This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Clinical Validation of AI-Based System for Continuous Remote Monitoring of Patient Severity - Experts' Opinion (NCT06237036), a registered phase not stated study. The primary outcome is Clinical Utility Questionnaire (CUS) Score.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT06237036 |
| Phase | Phase not stated |
| Condition | Skin Diseases, Skin Condition |
| Allocation | Not Stated |
| Design model | Not Stated |
| Masking | Not Stated |
| Enrollment | 160 |
| Arms in the primary outcome | n/a |
| Lead sponsor | AI Labs Group S.L |
| Results posted | Yes |
2. Clinical Question
The study concerns whether Legit Health Plus can support remote monitoring of chronic skin conditions and whether clinicians regard it as practically useful. The registry describes an observational evaluation without a comparison group, so the questions are about the experience and assessed utility of using the tool rather than a controlled comparison between treatments or monitoring strategies.
Population
Participants were people with specified chronic dermatological conditions, including skin diseases such as acne, psoriasis, or atopic dermatitis. The study enrolled 160 participants. The registry describes patients attended at the Dermatology Department of the Hospital Universitario de Torrejón.
Intervention
Participants were to use the Legit Health Plus smartphone app to send skin photographs to their doctor and answer symptom and daily-life surveys. The study description says app use was planned for 6 months, with participant surveys about satisfaction and ease of use every two months.
Comparator
No comparison group was used. The registry record does not describe a like-for-like control group, and the study is not a randomized comparison. The results therefore cannot directly contrast app monitoring with another monitoring approach.
Primary question
The primary outcome was the Clinical Utility Questionnaire score, which rates the practical value of the device. The registry also describes questions about tracking changes in skin condition, reducing in-person visits, and participant satisfaction, but a reported primary score result is not reported in the registry record.
The clinical question is consequently about the perceived utility of the system within the participating group. It is not, by itself, a test of whether the tool improves health outcomes or changes care compared with usual practice.
3. Trial Design
This was an observational study sponsored by AI Labs Group S.L. The registry lists the study as completed, with a start date of 2022-03-03 and primary completion date of 2023-10-23. Enrollment was 160. The conditions listed are Skin Diseases and Skin Condition, and the participant description refers to specified chronic dermatological conditions.
The registry describes a real-world evaluation of a remote monitoring tool rather than a randomized intervention study. Participants were to use a smartphone app to submit skin photographs and report symptoms and effects on daily life. The study description says app use would continue for 6 months, while the primary outcome timeframe is given as the conclusion of the study evaluation period, up to 18 months. The record does not explain the relationship between these two timeframes.
No comparison group was used. Allocation is not stated, and the registry record does not describe randomized assignment. The single participant group therefore supplies observations about use of the system, but does not provide a concurrent control for separating the effects of the tool from other influences or from changes over time.
The primary outcome was the Clinical Utility Questionnaire score. Secondary outcomes listed are the System Usability Scale score, Patient Satisfaction Questionnaire score, and Utility Questionnaire score. The record lists four outcome measures in total, but lists no analyses. It also does not report a protocol-level sample-size justification, interim analysis plan, or detailed statistical analysis plan. The record gives no primary score result with which to assess whether the stated utility threshold was reached.
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: Following enrollment, a significant screening process was conducted to ensure protocol adherence. Of the 400 potential participants initially considered, 240 individuals were excluded primarily due to low protocol adherence. This meticulous selection process ensured that only the 160 participants meeting all predefined eligibility criteria proceeded to the data collection phase. No additional washout or run-in periods were required.
