast should not be treated as a formal evaluation of this trial’s primary endpoint.
More generally, a planning calculation depends on assumptions about the effect to detect, variability, significance level, allocation, and statistical method. If an effect estimate comes from a small or incomplete dataset, it may itself be uncertain. The registry’s planning description does not establish that the completed trial had adequate precision, and no power conclusion can be drawn from the posted outcome information.
Why do analysis populations matter?
In general, an analysis population defines which participants contribute to a particular estimate. An intention-to-treat analysis typically retains participants according to randomized assignment, whereas analyses restricted to participants with observed outcomes can lose the balance created by randomization if missingness is related to participant characteristics or outcomes. The registry reports endpoint availability for the groups, but does not identify the analysis population or describe how missing observations were handled. The actual approach is not reported in the registry record.
These methods distinctions matter because the information available is insufficient to reproduce or assess an analysis. No model, variance estimate, confidence interval, or hypothesis test for the primary endpoint is posted. The sound interpretation is therefore limited to what the registration states about the design and sample availability, without inferring an unreported treatment estimate.
10. Multiplicity, Missing Data and Analysis Populations
The registry lists one primary outcome measure, but its description refers to measurements at different collection times and defines the comparison as the initial sample versus each participant’s last stool sample, up to 90 days. The brief summary also names other outcome domains, including C. difficile load, VRE loads, microbiome changes, and bowel-movement frequency, with assessments intended at several time points. The registry does not report a statistical plan specifying which outcomes or time points were confirmatory, how multiple comparisons were handled, or whether any adjustment for multiplicity was planned. Those details are not reported in the registry record.
In general, testing multiple outcomes or time points can increase the chance of finding an apparently notable result by chance if each test is interpreted independently. A prespecified hierarchy or multiplicity adjustment can address this issue, but the record does not identify such a strategy. No claim can therefore be made about how multiplicity was controlled.
Missing endpoint data are directly documented. The record says 4 participants in the vancomycin group were analyzed and notes that one failed to give stool samples. For placebo, initial samples were available for all 4 participants, whereas only 2 participants provided a follow-up sample. The registry does not explain why the other follow-up sample was unavailable, whether any samples were excluded for other reasons, or how missing data were handled analytically.
In general, missingness can affect estimates if the likelihood of having an observed outcome is related to the outcome itself or to participant characteristics. Complete-case analysis, imputation, and models using available repeated measurements rely on different assumptions. The record does not specify which approach was used, whether sensitivity analyses were conducted, or how the analysis population was defined. No analysis results are posted, so the impact of missing data on the primary comparison cannot be assessed.
11. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Vancomycin Treated Group | 2 | 5 | 40.0% |
| Placebo Group | 1 | 4 | 25.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Vancomycin Treated Group | 0 of 5 |
| Placebo Group | 0 of 4 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 1% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Vancomycin Treated Group | 5 of 5 |
| Placebo Group | 4 of 4 |
Most frequent serious adverse event terms
| Event term | Organ system | Vancomycin Treated Group | Placebo Group |
|---|---|---|---|
| sepsis | Infections and infestations | 1 of 5 | 0 of 4 |
| Leukocytosis | Blood and lymphatic system disorders | 1 of 5 | 0 of 4 |
| Hyperglycemia | Endocrine disorders | 0 of 5 | 1 of 4 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Vancomycin Treated Group | Placebo Group |
|---|---|---|---|
| Hypophosphatemia | Metabolism and nutrition disorders | 3 of 5 | 3 of 4 |
| Changes in hepatic function | Hepatobiliary disorders | 3 of 5 | 2 of 4 |
| abdominal pain | Gastrointestinal disorders | 2 of 5 | 2 of 4 |
| Edema | General disorders | 2 of 5 | 2 of 4 |
| Hyperglycemia | Endocrine disorders | 3 of 5 | 1 of 4 |
| Anemia | Blood and lymphatic system disorders | 1 of 5 | 2 of 4 |
| Anorexia | Metabolism and nutrition disorders | 2 of 5 | 1 of 4 |
| Diarrhea | Gastrointestinal disorders | 0 of 5 | 3 of 4 |
| Dizziness | Nervous system disorders | 2 of 5 | 1 of 4 |
| Fever | Infections and infestations | 2 of 5 | 1 of 4 |
Serious events with the highest arm-level rate: hyperglycemia (25.0%), sepsis (20.0%), leukocytosis (20.0%).
The registry reports serious adverse event counts by group. For the vancomycin-treated group, 2 participants were listed as affected among 5 at risk; for placebo, 1 was listed as affected among 4 at risk. The registry reports zero deaths in each group. These are descriptive safety counts and are not the primary bacterial-load endpoint.
The record also reports other adverse events affecting 5 participants among 5 at risk in the vancomycin group and 4 among 4 at risk in the placebo group. The listed serious-event terms and percentages are hyperglycemia at 25.0%, sepsis at 20.0%, and leukocytosis at 20.0%. The registry does not provide enough detail alongside those terms to establish their relationship to treatment, timing, severity beyond the serious-event classification, or whether events were counted by participant or occurrence in every listing. They should be read as registry-reported safety information, not as proof of causation.
