Providing Expanded Continuous Labor Support to Pregnant Women in New Mexico With Substance Use Disorders: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Providing Expanded Continuous Labor Support to Pregnant Women in New Mexico With Substance Use Disorders (NCT03808909), a non-randomized na study. The primary outcome is Number of Participants Who Remain in the Study.

2. Clinical Question

The study’s stated purpose was to determine the feasibility of offering expanded continuous labor support to pregnant women receiving care for substance use disorders. Its longer-term motivation was to address a behavioral health disparity in New Mexico, but the primary registry outcome is a feasibility measure: completion of follow-up. It is not itself a measure of labor support’s effect on birth outcomes, postpartum symptoms, or satisfaction.

The registry also lists alternative birth outcome, the Postpartum Posttraumatic Stress Disorder Checklist, and participant satisfaction as secondary outcomes. The clinical question therefore spans both whether follow-up was completed and other outcomes of interest. The record does not report results for those secondary outcomes or provide enough detail to establish how they were defined or analyzed.

3. Trial Design

The record describes a completed, parallel, nonrandomized study with no masking. The listed enrollment is 13. Its start date is 2019-02-06, and its primary completion date is 2019-06-30. The phase is listed as NA. The sponsor is the University of New Mexico.

Participants were assigned to a Doula arm or a Control arm. The arm descriptions distinguish participants assigned a doula from participants not assigned a doula. The study summary describes the service as expanded doula support offered to women receiving combined obstetric and substance use disorder treatment at the Milagro Program at UNMHSC. The work involved a partnership with Young Women United and doulas of the UNM Birth Companion Program.

Nonrandom allocation matters when interpreting comparisons between arms. Assignment may be associated with participant or care characteristics, and the record does not describe a random process that would balance such characteristics. Therefore, differences between the arms cannot automatically be attributed to doula assignment. The registry explicitly cautions that the arms are not a like-for-like control comparison.

The record does not report arm-specific enrollment, the method used to assign participants, participant characteristics by arm, or the numerical primary-outcome results. It lists 11 outcome measures and 0 analyses. The status is completed, but completion status alone does not establish that the primary outcome was achieved or that comparative effects were estimated. Further details about the protocol, recruitment procedures, and 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.

Overall Study

Reasons for not completing this period:

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 Number of Participants Who Remain in the Study, measured over 2 week postpartum follow-up assessment.

The primary endpoint is the number of participants who complete the 2 week postpartum follow-up assessment. It is a count of participants remaining in the study at that follow-up point, rather than a clinical outcome such as a birth measure or a symptom score.

Follow-up completion is used to assess whether participants can be retained through a planned study assessment. In a feasibility study, retention can inform whether the intended follow-up procedures were workable in the study setting. It can also help identify whether outcome data are available for the planned assessment. Those general uses do not establish why any individual participant did or did not complete follow-up.

The registry record does not report the number completing the assessment, the number eligible for follow-up, or participant-level reasons for noncompletion. It therefore does not permit calculation or interpretation of a completion proportion. The record also does not report a threshold for judging feasibility, or specify how the completion count would be compared between arms.

Because the endpoint is a count, it should be interpreted in the context of how many participants were enrolled and how many were assessed. The listed enrollment is 13, but arm-specific enrollment and primary-endpoint counts are not reported in the registry record. The endpoint’s definition is available; its observed result is not.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The design determines what kinds of conclusions the results can support. This study is recorded as nonrandomized, parallel, and unmasked. In a parallel design, participants are assigned to separate arms rather than crossing between conditions. In general, random assignment can help make groups comparable on average; without it, observed arm differences may reflect both the intervention and differences in who entered or was assigned to each arm. The registry cautions against treating these arms as a like-for-like comparison.

What does a count endpoint represent?

The primary endpoint is a count: the number of participants completing the 2 week postpartum follow-up. Counts report how many events or people meet a definition. A count alone does not describe the proportion completing follow-up unless the relevant denominator is also known. Here, the registry lists total enrollment as 13, but does not report the endpoint count or arm-specific denominators. It is therefore not possible to reconstruct a completion rate from the record.

For a count outcome, analyses may need to account for how variable the data are. In general, over-dispersion means the observed variability is greater than a model’s basic assumptions would expect; ignoring it can make uncertainty appear too small. Whether over-dispersion is relevant depends on the data and the analysis model. The registry record does not report a model, dispersion estimate, or analysis for the primary outcome, so no claim about over-dispersion in this study can be made.

