A Study in Participants With Non-cirrhotic NASH With Fibrosis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study in Participants With Non-cirrhotic NASH With Fibrosis (NCT05638737), a randomized phase 2 study. The primary outcome is Relative to Baseline Alanine Aminotransferase (ALT).

2. Clinical Question

This is a question about a measured biochemical outcome over the treatment period. The record identifies safety, tolerability, and pharmacodynamics as the trial’s broader aims, but the primary outcome described in the registry is ALT relative to baseline. ALT is measured in units per litre. The primary outcome timeframe includes measurements at baseline and at weeks 2, 4, 8, 12, and 16; the reported change is from baseline to week 12.

The posted summary states that participants were not expected to benefit directly during the trial. The study was intended to help researchers learn more about AZD4831 and its development for NASH. It does not establish what the findings would mean for people outside the trial population, or for outcomes not measured in the registry record.

3. Trial Design

The trial is listed as Phase 2 and is described in its official title as Phase IIa. It was randomized, double-blind, placebo-controlled, and parallel-group, with triple masking recorded in the registry. It was multicenter. These design features describe how the study was organized; the registry record does not identify which three groups were masked.

The record reports enrollment of 112 participants. The primary outcome results list 56.0 participants in the mitiperstat arm and 56.0 in the placebo arm. The interventions are AZD4831 and placebo; the treatment arm is named Mitiperstat (5mg). The registry lists the allocation as randomized, but details such as the randomization sequence and concealment procedures are not reported in the registry record.

Participants could be in the trial for up to 24 weeks, including screening lasting up to 8 weeks, a 12-week treatment period, and a 4-week safety follow-up. ALT was measured at baseline and at weeks 2, 4, 8, 12, and 16, with the primary change defined from baseline to week 12. The study began on 2022-10-26, its primary completion date was 2024-04-04, and its status is completed.

The record does not report the sample-size justification, the planned statistical analysis in full, or whether interim analyses were conducted. It also does not report further operational details such as the number of sites or the identity of the masked parties. The posted enrollment and results describe the trial, but do not by themselves explain how those design decisions were made.

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:

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Relative to Baseline Alanine Aminotransferase (ALT), measured over Measurements on Baseline, Week 2, Week 4, Week 8, Week 12 and Week 16. Change reported from Baseline to Week 12..

The primary endpoint is ALT at 12 weeks relative to baseline. ALT is measured in units per litre, and the registry reports the outcome as a ratio using a geometric least-squares mean with a 95% confidence interval. A relative measure expresses the week 12 result in relation to the baseline result, rather than reporting only an absolute change in units per litre.

ALT is a biochemical measurement used in this trial as an outcome for evaluating pharmacodynamic effects. Repeated measurement at the listed study visits allows the record to describe the course of the measure during the study; the designated primary change is from baseline to week 12. The record does not give a clinical threshold for interpreting a particular ALT ratio, nor does it state that this endpoint alone captures every aspect of NASH or participants’ health.

The reported arm-level geometric least-squares mean ratios are 0.959 for mitiperstat and 0.895 for placebo. Their respective 95% confidence intervals are 0.885 to 1.04 and 0.824 to 0.972. These are arm-level estimates relative to baseline. They should be distinguished from the separate mixed models result, which reports the percentage change relative to baseline versus placebo.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is reported as a geometric least-squares mean ratio. In general, a ratio compares a measurement with a reference value; in this trial, the reference is baseline, and the specified endpoint is ALT at week 12 relative to baseline. A ratio of 1 represents no change on that ratio scale. Ratios below or above 1 describe values on opposite sides of that reference. The registry’s arm-level estimates are 0.959 for mitiperstat and 0.895 for placebo, each with its own 95% confidence interval.

In general, a least-squares mean is a model-based mean, rather than necessarily the simple arithmetic average of the raw observations. The term geometric indicates that the estimate is expressed on a multiplicative scale. The record identifies the reported parameter as a geometric least-squares mean, but does not describe the model used to obtain the arm-level estimates. The mixed models analysis is separately identified as the method for the comparison against placebo.