Overall Study
| Stage | Patients With the Specified Chronic Dermatological Conditions |
|---|---|
| STARTED | 160 |
| COMPLETED | 160 |
| NOT COMPLETED | 0 |
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.
| Characteristic | Unit | Patients With the Specified Chronic Dermatological Conditions |
|---|---|---|
| Participants analysed | 160 | |
| Age, Continuous | Years | 64 (SD 19) |
| Sex: Female, Male: Female | Participants | 92 |
| Sex: Female, Male: Male | Participants | 68 |
| Race (NIH/OMB): American Indian or Alaska Native | Participants | 0 |
| Race (NIH/OMB): Asian | Participants | 0 |
| Race (NIH/OMB): Native Hawaiian or Other Pacific Islander | Participants | 3 |
| Race (NIH/OMB): Black or African American | Participants | 0 |
| Race (NIH/OMB): White | Participants | 157 |
| Race (NIH/OMB): More than one race | Participants | 0 |
| Race (NIH/OMB): Unknown or Not Reported | Participants | 0 |
6. Primary Endpoint
The registry lists the primary outcome as Clinical Utility Questionnaire (CUS) Score, measured over At the conclusion of the study evaluation period, up to 18 months..
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | Units on a scale |
| Endpoint classification | Continuous Endpoint |
The primary endpoint is the Clinical Utility Questionnaire score, a measure of the perceived practical value of the Legit Health Plus device. It is intended to capture clinicians’ assessment of how the system supports tracking disease progression and prioritizing participants for care. This makes the outcome relevant to the study’s aim of evaluating usefulness in practice, while distinguishing it from a direct measure of disease severity or a clinical health outcome.
The questionnaire has 13 items. Items 1-10 use a 0-10 Likert scale, with 0 indicating the lowest utility and 10 the highest. Items 11-12 are scored as 0 for No or 10 for Yes. Item 13 is scored as 0, 4, 8, or 10 according to the amount of consultation time saved. The raw item scores are summed, with a possible raw-score range from 0 to 130, then normalized to a 0-to-10 score. Higher scores indicate greater perceived clinical utility.
A score of 8.0 or higher was the pre-specified threshold for successful validation of device utility. The registry specifies reporting the mean and standard deviation at the conclusion of the evaluation period, up to 18 months. The score and its comparison with the threshold are not reported in the registry record, so whether the threshold was reached cannot be determined from the posted results.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The registry record describes the rationale, participant activities, and primary measure, but provides no primary Clinical Utility Questionnaire score and lists no analyses. The main numerical result needed to interpret the stated validation criterion is therefore absent: the record does not report whether the mean score was below, at, or above the pre-specified threshold of 8.0. No conclusion about meeting that criterion can be drawn from the record.
The planned endpoint is a clinician-rated measure of perceived practical utility. It concerns the usefulness of the device for tracking disease progression and prioritizing care; it is not equivalent to an objective measure of disease change, a measure of diagnostic accuracy, or evidence that clinical care improved. The registry description also raises questions about in-person visits and participant satisfaction, but the posted results do not include values for those questions.
The study’s observational design and lack of a comparison group shape what can be learned. Responses could describe clinicians’ experience of the tool within the participating group, but the design cannot directly establish how those responses compare with care without the tool. It also cannot isolate the tool’s contribution to any changes in visits or reported condition over time. These limits apply even if outcome scores were available.
The outcome is defined on a bounded scale from 0 to 10, with higher values representing greater perceived utility. A mean would describe the group’s average score, while the standard deviation would describe variation among scores around that average. Both are useful summaries, but neither is reported as a primary result in the registry record. Without those values, the distribution of clinician ratings and the degree of agreement among them remain unknown.
The registry lists 160 participants, but the record does not report how many contributed a completed primary outcome, how missing observations were handled, or which analysis population was used. Enrollment alone does not establish the number of evaluable scores. Consequently, precision cannot be assessed from the posted record, and no confidence interval or other uncertainty estimate for the primary endpoint is reported.
In short, the registry record supports a description of the study question and measurement plan, not a finding about the performance or utility of the device. The absence of a reported score is not evidence that the system did or did not meet the criterion. It means the primary result cannot be interpreted from the posted information.