How should uncertainty be evaluated?

In general, an estimate describes the observed result, while a confidence interval communicates its precision under stated assumptions. A hypothesis test addresses compatibility with a specified null model; a p-value is not a measure of effect size or the probability that a hypothesis is true. These concepts require an estimated result and a defined analysis. The record does not report a primary-outcome estimate, confidence interval, or test result, and it lists 0 analyses. Statistical significance and precision therefore cannot be assessed from the registry record.

The absence of a reported analysis is not evidence that no analysis was performed outside the registry. It means that the registry record does not document one. The statistical methods used for the primary or secondary outcomes, including any adjustment for baseline differences, are not reported in the registry record.

What do the planning assumptions mean?

The registry’s sample-size planning illustration is described as a calculation based on the observed effect, not the trial’s own design. Its stated assumptions are a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. The target effect is described as a stated fraction of the observed effect. For time-to-event calculations, the illustration gives total events using the Schoenfeld approach; other calculations are expressed as participants per arm.

These assumptions describe an illustration, not a design justification for this study. The record does not report the protocol’s sample-size justification, a target enrollment rationale, or a prespecified effect for planning. The observed effect and the calculation outputs are not reported in the registry record. Thus, the assumptions alone do not establish what sample size would be adequate for this study, nor do they demonstrate that the study had a particular probability of detecting an effect. Sample-size calculations are planning tools, not observed power.

More generally, a power calculation depends on the outcome, target effect, variability assumptions, significance level, allocation, and planned analysis. If assumptions do not match the actual design or data, the calculation may not describe the study’s ability to estimate an effect. Since assignment was nonrandomized and the registry does not document an analysis plan, the stated illustration should not be read as evidence that the study was designed for a valid causal comparison.

What is known about adverse-event entries?

The registry entries list zero serious events, zero other events, and zero deaths for each arm. In general, an adverse-event count depends on how events are defined, sought, and recorded. A zero entered count does not on its own describe surveillance completeness or establish the absence of events outside the recorded categories. The record does not report additional details about event collection or adjudication.

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("Doula", "Control")
n      <- c(9, 1)
events <- c(9, 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  Doula  9  9  100.0  66.4  100.0  70.1  100.0  69.2  99.7
ARM  Control  1  1  100.0  2.5  100.0  20.7  100.0  15.8  98.7

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 11 outcome measures, including the primary follow-up completion outcome and secondary outcomes for alternative birth outcome, the Postpartum Posttraumatic Stress Disorder Checklist, and participant satisfaction. When a study evaluates multiple outcomes, the chance of at least one apparently unusual result can depend on how many analyses are conducted and how they are selected. In general, multiplicity procedures can address this issue, but the appropriate approach depends on the prespecified questions and analysis plan.

Multiplicity adjustments, outcome hierarchies, and rules for interpreting secondary outcomes are not reported in the registry record. The record lists 0 analyses. It is therefore not possible to determine which outcomes were analyzed, whether all planned analyses were reported, or whether any multiplicity strategy was used. The listed outcome count should not be taken to mean that all outcomes yielded results.

Missing-data methods are also not reported in the registry record. The primary endpoint is defined in terms of completing a postpartum follow-up assessment, but the record does not give the number who completed it, identify reasons for noncompletion, or describe how incomplete assessments were handled. For the secondary outcomes, the record does not report missingness or analysis rules.

Analysis populations are not described. The record does not state whether analyses included all enrolled participants, only participants with follow-up data, or another defined group. It also does not report an interim-analysis plan or stopping rules. These omissions limit assessment of how missing information, multiple outcomes, and participant inclusion may have affected any results.

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

The record establishes that a completed, nonrandomized study was conducted to assess the feasibility of expanded continuous labor support for pregnant women receiving care for substance use disorders. It specifies follow-up completion as the primary endpoint and lists other outcome areas. It does not report the numerical result for the primary endpoint or results for the secondary outcomes.

Accordingly, the record does not establish how many participants completed follow-up, whether retention differed between arms, or whether the intended service was feasible according to any prespecified criterion. No such criterion is reported. The record also does not establish whether the intervention changed birth outcomes, postpartum symptoms, or participant satisfaction.

