Laparoscopic Peritoneal Lavage vs Laparoscopic Sigmoidectomy in Perforated Acute Diverticulitis: a Multicenter Prospective Observational Study (STELLA Study): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Laparoscopic Peritoneal Lavage vs Laparoscopic Sigmoidectomy in Perforated Acute Diverticulitis: a Multicenter Prospective Observational Study (STELLA Study) (NCT03008707), a registered phase not stated study. The primary outcome is Short-term Morbidity.

2. Clinical Question

The clinical question is comparative, but the study is described as prospective and observational rather than randomized. That distinction matters for interpretation: patients receiving LPL and LS may differ in ways that also relate to their outcomes. The registry record does not report the allocation process, the reasons clinicians selected each procedure, or whether any adjustment was planned to address differences between groups.

The brief summary frames the study as an evaluation of the two surgical strategies in complicated acute diverticulitis. It does not establish that the study can isolate a causal effect of procedure choice. Without outcome estimates and information about the groups' baseline characteristics, the comparative question remains unanswered by the posted registry results.

3. Trial Design

The registry identifies the STELLA Study as a multicenter prospective observational study. It lists enrollment of 66 participants, a start date of 2015-11, primary completion on 2018-12-31, and status as completed. The sponsor is Azienda Ospedaliero, Universitaria Pisana. These registry entries describe the study's administrative record; they do not supply a full protocol or a report of the findings.

The arm descriptions identify patients who underwent laparoscopic peritoneal lavage and patients who had a laparoscopically approached sigmoidectomy. The registry intervention listing names LPL. Allocation is not stated, and the record explicitly flags that this is not a randomized comparison. The two arms therefore should not be interpreted as if assignment had made them equivalent at the start of follow-up.

The primary outcome is short-term morbidity, measured as a count of participants and assessed within 30 days. The registry also names mean postoperative time, average length of postoperative hospital stay, recurrent colonic diverticulitis rate, and incisional hernia rate as secondary outcomes. It lists 8 outcome measures overall, but does not report results for those named outcomes in the information recorded.

The primary outcome population description says that, in the LPL group, 1 patient out of 28 was excluded because of conversion to open surgery and resection. The record does not explain whether this exclusion applied to every outcome analysis, nor does it report the corresponding analysis population for the LS group. Details such as eligibility criteria beyond the summary, follow-up completeness, and treatment assignment procedures 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

Analysis population for the primary outcome, as defined in the registry: In Laparoscopic Peritoneal Lavage, 1 patient out of 28 was excluded because of conversion to open surgery and resection

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Short-term Morbidity, measured over 30 days.

Short-term morbidity is the registry's primary endpoint, with a 30-day timeframe and a measure defined as the count of participants. In a binary outcome, each participant is classified according to whether the outcome occurred during the stated assessment period; the count records how many participants experienced it. The registry record does not define which complications or events qualify as morbidity, or how the endpoint was assessed.

Using a participant count can make a clinical outcome easier to interpret than a collection of event counts, particularly when the question concerns how many people experienced at least one qualifying outcome. However, that interpretation depends on a clear definition of the qualifying event and consistent ascertainment across groups. Neither the detailed morbidity definition nor the assessment procedures are reported in the registry record.

The endpoint is relevant to a short-term comparison of surgical strategies because it is framed around outcomes after the procedure, over the stated 30-day period. Relevance does not by itself establish that the measure is comprehensive or comparable between groups. The posted results do not report the number of participants with morbidity in either group, an effect estimate, or its precision. Consequently, the endpoint's comparative result cannot be interpreted from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a participant count mean?

General statistical explanation: For a binary endpoint, each participant is categorized according to whether an event meeting the outcome definition occurred. A participant count is the number classified as having that event. To interpret the count, readers also need the group denominator, a clear event definition, and a description of how missing observations were handled. The registry names the primary measure as a count of participants and gives a 30-day timeframe, but it does not report the primary outcome counts or define morbidity in detail.

What would an effect estimate add?

General statistical explanation: Group counts alone do not fully describe a comparison. An effect estimate expresses the contrast between groups on a stated scale, while a confidence interval describes the uncertainty around that estimate. A narrow interval indicates greater precision than a wide interval, but an interval still depends on the data and analysis assumptions. The registry record reports no primary effect estimate or confidence interval, so neither the size nor the precision of a comparative morbidity result can be assessed.

Why does the observational design matter?

General statistical explanation: Random allocation is one way to make treatment groups comparable with respect to both measured and unmeasured characteristics, on average. In an observational study, treatment choice may instead relate to patient condition, clinician judgment, or other circumstances. If those characteristics also relate to outcomes, a crude difference between groups may reflect those differences as well as any treatment association. Statistical adjustment can address measured differences when suitable data and methods are available, but it cannot automatically remove bias from unmeasured factors.