9. Statistical Methods Explained
The primary outcome is a continuous score summarized as a mean and standard deviation. This choice describes both the average clinician rating and the degree to which individual ratings vary. The score is bounded from 0 to 10, and its meaning is directional: higher values indicate greater perceived clinical utility. The pre-specified threshold of 8.0 gives a criterion for interpreting the score, but does not substitute for the observed result or its uncertainty.
What does a mean and standard deviation tell us?
In general, the mean is the arithmetic average of the observed scores. It offers a compact summary of the group’s central rating, but can conceal differences among participants or clinicians. The standard deviation describes how spread out the individual scores are around the mean. A small spread would indicate more similar ratings, while a large spread would indicate greater variation. Neither summary alone shows the full distribution, and a mean can be affected by unusually high or low values.
Because the score is bounded, its distribution may not resemble the symmetric, unbounded distributions often used in simple statistical models. Scores can cluster near the limits, especially when respondents tend to give very favorable or unfavorable ratings. In general, inspecting the score distribution helps assess whether a mean is an adequate summary and whether model assumptions are plausible. The registry record does not report score distributions or diagnostic checks.
How should the threshold be interpreted?
The stated cutoff of 8.0 was pre-specified as the threshold for successful validation of utility. In general, comparing an observed score with a prespecified cutoff makes the criterion explicit and avoids selecting a threshold after seeing results. Still, a threshold comparison is more informative when accompanied by an estimate of uncertainty. A mean just on one side of a cutoff may be estimated imprecisely, and the registry record does not report a confidence interval or any other uncertainty measure for this endpoint.
In general, a confidence interval gives a range of values compatible with the observed data under the assumptions of the method. It communicates estimation precision; it is not a guarantee that the true value lies within the interval, nor does it establish causal effects. No confidence interval is reported for the primary score, and the registry lists no analyses from which one could assess the methods used.
What can be inferred from an observational study?
In general, an observational study records outcomes without random assignment to competing study conditions. The absence of a comparison group means that observed ratings describe the participants and clinicians involved, but do not establish what ratings would have been under another monitoring approach. Changes in disease status, clinician expectations, participant engagement, and other influences could shape experience over time. The registry record does not describe a design feature that would separate these influences.
The record’s sample-size assumptions describe a planning illustration using a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect to detect set as a stated fraction of the observed effect. Those assumptions describe a hypothetical planning calculation, not the actual study design, which had no comparison group. The illustration is not observed power and does not demonstrate that the study was adequately sized. The record does not report the trial’s own sample-size justification or provide an observed effect value to interpret in this context.
General statistical power is a design-stage probability calculation for detecting a defined effect under stated assumptions. It is not a measure of how likely a result is true after the study, nor does a power calculation replace reporting the observed estimate and its uncertainty. Sample-size illustrations should therefore be treated as planning information, not as findings about the 160 enrolled participants.
What is not specified?
The registry lists the mean and standard deviation as the primary outcome summaries, but does not report a statistical analysis plan, a model, a confidence-interval method, or methods for handling incomplete outcome data. It does not say whether scores would be analyzed at the participant level, clinician level, or another level. These details matter because the unit of analysis and handling of repeated or clustered observations can affect estimates and their precision. No specific method should be assumed from the outcome description alone.
General statistical practice also distinguishes a prespecified analysis from exploratory analyses conducted after viewing results. Prespecification can reduce analytic flexibility, but the registry record does not provide enough detail to determine what analyses were planned beyond the stated outcome summary and threshold. Since no analyses are listed, the statistical evidence supporting the endpoint is unavailable in the posted record.
