Digital Intervention To Improve Diet Quality: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Digital Intervention To Improve Diet Quality (NCT04098016), a na na study. The primary outcome is Intervention Engagement- Number of Text Messages Completed.

2. Clinical Question

3. Trial Design

This completed study is registered as NCT04098016, with the title “Digital Intervention To Improve Diet Quality.” Its official title describes the feasibility of delivering a digital behavioral intervention to increase diet quality among women receiving WIC benefits. Duke University is listed as the sponsor.

The registry describes a single-group model, with allocation listed as not applicable and masking listed as none. It does not describe a randomized comparison or a control arm. The record lists an enrollment of 54. That is the registered enrollment figure; it does not establish how many participants contributed data to each outcome.

The intervention was called Healthy Roots in the study brief. The brief says it was adapted from Track, a previously tested adult digital obesity treatment intervention. The intervention description lists tailored behavior change goals, self-monitoring with tailored feedback, and skills training. The primary outcome focuses on completed text messages over the intervention period. Change in Healthy Eating Index Score is listed as a secondary outcome.

The study start date is 2021-03-08, the primary completion date is 2021-09-22, and the status is completed. The phase is listed as not applicable. Further details about recruitment, participant flow, intervention delivery, follow-up, and deviations from the planned intervention are not reported in the registry record.

A single-group feasibility study can describe whether participants engage with an intervention and can document outcomes over time. Without a concurrent control group, however, outcome changes cannot be attributed to the intervention through a controlled comparison. The registry record does not report an analysis plan or outcome analyses that would clarify how these aims were evaluated.

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: Only applicable to the intervention group.

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 Intervention Engagement- Number of Text Messages Completed, measured over 3 months.

The primary endpoint is the average number of text messages completed during the 3-month intervention period. The registry describes messages as being deployed three times a week throughout the 12-week intervention. The outcome is expressed as a mean, with standard deviation specified as the measure of dispersion. No mean or standard deviation result is reported in the registry record.

As a general statistical point, a message-completion count is a process measure: it describes participant engagement with one element of the intervention. In a feasibility study, engagement measures can help characterize how much participants interacted with the intervention as delivered. They do not, by themselves, measure whether diet quality changed or whether the intervention caused a change in diet quality.

The registry lists Change in Healthy Eating Index Score as a secondary outcome, which is more directly aligned with diet quality than message completion. The registry record does not report its definition, measurement schedule, analysis, or result. The primary endpoint is described as applicable only to the intervention group, consistent with the single-group design. The record does not specify how incomplete message data, differing exposure to the intervention, or participants with no recorded completions were handled.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the primary measure describe?

The primary measure is the average number of text messages completed over the 3-month intervention period. The record specifies a mean and standard deviation. In general, a mean summarizes the center of a set of quantitative observations, and a standard deviation summarizes how dispersed individual observations are around that mean. These statistics answer different questions: the mean describes the average completion count, while the standard deviation describes variability among participants.

The outcome is a count of completed messages. The registry does not report the distribution of counts, the observed mean, the observed standard deviation, or the number of participants with usable data. It also does not state how messages that were not completed, not delivered, or not recorded were classified. No particular statistical model for the count outcome is reported in the registry record.

What can a single-group design establish?

The registry describes a single-group study with no control comparison. In general, a single-group design can describe outcomes among participants receiving an intervention. If measurements are collected at multiple times, it may also describe within-group change, provided those measurements and analyses are reported. Such a design does not by itself estimate what would have happened to the same participants without the intervention. Changes over time may have other explanations, and the design cannot resolve those explanations through a concurrent control comparison.

Allocation is listed as not applicable and masking as none. The registry record does not report a randomization procedure, blinded outcome assessment, or a plan for adjusting comparisons. It would not be appropriate to infer these methods from the study’s feasibility focus or intervention description.

How should uncertainty be understood?

In general, an estimate is more informative when accompanied by a measure of uncertainty. A confidence interval expresses uncertainty about an estimated quantity under the analysis assumptions; a narrow interval indicates greater precision than a wide interval. It does not show that a result is free of bias or that a causal conclusion is justified. The registry record reports neither a confidence interval nor another uncertainty estimate for the primary outcome.