With small recorded group counts, descriptive differences can be unstable and do not by themselves establish a comparative safety effect. The record does not report statistical comparisons, confidence intervals, or a detailed safety analysis. The counts should therefore be interpreted cautiously and separately from any conclusion about the primary endpoint.
12. What the Result Does, and Does Not, Mean
The registry record establishes that the study was designed to compare oral vancomycin with placebo in hematology-oncology patients with active diarrhea and NAAT-positive, toxin EIA-negative test results. It also identifies a primary measure: change in stool C. difficile bacterial load, based on an initial sample and a last sample collected up to 90 days. The registration reports limited endpoint sample availability and safety counts.
It does not report the numerical primary endpoint results or a between-group analysis. As a result, the posted information cannot show the size or direction of a treatment contrast, the variability of the observed measurements, or the precision of an estimate. It also cannot support a conclusion that the groups had the same outcome. Missing statistical results are not a null result.
The recorded enrollment was 9, while the brief summary gives a target of 30 patients, with 15 per arm. This gap describes the relation between the enrollment record and the stated target; it does not explain why recruitment ended at the recorded amount. The record does not report a sample-size justification or an analysis of whether the trial had sufficient precision for its primary question.
The primary endpoint data are incomplete as described in the registry. The vancomycin group analysis included 4 participants, and one failed to give stool samples. For placebo, 4 initial samples were available, but only 2 participants contributed a follow-up sample. How missing observations were handled is not reported. The consequences for the estimated comparison therefore cannot be determined.
In general, a randomized design can support a treatment comparison when the analysis follows a clear plan and the outcome data are sufficiently complete. Here, the registration supplies design information but not the outcome analysis needed to interpret such a comparison. No medical conclusion about vancomycin’s effect should be drawn from the information reported in the registry.
13. Why This Trial Matters Statistically
This trial raises a statistically important question about interpreting a randomized study when the registration describes the intended comparison but the posted record lacks the primary outcome analysis. A study’s design can be informative, yet design information alone does not provide an estimate of treatment effect. Readers need the group results, an analysis that defines the comparison, and measures of uncertainty to assess what the data show.
The contrast between the stated enrollment target of 30 patients, with 15 per arm, and recorded enrollment of 9 also illustrates why recruitment and analysis information matter. Enrollment does not itself determine the precision of an estimate, but it frames the scale of the study. The registry does not explain the difference between the target and recorded enrollment, and it does not report a precision estimate for the primary endpoint.
Completeness of repeated measurements is another key issue. The endpoint depends on an initial and a later stool sample, but the registry reports that follow-up samples were unavailable for some participants. Because the endpoint uses each participant’s last sample up to 90 days, both missingness and the timing of samples may influence what an analysis estimates. The record does not explain how either issue was addressed.
Finally, the listed safety counts are descriptive and cannot substitute for an efficacy analysis. Separating endpoint results, missing-data handling, and safety summaries helps avoid interpreting one kind of evidence as another. The statistical lesson is that a transparent result requires more than a stated objective: it requires reported estimates, uncertainty, and enough methodological detail to understand the analysis.
14. 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 limitation of the registry record is that it does not report numerical results or a statistical analysis for the primary endpoint. There are no group means, standard deviations, treatment-effect estimate, confidence interval, or p-value. The direction and magnitude of any difference in bacterial load therefore cannot be assessed.
The recorded enrollment is 9, compared with a stated target of 30 patients and 15 per arm. The registry does not explain the lower recorded enrollment or describe whether recruitment stopped for a particular reason. It also does not report a trial-specific sample-size justification, so the intended precision of the primary estimate is unclear.
Endpoint availability was limited. The record reports analysis of 4 vancomycin-group participants and notes one participant who failed to provide stool samples. In placebo, initial samples were available for all 4 participants, but only 2 participants provided a follow-up sample. The reasons for missing samples, the handling of missing data, and the analysis population are not reported.
The endpoint compares an initial sample with the last sample collected up to 90 days, while the study summary lists multiple intended assessment times. Actual sample timing and the method for handling variation in follow-up are not reported. The statistical model, treatment of baseline values, and any sensitivity analyses are also not reported.
The registry does not provide a multiplicity plan despite describing several outcome domains and assessment times. It does not state how the randomization sequence was generated or concealed, or who was masked. These are limitations of the available record; they should not be mistaken for proof that the study did not use such procedures.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Vancomycin for C Difficile NAAT+/EIA- Hematology Oncology Patients — NCT03030248.
- Registry record last updated 2026-04-15; status last verified 2026-04.
- Results first posted 2026-04-15.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
18. Record Summary
NCT03030248 is a completed, randomized, triple-masked, parallel-group phase 2 trial sponsored by the Medical College of Wisconsin. It compared oral vancomycin capsules, 125 mg every 6 hours for 14 days, with placebo capsules every 6 hours for 14 days in hematology-oncology patients with active diarrhea and NAAT-positive, toxin EIA-negative results.
The stated enrollment target was 30 patients, with 15 per arm; the registry reports enrollment of 9. The primary endpoint was change in stool C. difficile bacterial load measured in CFUs by quantitative PCR, comparing an initial sample with the last sample collected up to 90 days. The record reports limited follow-up sample availability but no numerical primary results or analysis. Safety counts and selected serious-event terms are listed, without a reported comparative statistical analysis.