The design does not support a simple causal reading of arm differences. Participants were not randomly allocated, and the registry cautions that the arms are not a like-for-like comparison. Even if group results were available, they would need to be considered alongside the allocation process, participant characteristics, and analysis methods. Those details are not reported in the registry record.

The adverse-event entries show zero recorded counts in the listed categories for both arms, but they do not establish that no events occurred or that every event was captured. Likewise, a completed status and listed enrollment do not substitute for outcome data.

In general, a study’s result is most informative when its estimate, uncertainty, outcome definition, and analysis population are clear. Here, the endpoint definition is stated, but its result and statistical uncertainty are not reported. The appropriate interpretation is therefore limited to what the registry documents about study intent, structure, and outcome definitions—not a conclusion about benefit, lack of benefit, or safety.

13. Why This Trial Matters Statistically

This study raises statistical questions that are central to small feasibility studies: whether participants can be followed through the planned assessment, how outcomes are defined, and what conclusions a nonrandomized design permits. The primary endpoint is directly tied to retention at the 2 week postpartum follow-up. That makes the outcome relevant to the practical conduct of the study, while also distinguishing it from clinical outcomes.

Its nonrandomized allocation is especially important for interpretation. In general, a comparison between groups can be confounded when factors related to assignment also relate to outcomes. Randomization is one way to reduce that concern, but this study did not use random allocation. The registry appropriately cautions against treating the two arms as equivalent controls. The record does not provide enough detail to assess how assignment or participant differences were handled.

The registry also lists several secondary outcome areas. Multiple outcomes can broaden what a study describes, but require clear definitions and transparent analysis choices to avoid overemphasis on selected results. The record’s listing of 11 outcome measures alongside 0 analyses leaves those choices undocumented.

Finally, the planning illustration is distinguished from the trial’s own design. That distinction matters because a calculation based on an observed effect does not establish that the study was prospectively designed to detect that effect. With enrollment of 13 and no reported endpoint results or uncertainty estimates, the record cannot support a precision assessment. These features make transparent reporting of outcome counts, missingness, and analysis methods particularly important for understanding what the study can contribute.

14. Limitations

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

The registry record leaves important details unavailable for interpreting this specific study. It does not report arm-specific enrollment, participant characteristics, the allocation procedure, or reasons participants may not have completed follow-up. These omissions prevent assessment of baseline comparability and of the practical sources of missing outcome data.

The primary endpoint is defined, but its observed count is not reported. No completion threshold or other criterion for judging feasibility is reported. The record also does not give numerical results for the listed secondary outcomes, including alternative birth outcome, the Postpartum Posttraumatic Stress Disorder Checklist, and participant satisfaction.

Although the record lists 11 outcome measures, it lists 0 analyses. Statistical methods, analysis populations, missing-data handling, and multiplicity procedures are not reported in the registry record. There is no reported estimate or confidence interval for the primary endpoint. Without these details, readers cannot evaluate the magnitude or precision of an effect or determine how outcome data were analyzed.

The nonrandomized design limits causal interpretation, and the registry explicitly cautions that the arms are not a like-for-like control comparison. The record does not report whether or how potential differences between arms were addressed. The adverse-event fields contain zero entries in the listed categories, but the record does not describe event ascertainment or reporting completeness. These limitations mean that the registry supports a description of the study’s intended question and structure, but not a full evaluation of its outcomes.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Providing Expanded Continuous Labor Support to Pregnant Women in New Mexico With Substance Use Disorders — NCT03808909.
• Registry record last updated 2022-11-30; status last verified 2022-11.
• Results first posted 2022-11-30.
• 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.

18. Record Summary

NCT03808909 is a completed, parallel, nonrandomized study sponsored by the University of New Mexico. The registry lists enrollment of 13, no masking, and phase NA. The record lists a start date of 2019-02-06 and a primary completion date of 2019-06-30.

The study concerned expanded continuous labor support for pregnant women receiving care for substance use disorders in New Mexico. Participants assigned to the Doula arm were assigned a doula; participants in the Control arm were not. The primary outcome was the number completing the 2 week postpartum follow-up assessment.

The registry lists 11 outcome measures and 0 analyses. It does not report the primary outcome count, secondary outcome results, or statistical analysis methods. The record cautions that the nonrandomized arms are not a like-for-like control comparison.