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 Relapse-Prevention Study With Levomilnacipran ER (F2695 SR) in Patients With Major Depressive Disorder (NCT01085812), a randomized phase 3 study. The primary outcome is Time to Relapse (Days).
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT01085812 |
| Phase | Phase 3 |
| Condition | Depression, Major Depressive Disorder |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Triple |
| Enrollment | 734 |
| Arms in the primary outcome | 2 |
| Lead sponsor | Forest Laboratories |
| Results posted | Yes |
2. Clinical Question
Population
The study concerned people with major depressive disorder. The primary endpoint population is described as the double-blind intent-to-treat population: 342 randomized participants who received study drug and were evaluated for the primary outcome measure. This description identifies the group included in the posted endpoint definition; the registry record does not give further detail about participant characteristics or how people entered the double-blind period.
Intervention
Participants assigned to the active-treatment group received oral levomilnacipran ER capsules once daily. The arm description lists 40, 80 or 120 mg/day. The registry record does not specify how those doses were selected or changed during treatment.
Comparator
The comparison group received matching placebo capsules by oral administration once daily. The primary outcome lists 112 participants in the placebo arm and 230 in the levomilnacipran ER arm, with endpoint values and measures of spread absent for both groups.
Primary question
The primary question was whether time to relapse, measured in days over 24 Weeks, differed between the levomilnacipran ER and placebo groups. Relapse was defined using prespecified symptom, clinical-impression, or treatment-discontinuation criteria. The registry record reports the endpoint definition but not the observed mean time to relapse, standard deviation, between-group estimate, confidence interval, or statistical test result. The posted results therefore do not establish the direction or precision of any treatment-group difference.
3. Trial Design
The registry describes a Phase 3, randomized, parallel-group, placebo-controlled study of levomilnacipran ER for relapse prevention in people with major depressive disorder. Its official title describes the study as multicenter, randomized, double-blind and placebo-controlled. The masking field is recorded as triple. The record does not explain how these masking descriptions relate to one another or identify which roles were masked.
The registry lists total enrollment as 734. The primary outcome population is separately described as 342 randomized participants who received study drug and were evaluated for that endpoint. The outcome arm counts are 112 for placebo and 230 for levomilnacipran ER. These figures describe different registry entries and should not be treated as interchangeable denominators. The record does not provide a participant flow account that explains the transition between enrollment and the primary outcome population.
The active intervention was oral levomilnacipran ER capsules, taken once daily, with the arm description listing 40, 80 or 120 mg/day. The comparator was matching placebo capsules, also taken orally once daily. The primary outcome timeframe is 24 Weeks. The registry lists a start of 2010-03, primary completion of 2011-10, and status as completed.
The purpose stated in the record is to evaluate safety and efficacy in preventing depression relapse. The primary endpoint is time to relapse in days. No protocol or statistical analysis plan is reported in the registry record, so details such as dose assignment procedures, treatment duration beyond the endpoint timeframe, stratification, allocation concealment, and planned handling of participants who discontinue cannot be assessed from this 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: Patients began with a 12-week open-label treatment period, followed by a 24-week double-blind treatment period.
Open-Label Period
| Stage | Placebo | Levomilnacipran ER |
|---|---|---|
| STARTED | 0 | 734 |
| COMPLETED | 0 | 494 |
| NOT COMPLETED | 0 | 240 |
Reasons for not completing this period:
| Reason | Placebo | Levomilnacipran ER |
|---|---|---|
| Adverse Event | 0 | 80 |
| Lack of Efficacy | 0 | 26 |
| Protocol Violation | 0 | 39 |
| Withdrawal by Subject | 0 | 53 |
| Lost to Follow-up | 0 | 42 |
Double-Blind Period
| Stage | Placebo | Levomilnacipran ER |
|---|---|---|
| STARTED | 113 | 235 |
| COMPLETED | 92 | 177 |
| NOT COMPLETED | 21 | 58 |
Reasons for not completing this period:
| Reason | Placebo | Levomilnacipran ER |
|---|---|---|
| Adverse Event | 3 | 8 |
| Protocol Violation | 2 | 7 |
| Withdrawal by Subject | 11 | 24 |
| Lost to Follow-up | 5 | 17 |
| Other Reasons | 0 | 2 |
Double-blind Intent-to-treat Population
| Stage | Placebo | Levomilnacipran ER |
|---|---|---|
| STARTED | 112 | 230 |
| COMPLETED | 92 | 174 |
| NOT COMPLETED | 20 | 56 |
Reasons for not completing this period:
| Reason | Placebo | Levomilnacipran ER |
|---|---|---|
| Adverse Event | 3 | 8 |
| Protocol Violation | 2 | 7 |
| Withdrawal by Subject | 11 | 22 |
| Lost to Follow-up | 4 | 17 |
| Positive serum pregnancy test result | 0 | 2 |
Analysis population for the primary outcome, as defined in the registry: The double blind Intent-to-treat population consists of 342 randomized participants who received study drug and were evaluated for the Primary Outcome Measure
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 Baseline Participant population is based on the 734 enrolled patients who received at least one dose of open-label treatment.
