Study of PK/PD, Safety and Tolerability of LIK066 in Patients With Decreased Renal Function.: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of PK/PD, Safety and Tolerability of LIK066 in Patients With Decreased Renal Function. (NCT03131479), a non-randomized phase 2 study. The primary outcome is Change From Baseline in 24-hour Urinary Glucose Excretion (UGE) on Day 7.

2. Clinical Question

The study asked whether treatment with LIK066 was associated with a change in urinary glucose excretion among patients with decreased renal function, compared with subjects whose renal function was normal. The primary measure was change from baseline in 24-hour urinary glucose excretion at Day 7. Urinary glucose excretion was also measured after a single dose, on Day 1, but the primary endpoint focuses on the end of the 7-day treatment period.

The clinical question is about the measured pharmacodynamic response across groups with different renal-function categories. It is not, on the registry information available, a randomized comparison of treatment against no treatment or another treatment. The record describes LIK066 administration in all five groups and identifies normal renal function as the reference category. Because group assignment was non-randomized, any differences between groups could reflect group characteristics as well as differences in renal function. The record does not report criteria used to define the renal-function categories or the numerical endpoint results needed to describe the observed pattern.

3. Trial Design

This was a phase 2, non-randomized, parallel-group study of LIK066 in patients with decreased renal function and subjects with normal renal function. The registry record reports enrollment of 53 and a completed study. The listed study dates are 2017-04-28 for the start and 2018-01-16 for primary completion.

Five groups were defined by renal-function category: mild impairment, moderate impairment grade A, moderate impairment grade B, severe impairment, and normal renal function. Each group received LIK066 50 mg once daily before breakfast for 7 days. There was no separate untreated or active-treatment group described in the intervention information. Since allocation was non-randomized, comparisons across these groups should not be interpreted as randomized treatment contrasts.

The record has an internal design-label tension: its official title describes the study as open-label, while the masking field labels it triple masked. How masking was implemented, and how that label relates to the open-label wording, is not reported in the registry record. The record labels the model parallel-group and allocation non-randomized; it does not describe the practical procedures used to assign participants to renal-function groups.

The study collected urine over 24 hours to measure urinary glucose excretion at baseline, after a single dose on Day 1, and at the end of treatment on Day 7. Blood samples were collected to measure LIK066 concentrations and study pharmacokinetics. Pharmacokinetic results and detailed procedures are not reported in the information available in the registry record. The stated primary endpoint is change from baseline in 24-hour urinary glucose excretion on Day 7, while the record also lists other outcome measures without numerical results in the registry record presented.

The registry record does not report the study’s sample-size justification, eligibility criteria in detail, renal-function thresholds, allocation procedures, or the rationale for the 7-day dosing period. These omissions limit assessment of how representative the groups were and how the design addressed differences among them.

4. Participant Flow and Accounting

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

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Pharmacodynamic Analysis Set (PD), which consisted of all participants with an observed PD value, was considered. Only patients with evaluable data at each time point were analyzed for that time point.

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 Change From Baseline in 24-hour Urinary Glucose Excretion (UGE) on Day 7, measured over Baseline , Day 7.

The primary endpoint is change from baseline in 24-hour urinary glucose excretion, measured on Day 7 and expressed in grams. A 24-hour urine collection aims to capture glucose excreted over a full day rather than relying on a single urine sample. Measuring at baseline and again after treatment makes it possible to describe how the endpoint changed over the treatment period.

The endpoint is pharmacodynamic: it concerns a measured response associated with drug administration. The registry description says urine was collected at baseline (Day -1), following a single dose (Day 1), and at the end of the 7-day treatment (Day 7). The primary comparison of time points is baseline to Day 7. The Day 1 measurement provides an additional time point in the study description, but it is not the primary endpoint specified in the record.

The record identifies the endpoint statistic as a mean with standard deviation. In general, a mean describes the central value of a continuous measurement, while a standard deviation describes variation among measurements around that mean. Neither statistic alone describes the precision of an estimated group contrast; that would require an appropriate uncertainty measure, such as a confidence interval, and the relevant analysis details.

