The Food Allergy Superheroes Training (FAST) Program: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The Food Allergy Superheroes Training (FAST) Program (NCT04400214), a randomized na study. The primary outcome is Change in in Situ Food Assessment Score.

2. Clinical Question

In practical terms, FAST was designed as skills training and FAK as education about food allergies. The primary measure was intended to capture a child’s response to an unknown food item in a real-world setting, rather than relying only on a knowledge test or a parent’s report. The record also lists secondary outcomes concerning food allergy knowledge, parent burden, management and adaptation, and the impact of food allergy.

The registry reports overall enrollment of 22, while the primary outcome note says that three participants were randomized to an intervention condition. It does not describe the characteristics of those randomized participants or give the number assigned to each intervention. The available record therefore identifies the study question and intended groups, but does not establish how the groups compared on the primary outcome.

3. Trial Design

The Food Allergy Superheroes Training (FAST) Program study was registered as a randomized, single-masked, parallel-group trial. The phase is listed as NA, and the sponsor is Kent State University. The registry lists enrollment of 22 and a status of terminated. The study start is recorded as 2019-07-01, and primary completion as 2023-06-30.

The two interventions differed in their stated purpose. FAST offered skills training intended to promote adherence to food allergy safety guidelines. FAK offered educational training intended to increase food allergy knowledge. Each arm description specifies five sessions lasting 20 minutes, delivered over <2 weeks. Sessions were to take place at the principal investigator’s laboratory or in the participant’s home. The registry does not report the practical details of how randomization was carried out or who was masked.

The primary outcome was a change in an in situ food-assessment score. Its planned measurement periods included pre-intervention to post-intervention, pre-intervention to one-month follow-up, and post-intervention to one-month follow-up. The primary outcome description identifies the pre-intervention to one-month follow-up change as the score of interest. The record does not explain how the single-masked design was implemented for video coding or identify which study roles were masked.

The record lists four secondary outcomes: the Food Allergy Knowledge Test (FAKT), Food Allergy Quality of Life - Parent Burden (FAQL-PB), Food Allergy Management and Adaptation Scale (FAMAS), and Food Allergy Impact Scale (FAIS). It reports eight outcome measures overall, but does not provide statistical analyses for these outcomes. The enrollment figure describes the study as registered; it should not be treated as the number contributing primary-outcome data. The primary outcome note specifically states that three participants were randomized to an intervention condition and that data were unavailable for all three for the reasons described in that note.

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.

Before assignment: Twenty two participants were consented for the randomized trial. Eighteen participants withdrew due to a loss in funding (prior to completing the pre-intervention, primary outcome assessment). One family withdrew after completing the primary outcome assessment but before randomization to an intervention condition. This rate of attrition and randomization resulted in 3 remaining participants. All of these participants had been assigned to the FAK intervention.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Data missing/Data collection error. In total, three participants were randomized to an intervention condition. One participant did not attend their post-intervention assessment; thus, no data are available for said participant. The remaining two participants data are missing due to video not being uploaded properly; thus, no data are available for the two remaining participants.

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: As noted in previous sections, randomization occurred after completion of all pre-intervention assessments and prior to the child's first intervention session. Due to a loss in funding, multiple families withdrew from the study. The numbers reflected here are those families who remained part of the study, after loss of funding, and were randomized to an intervention condition.

6. Primary Endpoint

The registry lists the primary outcome as Change in in Situ Food Assessment Score, measured over Planned time frame: pre-intervention to post-intervention (approximately 2 weeks), pre-intervention to one-month follow-up (approximately 6 weeks), post-intervention to one-month follow-up (approximately 4 weeks)..

The primary endpoint was change in the in situ food-assessment score. The measure was designed to capture a child’s behavior when encountering an unknown food item in a real-world setting. The child’s response was to be coded from video assessment, using an approach modeled on prior skills-training research. The registry says that scores range from 0 to 4 and that higher scores indicate greater adherence.

