Mobile-health (mHealth) Intervention to Support HIV Self-testing and PrEP Uptake Among Young Men Who Have Sex With Men: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Mobile-health (mHealth) Intervention to Support HIV Self-testing and PrEP Uptake Among Young Men Who Have Sex With Men (NCT04865341), a randomized na study. The primary outcome is Number of Participants With Self-reported Self-administration of HIV Testing.

2. Clinical Question

This is a question about a reported behavior over a defined recall period, rather than a laboratory-confirmed test result or an outcome measuring HIV incidence. The registry record does not report a separate primary question about PrEP uptake in the posted results. It also does not report analyses of other outcomes, although it lists two outcome measures in total.

3. Trial Design

The registry identifies NCT04865341 as a completed randomized controlled pilot trial. Its title concerns a mobile-health intervention intended to support HIV self-testing and PrEP uptake among young men who have sex with men. The official title describes an IMB-guided intervention and a pilot randomized controlled trial. The listed phase is NA. The sponsor is the Medical College of Wisconsin.

Allocation is recorded as randomized, masking as double, and the model as factorial. The posted intervention arms are the Experimental IMB Group and the Information-Only Control. The IMB group received a behavioral intervention based on the Information-Motivation-Behavior model; the control is described as attention-matched and information-only. The registry record does not report who was masked, how masking was maintained, or what factorial factors or contrasts were used. The presence of a factorial designation therefore cannot, by itself, establish which additional comparisons were planned or performed.

Enrollment is recorded as 118. The study start date is 2024-03-21, and primary completion is recorded as 2024-08-31; status is completed. The brief description characterizes the eligible population as adolescent participants aged 17-24 years who are men who have sex with men. It says the intervention content draws on constructs of the IMB model and includes information about HIV testing, PrEP, and resources such as directories for finding clinics. Details such as the precise module sequence, delivery schedule, adherence measures, and implementation of the attention-matched condition are not reported in the registry record.

Randomization can support a fair comparison when allocation is implemented as intended and outcome measurement and follow-up are handled appropriately. Those operational details, along with the original trial design assumptions and the full statistical analysis plan, are not reported in the registry record. The posted outcome comparison is an unadjusted arm-level comparison, and no analyses are listed.

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: There is no difference between the number of participants enrolled in the study and the number who started the study.

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 Number of Participants With Self-reported Self-administration of HIV Testing, measured over 3 months.

The primary endpoint is the number of participants reporting self-administration of HIV testing within the past 3 months, described as the period since baseline assessment. It is measured at the 3-month timeframe. The posted result is a count in each arm: 46 participants in the Experimental IMB Group and 44 in the Information-Only Control. The corresponding arm sizes reported for this outcome are 58 and 60, respectively.

This endpoint captures whether participants say they performed HIV testing themselves during the specified recall period. It is relevant to the intervention’s stated focus on supporting self-testing, and it gives a behavioral outcome that can be compared between randomized groups. As a self-reported measure, it records participants’ reports rather than independently verified test completion. The registry record does not report validation procedures, the wording of the assessment instrument, or how missing responses were handled.

The measure is a binary participant outcome: each participant either contributes to the count of those reporting the behavior or does not. General statistical explanation: binary outcomes can be described as counts and as the proportion of each group with the outcome. A between-group risk difference expresses the difference in those proportions, while preserving the outcome’s original scale. The registry also lists a total of two outcome measures, but does not post secondary outcome results in the record. The posted endpoint should therefore be interpreted as evidence about reported self-testing during this recall period, not as a measure of PrEP uptake, HIV status, or longer-term behavior.

7. Results Posted in the Registry

• Experimental IMB Group: 79.3% (46/58) versus 73.3% (44/60) on control; risk difference 6.0 percentage points (95% CI -9.3 to 21.3), risk ratio 1.08 (0.88–1.32); unadjusted two-proportion z-test p = 0.445.

8. Statistical Interpretation

9. Statistical Methods Explained

What does the risk difference describe?

The registry reports a risk difference of 0.060 for the IMB group relative to the information-only control. For a binary outcome, a risk is the proportion of participants with the outcome in an arm. The risk difference subtracts the control-arm proportion from the intervention-arm proportion. It stays on the proportion scale, so its value describes the absolute separation between the groups rather than a relative multiplier. In this case, the reported arm proportions are 0.793 and 0.733. The posted risk difference should be used as recorded; no additional calculation is needed to interpret its direction.

General statistical explanation: an estimate is a summary of the observed data, not a guarantee that the same contrast would appear in another sample. Randomization is intended to make groups comparable on average, while chance variation can still produce differences in the groups observed in a particular trial. A pilot result can help describe a potential signal and uncertainty, but does not by itself settle whether the difference is reproducible.

