LIPS-A: Lung Injury Prevention Study With Aspirin: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for LIPS-A: Lung Injury Prevention Study With Aspirin (NCT01504867), a randomized phase 2 study. The primary outcome is Number of Participants Who Developed Acute Respiratory Distress Syndrome (ARDS) Within 7 Days.

2. Clinical Question

3. Trial Design

LIPS-A was a randomized, quadruple-masked, parallel-group phase 2 study sponsored by Mayo Clinic. The registry lists 400 participants enrolled. The posted primary analysis includes 195 participants in the aspirin group and 195 in the placebo group. Although those counts are the same, the relationship between the enrollment figure and the analysis counts is not explained in the registry record.

The aspirin group received a 325mg loading dose on study day one, followed by 81mg on days 2-7. The placebo group received matching lactose powder filled capsules on days 1-7. The primary outcome was the number of participants who developed ARDS within seven days from hospital presentation. The endpoint was defined using Berlin criteria modified to require invasive mechanical ventilation, and the analysis population is listed as intention-to-treat.

The registry lists the study as completed, with a start of 2012-01 and primary completion of 2015-09. These registry dates describe the study record; they do not provide additional detail about participant follow-up or the timing of individual analyses. The original sample-size justification, planned effect size, planned interim analyses, and full statistical analysis plan are not reported in the registry record.

Several secondary outcomes are listed, including hospital mortality, a combined ARDS-or-mortality outcome, mechanical ventilation, ventilator-free days, intensive care unit admission, and hospital length of stay. Numerical results are posted for only some of those outcomes in the record summarized by the available results. Results for outcomes without numerical estimates 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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intention-to-Treat

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: 400 subjects were randomized, and 10 subjects were excluded, leaving 390 in the final modified intention-to-treat analysis cohort.

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants Who Developed Acute Respiratory Distress Syndrome (ARDS) Within 7 Days, measured over Within seven days from hospital presentation.

The primary endpoint counts participants who developed ARDS within seven days from hospital presentation. The posted definition uses Berlin criteria, modified to require invasive mechanical ventilation. It is a binary outcome at the participant level: each participant either met the endpoint during the specified period or did not.

This kind of endpoint is useful because it makes the clinical event explicit and gives a defined time window for comparing randomized groups. A count is easy to interpret alongside the number of participants analyzed in each group. The related risk difference expresses the contrast as the event risk in the aspirin group minus the event risk in the placebo group; positive values indicate a higher observed event risk in the aspirin group, while negative values indicate a lower observed risk in that group.

The registry's stated primary hypothesis was that early aspirin administration would decrease the rate of developing acute lung injury during the first 7 days after hospital presentation. The posted primary outcome operationalizes this question as ARDS diagnosed within seven days, using the modified Berlin definition. Because the definition requires invasive mechanical ventilation, it is important to understand that the endpoint is not simply any lung injury or respiratory deterioration. The registry does not report further detail on how endpoint events were adjudicated or how missing endpoint status was handled.

7. Results Posted in the Registry

• Aspirin: 10.3% (20/195) versus 8.7% (17/195) on control; risk difference 1.5 percentage points (95% CI -4.3 to 7.4), risk ratio 1.18 (0.64–2.18); unadjusted two-proportion z-test p = 0.604.

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.

Hospital Mortality

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Aspirin: 7.2% (14/195) versus 7.2% (14/195) on control; risk difference 0.0 percentage points (95% CI -5.1 to 5.1), risk ratio 1.00 (0.49–2.04); unadjusted two-proportion z-test p = 1.000.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Aspirin and the control. The interval gives the range of effects that remain compatible with the data.

Number of Participants With ARDS or Mortality Within 7 Days

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Aspirin: 13.8% (27/195) versus 10.8% (21/195) on control; risk difference 3.1 percentage points (95% CI -3.4 to 9.6), risk ratio 1.29 (0.75–2.19); unadjusted two-proportion z-test p = 0.355.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Aspirin and the control. The interval gives the range of effects that remain compatible with the data.

Number of Subjects With Mechanical Ventilation at Any Time During Hospitalization

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Aspirin: 26.2% (51/195) versus 21.0% (41/195) on control; risk difference 5.1 percentage points (95% CI -3.3 to 13.5), risk ratio 1.24 (0.87–1.78); unadjusted two-proportion z-test p = 0.233.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Aspirin and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes with numerical results cover hospital mortality, the combined ARDS-or-mortality endpoint, and mechanical ventilation during hospitalization. In broad terms, the posted comparisons do not show a consistently precise separation between the randomized groups: the confidence intervals for the recalculated contrasts include no difference, and the registry-reported p-values do not indicate clear evidence of a group difference. The outcomes represent different aspects of illness and care, so they are not interchangeable measures of the primary ARDS endpoint.