The stated primary score represents change from pre-intervention to the one-month follow-up assessment. The record also gives planned intervals for assessing pre-intervention to post-intervention and post-intervention to one-month follow-up, but these are not the change designated in the primary score description. The endpoint was chosen to assess behavior directly rather than measuring only knowledge about food allergy. That distinction matters because knowledge and observed adherence are different kinds of outcomes: a knowledge measure reflects what a participant knows, whereas the in situ measure was intended to capture behavior in a food-related situation.

As general context, a change score expresses how an outcome differs between two assessment times. Its interpretation depends on the scoring rules and on the availability and quality of measurements at both times. Here, the registry reports no usable primary outcome data: one participant did not attend the post-intervention assessment, and the remaining two participants’ data are described as missing because of a video-related issue. The explanation of that issue is truncated in the registry record. Consequently, the record does not provide an observed change score or a comparison between the interventions.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

As general statistical context, a randomized parallel-group design assigns participants to distinct intervention groups and compares outcomes between those groups. Random allocation is intended to reduce systematic differences in participant characteristics at the point of assignment. The registry identifies the study as randomized and parallel, but does not describe the allocation procedure, concealment, or group sizes. Those details are not reported in the registry record.

What randomization can and cannot establish

Randomization supports a causal interpretation when assignment is implemented as planned, outcome data are sufficiently complete, and the analysis appropriately accounts for the design. It does not by itself guarantee that groups will be comparable in every observed or unobserved characteristic, especially when the number randomized is small. In this study, the outcome note identifies three participants randomized to an intervention condition, but does not give a group-by-group allocation. More importantly, it reports that primary outcome data were unavailable for those participants. Randomization cannot recover measurements that were not observed.

The record says the trial was single-masked, but does not identify who was masked or how masking applied to delivery, assessment, video coding, or analysis. Masking can reduce the chance that expectations influence the conduct or assessment of a study. Whether it did so in this trial cannot be evaluated from the registry description.

What the primary outcome represents

The primary endpoint is a change in an in situ score based on a child’s response to an unknown food item, coded from video. The range is 0 to 4, with higher scores indicating greater adherence. A change score compares a participant’s score at two times. A group comparison of change would ordinarily describe how the changes observed in the two intervention groups differ, but the registry record does not report such a comparison or its estimate.

As general context, outcome measurement requires a consistent scoring approach and interpretable observations at the relevant assessment times. Video coding may require the footage to be available and suitable for coding. The registry states that two participants’ data were missing because of a video-related issue, but the explanation is incomplete. It does not report details about coding procedures, assessor reliability, or whether any alternative outcome method was used.

Precision and statistical evidence

A confidence interval is a way to express the precision of an estimate. A narrower interval generally indicates greater precision under the analysis assumptions, while a wider interval indicates greater uncertainty. A hypothesis test and its p-value address a different question: how compatible the observed data are with a stated null hypothesis under the statistical model. Statistical evidence should be interpreted alongside the estimated effect and its precision. The registry record reports no confidence interval, p-value, or primary effect estimate, so none can be interpreted for this comparison.

As general context, missing outcome data can reduce precision and can also introduce bias if the availability of measurements is related to participant characteristics, intervention assignment, or the outcome itself. The direction and extent of any bias depend on why data are missing and on the analysis assumptions. The registry describes nonattendance for one participant and a video-related data problem for the remaining two, but does not report an analysis of missingness, an imputation method, or a sensitivity analysis. It is not possible to determine from the record whether missingness altered an estimate, because no estimate is reported.

Planning calculations

The registry describes a sample-size planning illustration using a two-sided significance level of 0.05, equal allocation between arms, a normal approximation, and an effect expressed as a stated fraction of the observed effect. It also distinguishes participant-per-arm calculations from total-event calculations for time-to-event settings. The study’s endpoint is not described as a time-to-event outcome. The specific effect fraction and planning results are not reported in the registry record.

As general context, a sample-size calculation asks what amount of information might be needed to detect a specified effect under stated assumptions. It does not describe what was actually observed in a trial, and a planning calculation is not observed power. The planning assumptions also do not establish that the study followed a particular analysis plan. The registry does not report a sample-size justification for the trial, the anticipated effect used in its original design, or the planned statistical model.