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.
| Arm | Participants | Mean | Standard deviation | 95% CI for the mean |
|---|---|---|---|---|
| Dermatologists Assessing the Device | 6 | 7.390 | 2.250 | 5.029 to 9.751 |
R code and output
arm <- c("Dermatologists Assessing the Device")
n <- c(6)
m <- c(7.39)
sp <- c(2.25)
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 Dermatologists Assessing the Device 6 7.390 2.250 5.029 9.75111. Multiplicity, Missing Data and Analysis Populations
The registry lists four outcome measures: the Clinical Utility Questionnaire score as primary, with the System Usability Scale score, Patient Satisfaction Questionnaire score, and Utility Questionnaire score as secondary outcomes. Considering multiple outcomes creates a multiplicity issue in general: the more separate results tested, the greater the chance that at least one appears noteworthy by chance alone. The record does not report whether any multiplicity adjustment or hierarchy among secondary outcomes was planned.
The primary outcome timeframe is described as the conclusion of the study evaluation period, up to 18 months. The study description also says participants would use the app for 6 months and complete satisfaction and usability surveys every two months. The registry record does not explain how repeated measurements were to be summarized or whether any particular timepoint was designated for the secondary outcomes.
Missing-data procedures are not reported in the registry record. The record does not say how incomplete questionnaires, missed follow-up surveys, or withdrawal would be handled, and does not state the number of participants with observed primary scores. The enrollment figure of 160 should not be taken as the number contributing to each outcome.
Analysis populations are also not reported in the registry record. It does not specify whether analyses were intended to include all enrolled participants, only participants who used the app, or only those with complete outcome data. Interim analyses are not reported in the registry record. These omissions prevent assessment of how the posted analysis population, missing observations, repeated measurements, and multiple outcomes would affect interpretation. No outcome analyses are listed.
12. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Patients With the Specified Chronic Dermatological Conditions | 0 | 160 | 0.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Patients With the Specified Chronic Dermatological Conditions | 0 of 160 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 0% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Patients With the Specified Chronic Dermatological Conditions | 0 of 160 |
The registry reports 160 participants at risk for serious adverse events and 0 affected. For other adverse events, 160 participants were at risk and 0 affected. The recorded number of deaths is 0, and no serious adverse event terms are listed.
These figures describe the adverse-event counts entered in the registry for this study. They should be read as reported observations, not as proof that adverse events were impossible or that the tool is risk-free. The registry record does not provide further detail about how events were collected, the observation period for these counts, or the completeness of adverse-event reporting.
Because this was an observational study without a comparison group, these counts do not show how event rates compare with another monitoring approach. They also do not by themselves establish that any event or absence of an event was caused by the device. The safety figures are limited to the counts recorded for the enrolled group, and should not be interpreted as a comparative safety estimate.
13. What the Result Does, and Does Not, Mean
The study is relevant to the practical evaluation of remote monitoring because it focuses on clinicians’ perceived utility of a tool intended to track chronic skin conditions and support care prioritization. Its outcome definition is explicit: the Clinical Utility Questionnaire combines ratings and categorical responses, converts the total to a score from 0 to 10, and identifies 8.0 or higher as the criterion for successful utility validation.
However, the registry record does not report the primary score, the secondary outcome results, or any analyses. It is therefore not possible to tell whether clinicians rated the tool highly, whether responses varied, or whether the pre-specified threshold was attained. The absence of a reported result must not be interpreted as either success or failure.
Even a reported high utility score would have a specific meaning: clinicians perceived the device as useful according to this questionnaire. It would not, on its own, show that the tool accurately measured disease severity, improved patient health, reduced unnecessary visits, or outperformed another approach. Those questions require relevant outcome data and, for comparative claims, a suitable comparison design.
Participant satisfaction and usability are listed as secondary outcomes, but their numerical results are not reported in the registry record. The study description mentions potential effects on in-person visits, but no visit outcome result is listed. Thus, the posted information cannot establish participant acceptance, ease of use, or a change in healthcare use.
The registry record is useful for understanding what the study set out to assess, who was enrolled, and how the primary measure was defined. It is not sufficient for assessing the observed clinical utility or the precision of that estimate. Interpretation should remain limited to the design and measurement plan that are documented.