| Characteristic | Unit | Open Label Levomilnacipran ER |
|---|---|---|
| Participants analysed | 734 | |
| Age, Continuous | years | 42.2 (SD 12.3) |
| Age, Customized: 18 years to 19 years | Participants | 8 |
| Age, Customized: 20 years to 29 years | Participants | 151 |
| Age, Customized: 30 years to 39 years | Participants | 127 |
| Age, Customized: 40 years to 49 years | Participants | 208 |
| Age, Customized: 50 years to 59 years | Participants | 186 |
| Age, Customized: 60 years to 65 years | Participants | 54 |
| Sex: Female, Male: Female | Participants | 425 |
| Sex: Female, Male: Male | Participants | 309 |
| Region of Enrollment: United States | Participants | 683 |
| Region of Enrollment: Canada | Participants | 51 |
| Weight | kg | 83.41 (SD 18.43) |
| Body Mass Index (BMI) | Kilograms Per Meter Squared | 28.88 (SD 5.42) |
6. Primary Endpoint
The registry lists the primary outcome as Time to Relapse (Days), measured over 24 Weeks.
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | Days |
| Endpoint classification | Continuous Endpoint |
The primary endpoint is time to relapse, recorded in days over 24 Weeks. It is a continuous measure of the interval between the relevant study reference point and meeting the study’s relapse criteria. The registry describes the summary parameter as a mean and the measure of spread as a standard deviation. The values for both treatment groups are not reported in the registry record, so the mean time, variability, and difference between groups cannot be described.
Relapse was defined as meeting one or more listed criteria: a MADRS total score of at least 22 at 2 consecutive visits; an increase of 2 or more points in CGI-I score compared with the CGI-I score at Visit 9 at 2 consecutive visits; premature discontinuation due to insufficient therapeutic response; or a MADRS item 10 score of at least 4. This composite definition allows relapse to be identified through symptom scores, clinical-impression change, or discontinuation attributed to insufficient response. The registry does not report how often each criterion triggered an endpoint.
Time to relapse is relevant to a relapse-prevention question because it describes when a defined relapse event occurs, rather than only whether a participant meets a symptom threshold at a single assessment. Interpretation still depends on how follow-up, discontinuation, and participants who do not relapse are handled. Those analysis details, including whether and how observations were censored, are not reported in the registry record. The endpoint definition alone cannot establish the treatment comparison.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The central limitation for interpreting the primary outcome is that the registry lists the endpoint and its population but gives no numeric outcome values for either arm. The mean time to relapse and standard deviation are absent, and the record includes no treatment-effect estimate, confidence interval, or p-value. Consequently, the posted results do not show whether the groups had different average times to relapse, how large any difference was, or how precisely it was estimated. No direction of effect can be inferred from the endpoint definition or the arm sizes.
The primary outcome population is identified as 342 randomized participants who received study drug and were evaluated for the endpoint. The arm-level outcome entries list 112 participants in the placebo group and 230 in the levomilnacipran ER group, but report no values or spread. The registry also lists 734 total enrolled participants. These are distinct population descriptions in the record; without a participant flow account, their relationship cannot be fully evaluated. The number randomized, treated, evaluated, and included in any specific analysis should not be assumed to be the same.