Outcome multiplicity

The record lists a primary outcome and four named secondary outcomes, and reports eight outcome measures overall. It does not report the statistical analysis plan, a multiplicity adjustment, or how results across outcomes or time points were to be interpreted. In general, examining several outcomes or contrasts can increase the chance of finding an apparently unusual result by chance if all are treated as confirmatory. Whether that issue was addressed in the study is not reported in the registry record. The registry also notes that the primary outcome has several categories or time points and was not reduced to one comparison in the posted analysis information.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary outcome and four secondary outcomes: food allergy knowledge, parent burden, management and adaptation, and food allergy impact. It also reports eight outcome measures overall. The primary outcome description includes multiple planned assessment intervals, while its stated score represents change from pre-intervention to one-month follow-up. The registry does not report a statistical analysis plan specifying which comparisons were primary for analysis, how the secondary outcomes were to be handled, or whether any adjustment for multiple comparisons was planned.

As general statistical context, multiplicity arises when several outcomes, time points, or group comparisons are examined. If many tests are interpreted as confirmatory without accounting for that broader set, the chance of a false-positive finding can increase. Adjustment methods and analysis hierarchies can address this concern, but the appropriate approach depends on the scientific questions and prespecified plan. A multiplicity strategy is not reported in the registry record, so it cannot be evaluated.

Missing data are central to interpretation of the primary endpoint. The record says that three participants were randomized to an intervention condition. One did not attend the post-intervention assessment; data for the other two are described as missing because of a video-related issue, and the explanation is truncated. No primary outcome analysis is listed. The registry does not report an analysis population, a missing-data method, imputation, or sensitivity analyses. It also does not report whether participants were analyzed according to randomized assignment or according to intervention received.

As general context, an intention-to-treat analysis retains participants in their randomized groups, while other analysis populations may apply additional criteria. The registry does not identify which approach, if any, was used. Overall enrollment of 22 should not be treated as the number with primary endpoint data. The record does not provide enough detail to determine the population underlying an analyzed result, and it reports no analyzed primary comparison.

11. 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’s adverse-event figures distinguish participants listed as at risk from participants listed as affected. In the FAST arm, zero participants are listed at risk for serious adverse events and zero are listed as affected; the same zero and zero counts are reported for other adverse events. In the FAK arm, three participants are listed at risk for serious adverse events and zero are listed as affected. For other adverse events, three are listed at risk and zero are listed as affected. Deaths are listed as zero in both arms, and no top serious-event terms are listed.

These counts should be read as registry entries, not as a comparative safety estimate. The number listed as at risk is not the same thing as the number who experienced an event. The registry record does not explain the definition or ascertainment period for these at-risk counts, nor does it provide event narratives or a statistical comparison between arms. Zero affected participants in the posted figures means no affected participants are listed there; it does not establish that the interventions have no risk. The trial status is terminated, but the record does not report the reason for termination or connect it to the adverse-event entries.

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

The record establishes that a randomized, single-masked, parallel-group study was registered to compare FAST skills training with FAK educational training. It specifies a behavioral primary endpoint intended to measure change in children’s adherence responses to an unknown food item, with higher scores indicating greater adherence. It also describes the planned delivery of both interventions and names several secondary outcomes.

What the record does not establish is whether either intervention produced a larger change in the primary score. No primary-outcome estimate, treatment contrast, confidence interval, or p-value is reported. The outcome note says that three participants were randomized to an intervention condition, one did not attend the post-intervention assessment, and data for the other two were missing because of a video-related issue. The reason for that issue is incomplete in the registry record. Without reported outcome measurements and an analysis, there is no basis for describing the direction, size, or precision of a treatment difference.

As general statistical context, a registered study question is not itself a result. Design features such as randomization and masking can strengthen an analysis, but they do not replace outcome data or disclose how an analysis was conducted. The registry lists overall enrollment of 22, but that enrollment figure does not establish the number with complete primary outcome measurements. Nor does a terminated status alone explain why the study stopped or what conclusions its investigators reached.

