Recurrence Following Nonoperative Management of 1st Episode of Hinchey II Diverticulitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Recurrence Following Nonoperative Management of 1st Episode of Hinchey II Diverticulitis (NCT01986686), a randomized na study. The primary outcome is Primary Study Endpoint.

2. Clinical Question

3. Trial Design

This was a randomized controlled trial of surgery versus observation following nonoperative management of a first episode of Hinchey II diverticulitis. The registry lists the allocation as randomized, masking as none, and the model as sequential. The record does not explain the meaning of the sequential model or describe the procedures used to generate or conceal the allocation.

The registry lists enrollment of 107. Its arm summaries report 81 participants in the observational group and 26 in the surgery group. The observational group was to receive clinical follow-up without further intervention until the primary endpoint was reached. Participants in the surgery group were offered colon resection. The listed intervention is colon resection; details about the procedure, timing, and uptake are not reported in the registry record.

The trial is marked completed. Its listed start is 2011-10 and its primary completion date is 2016-07-16. The primary outcome timeframe is a minimum of one year after enrollment. These registry dates do not establish the actual follow-up duration for each participant. The record does not report the distribution or completeness of follow-up.

Secondary outcomes listed include length of hospital stay, mortality, readmission, postoperative complications, and recurrence and treatment. The registry reports five posted secondary outcomes and six outcome measures overall. It lists no posted analyses. Details of the original statistical design, including the trial's own sample-size justification, 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

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 Primary Study Endpoint, measured over Minimum of 1 year after enrollment.

The primary endpoint counts participants with recurrent diverticulitis of the colon. The registry uses a specific definition: an acute episode had to be confirmed at CT scan and require hospitalization with intravenous antibiotics. It is not simply any return of symptoms or any repeat diagnosis; the recorded event definition sets a threshold based on imaging and treatment setting.

A defined endpoint helps make the outcome more consistent across participants and groups. Requiring CT confirmation and hospitalization with intravenous antibiotics focuses the measure on episodes meeting the trial's stated criteria. It also means that episodes not meeting those criteria are not counted as primary events under this definition. The endpoint is reported as a count of participants, rather than as a time-to-event estimate.

The registry specifies a minimum timeframe of one year after enrollment. It does not report participant-level follow-up times, how the minimum was achieved, or whether follow-up was complete for every participant. Those details matter when interpreting counts, because the opportunity to observe an event depends on follow-up. The exact follow-up experience and the handling of participants without complete outcome data are not reported in the registry record.

7. Results Posted in the Registry

• Surgery: 7.7% (2/26) versus 32.1% (26/81) on control; risk difference -24.4 percentage points (95% CI -38.8 to -10.0), risk ratio 0.24 (0.06–0.94); unadjusted two-proportion z-test p = 0.014.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is binary at the participant level: each participant is counted as having or not having the qualifying recurrence. For this kind of outcome, a comparison can be expressed as a difference between event proportions, a ratio of risks, or an odds ratio. These measures answer related but distinct questions, so their numerical scales should not be treated as interchangeable.

What does a risk difference describe?

A risk difference subtracts one group's event proportion from the other group's event proportion, using the stated comparison direction. A value below zero in this comparison means that the observed event proportion was lower in the surgery group than in the observational group. The posted estimate is negative, and its confidence interval remains below zero. This describes the direction of the estimated contrast, not certainty about what would happen in a different population or under different follow-up conditions.

How do risk ratios and odds ratios differ?

A risk ratio compares the event proportions directly. An odds ratio compares event odds, where odds are the event count relative to the count without the event. For outcomes that are not rare, odds ratios can appear farther from one than risk ratios, so the measures should be interpreted on their own scales. Both were included in the registry comparison, alongside the risk difference. The event counts and denominators remain essential context for all of them.

What does the p-value tell the reader?

