A Study to Evaluate the Efficacy and Safety of Safinamide, as add-on Therapy, in Idiopathic Chinese Parkinson's Disease (PD) Patients With Motor Fluctuations Treated With Stable Doses of Levodopa: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate the Efficacy and Safety of Safinamide, as add-on Therapy, in Idiopathic Chinese Parkinson's Disease (PD) Patients With Motor Fluctuations Treated With Stable Doses of Levodopa (NCT03881371), a randomized phase 3 study. The primary outcome is Change From Baseline to Week 16 in the Mean Total Daily "OFF" Time.

2. Clinical Question

OFF time refers to diary periods marked by stiffness, a marked decrease in mobility, or immobility. The primary measure therefore focuses on time spent in a defined motor state, rather than a general rating of Parkinson’s disease severity. The diary also distinguished ON time, ON time with different levels of dyskinesia, and sleep. This gives the endpoint a daily-life focus, while relying on patients’ completion and classification of diary periods.

The registry identifies this as a phase III, randomized, double-blind, placebo-controlled study. Its stated question is about the comparative change in OFF time over the treatment period, not about every symptom, longer-term outcomes, or outcomes beyond the measures and follow-up reported in the registry record. No broader claim follows from this endpoint alone.

3. Trial Design

The registry record describes a phase III, multicentre, randomized, double-blind, parallel-group study comparing safinamide with placebo. The sponsor is Zambon SpA, and the study status is completed. The record lists a start date of 2019-08-01 and primary completion on 2021-08-20. Enrollment is listed as 307. The brief study description planned 306 randomized patients, with 153 in each group; those planning figures are distinct from the analysis counts reported for the primary endpoint.

Participants received safinamide or matching placebo as add-on therapy to stable levodopa treatment, which could be used alone or with other anti-Parkinson drugs. The described safinamide schedule began at 50 mg once daily and increased to 100 mg once daily after week 2. The described placebo schedule followed the same dose-increase schedule. Treatment continued for 16 weeks. The registry does not report further details about how randomization was generated or concealed.

The primary endpoint was change from baseline to week 16 in mean total daily OFF time, measured in hours through 24-hour patient diary cards. The analysis population was the full analysis set: patients who gave informed consent, were randomized, and received at least one dose or partial dose of study drug. The posted primary arm summaries include 151 participants in the safinamide group and 154 in the placebo group.

The registry also lists secondary outcomes concerning pain, ON time, dyskinesia, UPDRS measures, and clinical global impressions. Numerical arm summaries and analyses are available for some secondary measures, but results for the remaining listed measures are not reported in the registry record. Details of the study’s original sample-size justification and the full statistical analysis plan 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: Patients who met the inclusion and none of the exclusion criteria were enrolled to the study. All study assessments were performed as per the schedule of assessment. The study was composed of a screening period (up to 2 weeks prior to the start of treatment, with 1 screening visit) and a treatment period (16 weeks).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full analysis set population (FAS) included all patients who provided informed consent, were randomized and received at least 1 dose or partial dose of the study drug.

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: Safety population were included all patients who provided informed consent and received at least 1 dose or partial dose of study drug.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline to Week 16 in the Mean Total Daily "OFF" Time, measured over At baseline and Week 16.

The primary endpoint is change from baseline to week 16 in mean total daily OFF time, expressed in hours. Participants recorded their daily states using diary cards divided into 30-minute periods. The diary options distinguished OFF, ON without dyskinesia, ON with non-troublesome dyskinesia, ON with troublesome dyskinesia, and asleep. OFF was defined for participants as stiffness, a marked decrease in mobility, or immobility.

This endpoint is used to quantify the amount of each day spent in the specified OFF state. A change score compares the week-16 measure with the baseline measure, so the reported group means describe change over the study period rather than the absolute daily OFF time at week 16. A negative change indicates a decrease in the measured hours of OFF time from baseline.

As a general statistical point, diary-based measures can capture repeated experiences during ordinary daily life, but they depend on consistent recording and on participants applying the diary definitions. The registry describes the diary categories but does not report diary-completion rates or how incomplete diary records were handled. The endpoint is one measure of motor fluctuations; by itself it does not describe every aspect of Parkinson’s disease or establish what an individual participant experienced.