The endpoint can describe urinary glucose excretion in the studied groups after LIK066 administration. It does not by itself establish why groups may differ or isolate a treatment effect from all other group differences. The numerical means, changes, variability estimates, and between-group estimates for this endpoint are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a continuous primary endpoint summarized as a mean and standard deviation. It also identifies an analysis population and says that only patients with evaluable data at each time point were analyzed for that time point. The record does not report the statistical model, exact method for calculating change, confidence intervals, or inferential tests used for the primary endpoint. The concepts below explain how these methods are generally interpreted; they should not be taken as a description of unreported procedures in this study.

What does a mean and standard deviation describe?

In general, the mean is an average that gives a summary of the central level of a continuous measurement. The standard deviation describes how spread out individual measurements are around that mean. A larger standard deviation indicates greater dispersion in the measured values, while a smaller one indicates that values lie more closely around the mean. These are descriptive summaries; by themselves they do not show whether a difference between groups is precise or whether it is compatible with no difference.

For a change endpoint, the mean change summarizes the average within-person change among the participants included in the analysis. The registry identifies change from baseline as the primary measure, but does not state whether the analysis used individual change scores, a model adjusting for baseline, or another approach. Those approaches can differ in their assumptions and in the way they use baseline information. The particular approach used is not reported in the registry record.

What does a confidence interval add?

In general, a confidence interval gives a range of values that are compatible with the observed data under a specified statistical procedure. It communicates precision: a narrower interval indicates a more precise estimate, and a wider interval indicates more uncertainty. A confidence interval for a group contrast would be needed to assess the precision of that contrast. The registry information available does not report a confidence interval for the primary endpoint or specify the method used to calculate one.

A confidence interval is not a guarantee that the true value lies within a particular observed interval, nor does it resolve design limitations. Even a precise estimate can be affected by non-random allocation, incomplete measurement, or other systematic differences between groups. Conversely, an imprecise estimate does not demonstrate that groups are equivalent. Interpretation depends on both the estimate and its uncertainty, alongside the study design.

Why does non-random allocation matter?

In general, random assignment helps balance measured and unmeasured participant characteristics between comparison groups on average. In this study, allocation is labeled non-randomized and the groups are defined by renal-function category. Those categories may differ in characteristics beyond the category label. A difference in urinary glucose excretion across groups could therefore reflect differences in those characteristics as well as differences associated with renal function. The record’s warning that the groups are not a like-for-like control comparison is relevant when interpreting any group contrast.

Statistical adjustment can sometimes account for measured differences, but it cannot automatically remove bias from unmeasured factors or inadequate measurement. The registry information does not report whether adjustment was used, which covariates were considered, or how the analysis addressed non-random group assignment. It is therefore not possible to infer an adjusted effect from the design description.

How should repeated measurements be understood?

The study description identifies urinary glucose excretion measurements at baseline, after a single dose on Day 1, and on Day 7. Repeated measurements can show how a measure changes over time within the observed participants. In general, measurements from the same participant are related rather than independent; an analysis of several time points may need to account for that correlation. The registry record does not state whether a repeated-measures model was used or how the time points were jointly analyzed. The primary endpoint remains the change from baseline on Day 7.

The record says that only patients with evaluable data at each time point were analyzed for that time point. This means the analyzed population could vary by time point if evaluability differed, but the actual amount and pattern of missing data are not reported. Without those details, it is not possible to assess whether missing measurements could have affected the observed summaries.

What does over-dispersion mean in general?

Over-dispersion is a general issue for count outcomes when the observed variability is greater than a chosen statistical model expects. A model that underestimates variability can produce uncertainty estimates that are too narrow. It is not a reported feature of the primary endpoint in this study: urinary glucose excretion is treated as a continuous measure, and the registry information does not report an over-dispersion assessment. The concept is relevant to some count-data analyses, not as a stated property of these endpoint results.

How do planning illustrations differ from trial power?

The sample-size assumptions describe planning illustrations computed from an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They describe the effect to detect as a stated fraction of the observed effect. Such illustrations are not observed power: they are planning calculations, not a measure of whether the completed trial had adequate power after its results were seen. Sample-size figures from the planning display should be understood as participants per arm for 80% power where that label applies, not as observed enrollment or an outcome of the trial.

The registry record does not report the trial’s own sample-size justification or statistical plan. The planning assumptions therefore should not be treated as evidence that the original design used those assumptions. Moreover, because the primary numerical endpoint results are not reported in the record information available, the effect used in the illustration cannot be independently understood from these registry entries.