A confidence interval describes uncertainty around an estimate under the statistical method and assumptions used. In general, a 95% confidence interval is constructed by a procedure that would contain the target parameter in 95% of repeated applications under those assumptions. It is not a statement that there is a 95% probability that this particular interval contains the true value. The arm-level intervals are 0.885 to 1.04 for mitiperstat and 0.824 to 0.972 for placebo. The treatment-versus-placebo interval is on a different scale: -4.1 to 20.5 for the percentage change contrast.

The mixed models result is reported as 7.5 for the percentage change in relative to baseline versus placebo, with a 95% confidence interval from -4.1 to 20.5 and p = 0.893. A contrast estimates a difference between groups according to the analysis scale. Here the scale is percentage change relative to baseline, not the arm-level ratio itself. The interval includes zero, the value corresponding to no difference on a difference scale. The record does not describe the model’s fixed effects, repeated-measures structure, adjustment variables, or the handling of measurements taken at different visits.

In general, a p-value measures how unusual data at least as incompatible with a specified null hypothesis would be, assuming that hypothesis and the model assumptions hold. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of an effect. The reported p-value is 0.893. Interpreted alongside the confidence interval, it does not provide strong statistical evidence of a group difference under the reported analysis. It does not prove that there is no difference.

Repeated measurements can help describe change over time, but observations from the same participant are generally related. In general, mixed models can account for such dependence and make use of repeated measurements under their specified model. The endpoint record lists measurements at baseline and weeks 2, 4, 8, 12, and 16, while specifying the primary change as baseline to week 12. The record does not say exactly which measurements entered the mixed model or how within-participant correlation was represented, so those details should not be inferred from the method label alone.

Random allocation is intended, in general, to make treatment groups comparable at the start of a trial with respect to measured and unmeasured factors, subject to chance variation and the conduct of the study. Masking can reduce some forms of influence on treatment delivery or assessment. This record describes the study as randomized, double-blind, and triple-masked, but does not report allocation concealment procedures or identify the masked groups. These labels do not replace information about how the study was implemented.

The registry describes the analysis as a superiority analysis. In general, a superiority test evaluates whether the data support a difference in a specified direction or contrast against a null of no difference; it is not the same as a non-inferiority or equivalence analysis. No non-inferiority margin or equivalence margin is reported. The result should therefore be interpreted as the reported superiority analysis, not as evidence from a design intended to establish equivalence.

The record does not report the full statistical analysis plan, sample-size justification, interim analyses, adjustment for multiple comparisons, missing-data method, or analysis populations. In general, multiple testing can increase the chance of obtaining a nominally unusual result when many hypotheses are evaluated; prespecified methods may address this issue. Without a reported multiplicity strategy, it is not possible to determine whether or how the analyses were adjusted. The registry gives planning assumptions for sample-size illustrations: two-sided significance level 0.05, equal allocation, and a normal approximation, with the target effect defined as a stated fraction of the observed effect. Those are planning illustrations, not observed power, and are not evidence of the trial’s own design justification.

10. Analyses Reported by the Sponsor

The registry reports the mixed models analysis as the primary between-group result: a percentage change relative to baseline versus placebo of 7.5, with a 95% confidence interval from -4.1 to 20.5 and p = 0.893. This is the sponsor-reported analysis recorded for the comparison. The arm-level geometric least-squares mean ratios, 0.959 for mitiperstat and 0.895 for placebo, are distinct estimates and should not be mistaken for that contrast.

A simple recalculation from posted summary statistics is not a replacement for the sponsor’s model-based analysis. The registry record does not flag a discrepancy between the reported analysis and the recalculation. The model-based result remains the relevant reported comparison because it is the analysis specified in the results record; the registry does not provide enough model detail to independently reproduce its full calculation.

The reported confidence interval includes zero and the reported p-value is 0.893. These statistics describe uncertainty and compatibility with a null difference under the analysis, not whether the effect is clinically important. The record does not report a clinical importance threshold or sufficient methodological detail to assess all modeling assumptions.

11. Multiplicity, Missing Data and Analysis Populations

The record lists ALT relative to baseline as the primary outcome and Pro-C3 relative to baseline as a secondary outcome. It reports one primary comparison and indicates that values are missing or not estimable for a two-arm comparison for the other endpoint. Therefore, a two-arm secondary estimate cannot be interpreted from the posted outcome information.