7. Results Posted in the Registry

• Safinamide: mean -1.93 versus -0.88 on control; difference -1.05 (95% CI -1.62 to -0.48), standardized effect d = -0.41; z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Change From Baseline to Week 16 in Pain Severity, as Assessed by an 11 Point Numerical Rating Scale (NRS)

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Safinamide: mean -0.00 versus -0.00 on control; difference 0.00 (95% CI -0.45 to 0.45), standardized effect d = 0.00; z-test p = 1.000.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Safinamide and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline to Week 16 in the Mean Total Daily "ON" Time

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Safinamide: mean 1.30 versus 0.51 on control; difference 0.79 (95% CI 0.12 to 1.46), standardized effect d = 0.28; z-test p = 0.021.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Safinamide than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline to Week 16 in the Mean Daily "ON" Time With no/Non Troublesome Dyskinesia

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Safinamide: mean 1.30 versus 0.39 on control; difference 0.91 (95% CI 0.17 to 1.65), standardized effect d = 0.30; z-test p = 0.016.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Safinamide than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted numerical secondary results have a mixed pattern across measures. The two reported ON-time outcomes show larger mean increases in the safinamide group than in the placebo group, and the sponsor’s ANCOVA results for those measures have confidence intervals above zero. For pain severity, the posted arm means are both -0.0, and the sponsor’s ANCOVA confidence interval includes zero. These outcomes measure different experiences and should not be treated as interchangeable with daily OFF time.

The ON-time findings are directionally consistent with the primary result in the broad sense that they concern time spent in motor states, but they do not independently establish the primary endpoint or explain its mechanism. The pain measure addresses a different symptom. The registry also lists UPDRS and clinical global impression outcomes, but their numerical results are not reported in the registry record. It is therefore not possible to characterize the full pattern across all listed secondary outcomes.

Secondary results generally carry less weight when several outcomes are examined and no adjustment for multiple comparisons is reported. Each additional test creates another opportunity for a nominally small p-value, even when there is no true effect on any of the outcomes. This is a general statistical concern, not a claim about how the trial’s analysis plan was set. The registry record does not report whether multiplicity was controlled, which outcomes were prioritized beyond the primary endpoint, or whether the secondary analyses were exploratory.

Accordingly, secondary estimates add context and can suggest areas for further study, but they should be interpreted alongside their confidence intervals, the number of outcomes considered, and the absence of a reported multiplicity strategy. They do not replace the primary analysis, and unreported secondary results should not be assumed to support or contradict it.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Change From Baseline to Week 16 in Pain Severity, as Assessed by an 11 Point Numerical Rating Scale (NRS)
• Change From Baseline to Week 16 in the Mean Total Daily "ON" Time
• Change From Baseline to Week 16 in the Mean Daily "ON" Time With no/Non Troublesome Dyskinesia
• Change From Baseline to Week 16 in the Unified Parkinson's Disease Rating Scale (UPDRS) Total Score During the "ON" Phase
• Change From Baseline to Week 16 in the UPDRS Part II Activities of Daily Living (ADL) Score During the "ON" Phase
• Change From Baseline to Week 16 in the UPDRS Part III (Motor Function) Score During the "ON" Phase
• Clinical Global Impression of Severity (CGI-S) Score Assessed at Week 16
• Clinical Global Impression of Change (CGI-C) Assessed at Week 16

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: it is a mean change in hours. A mean summarizes the central value of a group’s measurements, while the standard deviation describes how spread out individual measurements are around that mean. A mean difference compares the group means on the same measurement scale. It is not the same as the difference between outcomes for each matched participant, and it does not imply that all participants changed by the group average.

What does the unadjusted re-calculation represent?

The re-calculation compares the posted mean changes for safinamide and placebo without covariate adjustment. It reports a mean difference of -1.05 hours and an unadjusted p-value of <0.001. This provides a transparent comparison based on the posted group summaries, but it does not reproduce the trial’s full analysis model. In particular, the registry’s ANCOVA result is an adjusted least-square mean estimate, and the covariates and other model details are not reported in the registry record.

The re-calculation uses the reported sample sizes and standard deviations for the two groups. As a general statistical principle, the uncertainty of a mean difference depends on both the variability of observations and the number of observations. More variable measurements tend to make an estimate less precise, while more observations can improve precision, all else being equal. These principles explain why group sizes and standard deviations accompany the means; they do not establish the design assumptions used by the trial sponsor.

What does the ANCOVA result represent?