A standard deviation is useful for understanding the spread of individual completion counts, but it is not a substitute for uncertainty around the group mean. The record names standard deviation as the dispersion measure but gives no numerical result. Therefore, neither the average level of engagement nor its variability can be evaluated from the registry information.

What do the planning assumptions mean?

The registry’s sample-size assumptions describe planning illustrations based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They describe detecting a stated fraction of the observed effect. These are assumptions for hypothetical planning, not evidence that the study itself used a two-arm design. The actual study is registered as single-group, so the equal-allocation comparison does not match its listed design.

In general, a two-sided significance level sets a decision threshold for a test that considers departures in either direction. Equal allocation is an assumption about dividing participants between comparison groups. A normal approximation uses a normal distribution to approximate the behavior of an estimator or test statistic. These assumptions can be useful for planning, but their relevance depends on the outcome, design, and analysis being planned.

The record does not report the observed effect estimate or the numerical planning results needed to interpret a particular illustration. Such illustrations are not observed power and should not be read as proof that the study had adequate power for its actual single-group objectives. The registry also does not report the study’s own sample-size justification. That justification is not reported in the registry record.

Which analysis details are unavailable?

The record lists 0 analyses. It does not specify an inferential test, a model, covariate adjustment, a confidence-interval method, or assumptions about the distribution of the message count. It does not report how the Healthy Eating Index Score change was calculated or analyzed. These details matter because different analysis choices can produce different estimates and uncertainty, particularly when data are incomplete or outcomes have distributions that do not fit simple model assumptions.

As a general concept, over-dispersion occurs when count data vary more than a chosen count model expects. If present, it can make standard errors from an unsuitable model too small and uncertainty appear less than it is. The registry does not provide the outcome distribution or identify a count model, so it is not possible to determine whether over-dispersion was assessed or relevant to the analysis. No particular model or diagnostic should be assumed.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Intervention")
n   <- c(54)
m   <- c(7.4)
sp  <- c(4.6)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Intervention  54  7.400  4.600  6.144  8.656

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 2 outcome measures: the primary measure of completed text messages and the secondary outcome of Change in Healthy Eating Index Score. It lists 0 analyses and does not report an analysis plan, a hierarchy of hypotheses, or a method for addressing multiple outcomes. It is therefore not reported in the registry record whether any multiplicity adjustment was planned or used.

As a general statistical point, evaluating multiple outcomes or multiple hypotheses can increase the chance of obtaining at least one apparently unusual result by chance. Prespecifying a primary outcome and an analysis hierarchy, or using an adjustment when appropriate, can help make interpretation clearer. The record identifies a primary outcome but does not give enough analysis detail to establish how results across outcomes were handled. No outcome estimates or tests are reported, so the impact of multiplicity cannot be assessed.

The registry record does not report the number of participants with observed primary or secondary outcome data, reasons for missingness, or any method for handling missing data. It does not say whether an analysis used complete cases, imputation, or another approach. The enrolled count of 54 should not be treated as the analyzed sample size for either outcome.

The record also does not define an analysis population, such as all enrolled participants or only those with a specified amount of intervention exposure. The primary outcome is described as applicable only to the intervention group, but the criteria for inclusion in its analysis are not reported in the registry record. These omissions limit assessment of selection, attrition, and the population to which any outcome estimate might apply.

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

The registry record describes a completed feasibility study of a digital behavioral intervention and identifies text-message completion as its primary outcome. It also describes the intervention’s components and lists change in Healthy Eating Index Score as a secondary outcome. These details clarify what the study set out to examine, but the record does not report results for either outcome.

Accordingly, the registry information does not show how many messages participants completed on average, how much completion varied, or whether diet quality changed. It does not provide estimates or uncertainty measures from which the size or precision of any observed outcome could be judged. The registered enrollment of 54 is not a substitute for outcome results or for the number of participants analyzed.

Even if within-group outcome changes were available, the single-group design would not provide a controlled estimate of what would have happened without the intervention. The absence of a concurrent comparator limits causal interpretation. The registry also does not report enough information about missing data, participant flow, or outcome analyses to determine how representative an estimate would be of all enrolled participants.

