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 Evaluation of the AIVARIX in Detecting Signs C 1-2 Classes of CVD (NCT05612217), a registered phase not stated study. The primary outcome is Evaluation of Sensitivity (Sn) of the AI-based AIVARIX App in Detecting C1 and C2 Classes of CVD in Patients Who Are Seeking for Professional Advice From a Phlebologist Regarding Symptoms and Signs Suggestive to CVD..
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT05612217 |
| Phase | Phase not stated |
| Condition | Chronic Venous Disease, CVD |
| Allocation | Not Stated |
| Design model | Not Stated |
| Masking | Not Stated |
| Enrollment | 433 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Servier Russia |
| Results posted | Yes |
2. Clinical Question
Population
Outpatients in Russia seeking professional phlebologist advice for symptoms or signs suggestive of chronic venous disease (CVD). The study description includes patients with C1 and C2 disease as well as people with other specified venous-disease classes or lower-extremity skin conditions.
Intervention
The AIVARIX AI-based application, evaluated for its ability to detect signs of C1 and C2 classes of CVD.
Comparator
The application’s detection is considered against C1 or C2 CVD confirmed by phlebologists using objective or instrumental examinations. The record does not describe a randomized control group or provide further details of the assessment procedure.
Primary question
Among patients who truly have C1 or C2 CVD according to the phlebologist confirmation, what proportion are identified as positive by AIVARIX? This is the sensitivity question; the registry record does not report its numerical answer.
The clinical question is one of diagnostic accuracy, not a comparison of treatment outcomes. Sensitivity focuses on people who have the target condition: it asks how often the application detects them as positive. It does not by itself describe how often people without C1 or C2 disease are correctly classified as negative. The study intervention description also mentions estimating specificity, while the listed secondary outcomes concern positive and negative predictive values. Numerical results for these measures are not reported in the registry record.
The study is described as multicenter and observational, within routine clinical practice in Russia. Its brief summary says it would include patients suggestive of CVD, including but not limited to people with C1 and C2 classes. The primary endpoint wording narrows the accuracy question to patients seeking professional advice for symptoms and signs suggestive of CVD, with C1 or C2 confirmation as the target-positive condition. The record does not give additional eligibility criteria or a detailed account of how participants were recruited.
3. Trial Design
The record describes a completed, multicenter observational study conducted in routine clinical practice in Russia. It lists a start date of 2022-12-01 and a primary completion date of 2023-06-01. Recorded enrollment is 433. The brief summary states a planned number of 414 patients. The record does not explain the relationship between the planned number and the final enrollment.
The purpose was to evaluate the accuracy of the AIVARIX AI-based application for detecting signs of C1 and C2 classes of chronic venous disease in outpatients seeking phlebologist consultation. The primary outcome is sensitivity, defined in relation to positive C1 or C2 cases confirmed by phlebologists using objective or instrumental examinations. The intervention description also mentions sensitivity and specificity, and the listed secondary outcomes name positive and negative predictive values. Numerical outcome results are not reported in the registry record.
This is not described as a randomized comparison. The record does not identify a treatment allocation process, a parallel control arm, or a like-for-like control comparison. The application is the diagnostic tool under evaluation, while phlebologist confirmation supplies the reference for defining true positive cases in the primary sensitivity measure. Exact details of when and how the application assessment and confirmation examinations were performed are not reported in the registry record.
The arm description is titled Patients With CVD and says 20 patients per center. It lists patients with C1, C2, and other CVD classes, as well as people with C0s CVD or lower-extremity skin conditions other than CVD. The record does not provide a center count or a fuller account of how the listed categories relate to the overall enrollment. Further details on the number of centers, investigator blinding, the diagnostic workflow, and handling of indeterminate assessments are not reported in the registry record.
The study status is COMPLETED. That status and the recorded dates describe trial conduct, but do not establish that diagnostic results were posted. The primary outcome is specified with a timeframe of 1 month; the record does not add detail about the timing of individual assessments within that timeframe.