ANCOVA is a method for comparing group outcomes while adjusting for specified covariates. The registry reports a least-square mean result of -1.10 hours, a 95% confidence interval from -1.643 to -0.555, and p <.0001. A least-square mean is a model-based group estimate, rather than simply the raw arithmetic mean. Adjustment can change an estimate or its precision, depending on the model and data. The registry record does not report which covariates were included, how model assumptions were assessed, or how missing observations entered this analysis; those details cannot be inferred from the word ANCOVA alone.

The reported ANCOVA and the unadjusted re-calculation point in the same direction and are similar in magnitude. They are not identical quantities: one is the sponsor’s model-based analysis, and the other is a simple unadjusted comparison of summary statistics. The registry record does not flag a discrepancy between them. For interpretation of the trial’s own result, the sponsor’s analysis is the primary reported analysis, while the re-calculation is a check based on the posted summaries.

How should the p-values be understood?

A p-value describes how unusual data at least as discrepant as those observed would be under a particular null model and its assumptions. It is not the probability that the null hypothesis is true, and it does not measure the probability that the finding is due to chance in a general sense. It also does not communicate the size or practical importance of the estimated difference. The unadjusted p-value and the sponsor’s ANCOVA p-value come from different analyses, so they should not be treated as interchangeable.

The sponsor reports a superiority analysis. That label describes the stated comparison framework; the numerical result still needs to be read alongside the estimate, confidence interval, population, and endpoint. Statistical evidence from one outcome does not establish a result for every secondary endpoint or every possible clinical outcome.

Why do the diary and analysis population matter?

The primary measure is based on participant diary cards, which classify 30-minute periods into specified states. As a general measurement issue, self-recorded outcomes may be affected by recording completeness and interpretation of category definitions. The registry does not report diary-completion information or sensitivity analyses for alternative handling of missing diary entries.

The full analysis set is defined in the registry as participants who consented, were randomized, and received at least one dose or partial dose. This is the population attached to the primary endpoint description. The record does not give a fuller account of exclusions from other analyses or the exact analysis population for every secondary result. Likewise, it does not report the original sample-size justification, planned interim analyses, or the complete statistical analysis plan. Those omissions limit how fully the model choices and analysis decisions can be audited from the registry record.

11. Confidence Intervals and Precision

The sponsor’s primary estimate is -1.10 hours, with a 95% confidence interval from -1.643 to -0.555. A confidence interval is a range of values produced by a method designed, over repeated use under its assumptions, to capture the underlying parameter at the stated rate. In this trial, it expresses uncertainty about the adjusted group-level estimate of change in daily OFF time. It is not a range containing a specified proportion of individual participants’ outcomes.

Both confidence limits are negative, so the interval is consistent with a larger average reduction in OFF time in the safinamide group than in the placebo group under the reported analysis. The interval also shows that the estimate is not known with exact precision: a range of effect magnitudes remains compatible with the data and analysis. The p-value gives a related but different summary; it does not replace the estimate or its interval.

The unadjusted re-calculation reports a mean difference of -1.05 hours, and its p-value is <0.001. The recalculated confidence limit on the positive side is not quoted because the posted value has more than three decimal places. The sponsor’s interval is the appropriate interval to cite as the reported ANCOVA result.

Precision depends on measurement variability, sample size, and the analysis model. As a general point, diary-based measurement and missing outcome data can affect uncertainty, but the registry record does not report enough detail to quantify those effects. The confidence interval describes uncertainty under the reported analysis; it does not account for every possible source of bias, model misspecification, or limits to generalizability.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The sample-size entries are participants per arm, not total events. The planning illustration uses a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It considers an effect equal to 100%, 75%, or 50% of the observed effect. These are illustrative calculations based on the observed effect, not the trial’s original design justification; that original justification is not reported in the registry record.

The 80% power column gives the estimated number of participants per arm for a hypothetical study to have an 80% chance of rejecting the null hypothesis under the stated assumptions, if the chosen effect and model assumptions were correct. The 90% power column expresses the same idea at a higher target chance of detecting the specified effect. Power is a design calculation, not a measure of how likely the observed result is true.

For the primary outcome, the entries are 93 participants per arm for 80% power and 124 participants per arm for 90% power when planning for 100% of the observed effect. Planning for 75% of the observed effect gives 165 and 221 participants per arm, respectively; planning for 50% gives 371 and 496. The pattern illustrates the general principle that smaller effects require more participants to detect with the same target power, all else being equal.