The endpoint is described as a mean time in days, with standard deviation. A mean can communicate an average, while the standard deviation describes variability among observations. For time-to-event data, however, interpretation also requires knowing how participants without an observed relapse by the end of follow-up were treated analytically. The registry does not report that information or identify a time-to-event model. The posted endpoint summary is therefore insufficient to reconstruct the analysis or judge whether the selected summary fully addresses follow-up differences.
The registry record reports safety counts for several treatment periods or groups, including open-label levomilnacipran ER and double-blind treatment groups. Those counts are not substitutes for the missing primary efficacy result. Serious and other adverse-event counts describe safety reporting, not the comparative time-to-relapse estimate. In addition, the denominators differ across the listed groups, so direct comparisons require attention to which treatment period and population each number represents.
Overall, the record supports a description of the study question, endpoint definition, and some safety counts, but not a quantitative conclusion about the primary treatment comparison. Missing endpoint values are not evidence of no difference; they mean the posted results do not permit that difference to be estimated from this record. The absence of a reported confidence interval also prevents assessment of precision. Any stronger conclusion about efficacy, uncertainty, or clinical importance would require results that are not reported in the registry record.
9. Statistical Methods Explained
The registry identifies the primary measure as a continuous outcome summarized by a mean and standard deviation. It does not provide the group means or standard deviations, nor does it report an inferential analysis. The concepts below explain what these methods mean in general; they do not identify which calculations were actually conducted for this trial.
What does the mean describe?
In general, a mean is an average across observed measurements. For time to relapse, it would summarize the average number of days until participants met the defined relapse criteria, subject to the analysis population and rules for handling follow-up. A mean is most informative when the observations contributing to it are defined consistently and the treatment groups are compared using a method appropriate to the data. Here, the registry gives the intended summary type but not the numerical means. It is therefore not possible to describe the average in either group or the contrast between them.
A difference between group means, when reported, is an estimate of the contrast in average outcome under the analysis used. Its interpretation depends on the endpoint scale, population, and analysis assumptions. The record does not include such a contrast. No difference should be calculated from the posted information, because the group outcome values are missing.
What does the standard deviation describe?
In general, a standard deviation describes how spread out individual measurements are around their mean. It is not the same as a confidence interval: the standard deviation describes variation among observations, whereas a confidence interval describes uncertainty around an estimated quantity. Both are useful, but neither can be interpreted because the endpoint standard deviations and any confidence interval are not reported in the registry record.
Time-to-relapse observations can have features that complicate simple summaries. Some participants may not meet relapse criteria during the observed follow-up, and participants may leave the study before the endpoint is observed. In general, time-to-event methods can account for incomplete event observation through censoring, provided censoring rules and assumptions are specified. The registry does not report whether censoring occurred, how it was handled, or which analysis method was used. It is not possible to determine whether the reported mean-and-standard-deviation framework reflects a particular time-to-event approach.
Why do confidence intervals matter?
In general, a confidence interval gives a range of estimates compatible with the data and the method used, reflecting statistical uncertainty. A narrow interval indicates greater precision than a wide interval, while the location of the interval conveys the range of plausible treatment contrasts under that method. It does not by itself establish clinical importance. No confidence interval is reported for this endpoint, so neither the precision nor the plausible range of a treatment contrast can be assessed.
A p-value, when reported, measures how compatible the observed data are with a specified null hypothesis under the assumptions of the statistical test. It is not a measure of effect size, probability that a treatment works, or probability that the null hypothesis is true. The registry record does not report a p-value or name a test. Statistical significance cannot be evaluated from the posted endpoint entry.
What does randomization contribute?
In general, random allocation aims to make comparison groups similar with respect to both measured and unmeasured baseline factors on average. It supports a causal comparison when trial conduct, follow-up, and analysis preserve the benefits of randomization. The registry identifies the study as randomized, but does not report the sequence-generation or allocation-concealment procedures. It also does not provide the detailed analysis population or participant flow needed to assess how exclusions or missing follow-up might affect the randomized comparison.
Masking can reduce the influence of expectations on participant reports, clinical decisions, and outcome assessment. The official title describes a double-blind study, while the registry masking field is recorded as triple. The record does not explain which people were masked or how masking was maintained. The use of a matching placebo is described, but the record does not report an assessment of whether masking remained effective.
How should planning illustrations be read?