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
| Stage | Patients With CVD |
|---|---|
| STARTED | 433 |
| COMPLETED | 433 |
| 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 CVD |
|---|---|---|
| Participants analysed | 433 | |
| Age, Continuous | years | 46 (SD 18.43) |
| Sex: Female, Male: Female | Participants | 332 |
| Sex: Female, Male: Male | Participants | 101 |
| Race and Ethnicity Not Collected | Participants | — |
| Region of Enrollment: Russia | Participants | 433 |
6. Primary Endpoint
The registry lists the primary outcome as Evaluation of Sensitivity (Sn) of the AI-based AIVARIX App in Detecting C1 and C2 Classes of CVD in Patients Who Are Seeking for Professional Advice From a Phlebologist Regarding Symptoms and Signs Suggestive to CVD., measured over 1 month.
| Element | Registry entry |
|---|---|
| Result type | Number |
| Measure of spread | 95% Confidence Interval |
| Unit | percentage of of positive cases |
| Endpoint classification | not reduced to a single comparison |
The primary endpoint is sensitivity of AIVARIX for detecting signs of C1 or C2 chronic venous disease. The registry defines sensitivity as the number of positive application detections among the cases that are truly positive for C1 or C2 CVD, with true-positive status confirmed by phlebologists using objective or instrumental examinations. The stated unit is a percentage of positive cases, and the endpoint specifies a 95% confidence interval. Its timeframe is 1 month.
Sensitivity is useful in a diagnostic-accuracy assessment because it describes recognition among people who have the target condition according to the designated reference assessment. General statistical interpretation: a sensitivity estimate is more informative when considered alongside its confidence interval, which expresses the uncertainty around the estimate under the analysis method. The interval is not a guarantee that the true value lies within its limits.
Sensitivity does not measure performance among people without the target condition. Specificity addresses that complementary question, while positive and negative predictive values describe the probability of condition status given a positive or negative test result in the studied population. These measures answer different questions and are not interchangeable. The application description mentions sensitivity and specificity, and the secondary-outcome list names positive and negative predictive values. Their numerical results, as well as the numerical sensitivity estimate and its confidence interval, are not reported in the registry record.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The posted registry information identifies the diagnostic question and the planned form of the primary endpoint, but it does not include a numerical sensitivity result. It also does not report a confidence interval for sensitivity. Consequently, the record cannot establish from its posted results how many confirmed C1 or C2 cases the application detected, or how precise such an estimate would be. The study’s completed status does not fill this reporting gap.
For a sensitivity analysis, the denominator consists of cases classified as truly positive by the reference assessment, and the numerator consists of those cases also detected as positive by the application. The registry defines the reference-positive condition as C1 or C2 CVD confirmed by phlebologists using objective or instrumental examinations. General statistical interpretation: the confidence interval is important because the estimate is based on a finite set of evaluated cases and can vary across samples. Without the estimate, interval, and analyzed case count, precision cannot be assessed from the record.
The stated enrollment is 433, but that is not the same as the number of participants contributing to the primary sensitivity calculation. That calculation depends on the number of confirmed C1 or C2 cases with usable application and reference assessments. The number of such cases, the number with missing or indeterminate assessments, and the analysis population are not reported in the registry record. It would therefore be inappropriate to treat all enrolled patients as the sensitivity denominator.
The record does not report numerical specificity, positive predictive value, or negative predictive value results. The intervention description refers to estimating sensitivity and specificity, and the secondary-outcome list names PPV and NPV; neither statement substitutes for posted estimates. These measures address different parts of diagnostic performance. General statistical interpretation: sensitivity and specificity are defined relative to condition status, whereas predictive values also depend on how common the condition is in the population being assessed. Thus, a result from this clinical setting would need to be interpreted with attention to the study population and reference assessment.
No efficacy or clinical outcome conclusion follows from the registry information alone. The stated purpose is diagnostic accuracy, and the available record gives a design description without the numerical accuracy results. It also provides no basis for determining whether the assessment procedure was blinded, whether all participants received the same reference assessment, or how discordant or incomplete results were handled. Those details affect how a diagnostic-accuracy estimate is interpreted, but are not reported in the registry record.
