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 Investigation of Efficacy and Safety of Three Dose Levels of Subcutaneous Semaglutide Once Daily Versus Placebo in Subjects With Non-alcoholic Steatohepatitis. (NCT02970942), a randomized phase 2 study. The primary outcome is Percentage of Participants With Non- Alcoholic Steatohepatitis (NASH) Resolution Without Worsening of Fibrosis After 72 Weeks (Yes/No).
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT02970942 |
| Phase | Phase 2 |
| Condition | Hepatobiliary Disorders, Non-alcoholic Steatohepatitis |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Double |
| Enrollment | 320 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Novo Nordisk A/S |
| Results posted | Yes |
2. Clinical Question
Population
Participants with non-alcoholic steatohepatitis were enrolled. The primary endpoint analysis was described for participants with fibrosis stage 2 or 3 at baseline who contributed to the analysis; the number meeting that description is not reported in the registry record. The record also describes the full analysis set as including all randomized participants.
Intervention
Three dose levels of subcutaneous semaglutide were studied: 0.1 mg, 0.2 mg, and 0.4 mg, each administered once daily. The registry lists semaglutide as a drug intervention. Details beyond the dose and route are not reported in the registry record.
Comparator
Placebo was the comparator. The record lists one placebo intervention and separate placebo arm labels, but does not describe the reason for those labels or provide further details about the placebo regimen.
Primary question
After 72 weeks, what percentage of participants had NASH resolution without worsening of fibrosis? Resolution required the stated liver-histology criteria, and worsening meant an increase of at least one stage on the Kleiner fibrosis classification. The primary outcome values and comparisons are not reported in the registry record.
This is a question about a defined binary endpoint: each participant either met both parts of the primary definition or did not. The endpoint combines improvement in features of NASH with a constraint on fibrosis, rather than treating either component alone as the primary outcome. Consequently, a participant would need to satisfy the resolution definition and avoid the specified fibrosis worsening to count as a success.
The trial title and record describe an investigation of efficacy and safety across three semaglutide dose levels versus placebo. The primary question therefore concerns each dose-level comparison with placebo, not a single pooled comparison of all semaglutide groups. The registry record does not report the endpoint counts, percentages, estimated contrasts, confidence intervals, or statistical tests needed to assess those comparisons. It also does not report a result that would establish whether one dose level differed from another.
3. Trial Design
The registry identifies this as a phase 2, randomized, double-blind, parallel-group trial. The stated enrollment was 320 participants, and the record marks the study as completed. Its title says that it was conducted globally. The listed condition includes non-alcoholic steatohepatitis, and the sponsor is Novo Nordisk A/S.
Participants were assigned among three semaglutide dose levels and placebo. Semaglutide was administered subcutaneously once daily at 0.1 mg, 0.2 mg, or 0.4 mg. Placebo served as the comparator. The adverse-event record lists groups of 80, 78, 81, and 80 participants at risk for serious adverse events, respectively. These safety denominators describe the groups in that record; they should not be taken as a substitute for the missing primary-endpoint analysis counts.
Random allocation is intended, in general, to make treatment groups comparable at the start of a trial with respect to both measured and unmeasured factors. Double masking generally means that treatment assignment is concealed from participants and relevant trial personnel, reducing opportunities for expectations or knowledge of treatment to influence care or assessment. The registry record gives these design labels but does not describe the allocation procedure, masking arrangements in detail, or how treatment codes were handled.
A parallel-group design assigns participants to a study group and follows them in that group rather than having each participant receive multiple treatments in sequence. This is a general description of the design type, not a claim about any unreported trial procedures. The record does not report the planned allocation ratio, stratification factors, or whether any participants switched or discontinued assigned treatment.
The record gives a start date of 2016-11-30 and a primary completion date of 2020-02-13. The primary endpoint is framed at 72 weeks, while its description says endpoint evaluation used the in-trial period ending at the first of specified events, including a follow-up visit at Week 79. Details of visit timing beyond this description, recruitment by site, and the reasons for completion dates are not reported in the registry record.