The registry posts an unadjusted p-value of 0.014. In general, a p-value measures how compatible the observed data are with a specified null model, assuming that model and the test's assumptions. It is not a measure of effect size and does not express the probability that a result is due to chance. The precise test and its assumptions are not reported in the registry record, so the p-value should be read as the posted unadjusted result rather than as a complete account of the analysis.

Why does a confidence interval matter?

In general, a confidence interval gives a range of estimates compatible with the data and the interval method under repeated sampling assumptions. It communicates precision as well as direction. For the posted risk difference, the interval lies below zero, but the width also matters: a range can contain materially different estimates even when it remains on one side of the null value. The specific method used to calculate the interval is not reported in the registry record.

What can the arm counts tell us?

The observational group has 26 recorded primary events among 81 participants; the surgery group has 2 among 26. These are participant counts, not event rates calculated over person-time. A count-based comparison does not describe the timing of recurrence, and it cannot account for differences in follow-up duration unless the analysis incorporates that information. The registry specifies a minimum timeframe but does not report a time-to-event analysis for the primary endpoint.

In general, random allocation is intended to make comparison groups similar, on average, with respect to factors that could affect outcomes. It does not guarantee identical groups, especially in a trial with different group sizes. The record identifies the study as randomized but does not report allocation procedures, baseline characteristics, or an adjusted analysis. No further claims about balance or adjustment can be made from the posted analysis details.

Over-dispersion is a general concern when outcome variability exceeds what a chosen statistical model expects; accounting for it can affect uncertainty estimates. It is not reported whether over-dispersion was relevant or assessed in this trial. The primary endpoint is presented as participant counts, and the registry does not identify a model for the posted comparison. Likewise, methods for missing data, analysis populations, and multiplicity are not reported in the registry record. These omissions limit how fully the inferential calculations can be assessed from the record alone.

10. Confidence Intervals and Precision

The risk-difference estimate has a confidence interval entirely below zero. That placement indicates that the range of estimates represented by the interval has the same direction as the point estimate: a lower observed event proportion in the surgery group. The interval does not include the no-difference value. The posted unadjusted p-value is 0.014, which is consistent with evidence against a no-difference null model under the test used.

A confidence interval is useful because a single point estimate can make the result appear more exact than it is. In general, the interval shows a range of values compatible with the observed data and the calculation method, under repeated-sampling assumptions. A narrower interval indicates greater statistical precision, while a wider interval indicates greater uncertainty. The interval method itself is not reported in the registry record.

Precision should also be considered alongside the actual group counts: 26 events among 81 observational participants and 2 among 26 surgery participants. The surgery group is smaller, and its event count is low. Such counts can make estimates sensitive to a small number of outcomes. The confidence interval reflects sampling uncertainty under its method, but it does not account for every possible source of uncertainty, such as incomplete follow-up, outcome misclassification, or unreported analytic choices.

The posted interval supports a direction for the estimated comparison, but it is not a guarantee that the true effect lies within the interval for this particular trial. Nor does statistical precision alone establish clinical importance. The registry does not report a threshold for a clinically meaningful difference, so the clinical importance of the observed estimate cannot be judged from that information.

11. 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 participants per arm, not total participants and not total events. They are illustrations based on the observed effect, rather than the trial's own original design assumptions. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is expressed as a stated fraction of the observed effect. The original trial's design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the planned number of participants per arm under the stated assumptions for an 80% chance of detecting the selected effect if that effect were the true one and the model assumptions held. The 90% power column gives the corresponding number per arm for a 90% chance. These are planning concepts, not guarantees about the result of a future study. The displayed figures are 41 and 55 participants per arm for 100% of the observed effect; 82 and 109 for 75% of the observed effect; and 202 and 270 for 50% of the observed effect, respectively.

Smaller effects are harder to distinguish from random variation, so the planning illustration requires more participants per arm as the assumed effect gets smaller. The figures are not observed power and do not describe the probability that this completed trial detected an effect. They are hypothetical planning estimates under the listed assumptions, not a reconstruction of the trial's actual design.