The secondary findings should be read alongside, not as a replacement for, the primary result. The primary question concerned ARDS within seven days, while the secondary outcomes broadened the assessment to mortality, a combined endpoint, and other hospital events. Their general pattern does not resolve the uncertainty around the primary comparison, nor does it establish that all relevant outcomes were alike. Numerical results for ventilator-free days, intensive care unit admission, and hospital length of stay are not reported in the registry record.

General statistical principle: each additional outcome creates another opportunity for a chance finding when many comparisons are examined. Unless a testing hierarchy or multiplicity adjustment is planned and reported, secondary p-values are usually less conclusive than a single prespecified primary comparison. The registry record does not report a multiplicity adjustment or a hierarchy for these outcomes. Accordingly, secondary results are best treated as supportive context rather than independent confirmation. The record also does not report whether these outcomes were prespecified in a detailed analysis plan or how missing data were handled for them.

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

• Hospital Mortality
• Number of Participants With ARDS or Mortality Within 7 Days
• Number of Subjects With Mechanical Ventilation at Any Time During Hospitalization
• Mean Number of Days Participants Were Ventilator-Free To Day 28
• Number of Subjects Admitted to Intensive Care Unit (ICU)
• Mean Hospital Length of Stay

9. Statistical Interpretation

10. Statistical Methods Explained

The posted primary comparison is between two randomized groups: aspirin and placebo. The registry identifies the study as randomized, quadruple-masked, and parallel-group. Random allocation is intended to make the groups comparable on average at the start of a trial. Masking is intended to reduce the influence of expectations on care, outcome assessment, or reporting. Those are general purposes of these design features; the registry record does not describe how randomization or masking was implemented in practice.

What does a risk difference express?

For a binary endpoint, a risk is the proportion of participants who experience the event. A risk difference subtracts the comparison-group risk from the intervention-group risk. In this case, the posted estimate is 0.015, with aspirin contrasted against placebo. A positive estimate means the observed event risk was higher in the aspirin group; a negative estimate would mean it was lower. The estimate is an absolute contrast, rather than a relative measure such as a risk ratio.

The posted primary counts are 20 participants with ARDS among 195 in the aspirin group and 17 among 195 in the placebo group. The risk values are 0.103 and 0.087, respectively. These counts and risks describe the observed participants and are not themselves estimates of the exact risks in every population to which the results might be considered relevant.

How should the confidence interval be understood?

A confidence interval represents the uncertainty around an estimate under the statistical method used. It gives a range of values compatible with the observed data and method, rather than a guarantee that the true effect lies in that particular interval. The primary risk-difference interval is -0.043 to 0.073. Because it includes no difference and values in both directions, the data do not sharply distinguish a lower event risk from a higher event risk. A wide interval indicates less precision than a narrow interval would, although precision must be interpreted in relation to the outcome and effect scale.

What does the p-value contribute?

A p-value describes how unusual data at least as incompatible with a stated null hypothesis would be if that hypothesis and the analysis assumptions held. It does not give the probability that the null hypothesis is true, and it does not measure the size or clinical importance of an effect. The recalculated unadjusted primary p-value is 0.604. The registry reports a Wald analysis with p = 0.53. The registry record does not report enough detail to explain the difference between these values. Neither p-value should be interpreted in isolation from the estimate and its interval.

The recalculation is an unadjusted comparison from the posted summary statistics. It is not a reconstruction of an individual-participant analysis and does not add adjustment for covariates or other features not included in those summaries. The registry identifies the primary analysis population as intention-to-treat, but further detail about the analysis implementation is not reported in the registry record.

Why distinguish reported and recalculated analyses?

The registry's own primary analysis is reported as a Wald method, with p = 0.53. A separate unadjusted recalculation from the posted counts yields p = 0.604 for the risk-difference comparison. These are different reported analytic results, not grounds for replacing the registry's result with a more favorable one. The record does not explain whether the difference reflects a different test specification, rounding, or another analysis detail, so no explanation should be assumed. The discrepancy field is false; the numerical distinction is nevertheless worth making transparent.