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: Participants were randomised in a 3:3:3:1:1:1 ratio to receive once-daily semaglutide or placebo subcutaneously. After randomisation, the participants entered a dose-escalation period, with increase in dose every 4 weeks until the target dose was reached.
Overall Study
| Stage | Semaglutide 0.1 mg | Semaglutide 0.2 mg | Semaglutide 0.4 mg | Placebo |
|---|---|---|---|---|
| STARTED | 80 | 78 | 82 | 80 |
| Full Analysis Set | 80 | 78 | 82 | 80 |
| Safety Analysis Set | 80 | 78 | 81 | 80 |
| Exposed | 80 | 78 | 81 | 80 |
| COMPLETED | 76 | 72 | 77 | 77 |
| NOT COMPLETED | 4 | 6 | 5 | 3 |
Reasons for not completing this period:
| Reason | Semaglutide 0.1 mg | Semaglutide 0.2 mg | Semaglutide 0.4 mg | Placebo |
|---|---|---|---|---|
| Death | 0 | 1 | 0 | 0 |
| Lost to Follow-up | 1 | 0 | 2 | 1 |
| Withdrawal by Subject | 3 | 5 | 3 | 2 |
Analysis population for the primary outcome, as defined in the registry: Full analysis set included all randomised participants. Overall number of participants analysed = Number of participants with fibrosis stage 2 or 3 at baseline who contributed to the analysis. In below table, 'Yes' infers percentage of participants who achieved NASH resolution without worsening of fibrosis and 'No' infers vice-versa; 'Missing' refers to percentage of participants with data missing due to different reasons (lost to follow-up, withdrawal).
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 full analysis set included all randomised participants.
| Characteristic | Unit | Semaglutide 0.1 mg | Semaglutide 0.2 mg | Semaglutide 0.4 mg | Placebo | Total |
|---|---|---|---|---|---|---|
| Participants analysed | 80 | 78 | 82 | 80 | 320 | |
| Age, Continuous | years | 55.2 (SD 10.9) | 58.1 (SD 9.9) | 54.3 (SD 10.2) | 52.4 (SD 10.8) | 55.0 (SD 10.6) |
| Sex: Female, Male: Female | Participants | 51 | 52 | 47 | 44 | 194 |
| Sex: Female, Male: Male | Participants | 29 | 26 | 35 | 36 | 126 |
| Ethnicity (NIH/OMB): Hispanic or Latino | Participants | 7 | 10 | 14 | 9 | 40 |
| Ethnicity (NIH/OMB): Not Hispanic or Latino | Participants | 69 | 63 | 65 | 66 | 263 |
| Ethnicity (NIH/OMB): Unknown or Not Reported | Participants | 4 | 5 | 3 | 5 | 17 |
| Race/Ethnicity, Customized: American Indian or Alaska Native | Participants | 0 | 1 | 2 | 0 | 3 |
| Race/Ethnicity, Customized: Asian | Participants | 10 | 12 | 14 | 12 | 48 |
| Race/Ethnicity, Customized: Black or African American | Participants | 1 | 1 | 0 | 0 | 2 |
| Race/Ethnicity, Customized: Native Hawaiian or Other Pacific Islander | Participants | 0 | 0 | 0 | 0 | 0 |
| Race/Ethnicity, Customized: White | Participants | 65 | 59 | 62 | 62 | 248 |
| Race/Ethnicity, Customized: Other | Participants | 0 | 0 | 1 | 1 | 2 |
| Race/Ethnicity, Customized: Not applicable | Participants | 4 | 5 | 3 | 5 | 17 |
6. Primary Endpoint
The registry lists the primary outcome as Percentage of Participants With Non- Alcoholic Steatohepatitis (NASH) Resolution Without Worsening of Fibrosis After 72 Weeks (Yes/No), measured over After 72 weeks.
| Element | Registry entry |
|---|---|
| Result type | Number |
| Measure of spread | not applicable |
| Unit | Percentage of participants |
| Endpoint classification | Binary Endpoint |
The primary endpoint is the percentage of participants with NASH resolution without worsening of fibrosis after 72 weeks. It is a composite, binary outcome: the participant is classified as meeting the endpoint only if the resolution criteria are satisfied and fibrosis does not worsen according to the specified definition.