In general, a sample-size calculation is a planning exercise based on assumptions about the effect to detect, variability or event frequency, allocation, significance level, and desired power. It is not an observed trial result. The stated planning assumptions describe a two-sided significance level of 0.05, equal allocation, a normal approximation, and an effect defined as a stated fraction of the observed effect. They also distinguish total events for time-to-event calculations from participants per arm for other calculations. The registry outcome entries do not include the observed endpoint values needed to evaluate an effect-based illustration for this outcome.
Planning power must not be confused with observed power after a trial. In general, observed results are better interpreted through the estimated effect and its uncertainty than through a post hoc power calculation. Any sample-size illustration is conditional on its assumptions and does not establish that the trial was adequately powered for the actual effect. The registry record does not report the trial’s own sample-size justification or statistical plan, so it is not possible to establish how the stated illustration relates to the original design.
Over-dispersion is a general concern when count data vary more than a model assumes; it can make standard errors too small if ignored. That issue is not directly established by this continuous time-to-relapse endpoint entry, and the registry does not report a count model for the primary outcome. More broadly, choosing an analysis requires matching the model to the outcome scale and data structure. Since the primary analysis method is absent, the assumptions used for the reported endpoint cannot be evaluated.
10. Multiplicity, Missing Data and Analysis Populations
The registry lists one outcome measure and no posted analysis records. It also reports no posted secondary outcomes. These entries describe what is present in the registry record; they do not establish that no other outcomes or analyses were planned or conducted. The statistical analysis plan, including any prespecified hierarchy or adjustment for multiple comparisons, is not reported in the registry record.
Multiplicity arises in general when several outcomes, time points, subgroups, or analyses are tested, because repeated testing can increase the chance of a false-positive finding. The record does not provide enough information to determine whether multiple testing was relevant or how it was handled. Since no primary inferential result is posted, there is also no reported p-value whose multiplicity adjustment can be assessed.
The primary endpoint population is described as 342 randomized participants who received study drug and were evaluated for the outcome. That wording identifies the analyzed population as recorded, but does not explain the exclusions or missing observations that led to it. The registry does not report the amount or pattern of missing endpoint data, reasons for missingness, imputation procedures, sensitivity analyses, or rules for handling participants who discontinued or did not relapse during follow-up.
In general, missing-data methods depend on why observations are absent and on the estimand the analysis is intended to address. Complete-case analysis, imputation, and time-to-event censoring involve different assumptions and are not interchangeable. Without an analysis plan or participant-level accounting, the consequences of missing data cannot be judged. The registry’s use of the term intent-to-treat should be read alongside its stated restriction to participants who received study drug and were evaluated; the record does not provide enough detail to assess how closely the analyzed population matches a full randomized-group analysis.
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 |
|---|---|---|---|
| Open Label Levomilnacipran ER | 7 | 734 | 1.0% |
| Placebo - Double Blind Treatment | 4 | 112 | 3.6% |
| Levomilnacipran ER - Double Blind Treatment | 2 | 233 | 0.9% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Open Label Levomilnacipran ER | 0 of 734 |
| Placebo - Double Blind Treatment | 0 of 112 |
| Levomilnacipran ER - Double Blind Treatment | 0 of 233 |
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 |
|---|---|
| Open Label Levomilnacipran ER | 448 of 734 |
| Placebo - Double Blind Treatment | 31 of 112 |
| Levomilnacipran ER - Double Blind Treatment | 68 of 233 |
Most frequent serious adverse event terms
| Event term | Organ system | Open Label Levomilnacipran ER | Placebo - Double Blind Treatment | Levomilnacipran ER - Double Blind Treatment |
|---|---|---|---|---|
| Ankle fracture | Injury, poisoning and procedural complications | 1 of 734 | 0 of 112 | 0 of 233 |