14. Why This Trial Matters Statistically
This study raises a statistical question that is distinct from whether a digital tool can be built: how should its practical value be measured and interpreted in a real-world clinical setting? The Clinical Utility Questionnaire attempts to operationalize that value through ratings of disease tracking, care prioritization, and consultation time. Stating the instrument, scoring process, direction, and threshold makes the intended interpretation more transparent.
The record also illustrates why endpoint definition and outcome reporting are separate requirements. A detailed score definition clarifies what a future result would mean, but it cannot replace the score itself. Without an observed estimate, a measure of its variability, and an account of missing observations, readers cannot assess the result’s magnitude or precision.
The observational design is important to statistical interpretation. A single group can provide descriptive evidence about the experience of using the app, but it does not answer how that experience compares with a different monitoring strategy. The record’s discussion of real-world monitoring therefore needs to be read alongside the lack of a comparison group, especially for questions about reducing visits or changing care.
The study also lists usability and satisfaction outcomes, which address dimensions of implementation beyond the primary clinical-utility rating. Reporting those outcomes alongside the primary measure could help distinguish clinician-perceived utility from participant experience. In the posted record, however, no outcome analyses are listed.
For researchers planning similar evaluations, the record highlights the value of specifying how repeated questionnaires, incomplete observations, and multiple outcomes will be handled. Those details are not reported, leaving important aspects of the intended analysis unclear. The statistical importance of this study lies in its defined measurement framework and in the limits of what can be learned when results and analysis details are not posted.
15. 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 central limitation for interpreting this study is that the registry record lists no analyses and does not report the primary score. It is not possible to assess the mean, variability, uncertainty, or whether the pre-specified threshold was reached. Secondary outcome values are also not reported.
The study had no comparison group and was not a randomized comparison. As a result, the design cannot estimate a comparative effect of the tool versus another monitoring approach. Inferences about changes in visits, care prioritization, or disease tracking would also require outcome information that is not reported in the registry record.
The record describes app use for 6 months and gives the primary endpoint timeframe as the conclusion of the evaluation period, up to 18 months, but does not explain how those periods relate. It also does not report the number of participants with completed outcomes, how missing responses were handled, or the analysis populations. These gaps limit assessment of potential attrition and the representativeness of any eventual score.
The primary endpoint is a questionnaire-based assessment of perceived clinical utility. It is not a direct measure of disease severity or a controlled test of diagnostic accuracy. The registry record does not report details of instrument validation in this study, assessor procedures, or the statistical analysis plan. It also does not report a sample-size justification, interim analysis plan, or methods addressing multiplicity across the listed outcomes. These limitations do not show that the device was or was not useful; they constrain what the posted record can establish.
16. Related Tutorials
17. Related Statistical Calculators
18. Sources
- ClinicalTrials.gov: Clinical Validation of AI-Based System for Continuous Remote Monitoring of Patient Severity - Experts' Opinion — NCT06237036.
- Registry record last updated 2026-03-19; status last verified 2026-02.
- Results first posted 2026-03-19.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
19. Record Summary
NCT06237036 is a completed observational study sponsored by AI Labs Group S.L. It enrolled 160 participants with specified chronic dermatological conditions and evaluated Legit Health Plus for remote monitoring. The registry lists a study start date of 2022-03-03 and primary completion date of 2023-10-23.
The primary outcome was the Clinical Utility Questionnaire score, reported as a mean and standard deviation and defined on a 0-to-10 scale. A score of 8.0 or higher was the pre-specified threshold for successful validation of device utility. Secondary outcomes were usability, patient satisfaction, and utility questionnaire scores.
The study had no comparison group. The registry record lists no analyses and does not report the primary score, secondary results, missing-data methods, analysis populations, or a detailed statistical plan. Adverse-event counts were 0 serious events, 0 other events, and 0 deaths among 160 participants at risk.