The adverse-event entries report zero affected participants and zero deaths in both arms, alongside the listed at-risk counts. These entries do not support a broad conclusion about safety because the registry does not provide event details, an ascertainment explanation, or a comparative analysis. Likewise, the sample-size planning assumptions do not demonstrate an observed effect or show that a treatment difference was detected. They are planning information, not a substitute for trial results.

13. Why This Trial Matters Statistically

This trial’s statistical importance lies in the gap between a clearly stated behavioral measurement goal and the limited outcome information in the registry record. The study was designed to assess adherence through a child’s observed response in a food-related situation, coded from video. That is a different measurement target from food allergy knowledge or parent-reported burden, and the registry’s choice of several types of outcomes illustrates why the endpoint and its scoring rules matter.

The record also illustrates how the number enrolled and the amount of information available for a particular analysis can differ. Overall enrollment is listed as 22, while the primary outcome note discusses three randomized participants and reports that their endpoint data were unavailable for stated reasons. These figures refer to different aspects of the record; the enrollment count should not be interpreted as an analyzed sample for the primary endpoint. A reader needs the outcome-specific analysis population and the handling of missing measurements to assess the evidential basis of a result.

As general statistical context, precision depends on the information actually observed and on the variability of the outcome, not simply on a registration target. Missing measurements can limit precision and may complicate interpretation, especially when the reasons for missingness are not fully described. Here, the registry does not report a primary estimate or an analysis of missing data, so the amount of uncertainty around a treatment comparison cannot be quantified.

The record’s planning assumptions offer another useful distinction: a sample-size illustration depends on assumptions about an effect and analysis, whereas an observed trial result depends on the collected outcomes. Planning calculations do not establish that an effect was found. Because the record does not report the specific planning fraction or results, those assumptions cannot be used to characterize the evidence for FAST or FAK.

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 main limitation for interpreting the primary endpoint is that the registry reports no usable outcome data for the three participants discussed in its outcome note. One participant did not attend the post-intervention assessment, and data for the remaining two are attributed to a video-related problem. The explanation ends incomplete in the registry record, leaving the nature of that problem unclear. No primary-outcome estimate or group comparison is reported.

Although overall enrollment is listed as 22, the record does not reconcile that number with the three participants described as randomized to an intervention condition. It does not provide participant flow, group-specific numbers, or characteristics of the enrolled and randomized participants. As a result, the intended population—young children, with emphasis on low-income backgrounds—cannot be compared with the actual study population from the registry description.

The registry does not describe the randomization procedure, allocation concealment, the identity of masked roles, video-coding procedures, or assessor reliability. It also does not report the statistical analysis plan, analysis population, missing-data methods, treatment estimates, confidence intervals, p-values, or sensitivity analyses. The reason for study termination and any interim analyses are not reported in the registry record.

The adverse-event listing has no affected participants or deaths recorded, but does not explain how at-risk counts were defined or how events were collected. The record also gives no details about the implementation or fidelity of the training sessions. These limitations restrict interpretation of both the intervention comparison and the safety entries. They do not establish that a result was favorable or unfavorable; they identify information that is absent from the registry record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: The Food Allergy Superheroes Training (FAST) Program — NCT04400214.
• Registry record last updated 2026-04-23; status last verified 2026-04.
• Results first posted 2026-04-23.
• 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

The registry describes NCT04400214, The Food Allergy Superheroes Training (FAST) Program, as a randomized, single-masked, parallel-group study sponsored by Kent State University. It lists a status of terminated, enrollment of 22, a start date of 2019-07-01, and primary completion on 2023-06-30.

FAST was a skills-training intervention, compared with the Food Allergy Knowledge (FAK) educational intervention. Each arm was described as five 20 minutes sessions over <2 weeks. The primary endpoint was change in a video-coded in situ food-assessment score, where higher scores indicate greater adherence. The registry identifies missing primary outcome data for three randomized participants and reports no statistical analyses or treatment comparison.

Four secondary outcomes are named, and the adverse-event listing reports zero affected participants and zero deaths in both arms. The record does not report a primary effect estimate, its precision, or the reason for termination.