| Blood creatine phosphokinase MB increased | Investigations | 1 of 734 | 0 of 112 | 0 of 233 |
| Blood pressure increased | Investigations | 0 of 734 | 1 of 112 | 0 of 233 |
| Cellulitis | Infections and infestations | 0 of 734 | 1 of 112 | 0 of 233 |
| Chest pain | General disorders | 1 of 734 | 0 of 112 | 0 of 233 |
| Cholelithiasis | Hepatobiliary disorders | 1 of 734 | 0 of 112 | 0 of 233 |
| Deep vein thrombosis | Vascular disorders | 0 of 734 | 1 of 112 | 0 of 233 |
| Drug abuse | Psychiatric disorders | 1 of 734 | 0 of 112 | 0 of 233 |
| Drug hypersensitivity | Immune system disorders | 0 of 734 | 1 of 112 | 0 of 233 |
| Fall | Injury, poisoning and procedural complications | 1 of 734 | 0 of 112 | 0 of 233 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Open Label Levomilnacipran ER | Placebo - Double Blind Treatment | Levomilnacipran ER - Double Blind Treatment |
|---|---|---|---|---|
| Headache | Nervous system disorders | 141 of 734 | 11 of 112 | 31 of 233 |
| Nausea | Gastrointestinal disorders | 160 of 734 | 5 of 112 | 13 of 233 |
| Constipation | Gastrointestinal disorders | 82 of 734 | 5 of 112 | 2 of 233 |
| Dizziness | Nervous system disorders | 78 of 734 | 5 of 112 | 4 of 233 |
| Hyperhidrosis | Skin and subcutaneous tissue disorders | 80 of 734 | 1 of 112 | 4 of 233 |
| Dry mouth | Gastrointestinal disorders | 78 of 734 | 1 of 112 | 3 of 233 |
| Upper respiratory tract infection | Infections and infestations | 51 of 734 | 10 of 112 | 17 of 233 |
| Insomnia | Psychiatric disorders | 63 of 734 | 5 of 112 | 5 of 233 |
| Heart rate increased | Investigations | 54 of 734 | 1 of 112 | 3 of 233 |
| Nasopharyngitis | Infections and infestations | 25 of 734 | 9 of 112 | 20 of 233 |
Serious events with the highest arm-level rate: blood pressure increased (0.9%), cellulitis (0.9%), deep vein thrombosis (0.9%), drug hypersensitivity (0.9%), pneumonia (0.9%).
The registry reports serious adverse events for an open-label levomilnacipran ER group and for double-blind placebo and levomilnacipran ER groups. In the open-label group, 7 of 734 participants are listed as having a serious adverse event. In double-blind treatment, the registry lists 4 of 112 participants in the placebo group and 2 of 233 in the levomilnacipran ER group. Deaths are listed as 0 in each of these groups.
The record also lists other adverse events in 448 of 734 participants in the open-label group, 31 of 112 in the placebo group, and 68 of 233 in the double-blind levomilnacipran ER group. These categories and denominators refer to different group descriptions and should be read in their stated treatment-period context. The open-label group has a different denominator from the double-blind groups, and the record does not provide enough detail to treat them as a single direct comparison.
The listed serious-event terms include Blood pressure increased, Cellulitis, Deep vein thrombosis, Drug hypersensitivity, and Pneumonia, each reported as 0.9%, and Intestinal ischaemia, reported as 0.4%. These are registry-listed event terms, not evidence by themselves that treatment caused an event. The record does not give a complete account of event timing, duration, severity beyond the serious-event classification, or comparative statistical analysis. Counts should therefore be read descriptively and not as proof of a treatment-related difference.
12. What the Result Does, and Does Not, Mean
The registry record establishes that the study asked a relapse-prevention question in major depressive disorder and defined relapse using symptom scores, clinical-impression change, or premature discontinuation for insufficient therapeutic response. It also identifies the intended primary summary as mean time to relapse in days over 24 Weeks. These details clarify what the trial was designed to measure, but do not reveal what the primary outcome showed.
The group-level endpoint means and standard deviations are not reported in the registry record. There is no posted treatment contrast, confidence interval, or p-value. As a result, the data in the record cannot show whether time to relapse was longer or shorter in either group, how large a difference might have been, or how much uncertainty surrounded an estimate. Missing results do not demonstrate that the groups were the same; they leave the comparison unresolved.
The record lists safety counts, including serious adverse events and deaths, for the specified groups. These figures can describe what was recorded in those groups, but they do not establish causation or replace a comparative efficacy analysis. Differences in denominators and treatment-period descriptions also limit simple comparisons across the listed groups. A fuller safety interpretation would require more information about event definitions, timing, follow-up, and attribution.