General statistical principle: different tests or modeling choices can yield somewhat different p-values from the same underlying trial data. The estimate, its uncertainty, the analysis population, and the planned method all matter. Here, the registry's test label and p-value are known, but the full analysis plan and additional calculation details are not reported in the registry record.

What can be learned from the secondary outcomes?

For secondary binary outcomes with posted counts, the same broad concepts apply: compare event risks between groups, assess the estimated contrast, and examine its uncertainty. The registry reports secondary analyses using chi-squared methods. A chi-squared test evaluates evidence of a difference in categorical outcomes under its assumptions; it does not describe the size or precision of the difference by itself. The posted confidence intervals and effect estimates add that information for the recalculated comparisons.

General statistical principle: testing many outcomes increases the chance that at least one result may appear unusual even when there is no underlying difference. This is why secondary findings are generally interpreted cautiously when no multiplicity adjustment or prespecified testing hierarchy is reported. The registry record does not report such adjustment or hierarchy.

What is not documented?

The original sample-size assumptions, including the target effect and the trial's own power calculation, are not reported in the registry record. Details of interim analyses, missing-data procedures, and the handling of any deviations from the assigned groups are also not reported in the registry record. Those omissions limit what can be inferred about the intended analysis beyond the methods and populations explicitly identified in the registry. General statistical explanations in this discussion describe concepts; they do not fill those gaps or establish what the investigators planned.

11. Confidence Intervals and Precision

The primary risk-difference estimate is 0.015, with a 95% confidence interval from -0.043 to 0.073. In plain terms, the interval ranges from a negative difference, corresponding to a lower observed risk in the aspirin group, to a positive difference, corresponding to a higher observed risk in that group. It includes no difference. The trial therefore does not provide a narrowly defined estimate of the primary contrast.

The event counts were 20 of 195 participants in the aspirin group and 17 of 195 in the placebo group. The group risks were 0.103 and 0.087. The point estimate is only one value within the interval; it should not be treated as though it were known without uncertainty. The interval also indicates that effects of differing magnitude and direction remain compatible with the posted data and method.

General explanation: a confidence interval is a measure of statistical uncertainty around an estimate. Greater precision is usually reflected by a narrower interval, while a wider interval leaves more plausible values in play. An interval that includes no difference does not prove that the groups are identical; it means the data and method do not rule out no difference at the interval's stated confidence level. Nor does the interval establish that every value it contains is equally plausible.

Uncertainty is also evident in the secondary comparisons with posted confidence intervals. Those intervals include no difference as well. These outcomes are distinct from the primary endpoint and should not be combined into a single claim about precision. The registry does not report confidence intervals for some listed secondary outcomes, and numerical results for those outcomes are not reported in the registry record.

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 planning figures are illustrations based on the observed effect, not the original trial design. For the binary outcomes, the listed figures mean participants per arm; they are not total events. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each planning row uses the stated fraction of the observed effect as the effect to detect. The original trial's own design assumptions are not reported in the registry record.

The 80% power column gives the number of participants per arm that the illustration estimates would be needed to have an 80% chance of detecting the specified effect if that effect were the true one and the assumptions held. The 90% power column describes the corresponding planning target with a 90% chance. These are design-planning concepts, not probabilities that the trial's result is correct and not measures of whether the completed trial succeeded.

The rows that plan for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect let readers see how the planning requirement changes as the target effect changes. Smaller effects are harder to distinguish from random variation, so detecting smaller effects requires more participants under otherwise similar assumptions. The listed values can therefore be read as sensitivity illustrations across different assumed effects, rather than as a recommendation for a future study.

These figures are not observed power. Observed power is not a substitute for interpreting the estimated effect and its confidence interval. The original sample-size justification, the effect anticipated during the trial's design, and any allowance for loss to follow-up are not reported in the registry record. The planning numbers are computed from the observed effect and the stated assumptions, and should be read only in that context.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.087; treatment proportion p₁ = 0.103; average p̄ = 0.095.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.4144 = 0.8122.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4143 = 0.3487.
4. n = (0.8122 + 0.3487)² / (0.0154)² = 5,694.1, rounded up to 5,695 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
p0 <- 0.0871794871794872                          # control proportion
p1 <- 0.102564102564103                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(1504867)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 5,695 (80% power), 7,623 (90% power)
 75% of observed effect: n per arm = 9,940 (80% power), 13,306 (90% power)
 50% of observed effect: n per arm = 21,950 (80% power), 29,384 (90% power)
power.prop.test: 5694.1 
Simulated power at n = 5,695 per arm: 0.805 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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 registry reports the sponsor's primary analysis as a Wald analysis with p = 0.53. The unadjusted recalculation from the posted counts gives a risk difference of 0.015, with a 95% confidence interval from -0.043 to 0.073, and an unadjusted p-value of 0.604. The registry record does not provide enough detail to explain why the p-values differ, and the difference should not be attributed to a specific analytic choice without documentation.