NASH resolution is defined using the NASH Clinical Research Network criteria stated in the registry. Lobular inflammation must be 0 or 1, and hepatocellular ballooning must be reduced to 0; both conditions are necessary. The record gives a range of 0 to 3 for lobular inflammation and 0 to 2 for hepatocellular ballooning, with higher scores indicating more severe findings. Fibrosis worsening is defined as an increase of at least one stage on the Kleiner fibrosis classification. The stated stages range from 0 to 4, with higher stages indicating greater fibrosis, from none to cirrhosis.
In general, a binary endpoint makes a clinically defined state countable as an event or a non-event. A percentage can communicate how commonly that state occurred in a group, while a comparison between groups can describe the difference in those observed proportions. Combining resolution with no worsening of fibrosis makes the endpoint require both the specified NASH findings and the fibrosis condition.
The endpoint description says evaluation was based on the in-trial period, beginning at randomization and ending at the first of the Week 79 follow-up visit, withdrawal of consent, last contact for a participant lost to follow-up, or death. The primary outcome counts and percentages are not reported in the registry record, so the frequency of endpoint achievement and the precision of any treatment comparison cannot be assessed from the posted results.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The registry record identifies the primary outcome and its definition, but it does not report the primary outcome results. There are no posted endpoint counts or percentages for the dose groups and placebo, and no effect estimate, confidence interval, or p-value is reported in the registry record. It is therefore not possible to describe the direction, size, or statistical precision of a primary-outcome comparison from this record.
The primary outcome is not simply a change in one histology score. It requires NASH resolution under two stated component criteria and no increase of at least one stage in fibrosis. For interpretation, that means an endpoint comparison would represent the percentage meeting the combined definition. It would not, by itself, reveal the separate distribution of lobular inflammation, ballooning, or fibrosis changes. The registry lists secondary outcomes covering fibrosis improvement, changes in NAS components, fibrosis stage, the SAF activity component, and the Fibrosis-4 score, but results for those outcomes are not reported in the registry record.
The trial has four treatment groups in the adverse-event listing: three semaglutide dose groups and placebo. The groups have similar but not identical numbers at risk in that listing. This does not establish the analysis denominator for the primary endpoint, which the record describes separately as participants with fibrosis stage 2 or 3 at baseline who contributed to the analysis. The actual number analyzed for that endpoint is not reported in the registry record.
In general, a treatment contrast should be read alongside its uncertainty interval. An estimate describes the observed difference or other contrast, while a confidence interval conveys the range of values compatible with the data under the analysis assumptions. A p-value addresses compatibility with a specified null hypothesis; it does not measure the size or clinical importance of an effect. None of these primary comparison statistics is available in the registry record.
The study is marked completed, but completion status is not an efficacy result. Likewise, the planned enrollment does not show how many participants contributed to the endpoint analysis or what outcome they experienced. Without posted outcome values and their analysis details, no conclusion about the comparative primary outcome can be drawn from the registry record. The description supports understanding what the trial set out to measure, not a claim about the result.
9. Statistical Methods Explained
The record describes a randomized, double-blind, parallel-group phase 2 trial with three semaglutide dose levels and placebo. These design features provide context for how a treatment comparison may be made. They do not specify the full statistical analysis plan. The statistical plan, including the model used for the primary endpoint, adjustment variables, handling of protocol deviations, and planned estimand, is not reported in the registry record.
What does a binary endpoint represent?