In general, statistical significance, if reported, would not by itself establish clinical importance or remove limitations from the non-randomized design. A complete interpretation would consider the estimated effect, its uncertainty, the analysis population, missingness, and the design. Several of those details 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("Normal", "Mild", "Moderate A", "Moderate B", "Severe")
n   <- c(10, 10, 10, 11, 12)
m   <- c(40.45, 31.87, 36.27, 19.88, 5.5)
sp  <- c(21.93, 13.79, 19.51, 18.66, 3.75)
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  Normal  10  40.450  21.930  24.762  56.138
CARM  Mild  10  31.870  13.790  22.005  41.735
CARM  Moderate A  10  36.270  19.510  22.313  50.227
CARM  Moderate B  11  19.880  18.660  7.344  32.416
CARM  Severe  12  5.500  3.750  3.117  7.883

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 10 outcome measures and 4 analyses, but the information available does not specify how many statistical hypotheses were tested, which were considered primary or secondary beyond the named primary endpoint, or how multiplicity was handled. Multiplicity arises when several outcomes, time points, groups, or analyses are examined: the chance of at least one apparently unusual result can increase when many tests are conducted. In general, prespecified priorities or statistical adjustments can help address that issue. Whether any such approach was used in this study is not reported in the registry record.

The primary endpoint is identified as change from baseline in 24-hour urinary glucose excretion on Day 7. The record also describes measurements at baseline and Day 1, but does not say whether comparisons involving those time points were formal hypothesis tests or descriptive summaries. It does not report a hierarchy of tests, adjustment procedure, or analysis plan for the several renal-function groups. No inference about multiplicity control can therefore be made.

For missing data, the record states that the Pharmacodynamic Analysis Set consisted of participants with an observed pharmacodynamic value, and that only patients with evaluable data at each time point were analyzed for that time point. This indicates that evaluability was assessed by time point. The number of missing or unevaluable measurements, reasons for missingness, and any imputation or sensitivity analyses are not reported in the registry record.

In general, complete-case summaries can be affected if the participants with observed values differ systematically from those without them. The direction and size of any such effect depend on why data are missing and how missingness relates to the outcome. The available record does not allow that assessment. The definition of the analysis population should therefore be considered alongside the absence of information about missingness and the statistical plan.

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 1% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: acute myocardial infarction (9.1%), acute left ventricular failure (8.3%).

The registry record reports serious adverse events by renal-function group. It lists no serious adverse events in the Normal, Mild, or Moderate A groups, and one in the Moderate B group and one in the Severe group. The reported numbers at risk for this serious-event summary are 10 for Normal, 10 for Mild, 10 for Moderate A, 11 for Moderate B, and 12 for Severe. No deaths are reported in any listed group.

The other-adverse-event counts are reported separately: 9 in Normal, 10 in Mild, 10 in Moderate A, 11 in Moderate B, and 11 in Severe, with the corresponding reported numbers at risk of 10, 10, 10, 11, and 12. These are descriptive counts from the registry record; they do not establish that an event was caused by LIK066. The study description does not identify a separate untreated comparison group, and allocation was non-randomized, so the counts do not support a like-for-like comparative safety estimate.

The record lists acute myocardial infarction (9.1%) and acute left ventricular failure (8.3%) as the top serious terms. The information available does not specify the denominators or group context for those percentages. They should not be read as group-specific risks without that context. The registry record also does not provide event timing, severity details beyond the serious-event classification, or an assessment of causality.

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

The study’s primary endpoint was designed to describe change in 24-hour urinary glucose excretion from baseline to Day 7 after LIK066 administration. The registry record provides the endpoint definition, measurement schedule, unit, and planned summary as a mean with standard deviation. It does not report the numerical primary endpoint results. As a result, the direction and magnitude of the observed change, the differences across renal-function groups, and the precision of any such estimates cannot be stated from the registry information available.

The design also limits what group differences would mean. Participants were not randomly allocated, and each group was defined by renal-function category. A comparison between categories would not be equivalent to a randomized comparison of treatment with a control condition. Group contrasts could reflect differences between the people in the groups, and the record does not report an adjustment strategy that might address measured differences.

The endpoint is pharmacodynamic, while the study also collected blood samples to assess pharmacokinetics. Neither the numerical pharmacodynamic results nor the pharmacokinetic findings are reported in the information. The study description says its results may inform evaluation of LIK066 in people with reduced renal function and dosing, but that purpose does not itself establish a clinical benefit, an appropriate regimen, or a treatment recommendation.