The two analyses are not labeled identically: the registry reports a Wald method, while the recalculation is an unadjusted comparison based on the posted summary counts. The registry identifies the primary population as intention-to-treat. It does not report additional details that would allow the recalculation to reproduce every aspect of the sponsor's analysis. The discrepancy field is false, but that does not make the reported p-values numerically identical.

Both p-values indicate that the posted analysis does not show a clear separation between the groups. The risk-difference interval is useful for understanding the direction and range of effects compatible with the data. Neither the registry's p-value nor the recalculated p-value should be treated as a standalone measure of effect size or certainty. The sponsor's result remains the registry-reported analysis; the recalculation is supplementary and does not replace it.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study tests several outcomes or comparisons. Even if each individual test uses a conventional threshold, considering many tests can increase the chance of at least one result appearing unusual by chance. General statistical practice addresses this issue through prespecified testing hierarchies, adjusted thresholds, or other approaches, depending on the study aims. The registry record lists multiple secondary outcomes but does not report a multiplicity adjustment or a testing hierarchy. The secondary results should therefore be interpreted with caution and should not be treated as if they were independent primary findings.

The registry identifies the primary analysis population as intention-to-treat. This generally refers to analyzing participants according to their randomized group, regardless of treatment received, but the precise operational details for this study are not reported in the registry record. The posted primary counts include 195 participants in each group. The record lists enrollment of 400, but does not explain the relationship between total enrollment and the primary analysis counts.

Missing-data handling is not reported in the registry record. The record does not state whether any endpoint status was missing, how missing outcomes were classified, or whether any imputation or sensitivity analysis was performed. Those details matter because missing outcome information can affect estimates and uncertainty, especially if missingness differs between groups or relates to outcome status. No such pattern should be assumed from the posted counts.

The record also does not report the original statistical analysis plan, interim analyses, or detailed rules for the secondary analysis populations. It is therefore not possible to determine from the registry information whether the reported analyses followed a more detailed plan or whether additional analyses were conducted. These are limits on what can be assessed from the registry record, not evidence that any particular procedure was or was not used.

16. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: gastrointestinal bleeding (1.0%), bleeding stress ulcer (0.5%), chest pain (0.5%), hematoma (0.5%), anemia due to upper gi bleeding (0.5%).

The serious adverse event figures list 4 affected participants among 195 at risk in the aspirin group and 8 among 195 at risk in the placebo group. The record also lists other adverse events for 13 participants in the aspirin group and 5 in the placebo group, with 195 at risk in each group. These are descriptive counts. The registry record does not report a comparative statistical analysis for these safety counts, and the counts alone do not establish whether an event was caused by study treatment.

The listed serious adverse event terms include gastrointestinal bleeding at 1.0%, and bleeding stress ulcer, chest pain, hematoma, anemia due to upper GI bleeding, and hemoptysis at 0.5% each. These are the terms and percentages reported in the registry. They should be read as listed event information, not as a complete assessment of all possible harms or as a treatment-effect estimate. Death counts in the serious adverse event record are not reported.

Differences in adverse event counts can reflect chance and do not, without further context, show the cause or comparative risk of events. The registry record does not report event-level timing, severity beyond the serious-event classification, relatedness assessments, or a statistical comparison for these figures. The posted counts therefore support a descriptive account only.

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

The primary result describes an observed comparison in a randomized trial: 20 participants in the aspirin group and 17 in the placebo group developed ARDS within seven days, among 195 participants in each group. The risk difference was 0.015, and its 95% confidence interval ranged from -0.043 to 0.073. The interval includes no difference and allows effects in either direction. The result is therefore uncertain in both its direction and magnitude.

This does not mean the groups have been proven identical. A failure to show a clear statistical difference is not proof of equivalence, and the registry does not describe an equivalence or non-inferiority objective. Conversely, the point estimate alone does not establish that aspirin increased ARDS. It is the observed estimate in this sample, with uncertainty that must be considered.