The primary endpoint is recorded as Yes or No for each participant according to the combined histology definition. A binary outcome analysis generally compares the frequency of participants meeting the definition across groups. Common summaries include group-specific proportions and a between-group contrast. These summaries answer different questions: a proportion describes one group, while a contrast describes how groups differ. The registry record does not give the primary endpoint values or identify which contrast measure was used.
In general, a confidence interval describes statistical uncertainty around an estimate under the assumptions of the analysis. A narrower interval indicates greater precision, while a wider interval indicates less precision. An interval should be interpreted in relation to the measure being reported and the clinical question; it is not a guarantee that the true value lies in a particular range. No primary-endpoint confidence interval is reported in the registry record.
Why does the analysis population matter?
The registry describes the full analysis set as including all randomized participants. It also says that the overall number analyzed for the primary endpoint was the number of participants with fibrosis stage 2 or 3 at baseline who contributed to the analysis. These descriptions identify the intended population language but do not provide the number contributing in each group. The actual analysis population and the treatment of participants without endpoint information are not reported in the registry record.
In general, an analysis population defines which participants contribute to a particular estimate. Results from all randomized participants can preserve the comparison created by random allocation, but the operational definition and handling of missing observations still matter. An endpoint analysis restricted to a baseline subgroup or to participants with available data can answer a narrower question. The registry description indicates a baseline fibrosis restriction for the primary endpoint analysis; it does not give enough information to determine the detailed analysis rules or how missing endpoint data affected the estimates.
How should multiple doses and outcomes be considered?
Three active dose levels create more than one possible comparison with placebo. The registry also lists numerous secondary outcomes, including a fibrosis-improvement outcome, changes in NAS and its components, changes in fibrosis stage, a SAF activity component, and Fibrosis-4 score. It reports 88 outcome measures. In general, when many comparisons are examined, the chance of finding at least one apparently notable result can increase if each is assessed separately without accounting for multiplicity. Methods to address this can include prespecified outcome hierarchies or statistical adjustment, but the approach used in this trial is not reported in the registry record.
The record lists no analyses. It therefore does not provide estimates or tests with which to assess how the multiple dose comparisons and outcomes were handled. The ordering of outcomes, any distinction between confirmatory and exploratory analyses, and any multiplicity adjustment are not reported in the registry record. The existence of several listed outcomes alone does not show that every outcome was tested or that any particular adjustment was used.
What do planning assumptions tell us?
In general, a sample-size calculation is a planning exercise based on assumptions about the effect to detect, variability or event frequency, significance level, power, and allocation. It is not a result from the trial. The planning illustration described in the registry material assumes a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is expressed as a stated fraction of the observed effect. For non-time-to-event outcomes, such illustrations are described as participants per arm, while time-to-event illustrations use a total event count.
Those assumptions do not establish that the trial was designed using that calculation, and they do not constitute observed power. The registry record does not report the trial's own sample-size justification or the results of a primary comparison needed to interpret an illustration based on the observed effect. Any sample-size illustration should be understood as hypothetical planning context, not as a measure of how convincing or reliable the trial result is.
Why can event rates be more variable than a simple model assumes?
General statistical models for count outcomes often assume a particular relationship between the mean and variance. Over-dispersion occurs when the observed variability exceeds that assumed by a simpler model. If it is ignored, standard errors and uncertainty intervals may be miscalibrated. This concept is not a claim about the primary analysis in this trial: the primary outcome is binary, and the registry record does not report an analysis model or a diagnostic for over-dispersion.
Overall, the design labels and endpoint definition establish the broad comparison and outcome being studied. They do not replace the missing analysis results or analysis plan. The registry record does not report the primary estimates, their uncertainty, the specific statistical model, or the rules used to handle incomplete data.
10. Multiplicity, Missing Data and Analysis Populations
The trial includes three semaglutide dose levels compared with placebo and lists a range of secondary outcomes. The registry reports 88 outcome measures, but no analyses are listed. The primary endpoint values and comparison statistics are not reported in the registry record. The statistical plan for selecting, ordering, or adjusting tests across dose comparisons and outcomes is not reported in the registry record.