The registry describes STELLA as observational and says allocation is not stated. It does not report baseline characteristics, adjustment variables, or an analysis plan. Therefore, the record does not establish whether the groups were similar or whether any adjusted comparison was performed. No causal interpretation should be inferred from the study label or from the presence of two treatment groups alone.

Why do event definitions and follow-up matter?

General statistical explanation: A binary endpoint depends on a decision rule: which events count, what observation period applies, and how events are recorded. If groups are assessed differently or follow-up is incomplete, the observed counts may not be directly comparable. The stated primary timeframe is 30 days, but the registry does not report the operational definition of morbidity, adjudication procedures, or completeness of follow-up. The term short-term morbidity should therefore be read as the registry's outcome label, not as a fully specified event definition.

How should planning illustrations be read?

General statistical explanation: Sample-size planning concerns the number of participants needed under stated assumptions to detect an effect at a chosen error rate and power. A calculation based on an observed effect is a retrospective planning illustration, not evidence that the trial was originally designed with that target and not a measure of observed power. The record describes a planning illustration using a two-sided significance level of 0.05, equal allocation, and a normal approximation. It does not report the study's own sample-size justification in the registry record. The illustration should not be mistaken for a documented prospective design decision.

In general, a power calculation depends on the assumed effect, outcome variability or event frequency, allocation, and statistical method. When the observed effect is used as the assumed target, the illustration inherits uncertainty from the observed data. In this registry record, no primary endpoint result or analysis is listed, so a reader cannot use the record to evaluate the observed effect underlying a primary-outcome planning calculation. A planning number, where displayed separately, would still be an assumption-based illustration rather than evidence that the trial could or could not detect a particular effect.

Why does over-dispersion matter?

General statistical explanation: Over-dispersion occurs when observed variability is greater than a model assumes. It is especially relevant for count outcomes when events vary substantially across participants or when observations are more heterogeneous than expected under a simple model. Ignoring over-dispersion can make uncertainty estimates too small. This primary outcome is described as a binary participant count, not a rate or repeated event count, and the registry record does not report a model or any over-dispersion assessment. It would not be appropriate to assume that such a method was used.

More generally, a statistical method should match the outcome scale, design, follow-up, and missingness. The registry record does not report a test, model, confidence-interval method, covariate adjustment, or interim analysis plan. These omissions do not prove that no such methods were used in a separate study report; they mean that they are not reported in the registry record. Interpretation should remain limited to the information that the record actually documents.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Laparoscopic Peritoneal Lavage", "Laparoscopically Approached Sigmoidectomy")
n      <- c(27, 38)
events <- c(8, 1)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Laparoscopic Peritoneal Lavage  27  8  29.6  13.8  50.2  15.9  48.5  15.9  48.7
ARM  Laparoscopically Approached Sigmoidectomy  38  1  2.6  0.1  13.8  0.5  13.5  0.6  13.5

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 8 outcome measures, including short-term morbidity and the named secondary outcomes of mean postoperative time, average length of postoperative hospital stay, recurrent colonic diverticulitis rate, and incisional hernia rate. Considering multiple outcomes can create multiplicity: in general, when many hypotheses are tested, the chance of at least one apparently notable result can increase. Researchers may address this through a prespecified hierarchy, adjusted thresholds, or other strategies. Any multiplicity strategy is not reported in the registry record, and no analysis entries are listed.

The record does not report how missing outcome data were handled, whether follow-up was complete, or whether participants were excluded from particular analyses. These details matter because a count of events is interpretable only in relation to the participants whose outcome status is known. The primary population description states that, in the LPL group, 1 patient out of 28 was excluded because of conversion to open surgery and resection. It does not state whether this exclusion was limited to the primary endpoint, how the conversion was classified elsewhere, or how the analysis population was defined for the other outcomes.

The registry record does not describe an intention-to-treat population, a per-protocol population, imputation, or sensitivity analyses. These are general analysis approaches, not methods that can be attributed to this study without documentation. The record also does not report interim analyses or stopping rules. Those elements should be treated as unknown rather than inferred from the completed status or the available outcome listings.

12. Safety Results

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

Deaths

Other (non-serious) adverse events

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

The registry lists 0 serious adverse events among 27 participants at risk in the LPL group and 0 among 38 participants at risk in the laparoscopically approached sigmoidectomy group. It also lists 0 other adverse events and 0 deaths in each group, using the same at-risk counts. The serious adverse event term list is empty.

These are the recorded safety counts in the registry. A zero count means no events were entered for that category in the listed group; it does not establish that the underlying risk is zero, that all participants were observed completely, or that no events outside the recorded categories occurred. The registry record does not report the detailed safety definitions, ascertainment process, or follow-up completeness for these entries.

Safety counts should also be kept distinct from the primary outcome. Short-term morbidity is the named primary endpoint, but its group counts are not reported. The zero adverse-event entries therefore cannot be used as a replacement for the missing primary morbidity results or as a complete account of all postoperative outcomes.