What does a confidence interval add?

A confidence interval gives a range of values compatible with the data under the interval’s statistical procedure and assumptions. The posted interval for the risk difference runs from -0.093 to 0.213. Because this range includes zero, it includes the possibility of no difference and values on either side of no difference. It also spans effects whose practical importance could differ. A confidence interval is not a probability statement that the true effect lies within these particular endpoints, and it does not account for every source of uncertainty, such as measurement error, missing outcomes, or deviations from the analysis plan.

The registry does not report how the interval was constructed, whether it was adjusted for other factors, or whether it reflects any multiplicity correction. Therefore, the interval should be interpreted as the interval posted for the arm comparison, without assuming a particular formula or adjustment.

How should the p-value be read?

The unadjusted p-value is 0.445. In general, a p-value measures the compatibility of data with a null hypothesis under the model and test used. A larger p-value does not prove that the null hypothesis is true, and it does not show that there is no meaningful effect. Nor is it the chance that the observed result happened randomly. Its interpretation depends on the test, assumptions, and analysis plan. The registry record does not report the test used or its prespecified decision rule. The p-value should therefore be considered alongside the estimate and confidence interval, rather than used as a standalone verdict.

The reported comparison includes a risk ratio and an odds ratio as well as the risk difference. General statistical explanation: a risk ratio compares the outcome proportions between groups as a relative quantity. An odds ratio compares the odds rather than the proportions. The measures answer related but not identical questions, and their numerical values are not interchangeable. The risk ratio is 1.082 with an interval from 0.884 to 1.323; the odds ratio is 1.394 with an interval from 0.593 to 3.278. Both intervals include their respective no-association values. These additional scales do not eliminate uncertainty in the comparison.

What does binary outcome analysis mean?

The primary endpoint is a count of participants reporting an event, rather than a continuous measurement such as a score. For binary outcomes, analyses commonly compare event proportions across arms. The registry’s comparison provides the arm proportions and several effect measures, but does not identify the underlying statistical procedure. The record also does not state whether covariates, stratification variables, or features of the factorial design were included. It would be inappropriate to infer those details from the posted point estimates alone.

General statistical explanation: over-dispersion is a concern when the variability in data is greater than an assumed model expects. It can make standard errors too small and intervals too narrow if the model does not account for the extra variability. The posted outcome is a binary participant count, and no over-dispersion assessment or modeling approach is reported. There is consequently no basis in the registry record to claim that over-dispersion was assessed or relevant to the analysis.

What can be inferred from the analysis record?

The registry reports no analyses, while also posting a primary outcome comparison. This means the record does not provide a fuller account of analysis specifications, rather than proving that no analysis occurred. The comparison is marked unadjusted and no discrepancy is flagged. No sponsor analysis is identified as taking precedence. The record does not report whether the analysis followed intention-to-treat principles, how participants were assigned to analysis populations, whether outcome data were complete, or how any missing responses were treated. Those questions matter because the analysis population and handling of missing observations can affect the estimated comparison and its precision.

10. Confidence Intervals and Precision

The central precision feature is the width and span of the risk-difference interval. The estimate is 0.060, while its confidence interval extends from -0.093 to 0.213. This interval includes zero and reaches across negative and positive values. Thus, the posted data do not pinpoint the direction of the underlying difference, and the plausible values under the interval procedure range from a control-favoring contrast to an IMB-favoring contrast. The interval also leaves uncertainty about the size of any difference.

The risk-ratio interval, from 0.884 to 1.323 around an estimate of 1.082, also includes its no-difference value. The odds-ratio interval, from 0.593 to 3.278 around an estimate of 1.394, likewise includes its no-association value. These ranges reinforce that the relative estimates are imprecise. The estimates use different scales, so their numerical widths should not be compared as if they measured uncertainty in the same units.

General statistical explanation: confidence intervals tend to be wider when information is limited or when outcomes are variable, and narrower when data provide more information. Precision is distinct from whether an estimate is statistically significant: an interval can include no difference while still allowing effects that could matter in either direction. The registry does not report an interval method, adjustment strategy, or the number of participants with missing primary outcomes, so the listed intervals should not be treated as accounting for unreported sources of uncertainty.

The 3-month, self-reported endpoint also limits the scope of interpretation. The interval describes uncertainty for the reported behavior and comparison as analyzed, not measurement reliability or generalizability. It does not quantify uncertainty for PrEP uptake or other outcomes. Because the original design assumptions are not reported in the registry record, the observed precision cannot be judged against a stated target for the pilot.

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 event counts. They are illustrations based on the observed effect and use the planning assumptions stated in the registry: a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. These are planning illustrations, not a report of the trial’s original design. The original sample-size assumptions and justification are not reported in the registry record.