12. 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 = 0.321; treatment proportion p₁ = 0.077; average p̄ = 0.199.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5646 = 1.1065.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5376 = 0.4524.
4. n = (1.1065 + 0.4524)² / (-0.2441)² = 40.8, rounded up to 41 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 <- 0.320987654320988                          # control proportion
p1 <- 0.0769230769230769                          # 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(1986686)
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 = 41 (80% power), 55 (90% power)
 75% of observed effect: n per arm = 82 (80% power), 109 (90% power)
 50% of observed effect: n per arm = 202 (80% power), 270 (90% power)
power.prop.test: 40.8 
Simulated power at n = 41 per arm: 0.826 (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.

13. Multiplicity, Missing Data and Analysis Populations

The registry lists five secondary outcomes: length of hospital stay, mortality, readmission, postoperative complications, and recurrence and treatment. It also reports six outcome measures overall. The record lists zero analyses, so it does not provide posted statistical analyses for those secondary outcomes. Their results, effect estimates, uncertainty intervals, and analysis methods are not reported in the registry record.

Multiplicity arises when several outcomes or comparisons are tested. In general, conducting multiple tests can increase the chance of at least one apparently unusual result under a collection of null hypotheses. Researchers may address this with a prespecified hierarchy or an adjustment method, but the planned approach for this trial is not reported in the registry record. The primary comparison is identified as unadjusted; no multiplicity adjustment is reported.

The record does not report how missing primary outcome data were handled, whether every randomized participant was included in the primary analysis, or what analysis population was used. It also does not report exclusions after randomization, adherence to the surgery offer, or treatment crossovers. These details are important because an analysis of participants as randomized may differ from one based on treatment received or on participants with complete follow-up.

The registry specifies a minimum primary-outcome timeframe of one year after enrollment, but does not report completeness of follow-up, censoring rules, or imputation methods. A reader therefore cannot determine from the record whether the posted counts represent complete outcome ascertainment in both groups. No interim analyses or stopping rules are reported in the registry record. Their absence from the record should not be interpreted as proof that none occurred.

14. 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 5% reporting threshold.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: partial small bowel obstruction due to ileus (3.8%), surgical site infection (3.8%).

The serious adverse event summary reports 0 affected participants among 81 at risk in the observational group and 2 among 26 at risk in the surgery group. The other adverse event summary reports 0 affected participants in each group, with 81 and 26 participants at risk, respectively. These are the posted counts and denominators; the registry does not provide additional detail about event timing or how events were attributed.

The listed serious adverse event terms are partial small bowel obstruction due to ileus at 3.8% and surgical site infection at 3.8%. The record does not explain whether these terms refer to distinct participants or how the percentages were calculated. Death counts are not reported in the registry record. A blank or unreported death count should not be read as a count of zero.

These safety figures are descriptive. The groups differ in size, and the registry does not report a formal comparative safety analysis, follow-up completeness for adverse events, or detailed severity and duration information. They should be read alongside the posted definitions and denominators, without treating an unreported detail as evidence that an event did or did not occur.

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

The posted primary outcome comparison records 26 qualifying recurrences among 81 observational participants and 2 among 26 participants in the surgery group. The estimated risk difference is negative, and its confidence interval lies entirely below zero; the unadjusted p-value is 0.014. Together, these describe a lower observed event proportion in the surgery group for the registry's specific recurrence definition.

The result concerns acute episodes confirmed by CT scan and requiring hospitalization with intravenous antibiotics. It does not cover every possible symptom, outpatient episode, or event outside that definition. The record gives a minimum follow-up timeframe of one year after enrollment, but does not report the actual follow-up distribution or the completeness of event ascertainment.

Statistical evidence against a no-difference model is not the same as proof of an effect in every setting. The confidence interval describes uncertainty under its calculation method, and the method is not reported in the registry record. The p-value does not measure clinical importance, and the record does not state what size of difference would be meaningful to patients or clinicians.