The record lists zero serious adverse events, zero other adverse events, and zero deaths among 433 patients at risk in each of the adverse-event categories shown. These are registry counts, not diagnostic-performance outcomes. They do not supply information about sensitivity or specificity, and the record does not describe adverse-event ascertainment in enough detail to infer that no events occurred outside the recorded categories or observation period.
9. Statistical Methods Explained
What does sensitivity measure?
General statistical explanation: sensitivity is the proportion of reference-positive cases that the test identifies as positive. In this study, the registry defines reference-positive cases as C1 or C2 CVD confirmed by phlebologists using objective or instrumental examinations. The application’s positive classifications are evaluated against that reference. Sensitivity is therefore conditional on having the target condition according to the reference assessment; it is not the proportion of all enrolled patients classified correctly.
The registry specifies sensitivity as the primary outcome and expresses it as a percentage of positive cases, with a 95% confidence interval. It does not report the point estimate, confidence limits, or the number of confirmed positive cases used in the calculation. Without these, neither the observed detection proportion nor its statistical precision can be described.
How does the reference assessment matter?
General statistical explanation: diagnostic accuracy depends on how the condition is defined. Here, the registry definition uses phlebologist confirmation based on objective or instrumental examinations to identify true C1 or C2 cases. Such a reference assessment is the standard against which the application’s classifications are judged. Details that could affect interpretation include the specific examination procedures, whether assessors knew the application result, how disagreements were resolved, and how uncertain classifications were handled. These procedural details are not reported in the registry record.
The registry does not report whether every enrolled participant received the same reference assessment or whether any participants had missing assessments. It also does not state the count of participants whose results entered each diagnostic-accuracy measure. These are important because sensitivity requires known status among reference-positive participants, while specificity requires known status among reference-negative participants.
Why are sensitivity, specificity, and predictive values distinct?
General statistical explanation: sensitivity asks how frequently a test is positive among people with the condition. Specificity asks how frequently the test is negative among people without it. Positive predictive value asks how often a positive test corresponds to the condition, and negative predictive value asks how often a negative test corresponds to its absence. Each measure uses a different conditional denominator. An accuracy result should therefore be read with its measure and population clearly identified.
The AIVARIX intervention description says sensitivity and specificity are to be estimated. The secondary outcomes list positive and negative predictive values. The record does not provide numerical estimates for any of these measures. Nor does it report the distribution of CVD status among the analyzed participants, which would be needed to contextualize predictive values in the study population.
What does a confidence interval contribute?
General statistical explanation: a confidence interval describes uncertainty in an estimate under a specified statistical procedure. It helps distinguish a precise estimate from one that is compatible with a broader range of values. Its width is influenced by the information available for the calculation, including the number of relevant cases and the observed pattern of classifications. A confidence interval does not resolve possible bias in participant selection, reference assessment, or missing data.
The primary outcome specifies a 95% confidence interval, but no interval is posted in the registry record. The confidence level alone is not evidence of precision; the calculated limits and the underlying analysis population are needed to judge it.
How should planning illustrations be read?
General statistical explanation: sample-size planning translates an assumed effect and analysis approach into a target number of observations for a design objective. The planning illustration associated with this record is described as computed from the observed effect, not as the trial’s own design. It uses a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is described as a stated fraction of the observed effect. For non-time-to-event outcomes, the stated convention is participants per arm for a power target. Time-to-event calculations are described as total event counts, but the primary outcome in this record is a diagnostic-accuracy measure.
These assumptions describe an illustration, not a prospectively specified design justification. The registry record does not report its own sample-size justification, a target power, or the assumptions used to set planned enrollment. The brief summary states a planned number of 414, and recorded enrollment is 433. The planning illustrations are not observed power and cannot replace the missing diagnostic results or their confidence intervals.
General statistical explanation: power is a design concept related to the chance of detecting a specified effect under stated assumptions. It is not a measure of whether a study result is true, nor a way to determine the probability that an observed finding arose by chance. In this record, because numerical primary results and the relevant analyzed case counts are not reported, an outcome-specific precision assessment cannot be recovered from enrollment alone.