In general, testing multiple hypotheses can make isolated nominal findings harder to interpret because the opportunity for chance findings increases as the number of tests grows. Prespecified hierarchies, family-wise error control, or other approaches may be used to address this issue, but none can be attributed to this trial based on the registry record. A list of outcomes does not establish which analyses were actually conducted or which results were intended to be confirmatory.
The registry describes the full analysis set as all randomized participants and says the primary endpoint analysis count was based on participants with fibrosis stage 2 or 3 at baseline who contributed to the analysis. It does not provide the actual number analyzed by group. The number of participants with missing endpoint data, reasons for missingness, and methods used to address missing data are not reported in the registry record.
In general, missing data can affect estimates when the probability of observing an outcome is related to treatment assignment or to the outcome itself. Complete-case summaries may describe only participants with observed data, while imputation or sensitivity analyses can examine assumptions about missing outcomes. The registry record does not report whether such methods or sensitivity analyses were used. Without these details, the consequences of missingness for the primary comparison cannot be evaluated.
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 |
|---|---|---|---|
| Semaglutide 0.1 mg | 12 | 80 | 15.0% |
| Semaglutide 0.2 mg | 15 | 78 | 19.2% |
| Semaglutide 0.4 mg | 12 | 81 | 14.8% |
| Placebo | 8 | 80 | 10.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Semaglutide 0.1 mg | 0 of 80 |
| Semaglutide 0.2 mg | 1 of 78 |
| Semaglutide 0.4 mg | 0 of 81 |
| Placebo | 0 of 80 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 5% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Semaglutide 0.1 mg | 61 of 80 |
| Semaglutide 0.2 mg | 64 of 78 |
| Semaglutide 0.4 mg | 63 of 81 |
| Placebo | 55 of 80 |
Most frequent serious adverse event terms
| Event term | Organ system | Semaglutide 0.1 mg | Semaglutide 0.2 mg | Semaglutide 0.4 mg | Placebo |
|---|---|---|---|---|---|
| Acute kidney injury | Renal and urinary disorders | 0 of 80 | 2 of 78 | 0 of 81 | 0 of 80 |
| Cholecystitis | Hepatobiliary disorders | 1 of 80 | 0 of 78 | 1 of 81 | 0 of 80 |
| Cholelithiasis | Hepatobiliary disorders | 1 of 80 | 1 of 78 | 0 of 81 | 0 of 80 |
| Hyperglycaemia | Metabolism and nutrition disorders | 1 of 80 | 1 of 78 | 0 of 81 | 0 of 80 |
| Post procedural haematoma | Injury, poisoning and procedural complications | 0 of 80 | 0 of 78 | 1 of 81 | 1 of 80 |
| Abdominal adhesions | Gastrointestinal disorders | 0 of 80 | 0 of 78 | 1 of 81 | 0 of 80 |
| Acute respiratory failure | Respiratory, thoracic and mediastinal disorders | 0 of 80 | 1 of 78 | 0 of 81 | 0 of 80 |
| Anaemia | Blood and lymphatic system disorders | 0 of 80 | 1 of 78 | 0 of 81 | 0 of 80 |
| Anal abscess | Infections and infestations | 1 of 80 | 0 of 78 | 0 of 81 | 0 of 80 |
| Angina unstable | Cardiac disorders | 0 of 80 | 0 of 78 | 1 of 81 | 0 of 80 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Semaglutide 0.1 mg | Semaglutide 0.2 mg | Semaglutide 0.4 mg | Placebo |
|---|---|---|---|---|---|
| Nausea | Gastrointestinal disorders | 24 of 80 | 29 of 78 | 33 of 81 | 9 of 80 |
| Diarrhoea | Gastrointestinal disorders | 23 of 80 | 22 of 78 | 16 of 81 | 11 of 80 |
| Constipation | Gastrointestinal disorders | 12 of 80 | 17 of 78 | 18 of 81 | 10 of 80 |
| Decreased appetite | Metabolism and nutrition disorders | 16 of 80 | 18 of 78 | 18 of 81 | 4 of 80 |
| Nasopharyngitis | Infections and infestations | 11 of 80 | 15 of 78 | 10 of 81 | 12 of 80 |
| Vomiting | Gastrointestinal disorders | 14 of 80 | 17 of 78 | 12 of 81 | 2 of 80 |
| Headache | Nervous system disorders | 7 of 80 | 10 of 78 | 10 of 81 | 8 of 80 |
| Fatigue | General disorders | 7 of 80 | 8 of 78 | 7 of 81 | 7 of 80 |
| Back pain | Musculoskeletal and connective tissue disorders | 7 of 80 | 5 of 78 | 10 of 81 | 6 of 80 |
| Abdominal pain | Gastrointestinal disorders | 9 of 80 | 8 of 78 | 6 of 81 | 3 of 80 |
Serious events with the highest arm-level rate: acute kidney injury (2.6%), acute respiratory failure (1.3%), anaemia (1.3%), cataract (1.3%), cholangitis acute (1.3%).
