Screening Wizard- Phase 2: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Screening Wizard- Phase 2 (NCT04646369), a randomized na study. The primary outcome is Number of Participants Referred to Treatment.

2. Clinical Question

3. Trial Design

This is a randomized, single-masked, parallel-group study listed as phase NA. The registry records an enrollment of 100 and identifies three behavioral intervention groups: “screening as usual,” Screening Wizard 2.0, and Screening Wizard 2.0 + SOVA. The record does not identify who was masked, so the masking description cannot be used to infer whether participants, providers, outcome reviewers, or another group were unaware of assignment.

In the screening-as-usual group, a symptom-score report based on Screening Wizard responses is sent to the participant’s provider. Screening Wizard 2.0 adds the participant’s treatment preferences and barriers, as well as recommendations, to the information sent to the provider. The third group receives the Screening Wizard 2.0 information and access to SOVA, described as a website intended to address perceptions about mental health and provide support through peer interaction moderated by social workers and doctors.

The study summary says participants are randomized after answering adaptive screens about suicidal risk, anxiety, and mania, and questions about treatment preferences and perceived barriers. The summary identifies primary care providers as the intended recipients of the reports. It does not give the randomization procedure, allocation ratio, or details about how assignment was concealed. Those design details are not reported in the registry record.

The registry lists a start date of 2020-11-05, a primary completion date of 2021-09-17, and a status of completed. These dates and status describe the trial record; they do not, by themselves, establish that all planned analyses or results were posted. The record contains no listed analyses for the primary outcome. It also does not report a protocol-level sample-size justification or a detailed statistical analysis plan.

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: 92 of 100 participants had documentation or an accessible electronic medical record to review referrals made following screening wizard report. Note-Screening Wizard arm (N=38) and Screening Wizard + Sova arm (N=39) are combined because both arms received same Screening Wizard intervention but the 3rd Arm also received SOVA. Data was reviewed and entered from the electronic health record based on referrals made by pediatric providers at time the intervention was implemented.

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 Referred to Treatment, measured over Baseline (in office) visit.

The primary outcome is titled “Number of Participants Referred to Treatment” and is measured at the baseline in-office visit. It is a count of participants, rather than a continuous score or a time-to-event measure. The outcome description frames the measure around whether primary care providers made personalized referrals after receiving Screening Wizard information. It also mentions monitoring treatment initiation, but the registry does not provide a separate definition, time window, or reported result for initiation.

This type of endpoint is useful for assessing a step in the pathway between screening and care: whether a provider makes a referral after receiving screening information. It is distinct from measuring symptom improvement, treatment attendance, or clinical outcomes. A referral count can indicate provider action as recorded in the study, but it cannot alone establish whether a participant took up the referral or benefited from subsequent care.

The registry notes that 92 of 100 participants had documentation or an accessible electronic medical record to review referrals made after the screening report. It also says that the Screening Wizard and Screening Wizard + SOVA arms were combined for this referral documentation note because both received the same Screening Wizard intervention, but the accompanying explanation is truncated. The registry record does not report the referral counts by group, so the size or direction of any difference cannot be assessed from the posted primary outcome information.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The statistical information available for this study is limited. The record identifies randomization, three parallel groups, a count outcome, and a primary endpoint, but it does not report an analysis plan or primary outcome estimates. The concepts below explain how such information is generally interpreted; they do not describe unreported analyses as if they were performed.

What does a count endpoint represent?

As a general statistical principle, a count endpoint records how many participants experience a defined event. Here, the stated endpoint is the number of participants referred to treatment. A count can be presented for each study group and compared across groups, but the interpretation depends on the definition of the event, the population included, and the observation period. The registry identifies the baseline in-office visit as the timeframe and describes provider referral review. It does not provide the count values by group.

A count of participants with an event is different from a count of all events when one participant could experience the event more than once. The endpoint title refers to participants referred, so the intended unit is people rather than repeated referral episodes. The record does not specify whether multiple referrals for one participant were possible or how they would be handled. No assumptions about that detail should be made.

How would a randomized comparison be interpreted?

In general, random assignment is intended to create groups that can be compared without deliberately assigning participants according to their likely outcome. A parallel-group design follows participants in their assigned groups rather than crossing each participant through each intervention. The registry identifies this trial as randomized and parallel, but it does not report the allocation procedure, concealment method, or planned statistical test. Randomization alone does not supply the missing outcome results, and it does not guarantee that all sources of bias or missing data are resolved.

For a binary event summarized as a count of participants, a statistical report might include the event count and the number assessed in each group, along with an effect estimate and an interval expressing uncertainty. A confidence interval is, in general, a range of values compatible with the data and the chosen statistical procedure; a wider interval indicates less precision. The registry record does not report an effect estimate or confidence interval for referrals, so neither the estimated size nor its precision can be evaluated.