10. Multiplicity, Missing Data and Analysis Populations
The record identifies one primary outcome: sensitivity for detecting C1 or C2 CVD, reported as a percentage with a 95% confidence interval. The intervention description also mentions estimating specificity, and the secondary-outcome list names positive and negative predictive values. The record lists four outcome measures in total, but the other outcome titles and numerical results are not fully specified in the available registry information. No analysis results are listed.
Multiplicity concerns arise when several outcomes or analyses are examined, because repeated testing can affect the chance of at least one apparently notable result. General statistical explanation: a prespecified hierarchy or adjustment can help explain how multiple outcomes are interpreted. The statistical plan, any multiplicity strategy, and whether any outcomes were prioritized beyond the primary endpoint are not reported in the registry record. No interim analyses or other analysis procedures are reported either.
The registry does not state how missing, indeterminate, or unevaluable application or reference assessments were handled. It does not provide analysis-population definitions, participant flow, or the number included in each endpoint calculation. These omissions matter because the enrolled population of 433 may not be the same as the population contributing to each diagnostic-accuracy estimate.
The record also does not report whether the primary analysis used all eligible participants with available paired assessments, whether exclusions were made, or how incomplete assessments affected denominators. Without those details, the potential influence of missing data or exclusions on the reported accuracy measures cannot be evaluated. Numerical outcome results and a statistical analysis plan are not reported in the registry record.
11. 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 CVD | 0 | 433 | 0.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Patients With CVD | 0 of 433 |
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 CVD | 0 of 433 |
The adverse-event record lists 433 patients at risk for serious adverse events and 433 at risk for other adverse events. It records zero serious adverse events, zero other adverse events, and zero deaths. These are the posted counts for the categories shown; the record does not list serious adverse-event terms.
General statistical interpretation: a recorded count of zero means no events were entered in that category for the stated group in the registry record. It does not establish that an event is impossible, and it is not itself a measure of diagnostic accuracy. The record does not describe the adverse-event collection method, the observation period for these counts, or the criteria used to classify events. It is therefore not possible to assess reporting completeness or compare event rates across groups from the record.
The study is described as observational and evaluates an application, rather than a treatment comparison. The listed safety counts should be read in that context and should not be taken as evidence about the application’s sensitivity or specificity. No additional safety details are reported in the registry record.
12. What the Result Does, and Does Not, Mean
The registry record establishes that AIVARIX was evaluated in a completed multicenter observational study in Russian routine clinical practice, with a stated focus on detecting C1 and C2 chronic venous disease among outpatients seeking phlebologist advice. It defines sensitivity against C1 or C2 status confirmed by phlebologists using objective or instrumental examinations and specifies a 95% confidence interval for that primary outcome. Those details identify the intended diagnostic question.
The record does not report a numerical sensitivity estimate or confidence interval. It also does not report numerical results for specificity, positive predictive value, or negative predictive value. Therefore, the posted information does not show the frequency with which the application identified confirmed cases, the precision of that estimate, or how its classifications performed among participants without the target condition.
General statistical interpretation: diagnostic accuracy is specific to the population, target condition, application version, assessment process, and reference definition used in a study. The brief summary describes patients suggestive of CVD and includes people beyond C1 and C2 classes; the primary question focuses on detecting C1 or C2 disease. Without further participant characteristics and analysis details, the scope of any future numerical estimates would need to be considered in light of the enrolled and analyzed populations.
The record does not support conclusions about comparative benefit, clinical outcomes, or how use of the application affects care. It is not a randomized treatment comparison. It also does not provide enough procedural detail to evaluate blinding, incomplete testing, or the handling of uncertain classifications. These considerations limit interpretation even if accuracy estimates were available.
The adverse-event counts are zero for the listed categories, but those counts do not answer the diagnostic-performance question and lack details about ascertainment and observation. Likewise, the enrollment figure and the planning illustration cannot stand in for primary outcome results. The central statistical conclusion is limited: the registry specifies a diagnostic-accuracy objective, while its posted record does not report the numerical findings needed to judge that objective.