In general, a trial result is interpreted by considering the estimated effect, its precision, the analysis population, and the way missing observations and follow-up were handled. Here, key pieces of that evidence are not reported in the registry record. The record therefore supports a description of the study design and endpoint, not a conclusion that levomilnacipran ER did or did not prevent relapse. Nor does it support a judgment about the clinical importance of a treatment difference. Those judgments require outcome estimates and analysis details that are absent.
13. Why This Trial Matters Statistically
This trial illustrates an important distinction between a clearly specified research question and an interpretable result. The registry identifies a randomized, placebo-controlled relapse-prevention study and describes a time-to-relapse endpoint with operational criteria. That information helps readers understand what event the investigators intended to measure and which participant group was identified for the primary outcome.
At the same time, an endpoint definition is not an outcome estimate. For quantitative interpretation, readers need the observed group results and a measure of uncertainty. Without the means, standard deviations, treatment contrast, or confidence interval, the primary comparison cannot be assessed. Reporting the sample sizes alone cannot indicate the direction, magnitude, or precision of the result.
The record also demonstrates why population labels and denominators matter. Total enrollment, the primary endpoint population, and the safety group denominators are not identical entries. Clear participant flow and explicit analysis-population definitions help readers understand who contributed to each result and whether missing follow-up or discontinuation could affect interpretation.
Finally, statistical conclusions depend on methods as well as numbers. The registry does not report the statistical analysis plan, handling of incomplete time-to-relapse observations, or multiplicity procedures. General planning illustrations cannot substitute for those details or for the actual trial estimates. The study is therefore useful as an example of how a registry can document design and endpoint definitions while leaving the central efficacy result and its precision unavailable to readers.
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 main trial-specific limitation is the absence of numeric primary endpoint results. Although the registry specifies mean and standard deviation as the summary measures, neither is reported for either arm. There is no treatment-effect estimate or uncertainty interval, and the record does not identify a statistical test. The primary question therefore cannot be answered from the posted outcome entry.
The record gives several population counts without a participant flow explanation. Total enrollment is 734, while the primary outcome population is described as 342 participants, with arm counts of 112 and 230. The registry does not explain the transition between these descriptions or report how many participants were randomized, treated, assessed, or excluded at each stage beyond the stated population details. This makes it difficult to evaluate the relationship between enrollment and the endpoint analysis.
Further limitations concern the time-to-relapse analysis. The registry does not report follow-up completeness, censoring rules, how participants who did not relapse were handled, or the analysis method. It also does not report the amount, reasons, or handling of missing endpoint data. The relapse definition is detailed, but the frequency of each criterion and the procedures used to adjudicate events are not reported in the registry record.
The record identifies randomization and masking, but does not describe sequence generation, allocation concealment, or who was masked. Its title says double-blind while the masking field says triple; the difference is not explained. The statistical analysis plan and sample-size justification are also not reported. Finally, safety entries include open-label and double-blind groups with different denominators, and the record does not provide enough context to use them as a direct treatment comparison. These gaps limit both efficacy interpretation and assessment of how robust the posted safety descriptions are.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Relapse-Prevention Study With Levomilnacipran ER (F2695 SR) in Patients With Major Depressive Disorder — NCT01085812.
- Registry record last updated 2020-01-13; status last verified 2019-12.
- Results first posted 2020-01-13.
- 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
The registry record describes NCT01085812, a completed Phase 3 randomized, parallel-group study of levomilnacipran ER versus matching placebo for relapse prevention in major depressive disorder. It lists enrollment of 734 and identifies the primary outcome as time to relapse in days over 24 Weeks. Relapse criteria include specified MADRS and CGI-I thresholds, premature discontinuation for insufficient therapeutic response, or a MADRS item 10 score of at least 4.
The primary outcome population is described as 342 randomized participants who received study drug and were evaluated. The outcome entries list 112 participants for placebo and 230 for levomilnacipran ER, but no group means or standard deviations. No primary treatment-effect estimate, confidence interval, or p-value is reported in the registry record. Safety counts are listed for open-label and double-blind groups, including 0 deaths in each listed group. The record does not report the analysis plan, missing-data procedures, or participant flow needed to resolve the primary comparison.