The endpoint was specifically ARDS within seven days, defined using Berlin criteria modified to require invasive mechanical ventilation. It does not represent every form of acute lung injury, every later respiratory outcome, or the full range of patient outcomes. Secondary outcomes add context, but the available numerical results are limited, and unadjusted secondary comparisons carry less weight when multiple outcomes are assessed.

The registry record does not provide the original sample-size justification, missing-data procedures, or a full statistical analysis plan. Those gaps constrain how comprehensively the analysis can be evaluated. Results from this trial also do not by themselves settle questions about different populations, treatment regimens, or clinical settings. The statistical interpretation is limited to the posted trial design, outcomes, and results, and is not medical advice.

18. Why This Trial Matters Statistically

This trial illustrates why statistical interpretation should combine the event counts, effect estimate, confidence interval, and analysis method. The primary counts are straightforward to understand, but the risk-difference estimate remains uncertain: its interval includes both negative and positive values as well as no difference. Looking only at the observed counts or at a single p-value would leave out important information about that uncertainty.

It also demonstrates the value of distinguishing a registry-reported analysis from an unadjusted recalculation. The registry reports a Wald analysis with p = 0.53, while the recalculated unadjusted comparison gives p = 0.604. The record does not explain the difference. Stating both results transparently avoids presenting a recalculation as though it were the sponsor's analysis, while allowing readers to see what can be derived from the posted summary statistics.

The secondary outcomes show why a collection of outcomes needs a clear inferential plan. Several clinical events are listed, but the registry does not report a multiplicity adjustment or hierarchy. A pattern across outcomes can provide context, yet it cannot automatically be treated as multiple independent confirmations of the primary result.

Finally, the sample-size illustrations distinguish planning from inference. They show how assumptions about the effect to detect influence the number of participants needed, but they are not the trial's original design justification and are not observed power. Together, these points make LIPS-A a useful example of reading clinical trial results with attention to uncertainty, analysis provenance, outcome multiplicity, and the limits of registry reporting.

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 primary result is based on 195 participants in each group, with 20 ARDS events in the aspirin group and 17 in the placebo group. The confidence interval for the risk difference extends in both directions and includes no difference, limiting precision about the underlying contrast. The record does not report the original sample-size justification, so the intended detectable effect and design assumptions cannot be assessed from the posted information.

The registry gives a sponsor-reported Wald p-value of 0.53 and an unadjusted recalculated p-value of 0.604. It does not explain the difference. Although both results indicate that the available analysis does not show a clear group separation, the lack of detail prevents a full reconciliation of the analysis methods. The registry identifies an intention-to-treat primary population, but does not report detailed implementation or missing-data handling.

Only some listed secondary outcomes have numerical results available in the registry record. Results for ventilator-free days, intensive care unit admission, and hospital length of stay are not reported in the registry record. The record does not report a multiplicity correction or a prespecified testing hierarchy, making secondary comparisons less definitive. The safety data are descriptive counts and listed terms; comparative analyses and some event details are not reported.

The trial is identified as phase 2 and has a registry enrollment of 400, while the primary analysis lists 195 participants per group. The record does not explain this relationship. Further details about eligibility, endpoint adjudication, adherence, treatment discontinuation, and follow-up completeness are not reported in the registry record. These limitations restrict interpretation of the posted summary but do not establish that any unreported procedure was absent.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: LIPS-A: Lung Injury Prevention Study With Aspirin — NCT01504867.
• Registry record last updated 2017-03-06; status last verified 2017-01.
• Results first posted 2016-10-13.
• 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.

23. Record Summary

LIPS-A was a randomized, quadruple-masked, parallel-group phase 2 trial sponsored by Mayo Clinic. The registry lists 400 participants enrolled and identifies the study as completed. The primary question concerned whether early aspirin administration would reduce ARDS within seven days of hospital presentation, compared with matching placebo.

The primary intention-to-treat results report 20 ARDS events among 195 participants assigned to aspirin and 17 among 195 assigned to placebo. The recalculated risk difference is 0.015, with a 95% confidence interval from -0.043 to 0.073. The registry reports a Wald analysis with p = 0.53; the unadjusted recalculated p-value is 0.604. The interval includes no difference and effects in both directions.

Some secondary outcomes and adverse event counts are posted, but other listed secondary results, original design assumptions, missing-data procedures, and multiplicity methods are not reported in the registry record. The results are best understood as an imprecise comparison with limited detail about some analysis choices.