These figures are not observed power. They should be read as conditional planning illustrations rather than as evidence that the completed trial had a particular chance of finding its result. The trial’s own planning assumptions and justification are not reported in the registry record.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -1.050; pooled standard deviation σ = 2.549.
2. n = 2 × (1.96 + 0.842)² × 2.549² / -1.050² = 92.5, rounded up to 93 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -1.05                      # observed difference in means
sigma <- 2.54944392888619                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(3881371)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 93 (80% power), 124 (90% power)
 75% of observed effect: n per arm = 165 (80% power), 221 (90% power)
 50% of observed effect: n per arm = 371 (80% power), 496 (90% power)
power.t.test: 93.5 
Simulated power at n = 93 per arm: 0.794 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The sponsor’s reported primary analysis is an ANCOVA comparison of least-square means. It estimates a difference of -1.10 hours, with a 95% confidence interval from -1.643 to -0.555 and p <.0001. This is the trial’s own reported analysis and should take precedence when describing the sponsor’s result.

The simple re-calculation from the posted arm means gives a mean difference of -1.05 hours and an unadjusted p-value of <0.001. Its direction and approximate size are consistent with the sponsor’s estimate. The two results are not identical because one is a model-based adjusted analysis and the other is an unadjusted calculation from group summaries. The registry record does not report the ANCOVA covariates, so the specific source of the numerical difference cannot be determined.

The registry record does not identify a discrepancy between the sponsor analysis and the recalculation. The recalculation is therefore best used as a transparent check on the posted summary data, not as a replacement for the trial’s prespecified or full analysis. Details of the original analysis plan and whether every model choice was prespecified are not reported in the registry record.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies one primary endpoint and lists several secondary outcomes. It reports analyses for the primary endpoint and some secondary measures, but a multiplicity procedure is not reported in the registry record. When researchers test multiple outcomes, the chance of at least one nominally positive result can increase. As a general statistical approach, multiplicity may be addressed through prespecified testing sequences, adjusted significance thresholds, or other procedures. None should be attributed to this trial without a report of the plan.

The primary population is described as the full analysis set, including patients who consented, were randomized, and received at least one dose or partial dose of study drug. The registry gives primary arm counts of 151 and 154. For two reported ON-time outcomes, the arm counts are 137 and 130. The record does not explain why those secondary analysis counts differ from the primary counts. The reason should not be assumed to be dropout, diary incompleteness, or any particular exclusion.

Handling of missing data is not reported in the registry record. This includes the method used for missing primary or secondary measurements, whether any imputation was performed, and whether sensitivity analyses assessed alternative assumptions. As a general matter, missing-data methods can affect estimates and uncertainty when the probability of a value being missing is related to outcomes or participant characteristics. The posted summaries alone cannot show whether that concern affected these results.

The registry reports an ANCOVA for the primary endpoint, but does not report the covariates or fuller model specification. Randomization generation, allocation concealment, detailed analysis populations for every measure, and planned interim analyses are also not reported in the registry record. These gaps limit assessment of the statistical plan and of how robust the result is to alternative analysis choices; they do not by themselves establish that the analyses were inappropriate.

16. 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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: dizziness (0.7%), vascular headache (0.7%), ventricular extrasystoles (0.7%), haemorrhoids (0.7%), chest discomfort (0.7%).

The posted safety counts show serious adverse events in 8 of 151 participants at risk in the safinamide group and 5 of 154 in the placebo group. Other adverse events are reported for 42 of 151 and 35 of 154, respectively. The registry also reports 1 death in the safinamide group and 0 in the placebo group. These are counts within the reported groups; they are not, by themselves, evidence that study treatment caused an event or death.

The serious-event term list includes dizziness, vascular headache, ventricular extrasystoles, haemorrhoids, chest discomfort, and completed suicide, each listed at 0.7%. The record does not attach these terms to treatment groups in the term list, so group-specific attribution should not be inferred from those entries. The death count and the serious-event term list are separate reported summaries; the registry does not state that they represent the same event.

Safety counts require context about event definitions, follow-up, exposure, and participant characteristics. The study lasted 16 weeks, and the registry does not report enough detail to establish comparative risks over longer periods or to determine causation. These figures describe the posted safety data, not individualized risk.

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

The primary analysis estimates a larger average decrease in daily OFF time in the safinamide group than in the placebo group over the reported study period. The sponsor’s ANCOVA estimate is -1.10 hours, with a 95% confidence interval from -1.643 to -0.555. The unadjusted comparison of posted arm means is similar in direction. These results describe group averages for the endpoint and analysis population in this trial.

They do not show that every participant experienced a decrease, that the size of change was the same for everyone, or that an individual can expect a particular outcome. A group mean can conceal variation in responses. The registry reports standard deviations for the arm summaries, but those do not identify each participant’s experience.