Multiplicity concerns arise in general when multiple outcomes, time points, or analyses are tested. Conducting several tests can increase the chance of at least one apparently unusual result even when none of the underlying effects exists. Statistical plans may address this through prespecified testing sequences or other adjustments. The registry record does not report whether any multiplicity adjustment was planned or applied, or how the primary and secondary outcomes were ordered for inferential testing. The reported p-value should be understood as recorded, without assuming an adjustment that is not described.

The endpoint lists measurement times at baseline and weeks 2, 4, 8, 12, and 16, but specifies the primary change as baseline to week 12. The record does not report whether other visit comparisons were analyzed, whether those analyses were inferential or descriptive, or how any such tests related to the primary test.

Missing-data methods and analysis populations are not reported in the registry record. In particular, the record does not state whether the analysis included all randomized participants, participants who received treatment, or participants with available measurements under another definition. It also does not describe imputation, likelihood-based handling, or sensitivity analyses for missing observations. The outcome listings of 56.0 participants in each arm do not establish that every randomized participant had complete data at every scheduled visit.

The sample-size justification and interim analyses are also not reported. The registry includes assumptions used for planning illustrations, but those illustrations are not evidence of the original trial’s sample-size rationale or of observed power. These omissions limit how fully the reported estimates can be evaluated for prespecification, selective reporting, and robustness to missing data.

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: bronchitis (1.8%), herpes zoster (1.8%), pneumonia (1.8%), sepsis (1.8%), chronic obstructive pulmonary disease (1.8%).

The safety record lists serious adverse events in 0 of 56 participants in the treatment group and 3 of 56 participants in the placebo group. It reports no deaths in either group. Other adverse events are listed for 33 of 56 participants in the treatment group and 36 of 56 participants in the placebo group. These are descriptive counts in the registry record, not a complete assessment of the nature, timing, severity, or duration of every event.

The record lists bronchitis, herpes zoster, pneumonia, sepsis, and chronic obstructive pulmonary disease among the top serious adverse event terms, each at 1.8%. It does not identify which arm each listed term occurred in or provide further event-level detail in the information recorded. The percentages should not be used to infer additional counts or arm-specific rates.

Safety counts from a trial of this size and duration can describe events observed during the study but do not, by themselves, establish whether a treatment caused an event or provide a complete picture of uncommon or longer-term harms. The record does not report additional details such as event-related discontinuations or the statistical methods used for safety comparisons. These figures should be read as recorded events, not as a formal comparative safety conclusion.

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

The posted results describe a randomized comparison of mitiperstat and placebo in participants with non-cirrhotic NASH with fibrosis. For the primary outcome, the registry gives arm-level ALT ratios relative to baseline and a mixed models comparison of percentage change relative to baseline versus placebo. The reported comparison is 7.5, with a 95% confidence interval from -4.1 to 20.5 and p = 0.893. The interval spans zero, so the estimate is uncertain about the direction and size of the between-group difference.

This result does not establish that the groups had identical outcomes. A result that does not show strong evidence of a difference can reflect uncertainty, including limited precision, as well as a small or absent underlying difference. The interval is the relevant guide to the range of estimates compatible with the analysis, while the p-value is not a measure of the probability that either treatment is effective.

The result is specific to ALT relative to baseline and to the reported week 12 comparison. It does not establish effects on clinical outcomes or on aspects of NASH not assessed by this endpoint. The registry record does not give a clinical threshold for interpreting the size of the ALT contrast. It also does not provide a two-arm result for the listed secondary outcome, Pro-C3, because values are missing or not estimable for that comparison.

The safety counts describe serious and other adverse events recorded during the study, including no deaths in either group. They do not prove that events were caused by an assigned intervention, nor do they establish comparative safety across a broader population or longer period. The registry summary states that participants were not expected to benefit directly during the trial.