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

The record establishes that a completed multicenter prospective observational study was registered to compare LPL with laparoscopically approached sigmoidectomy in complicated acute diverticulitis. It identifies short-term morbidity within 30 days as the primary endpoint and records 0 serious adverse events, 0 other adverse events, and 0 deaths in each group's safety entries. These are descriptions of the study record, not estimates of comparative effectiveness.

The primary result needed to answer the stated comparison is not reported in the registry record. There are no group counts for short-term morbidity, no effect estimate, and no precision interval. The direction and magnitude of any difference between the procedures therefore cannot be determined from the posted results. The named secondary outcomes also lack reported results in the record.

Even if outcome estimates were available, the observational design would require attention to how treatment groups differed and how those differences were handled. Allocation is not stated, and adjustment methods are not reported. Consequently, the registry record does not establish that any observed contrast would be attributable to procedure choice rather than other differences between the groups.

The completion status and enrollment entry do not resolve these uncertainties. Enrollment of 66 describes the registry's enrollment field, while the safety entries use group-specific at-risk counts. The primary population description also notes an exclusion in the LPL group following conversion to open surgery and resection. The record does not explain how that participant was handled across all outcomes.

In short, the record documents a clinically focused observational comparison and limited safety counts. It does not provide the primary outcome evidence required to judge the comparative short-term morbidity result, its precision, or its susceptibility to confounding.

14. Why This Trial Matters Statistically

This study matters statistically because it poses a comparative question in a setting where treatment assignment is observational. That design can generate useful clinical data, but it makes the route from observed group differences to causal conclusions especially dependent on how treatment choice and patient characteristics are handled. Here, allocation is not stated, and the registry does not report baseline comparisons or adjusted analyses. Those omissions limit what can be learned about comparability from the registry record.

The endpoint also illustrates why clear outcome reporting is essential. The record names short-term morbidity, specifies a 30-day timeframe, and defines the measure as a participant count. Yet it does not state which events qualify or report the group counts. Without the event definition and results, the reader cannot assess the magnitude or precision of the primary comparison.

The listed zero adverse-event counts are informative as registry entries, but they answer a narrower question than the primary endpoint and do not establish absence of risk. Keeping safety categories separate from the morbidity endpoint prevents a reassuring-looking count from being mistaken for a complete outcome analysis.

Finally, the record lists several outcomes but no analysis entries. In general, multiple outcomes raise questions about prespecification and multiplicity, while exclusions raise questions about analysis populations and missing data. Because those methods are not documented in the registry record, they remain important uncertainties rather than details that can be filled in by assumption. The statistical value of the record is therefore chiefly in clarifying the design and identifying what results and methods would be needed for a fuller interpretation.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

A central limitation of the registry record is that it does not report the primary outcome counts, a comparative estimate, or its uncertainty. The endpoint is named as short-term morbidity within 30 days, but its event definition and assessment procedures are not reported. The named secondary outcomes likewise have no reported results in the record.

The study is observational, and allocation is not stated. Baseline characteristics, reasons for procedure selection, and statistical adjustment methods are not reported. This prevents assessment of how comparable the groups were or whether confounding was considered. The record does not report whether the outcome analyses followed a prespecified statistical plan.

The primary population description notes that 1 patient out of 28 in the LPL group was excluded because of conversion to open surgery and resection. The record does not describe the analysis populations for each outcome, the handling of missing data, or whether this exclusion was applied consistently. Follow-up completeness and outcome ascertainment details are also not reported.

Although the registry lists 8 outcome measures and several named secondary outcomes, it lists 0 analyses. No multiplicity strategy or interim analysis information is reported. The safety entries record zero events in the listed categories, but the definitions and completeness of safety reporting are not described. These limitations concern what can be concluded from the registry record; they do not establish what may or may not be available in separate study materials.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Laparoscopic Peritoneal Lavage vs Laparoscopic Sigmoidectomy in Perforated Acute Diverticulitis: a Multicenter Prospective Observational Study (STELLA Study) — NCT03008707.
• Registry record last updated 2019-09-25; status last verified 2019-08.
• Results first posted 2019-09-25.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

19. Record Summary

The STELLA Study is listed as a completed multicenter prospective observational study sponsored by Azienda Ospedaliero, Universitaria Pisana. The registry records enrollment of 66, a start date of 2015-11, and primary completion on 2018-12-31. It describes a comparison of laparoscopic peritoneal lavage and laparoscopically approached sigmoidectomy in complicated acute diverticulitis.

Short-term morbidity within 30 days is the primary outcome. The record lists 8 outcome measures and 0 analyses. It reports no primary endpoint comparison or results for the named secondary outcomes. Safety entries list zero serious adverse events, zero other adverse events, and zero deaths in both groups, with 27 participants at risk in the LPL group and 38 in the sigmoidectomy group.

The record describes an exclusion in the LPL group following conversion to open surgery and resection. Allocation, analysis methods, missing-data handling, and multiplicity procedures are not reported in the registry record. The posted information therefore describes the study design and recorded safety counts but does not establish the comparative primary outcome.