For planning at 100% of the observed effect, the figures are 793 participants per arm for 80% power and 1,061 participants per arm for 90% power. For planning at 75% of the observed effect, they are 1,441 participants per arm for 80% power and 1,929 participants per arm for 90% power. For planning at 50% of the observed effect, they are 3,310 participants per arm for 80% power and 4,430 participants per arm for 90% power.

In plain language, the 80% power column gives the illustrative number of participants per arm for a design with an 80% chance of detecting the specified effect under the stated assumptions, if that effect is real and the assumptions hold. The 90% power column describes the corresponding planning target for a higher chance of detection. Power is not the probability that a finding is true, nor is it a measure of the quality of the observed result. Smaller effects need more participants to detect under otherwise similar assumptions. These calculations are not observed power.

These planning values depend on using the observed effect as a reference, and that estimate itself is uncertain. They should not be read as recommendations or as proof that the study was under- or over-sized. The record does not report the trial’s own intended effect size, power target, or sample-size calculation.

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 = 0.733; treatment proportion p₁ = 0.793; average p̄ = 0.763.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6012 = 1.1783.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5997 = 0.5047.
4. n = (1.1783 + 0.5047)² / (0.0598)² = 792.9, rounded up to 793 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 <- 0.733333333333333                          # control proportion
p1 <- 0.793103448275862                          # 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(4865341)
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 = 793 (80% power), 1,061 (90% power)
 75% of observed effect: n per arm = 1,441 (80% power), 1,929 (90% power)
 50% of observed effect: n per arm = 3,310 (80% power), 4,430 (90% power)
power.prop.test: 792.9 
Simulated power at n = 793 per arm: 0.806 (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 record does not report a multiplicity procedure. This matters because the record lists two outcome measures, describes a factorial model, and posts several effect measures for the primary comparison. The record does not explain which outcomes or contrasts were prespecified for formal testing, whether the posted comparison was the only primary hypothesis, or whether any adjustment was planned for multiple testing. Without that information, the unadjusted p-value should not be interpreted as if the registry documented a complete family of tests or a controlled overall error rate.

The registry lists no analyses. It does not report a statistical analysis plan, analysis populations, or whether an intention-to-treat approach was used. The arm-level outcome counts therefore cannot establish whether all randomized participants were included in the analysis, how eligibility after randomization was handled, or whether a per-protocol or other population was used. These details are not reported in the registry record.

Missing outcome data can affect both the estimated event proportions and their uncertainty. The posted arm sizes and event counts are available, but the record does not explain whether the arm sizes represent all randomized participants, participants assessed at follow-up, or another analysis set. It also does not state whether any outcomes were missing, how missing responses were classified, or whether imputation or sensitivity analyses were performed. No missing-data assumptions should be inferred from the counts alone.

The record does not describe how the factorial designation relates to the reported two-arm comparison, whether interaction effects were evaluated, or whether any factorial components were combined for this estimate. It also does not report adjustment for baseline measures or other covariates. These omissions do not invalidate the posted descriptive comparison, but they limit reconstruction of the intended analysis and evaluation of its robustness. Further details about prespecification, analysis populations, missingness, and multiplicity are not reported in the registry record.

14. 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 serious-adverse-event figures list 0 serious adverse events among 58 participants at risk in the Experimental IMB Group and 0 among 60 participants at risk in the Information-Only Control. Deaths are recorded as 0 in each arm. The other-adverse-event figures also list 0 affected participants in each arm, with 58 and 60 participants at risk, respectively.

These entries indicate what the registry reports for the recorded safety categories. They do not establish that no adverse experiences of any kind occurred: the record does not provide event terms, detailed safety definitions, ascertainment procedures, or a narrative explanation of collection and reporting. It lists no serious adverse-event terms. A zero count is not evidence that a risk is impossible, especially when the registry does not describe the duration and completeness of safety monitoring.

General statistical explanation: safety counts are interpreted in relation to who was monitored, how events were defined, and how completely they were captured. The registry record does not report these details. The figures should therefore be read narrowly as the posted counts, not as a comprehensive assessment of safety or a comparison capable of ruling out uncommon events.

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

The result establishes that the registry reports self-reported self-administration of HIV testing within the past 3 months for participants in both randomized arms. The reported counts are 46 in the Experimental IMB Group and 44 in the Information-Only Control. The unadjusted comparison estimates a risk difference of 0.060, with a confidence interval from -0.093 to 0.213 and an unadjusted p-value of 0.445. The result is compatible with a range of possible differences, including values in either direction.

It does not establish that the IMB intervention caused the observed point estimate. Randomization is a design feature, but causal interpretation also depends on appropriate allocation, follow-up, measurement, and analysis. Details about those processes and the analysis plan are not reported in the registry record. The outcome is self-reported, and the registry does not describe independent verification of testing.