Interpretation is further bounded by missing information about the statistical plan, analysis populations, missing-data handling, multiplicity, and sample-size justification. Those omissions do not invalidate the estimates, but they limit the degree to which their prespecification and robustness can be assessed from the registry record alone. The results are best understood as the reported estimates and their uncertainty, not as a complete answer about treatment effects in all people with NASH.

14. Why This Trial Matters Statistically

This trial is statistically informative because it illustrates the distinction between an arm-level change and a between-group contrast. The reported ratios of 0.959 for mitiperstat and 0.895 for placebo describe each group relative to its own baseline. The mixed models estimate of 7.5 addresses a different question: the percentage change relative to baseline versus placebo. These measures should not be treated as interchangeable. A treatment effect is assessed by comparing groups, rather than by examining one arm’s change alone.

The precision of a result matters alongside its point estimate. The 95% confidence interval for the between-group result extends from -4.1 to 20.5 and includes zero. This range communicates uncertainty about both direction and magnitude. The p-value of 0.893 is another summary of the data under the model, but it does not replace the interval or express clinical importance.

The trial also demonstrates why outcome definitions and time points matter. ALT was measured at several scheduled visits, while the primary change was defined from baseline to week 12. The endpoint and visit definition give context to the estimate and prevent it from being read as a summary of all measurements or all possible outcomes.

Finally, the registry provides useful design and safety information but leaves important statistical details unreported. The analysis populations, missing-data methods, multiplicity strategy, and sample-size justification are not reported in the registry record. Recognizing those gaps is part of interpreting clinical trial evidence: reported estimates are meaningful, but their scope and precision should not be extended beyond the analysis and outcome actually described.

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 primary outcome is a biochemical measure, ALT relative to baseline at week 12. The registry does not provide a clinical interpretation threshold, and the outcome alone does not represent every relevant feature of NASH or participants’ health. The listed secondary endpoint, Pro-C3 relative to baseline, has no estimable two-arm comparison in the posted results.

The mixed models analysis is identified by name, but the registry does not describe its specification, adjustment variables, repeated-measures structure, or assumptions. It is therefore not possible to assess from the record whether the model included all scheduled visits or how it represented correlations among repeated measurements. The record also does not report the analysis populations, missing-data handling, sensitivity analyses, or the number of participants contributing data at each visit.

The statistical plan, multiplicity approach, interim analyses, and sample-size justification are not reported in the registry record. This limits assessment of whether the reported analysis followed a prespecified plan and how uncertainty across multiple outcomes or analyses was handled. The planning assumptions recorded for sample-size illustrations do not establish the rationale used to design the completed trial.

The safety information is brief. Serious adverse event counts and selected terms are listed, but additional details about event timing, duration, severity, treatment attribution, and discontinuations are not reported in the registry record. The trial’s follow-up is described as up to 24 weeks, so these results do not characterize longer-term outcomes.

Finally, the record does not provide further participant characteristics or detailed eligibility criteria. The findings therefore cannot be judged against unreported features of the enrolled population, and their applicability beyond participants described as having non-cirrhotic NASH with fibrosis cannot be established from this record alone.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study in Participants With Non-cirrhotic NASH With Fibrosis — NCT05638737.
• Registry record last updated 2025-07-09; status last verified 2025-07.
• Results first posted 2025-07-09.
• 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.

19. Record Summary

NCT05638737 is a completed randomized, triple-masked, placebo-controlled, parallel-group Phase 2 trial, described in its official title as Phase IIa. It enrolled 112 participants with non-cirrhotic NASH with fibrosis. The trial compared AZD4831, named as Mitiperstat (5mg) in the arm results, with placebo.

The primary outcome was ALT at week 12 relative to baseline. The registry reports arm-level geometric least-squares mean ratios of 0.959 for mitiperstat and 0.895 for placebo, plus a mixed models comparison of 7.5 with a 95% confidence interval from -4.1 to 20.5 and p = 0.893. No deaths were recorded; serious adverse events affected 0 of 56 participants in the treatment group and 3 of 56 in the placebo group.

The study began on 2022-10-26, reached primary completion on 2024-04-04, and is listed as completed. Statistical-plan details, analysis populations, missing-data methods, and a two-arm estimate for the secondary outcome are not reported or estimable in the registry record.