13. Why This Trial Matters Statistically
This study is statistically relevant because it frames an AI-based application as a diagnostic test and specifies a reference-based accuracy question. Sensitivity is not an overall correctness measure; it is focused on identification among cases considered positive under the study’s reference definition. The registry’s definition makes the phlebologist-confirmed C1 or C2 status central to interpreting the primary outcome.
The record also names complementary measures. Specificity concerns classification among reference-negative cases, while positive and negative predictive values describe the relation between a test result and condition status in the study population. General statistical explanation: no single one of these measures answers every question about diagnostic performance. Reporting the measure definitions, denominators, estimates, and uncertainty is essential for readers to understand what an accuracy result means.
The clinical setting matters statistically because the study concerns outpatients seeking phlebologist consultation for suggestive symptoms or signs, and the brief summary includes a broader range of CVD-related and non-CVD categories. The distribution of disease status in the population affects interpretation of predictive values. The registry record does not provide the analyzed distribution or the numerical predictive values, so that context cannot be quantified.
The most important statistical limitation in the posted record is the absence of numerical results for the primary sensitivity outcome and the other named diagnostic measures. The study’s completion status and enrollment count do not answer the diagnostic question. Nor does a stated confidence level provide precision without the calculated interval. Results, analyzed denominators, and methodological details are needed to assess performance and uncertainty.
Finally, the planning illustrations are not evidence of achieved statistical power or observed performance. They are described as illustrations based on an observed effect and specified assumptions, while the registry does not report its own sample-size justification. Keeping planning assumptions separate from observed outcomes is necessary to avoid treating design calculations as clinical findings.
14. Limitations
- The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
- Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
The registry record gives limited detail about the diagnostic workflow. It defines reference-positive C1 or C2 cases through phlebologist confirmation using objective or instrumental examinations, but does not specify the examinations, application assessment procedures, or timing of each assessment. The timeframe for the primary endpoint is 1 month, without further detail about scheduling.
The record does not report whether application readers or phlebologists were blinded to one another’s findings. It also does not explain how discrepant assessments, indeterminate classifications, or incomplete testing were handled. These details can affect diagnostic-accuracy estimates and their interpretation.
The arm description says 20 patients per center and lists several CVD and non-CVD groups, but the registry record does not state the number of centers or explain the relationship between those categories and the full enrollment of 433. It does not give participant flow, baseline characteristics, or the number of patients with confirmed C1 or C2 disease. The sensitivity denominator and analysis population therefore cannot be identified from the posted record.
The registry reports no numerical estimates for sensitivity, specificity, PPV, or NPV, and no confidence limits for the primary outcome. It also does not provide the statistical analysis plan, missing-data approach, or multiplicity strategy. The study is observational rather than a randomized comparison, so it does not establish comparative effects of a treatment. These limitations are specific to interpreting the record’s stated diagnostic-accuracy objective.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Evaluation of the AIVARIX in Detecting Signs C 1-2 Classes of CVD — NCT05612217.
- Registry record last updated 2024-09-25; status last verified 2024-09.
- Results first posted 2024-09-25.
- 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.
18. Record Summary
NCT05612217 is a completed multicenter observational study sponsored by Servier Russia. Its stated purpose was to evaluate the AIVARIX AI-based application for detecting C1 and C2 classes of chronic venous disease in outpatients seeking phlebologist advice in Russia. The record lists a start date of 2022-12-01, a primary completion date of 2023-06-01, and enrollment of 433; the brief summary states a planned number of 414.
The primary outcome is sensitivity, defined using C1 or C2 cases confirmed by phlebologists through objective or instrumental examinations, with a stated 95% confidence interval and a 1-month timeframe. The intervention description mentions sensitivity and specificity, and the secondary outcomes name positive and negative predictive values. Numerical diagnostic-accuracy results and analysis details are not reported in the registry record.
The adverse-event fields list zero serious adverse events, zero other adverse events, and zero deaths among 433 at risk in each stated category. Further information about event ascertainment is not reported in the registry record.