The comparison does not answer whether the intervention changed PrEP uptake. Although PrEP is part of the study’s title and intervention rationale, the posted primary endpoint concerns self-reported HIV testing, and the record does not post secondary outcome results. It does not assess HIV incidence, infection prevention, or longer-term behavior through this primary result. Nor does it establish that the result applies beyond the population described in the registry.

A non-small p-value is not proof of no difference, and a positive point estimate is not proof of benefit. The interval’s breadth is important: it shows substantial uncertainty about the magnitude and direction of the contrast. This is a pilot trial, so the result can be considered an estimate that may inform further research, but it should not be treated as a definitive clinical conclusion. The registry record does not report the original design assumptions that would clarify the role the pilot result was intended to play.

16. Why This Trial Matters Statistically

This trial is statistically informative because it illustrates the distinction between a point estimate and the precision of that estimate. The observed risk difference is positive, but the confidence interval extends across zero and includes values in either direction. A reader who focuses only on the point estimate or only on the p-value would miss how much uncertainty remains about the contrast.

The outcome is a binary, self-reported behavior, and its meaning depends on the recall period and assessment method. The primary endpoint concerns self-administration of HIV testing since baseline assessment, measured at 3 months. This specificity matters: a result for reported testing behavior should not be generalized to PrEP uptake or other outcomes that the posted comparison does not measure.

The record also highlights the difference between a pilot trial’s observed estimate and planning assumptions for later research. The sample-size illustrations use fractions of the observed effect, and the planning requirements rise as the targeted effect becomes smaller. Those illustrations are not observed power and do not reveal the original study’s intended design rationale. Their interpretation depends on assumptions that may not match the trial’s own plan, which is not reported in the registry record.

Finally, important analytic details are absent: the record lists no analyses, does not describe missing-data handling or analysis populations, and does not explain the factorial designation in relation to the posted comparison. Such details are central to evaluating how an estimate was obtained and how robust it may be. The posted results are useful as a transparent account of the outcome counts and uncertainty, while the unreported design and analysis information limits stronger conclusions.

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.

Several limitations are specific to the information recorded for this trial. The primary endpoint is self-reported, and the registry record does not report how the report was verified, the exact assessment instrument, or procedures intended to reduce recall or reporting error. The endpoint’s recall period is the past 3 months, described as since baseline assessment; the record does not provide further information about the timing or administration of the assessment.

The trial is described as factorial, but the registry record does not report the factorial factors, the allocation structure beyond the listed arms, or any interaction or factorial analyses. It also records double masking without stating who was masked or how masking was feasible and maintained. The brief study description is truncated, so it does not provide a complete account of intervention delivery or follow-up procedures.

The posted comparison is unadjusted, and the registry lists no analyses. The record does not report the statistical test, confidence-interval method, prespecified analysis plan, multiplicity handling, analysis population, or treatment of missing outcomes. These omissions make it difficult to evaluate whether the posted comparison matches a prespecified primary analysis or to assess sensitivity to analytic choices.

The registry lists two outcome measures but posts no secondary results. The primary endpoint addresses self-testing, so the posted findings do not provide evidence about PrEP uptake. Finally, the confidence interval is broad and includes differences in either direction. Together, the reporting gaps and imprecision mean the result should be treated as a limited estimate of the recorded self-reported outcome, rather than a complete assessment of intervention effects or safety.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Mobile-health (mHealth) Intervention to Support HIV Self-testing and PrEP Uptake Among Young Men Who Have Sex With Men — NCT04865341.
• Registry record last updated 2026-05-01; status last verified 2026-04.
• Results first posted 2026-05-01.
• 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.

21. Record Summary

NCT04865341 is recorded as a completed randomized pilot trial sponsored by the Medical College of Wisconsin. It compares an IMB-based behavioral intervention with an attention-matched information-only control among young men who have sex with men. The registry describes eligible participants as ages 17-24 years and records enrollment of 118. The study start date is 2024-03-21, and primary completion is 2024-08-31.

The primary outcome is the number of participants reporting self-administration of HIV testing within the past 3 months at the 3-month timeframe. The posted counts are 46 of 58 in the Experimental IMB Group and 44 of 60 in the Information-Only Control. The unadjusted risk difference is 0.060, with a confidence interval from -0.093 to 0.213 and an unadjusted p-value of 0.445. The interval reflects substantial uncertainty and includes differences in either direction.

The registry record does not report a full statistical analysis plan, missing-data procedures, analysis populations, or details clarifying the factorial designation. No secondary results are posted. Serious adverse events and deaths are recorded as 0 in each arm.