In general, an engagement measure can describe participation in an intervention, while a diet-quality outcome addresses a different outcome domain. Engagement alone does not establish a change in diet quality. A registry entry marked completed indicates study status; it does not establish that the intervention met a particular objective or that an outcome changed in a particular direction.

The information supports a description of the registered design and outcome definitions, not a conclusion about the intervention’s observed effects. The absence of reported results in the registry record should not be interpreted as evidence of either benefit or lack of benefit.

13. Why This Trial Matters Statistically

This study is statistically notable for the distinction between a feasibility question and an effectiveness comparison. Its registered primary outcome, completed text messages, is an engagement measure. That can describe interaction with a digital intervention, but it is not itself a measure of diet quality. The listed secondary outcome, Change in Healthy Eating Index Score, addresses diet quality more directly, yet its result is not reported in the registry record.

The design also matters for interpretation. A single-group study can characterize outcomes in participants who receive an intervention, but it lacks a concurrent control group for separating intervention-associated changes from other changes over time. This limits the kinds of statistical claims that can be supported, regardless of the number enrolled.

The registry lists an enrollment of 54 and a completed status, but does not report analyzed sample sizes, outcome estimates, confidence intervals, or analyses. This illustrates why enrollment and completion status should not be confused with evidence about an outcome or the precision of an estimate. Without outcome data and an analysis description, readers cannot assess variability, missingness, or uncertainty.

The sample-size assumptions describe a two-arm planning illustration with equal allocation, while the registered study is single-group. Such a planning framework is not a description of the study design and does not establish observed power. Keeping the planned comparison distinct from the design actually registered is important when interpreting statistical planning material.

Overall, the record provides a useful outline of the intervention and its intended measures, while leaving central result and analysis details unavailable. The difference between what a study intends to measure, what it measures, and what it can establish is central to interpreting feasibility research.

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 does not report the primary outcome result, the secondary outcome result, or any statistical analyses. It therefore does not permit assessment of engagement levels, changes in diet quality, or the precision of any estimate. Although enrollment is listed as 54, the number of participants with usable outcome data is not reported.

The single-group design has no concurrent control group. Any within-group change, if measured, would not isolate the intervention’s contribution from other possible explanations. The registry does not report baseline outcome values, repeated-measure details, or an analytic approach for assessing change.

Important participant and implementation details are also not reported in the registry record. These include eligibility criteria, participant characteristics, recruitment and retention, intervention exposure, and fidelity of delivery. The endpoint description does not specify how message completion was recorded or how missing message data were handled. The method and timing for assessing the Healthy Eating Index Score are also not reported.

The record does not describe a statistical analysis plan, an analysis population, missing-data procedures, or multiplicity handling. It does not report confidence intervals or other measures of uncertainty. As a result, readers cannot evaluate whether the outcome analyses followed a prespecified plan, how exclusions or incomplete data affected results, or how precise any estimates would be.

The listed adverse-event fields report zero participants at risk and zero affected in the intervention group, including zero deaths. With zero participants recorded as at risk, those entries do not establish that no adverse events occurred among participants; the registry does not provide further detail to resolve that limitation.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Digital Intervention To Improve Diet Quality — NCT04098016.
• Registry record last updated 2024-03-01; status last verified 2023-08.
• Results first posted 2024-03-01.
• 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

NCT04098016 is a completed, single-group study sponsored by Duke University. The registry lists enrollment of 54, a start date of 2021-03-08, and a primary completion date of 2021-09-22. Allocation is not applicable, masking is none, and the phase is not applicable.

The intervention is a digital behavioral program with tailored behavior change goals, self-monitoring with tailored feedback, and skills training. The primary outcome is the mean number of text messages completed over the 3-month intervention period, with standard deviation specified as the dispersion measure. Change in Healthy Eating Index Score is listed as a secondary outcome.

The registry record lists 2 outcome measures and 0 analyses. It does not report numerical results for the primary or secondary outcome, analyzed sample sizes, or the statistical analysis plan. The design does not include a concurrent control comparison.