A p-value, when reported, describes how unusual data at least as incompatible with a specified null hypothesis would be under the assumptions of a statistical test. It does not measure the size or importance of an effect. No primary outcome p-value or test is listed in the registry record. It would therefore be inappropriate to infer statistical significance or lack of significance from the absence of an analysis.

What role could over-dispersion play?

As a general concept, over-dispersion arises when count data vary more than a statistical model expects. It matters because a model that understates variability can produce uncertainty estimates that are too narrow. The registry classifies the primary outcome as a count of participants and does not report a dispersion parameter or a fitted count model. Since the outcome is specifically described as participants with a referral, and no analysis is posted, there is no basis to claim that over-dispersion was assessed or affected this study’s results.

What can be inferred from the planning assumptions?

The record describes a planning illustration based on a fraction of an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. Such assumptions describe a hypothetical planning exercise, not an observed treatment effect and not observed power. Planning calculations can illustrate how a study might be sized to detect an effect under chosen assumptions, but they do not establish that the trial was designed with those assumptions or that a result is precise.

The registry record does not report the study’s own sample-size justification, and the primary outcome effect needed for an observed-effect-based planning illustration is not reported in the available outcome information. No numerical planning estimate can therefore be interpreted from this record. Any sample-size illustration should be treated as hypothetical rather than as evidence that the study had adequate power or that an effect was present.

Why are the analysis details important?

Statistical interpretation requires knowing which participants contributed data, how missing observations were handled, which outcomes and comparisons were prespecified, and what model or test was used. These details influence both the estimate and its uncertainty. The registry provides a note about referral documentation availability, but not a complete account of the analysis population or missing-data method. It also does not report an analysis plan or inferential results. These omissions prevent a reconstruction of the intended comparison and make it important to distinguish the described design from unreported analytical decisions.

10. Multiplicity, Missing Data and Analysis Populations

The registry record does not report a multiplicity strategy. Multiplicity concerns the increased chance of a misleading positive result when several outcomes, comparisons, or time points are tested. This study has three intervention groups and lists a primary referral outcome along with secondary outcomes concerning intervention cost, usability and satisfaction, and satisfaction with technical components. The record does not specify which pairwise comparisons were planned, whether particular comparisons were prioritized, or whether any adjustment for multiple testing was intended. Without the analysis plan and results, the risk and handling of multiplicity cannot be evaluated.

The record does not report a missing-data method or define the analysis population for the primary outcome. It states that 92 of 100 participants had documentation or an accessible electronic medical record available for referral review. It does not explain the reason documentation was unavailable for other participants, whether those participants were excluded from the endpoint analysis, or whether any missing values were imputed. The primary outcome population note says that the Screening Wizard and Screening Wizard + SOVA arms were combined for the referral documentation description, but the explanation is incomplete. This makes it unclear how the reported availability note relates to the planned arm comparisons.

The registry does not specify whether the primary analysis followed randomized assignment regardless of intervention received, used only participants with available records, or applied another rule. These approaches can yield different interpretations, especially when outcome information is unavailable. The record also does not report protocol deviations, participant flow by group, or sensitivity analyses addressing missing records. Consequently, the completeness and comparability of the primary outcome data cannot be assessed from the registry entry.

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 lists serious and other adverse-event counts separately for the three groups. For “Screening as Usual,” 23 participants are listed at risk for serious adverse events and 23 at risk for other adverse events; the recorded affected counts are 0 and 0, and deaths are listed as 0. For Screening Wizard 2.0, the corresponding at-risk figures are 38 and 38, with 0 serious events, 0 other events, and 0 deaths. For Screening Wizard 2.0 + SOVA, the at-risk figures are 39 and 39, with 0 serious events, 0 other events, and 0 deaths.

These are the adverse-event figures recorded in the registry. They should be read as reported counts, not as proof that no adverse experiences occurred outside the definitions, observation procedures, or reporting captured in the record. The registry does not provide event terms, follow-up duration for safety monitoring, or a fuller description of ascertainment. The absence of listed serious events also does not establish that the interventions have no risks. These safety counts are separate from the unreported primary referral outcome and do not answer whether referral patterns differed among groups.

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

The study addresses a practical question about how information from adolescent screening is conveyed to primary care providers. Its three groups differ in the information shared after Screening Wizard responses, and one group also receives access to SOVA. The primary outcome is provider referral to treatment at the baseline in-office visit. This design identifies a question that can be assessed empirically: whether the approach to sharing screening information is associated with the number of participants referred.