The registry lists serious adverse events by group and gives the number at risk and the number affected. The serious-event counts are 12 among 80 at risk for semaglutide 0.1 mg, 15 among 78 for semaglutide 0.2 mg, 12 among 81 for semaglutide 0.4 mg, and 8 among 80 for placebo. These are descriptive counts in the posted safety record; they do not establish that treatment caused an event or that the groups differ statistically.
The record lists deaths of 0, 1, 0, and 0 in those groups, respectively. It also lists serious-event terms with percentages, including acute kidney injury at 2.6%, and acute respiratory failure, anaemia, cataract, acute cholangitis, and cholelithiasis at 1.3% each. These term-specific percentages should be read as registry safety entries, not as a complete account of every possible adverse event.
In general, safety counts depend on the observation period, event definitions, and rules for coding and attribution. The registry record does not provide enough detail to interpret exposure-adjusted rates, event timing, recurrence, severity beyond the serious-event classification, or investigator assessments of relatedness. The listed counts alone do not support causal conclusions or comparisons of safety risk.
12. What the Result Does, and Does Not, Mean
The registry record establishes the question the trial was designed to address: whether participants receiving one of three daily subcutaneous semaglutide doses met a specified histology endpoint after 72 weeks, compared with placebo. It also defines the endpoint in terms of NASH resolution and no worsening of fibrosis. Those details explain what an eventual primary result would represent.
The record does not report the primary endpoint results. It gives no group-specific success counts or percentages and no treatment contrast, confidence interval, or p-value. Therefore, the posted record does not show the direction or magnitude of a primary-outcome difference, how precise a comparison might be, or whether any comparison met a statistical threshold. No conclusion about treatment efficacy can be drawn from the endpoint description or the completed status alone.
Even if a group-level percentage were available, it would describe the proportion meeting the defined endpoint, not every aspect of liver disease or every participant's experience. The primary definition also combines two requirements, so the overall endpoint would not by itself identify which component accounted for a participant's classification. The listed secondary outcomes could address other measured features, but their results are not reported in the registry record.
In general, statistical significance and clinical importance are distinct. A p-value, if reported, would not by itself describe the size of an effect or its practical relevance; an estimate and its uncertainty would be needed for that interpretation. The registry record does not contain those primary comparison statistics. Likewise, the safety counts are descriptive entries and do not establish causation or comparative risk.
These boundaries are important: design information explains the planned comparison, while outcome data are needed to interpret what occurred. The record supports a clear account of the intervention groups, primary endpoint definition, and selected safety counts. It does not support claims that semaglutide did or did not improve the endpoint, nor a ranking of the dose levels.
13. Why This Trial Matters Statistically
Statistically, this trial is notable for combining a placebo comparison with three active dose levels and a histology-based binary primary endpoint. The endpoint requires both the stated NASH resolution criteria and no fibrosis worsening. This structure makes the clinical definition central to interpreting any percentage: success is determined by the conjunction of the component conditions, rather than by a single score in isolation.