The result is specific to Chinese patients with idiopathic Parkinson’s disease and motor fluctuations who were receiving stable levodopa treatment, under the study’s add-on treatment conditions and 16-week follow-up. The registry does not establish whether the estimate applies to other populations, treatment settings, doses, or longer time periods. It also does not report results for every secondary outcome listed in the record.

Statistical evidence and clinical importance are distinct questions. A confidence interval and p-value describe the estimate’s statistical uncertainty under an analysis; they do not set a threshold for a change that patients would consider important. The registry does not report a threshold for clinically meaningful change in OFF time. No conclusion about individual treatment decisions follows from the statistical result alone.

The safety summaries also require cautious interpretation. Counts of serious and other adverse events, and the reported deaths, describe events observed in the groups but do not establish their cause. The record does not provide the additional information needed to draw conclusions about long-term safety or uncommon events.

18. Why This Trial Matters Statistically

This trial offers a clear example of how a clinical registry can contain both a sponsor-reported model-based analysis and enough summary statistics for an independent, simple comparison. The estimates are similar in direction and approximate magnitude, while remaining distinct because the sponsor used ANCOVA and the re-calculation is unadjusted. Keeping those analyses separate helps readers understand what was reported by the trial and what can be checked from summary data.

The endpoint also illustrates the value and limitations of patient diaries. OFF time is a defined daily experience recorded in repeated periods, rather than a single broad judgment at the end of follow-up. Such measures can be closely tied to daily functioning, but their interpretation depends on the diary categories and the completeness of recording. The registry describes the categories but does not report diary-completion details.

Statistically, the result is more informative when read as an estimate with an interval than as a p-value alone. The confidence interval communicates a range of plausible adjusted group differences under the reported analysis, while the p-value addresses compatibility with a null model. Neither alone describes how participants varied or establishes the clinical importance of the estimated change.

The record also makes clear why secondary outcomes and missing-data methods matter. Additional measures may add context, but the registry does not report a multiplicity strategy or complete results for every listed secondary outcome. Further details about analysis specifications and missing data would help readers assess the robustness and scope of the findings.

19. 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 registry record does not report the original sample-size justification, the full statistical analysis plan, planned interim analyses, or the covariates used in the primary ANCOVA. It also does not describe randomization generation or allocation concealment. These omissions prevent a full assessment of how the analysis was planned and implemented.

The primary measure relies on patient diary cards. Although the registry defines the diary categories and identifies the 30-minute recording periods, diary completion, missing diary entries, and the method for handling incomplete records are not reported in the registry record. The reasons for differences in the arm counts across some reported outcomes are likewise not stated.

The reported follow-up is 16 weeks. Longer-term outcomes are not reported in the registry record. The available safety summaries give event counts and a list of serious-event terms, but do not provide enough detail to assess causation or characterize longer-term safety. The serious-event terms are not linked to treatment groups in the listed term summary.

Numerical results are not reported for every secondary outcome named in the registry. A multiplicity procedure is also not reported, limiting interpretation of nominal secondary p-values as confirmatory evidence. Finally, the primary estimate applies to the stated population and add-on treatment conditions. The registry record does not establish generalizability to other populations or settings.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study to Evaluate the Efficacy and Safety of Safinamide, as add-on Therapy, in Idiopathic Chinese Parkinson's Disease (PD) Patients With Motor Fluctuations Treated With Stable Doses of Levodopa — NCT03881371.
• Registry record last updated 2024-03-20; status last verified 2024-03.
• Results first posted 2024-03-20.
• 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.

23. Record Summary

NCT03881371 is a completed phase III, randomized, double-blind, placebo-controlled, parallel-group study sponsored by Zambon SpA. It enrolled 307 and studied add-on safinamide compared with placebo in Chinese patients with Parkinson’s disease and motor fluctuations on stable levodopa treatment. The described treatment period was 16 weeks.

The primary outcome was change from baseline to week 16 in mean total daily OFF time, measured by patient diary. The sponsor’s ANCOVA estimate was -1.10 hours, with a 95% confidence interval from -1.643 to -0.555 and p <.0001. An unadjusted re-calculation from the posted arm summaries gave a mean difference of -1.05 hours and p <0.001.

Some secondary outcomes and safety counts are also reported. Details about the original sample-size justification, multiplicity, missing-data handling, and several analysis specifications are not reported in the registry record.