The results do not establish how participants who did not receive the offered procedure were analyzed, how missing outcomes were handled, or whether any adjusted analyses were conducted. The registry record also does not provide the original sample-size justification or a detailed analysis plan. Those gaps mean the posted comparison should be interpreted as the registry's reported result, with the trial and outcome definitions in mind, rather than as a complete account of all possible analyses or consequences of either strategy.

This statistical interpretation is not medical advice. Decisions about care require clinical context that is not contained in the registry results.

16. Why This Trial Matters Statistically

This trial illustrates why a binary clinical endpoint needs a precise definition. Counting only a CT-confirmed acute episode that required hospitalization with intravenous antibiotics makes clear which recurrences contribute to the primary outcome. It also defines the boundary of the result: events not meeting those criteria are not represented in the primary count.

It also illustrates the value of reading event counts alongside comparative estimates. The observational group had 26 events among 81 participants, while the surgery group had 2 among 26. The risk-difference estimate, its confidence interval, and the unadjusted p-value offer different views of the comparison: direction and magnitude, uncertainty, and compatibility with a null model under the test used. No single statistic provides all of that information.

Unequal arm sizes and a low number of recorded events in one arm make the underlying denominators particularly important. Confidence intervals help communicate that estimates are uncertain, but their interpretation depends on the calculation method, which is not reported in the registry record. The absence of posted analysis details also makes it harder to assess the treatment of missing outcomes, multiplicity, or deviations from the assigned strategy.

Finally, planning estimates based on the observed effect are not substitutes for a trial's original design rationale. This record allows readers to consider hypothetical planning scenarios, but the protocol's own sample-size assumptions are not reported. The distinction between observed results, inferential uncertainty, and planning illustrations is essential when interpreting a completed randomized trial.

17. 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 leaves several trial-specific details unreported. It does not provide the eligibility criteria beyond the first episode of Hinchey II diverticulitis after nonoperative management, baseline characteristics, allocation procedures, or details of the colon resection. It lists no masking and gives the model as sequential, but does not explain the operational details of that model.

Although the primary timeframe is a minimum of one year after enrollment, actual participant follow-up duration and completeness are not reported. The registry does not describe missing outcome handling, exclusions, analysis populations, adherence to the assigned strategy, or crossover between observation and surgery. These gaps limit assessment of how representative the posted event counts are of all randomized participants over follow-up.

The registry does not report the statistical test or confidence-interval method for the primary comparison, the original sample-size justification, or the planned approach to multiplicity. It lists secondary outcomes but does not post their analyses. No interim analysis or stopping-rule details are reported. These limitations concern what can be established from the registry record and do not by themselves establish that a particular procedure was or was not used.

The surgery group is smaller than the observational group, and only 2 primary events are recorded in the surgery group. The comparison should therefore be read with the denominators and uncertainty interval in view. The record's limited analytic detail means that readers cannot independently assess all assumptions underlying the reported inference.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Recurrence Following Nonoperative Management of 1st Episode of Hinchey II Diverticulitis — NCT01986686.
• Registry record last updated 2017-10-18; status last verified 2017-05.
• Results first posted 2017-10-18.
• 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.

21. Record Summary

NCT01986686 is a completed randomized trial sponsored by Stony Brook University. It compared observation with an offer of colon resection following nonoperative management of a first episode of Hinchey II diverticulitis. Enrollment is listed as 107, with 81 participants in the observational group and 26 in the surgery group. The primary endpoint was recurrent diverticulitis confirmed by CT scan and requiring hospitalization with intravenous antibiotics, with a minimum timeframe of one year after enrollment.

The posted event counts are 26 among 81 participants in the observational group and 2 among 26 in the surgery group. The reported risk-difference estimate is negative, its confidence interval lies entirely below zero, and the unadjusted p-value is 0.014. The registry also lists secondary outcomes and serious adverse event summaries, but provides no posted secondary analyses. Details of missing-data handling, analysis populations, and the trial's original sample-size justification are not reported in the registry record.