Having multiple dose groups can allow dose-specific comparisons, but it also creates a multiplicity question. The registry lists 88 outcome measures and does not report an analysis plan, hierarchy, or adjustment strategy. In general, prespecified analysis choices help readers distinguish planned primary questions from exploratory comparisons. Without those details and without results, the statistical evidence across doses and outcomes cannot be assessed.
The record also illustrates why analysis populations and endpoint availability matter. It describes a full analysis set including all randomized participants, while the primary analysis population is described in relation to baseline fibrosis stage 2 or 3 and contribution to the analysis. The actual number analyzed and the missing-data approach are not reported in the registry record. Those details would be needed to understand how the randomized comparison was carried through to the endpoint estimate.
Finally, the posted safety information and the primary endpoint address different aspects of the study. Serious-event counts provide descriptive safety information; they do not substitute for the efficacy analysis or establish comparative risk. The statistical importance of the registry entry lies in the clearly stated endpoint and design question, alongside the need for posted estimates, uncertainty, and analysis details before drawing conclusions about results.
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.
A central limitation of the registry record for interpretation is that it does not report the primary endpoint results. Without group-specific counts, percentages, or comparative estimates, the primary outcome cannot be evaluated statistically. The record also does not report confidence intervals or p-values for the primary comparison.
The primary endpoint analysis is described for participants with fibrosis stage 2 or 3 at baseline who contributed to the analysis, but the number meeting that description is not reported in the registry record. The safety listing gives separate numbers at risk by group; those denominators do not supply the missing endpoint analysis denominators. How participants with unavailable endpoint measurements were handled is not reported in the registry record.
The record identifies several dose groups and many outcome measures, but does not report the statistical plan for multiplicity, the model used for the binary endpoint, or the prespecified approach to comparisons. It is therefore not possible to determine whether the posted analysis followed a particular testing hierarchy or adjustment method. The trial's own sample-size justification is not reported in the registry record.
The endpoint depends on histology criteria and combines NASH resolution with no worsening of fibrosis. That definition is specific and gives a clear classification rule, but the registry record does not provide the component-level primary results needed to distinguish how each requirement contributed to the overall endpoint. The detailed procedures for assessment and any measures used to address assessment variability are not reported in the registry record.
The safety record reports selected serious adverse-event counts, deaths, and event terms, but does not provide the additional detail needed to assess timing, exposure, recurrence, or causal attribution. These limitations apply to interpretation of the posted registry information; they do not establish that the trial did or did not collect additional information.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Investigation of Efficacy and Safety of Three Dose Levels of Subcutaneous Semaglutide Once Daily Versus Placebo in Subjects With Non-alcoholic Steatohepatitis. — NCT02970942.
- Registry record last updated 2021-11-16; status last verified 2021-11.
- Results first posted 2021-04-21.
- 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
This completed phase 2 trial is recorded as randomized, double-blind, and parallel-group, with stated enrollment of 320 participants. It studied subcutaneous semaglutide once daily at 0.1 mg, 0.2 mg, and 0.4 mg versus placebo in participants with non-alcoholic steatohepatitis. The record says the trial was conducted globally and identifies Novo Nordisk A/S as sponsor.
The primary endpoint was the percentage of participants with NASH resolution without worsening of fibrosis after 72 weeks. Resolution required the specified lobular inflammation and hepatocellular ballooning criteria; fibrosis worsening meant an increase of at least one Kleiner stage. The primary outcome results, analysis estimates, confidence intervals, and p-values are not reported in the registry record.
The registry lists secondary outcomes and descriptive serious adverse-event counts by group. It does not report the trial's statistical analysis plan, missing-data methods, multiplicity approach, or sample-size justification. The posted record therefore describes the design and measurement question but does not provide the primary results needed to assess the treatment comparisons.