The safety counts provide limited descriptive information: serious events are reported in two of the listed renal-function groups, and deaths are reported as zero in each group. Counts alone do not establish causation or allow strong comparative conclusions, particularly without a randomized control group and fuller event context. The two listed serious terms also lack the denominator and group context required for a more specific interpretation.

Accordingly, the registry record supports statements about what was measured, how groups were organized, and which safety counts were recorded. It does not support a quantified conclusion about the primary response or its clinical importance. It also does not establish whether LIK066 is effective or ineffective for any condition.

14. Why This Trial Matters Statistically

This study is statistically informative as an example of a pharmacodynamic question organized around renal-function categories. Measuring 24-hour urinary glucose excretion at baseline and after treatment gives a defined continuous endpoint, while the additional Day 1 measurement describes an earlier post-dose time point. Collecting blood samples for pharmacokinetic assessment also reflects the study’s interest in how drug concentrations relate to renal function, although numerical pharmacokinetic findings are not reported in the registry information available.

The non-randomized parallel-group design is central to the interpretation. The normal renal-function group offers a reference for describing patterns across categories, but it does not create a randomized control comparison. This illustrates why the design of a study determines what a statistical contrast can mean: descriptive differences between groups are not automatically causal effects. The record itself cautions that the arms are not a like-for-like control comparison.

The endpoint definition also matters. A change from baseline is not interchangeable with a single post-treatment value, and the analysis population is defined around observed pharmacodynamic values with evaluability assessed at each time point. Those choices make missing-data reporting and the analysis method important for understanding the results. The registry record does not provide enough detail to assess these aspects fully.

Finally, the record shows why completeness matters for statistical interpretation. It identifies an endpoint and some safety counts, but the numerical primary outcome results, uncertainty estimates, detailed statistical methods, and multiplicity approach are not reported in the information available. Without the effect estimates and their precision, readers cannot judge the size or reliability of the measured response. Without a randomized control group, even reported group differences would require cautious interpretation. The study therefore highlights the distinction between a well-defined research question and the information needed to evaluate its results.

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.

A key limitation is that the numerical results for the primary endpoint are not reported in the registry record. The endpoint definition alone cannot show the observed change in urinary glucose excretion, its variability, or the precision of comparisons between renal-function groups. Numerical results for the other listed outcomes are also not included in the information available.

The non-randomized allocation means the groups are not like-for-like control groups. Differences among the renal-function categories may reflect participant characteristics as well as renal-function category. The registry record does not report detailed eligibility criteria, the definitions or thresholds for the renal-function categories, or an adjusted analysis that could help address measured group differences.

The analysis description is limited. The record identifies the Pharmacodynamic Analysis Set and says that participants needed evaluable data at each time point, but does not report missing-data counts, reasons for missingness, or sensitivity analyses. It does not report the model used, how baseline values were handled, confidence intervals, hypothesis tests, or a multiplicity strategy. These details are needed to assess the analysis and uncertainty.

There is also a design-label discrepancy: the official title says open-label, while the masking field says triple masked. The record does not explain how these descriptions fit together. The study is reported as completed, but that status does not resolve the absence of endpoint results or methodological detail. Safety reporting is similarly limited to summarized counts and listed terms, without detailed timing, causality assessment, or context for the percentages attached to the top serious terms.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Study of PK/PD, Safety and Tolerability of LIK066 in Patients With Decreased Renal Function. — NCT03131479.
• Registry record last updated 2021-01-05; status last verified 2019-06.
• Results first posted 2019-02-06.
• 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 completed phase 2, non-randomized, parallel-group study of LIK066 in patients with varying degrees of decreased renal function and subjects with normal renal function. Enrollment is reported as 53. The study dates are 2017-04-28 to 2018-01-16 for start and primary completion.

All five renal-function groups received LIK066 50 mg once daily before breakfast for 7 days. The primary endpoint was change from baseline in 24-hour urinary glucose excretion on Day 7, measured in grams and summarized as a mean with standard deviation. Urinary glucose excretion was measured at baseline, Day 1, and Day 7; blood samples were collected for pharmacokinetic assessment.

The primary numerical endpoint results and detailed statistical plan are not reported in the registry record. The record reports serious and other adverse-event counts by group and no deaths in the listed groups. Because allocation was non-randomized, the groups should not be treated as a like-for-like control comparison.