The registry record does not report the primary outcome counts by group or a statistical comparison. It therefore does not show whether referral counts were higher in one group, lower in one group, or similar across groups. It also does not provide an estimate with uncertainty that would indicate how precisely any difference was measured. The lack of a posted estimate should not be interpreted as evidence of no effect, and it cannot support a claim of benefit.

The outcome is focused on referral, not on subsequent treatment initiation, treatment quality, symptom change, or longer-term health outcomes. Although the description mentions monitoring treatment initiation, the registry does not give a separate result or operational definition for that measure. A referral is one step in a pathway and does not establish that treatment was started or continued.

The record’s note that 92 of 100 participants had documentation or an accessible electronic medical record for referral review is relevant to how much outcome information was available. However, the handling and characteristics of unavailable documentation are not described. The note also describes combining two Screening Wizard arms for a referral documentation summary, with an incomplete explanation. These gaps limit assessment of how fully the reported endpoint could represent the randomized group comparison.

The appropriate conclusion is therefore about the evidence available in the registry, not about whether the interventions succeed or fail. The design and endpoint are described, and safety counts are listed, but the primary outcome findings needed to evaluate the trial question are not reported in the registry record.

13. Why This Trial Matters Statistically

This study is statistically relevant because it illustrates the distinction between a clearly stated trial question and an interpretable result. The registry describes random assignment to approaches for communicating screening information and identifies referral as the primary endpoint. Those details help define what the study was intended to examine. Yet a design description cannot substitute for outcome counts, group comparisons, and estimates of uncertainty.

The endpoint also highlights an important distinction in clinical research: a process measure can capture an action in care without measuring the patient’s later experience or outcome. Provider referral is a meaningful step to study, but it is not equivalent to treatment initiation or symptom improvement. Keeping the endpoint’s scope clear helps prevent conclusions from extending beyond what the measure represents.

Documentation availability is another statistical consideration. The record says referral information was available for review for 92 of 100 participants, but does not explain the analysis of unavailable documentation. When outcome ascertainment depends on medical records, differences in availability or recording can influence which observations contribute to a comparison. Transparent reporting of participant flow, missingness, and analysis populations is therefore important for judging the credibility and generalizability of an estimate.

Finally, the entry underscores why statistical results need both estimates and uncertainty. Counts alone can describe observed events, while comparative estimates and confidence intervals help show the size and precision of a difference. Since the registry does not report the referral counts or analysis, no such interpretation is possible. The trial remains a useful example of how registry methods and results must be read as separate parts of the evidence.

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.

Several limitations specific to this registry entry constrain interpretation. Most importantly, arm-level primary outcome counts and comparative estimates are not reported in the registry record. The entry lists no analyses, so the direction and precision of any difference in referrals cannot be evaluated. The primary outcome description refers to both referrals and treatment initiation, but the registry does not provide a separate initiation definition or result.

The referral documentation note says 92 of 100 participants had documentation or an accessible electronic medical record available. The record does not explain why documentation was unavailable for others or how their outcomes were handled. It also says the Screening Wizard and Screening Wizard + SOVA arms were combined for this note, but the explanation is truncated. This makes the scope of the documented referral review difficult to reconcile with the three-group randomized design.

The registry does not report participant flow by group, criteria for inclusion in the primary analysis, allocation procedures, the identity of the masked party, or a statistical analysis plan. It does not report details of the usual-care context, the primary outcome’s event-ascertainment rules, or the observation period beyond the stated baseline in-office visit. These omissions prevent assessment of whether the planned analysis matched the randomized comparison and whether referral events were measured consistently.

Secondary outcomes are named, but their results and analysis details are not reported in the record. The available adverse-event counts lack further detail about ascertainment and monitoring duration. These limitations are about what the registry entry documents; they do not establish what was or was not measured in the full study.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Screening Wizard- Phase 2 — NCT04646369.
• Registry record last updated 2022-10-07; status last verified 2022-10.
• Results first posted 2022-09-27.
• 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

NCT04646369, titled “Screening Wizard- Phase 2,” is listed as a completed, randomized, single-masked, parallel study with phase recorded as NA. The registry records enrollment of 100 and a start date of 2020-11-05, with primary completion on 2021-09-17. The three behavioral groups are “screening as usual,” Screening Wizard 2.0, and Screening Wizard 2.0 + SOVA.

The primary endpoint is the number of participants referred to treatment at the baseline in-office visit. The entry describes monitoring personalized referrals and treatment initiation, and notes that referral documentation or an accessible electronic medical record was available for 92 of 100 participants. It does not report arm-level primary outcome counts or inferential analyses. Listed safety figures show zero serious events, zero other events, and zero deaths in each group. Secondary outcomes are named, but their results are not reported in the registry record.