Longitudinal Study of Dental Implant Therapy in HIV Positive Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Longitudinal Study of Dental Implant Therapy in HIV Positive Patients (NCT01211288), a randomized na study. The primary outcome is Number of Implants Functioning in HIV Positive Subjects Compared to HIV Negative Subjects.

2. Clinical Question

The clinical question concerns implant performance in the context of HIV status. It is not a comparison of an implant against no implant: the group descriptions say that participants in both groups consented to receive implants. Although the registry classifies the study allocation as randomized, it does not state what was randomized or explain how that classification relates to a comparison defined by HIV status. HIV status itself should therefore not be treated as a randomized intervention.

The planned follow-up extended over a 3 years period according to the brief summary, while the primary outcome timeframe is baseline to 12 months after restoration completion. These descriptions refer to the study’s overall follow-up purpose and the specific primary outcome timeframe, respectively. The registry record does not explain the timing of every measurement or how the primary outcome timeframe relates to the longer follow-up.

3. Trial Design

The registry describes a completed, parallel-group study with randomized allocation and no masking. The groups are labelled HIV Negative Group and HIV Positive Group, and both are described as containing participants who consented to receive implants. Astra implants are the listed device intervention. The registry does not report the randomization method, what was allocated, allocation concealment, or a protocol explaining how randomization was used in a study whose main comparison is between HIV-status groups. Those details are not reported in the registry record.

Enrollment is listed as 41. For the primary outcome, the registry reports 19 participants in each group, alongside counts of functioning implants. The primary outcome description also says that follow-up could not be completed for 3 participants—two from the HIV-negative group and one from the HIV-positive group—and mentions one implant failure from the HIV-positive group. The record does not provide a participant-flow account that reconciles these statements with the enrollment and outcome counts. The implant counts and participant counts are different kinds of quantities and should not be interpreted as interchangeable.

The study status is completed. Its recorded start is 2010-05, and its primary completion date is 2019-04-01. The listed phase is NA. The registry states a broad aim of following implant performance in HIV-positive and HIV-negative patients, while the primary outcome focuses on functioning implants through 12 months after restoration was complete. The study protocol, planned enrollment rationale, and statistical analysis plan are not reported in the registry record.

The study is useful to read as a longitudinal comparison of outcomes recorded in two groups, not as a randomized test of HIV status. The randomized-allocation label does not by itself establish that HIV status or any other particular feature was assigned at random. Without details of the allocation process and the analysis population, the registry information does not establish which potential sources of group differences were addressed.

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

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Unable to do follow up on 3 participants - two participants from HIV negative group and one participant from HIV positive group, and one implant failure from HIV positive group

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 Implants Functioning in HIV Positive Subjects Compared to HIV Negative Subjects, measured over Baseline to 12 months after implant restoration complete.

The primary endpoint is the number of implants functioning in HIV-positive participants compared with HIV-negative participants. The timeframe is baseline to 12 months after implant restoration was complete. An implant is defined as functioning when its restoration is in the mouth with no pain, no mobility, no infection, and less than 50% bone loss around the implant site.

This count is intended to describe the number of implants meeting the study’s functional criteria, rather than a mean measurement or a participant-level percentage. An implant-level count can be clinically interpretable as a summary of how many implants met the stated criteria, but it does not on its own show how outcomes were distributed across participants. The registry does not report the total number of implants assessed in each group, so the counts should not be converted to rates or proportions.

The outcome definition combines clinical observations with a bone-loss criterion. This offers a stated rule for classifying an implant as functioning, but the registry does not report how each component was assessed, whether assessment was blinded, or how missing observations were handled. It also does not report a statistical analysis comparing the group counts. Consequently, the posted primary values describe the reported counts, but do not establish the precision of a between-group effect.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical interpretation depends on matching the method to the outcome and its unit of observation. The primary endpoint is a count of functioning implants, whereas the secondary radiographic endpoint is reported as a group mean with a standard deviation. Those summaries answer different descriptive questions, and they call for different approaches to estimating uncertainty.

What does the confidence interval describe?

General explanation: a confidence interval describes uncertainty around an estimate under the assumptions of the method used to calculate it. It is not a range containing every individual observation, and it is not a probability statement that a particular fixed effect lies within the interval. For the secondary mean difference, the interval extends from -0.402 to 0.422 millmeters. Because it includes zero, the posted summary does not rule out a zero difference under the recalculation’s assumptions. Its breadth also indicates that differences in either direction remain compatible with the data and method. The interval should not be read as proof of equivalence.

The registry does not report a confidence interval for the primary implant counts. Counts without denominators or a model-based estimate do not show how much sampling uncertainty surrounds a comparison. The posted numbers alone cannot establish that one group’s underlying probability of implant function is higher or lower. A count comparison would require an explicitly defined unit of analysis and suitable information about the number of implants assessed and the way implants are distributed among participants.

What does the p-value add?

General explanation: a p-value describes how unusual data at least as incompatible with a specified null model would be, assuming that model and the analysis assumptions hold. It is not the probability that the null hypothesis is true, nor a direct measure of clinical importance. The unadjusted p-value for the secondary mean comparison is 0.962. In context, that value does not provide evidence against a zero mean difference under the recalculated test. It does not show that the groups are identical, because the confidence interval remains compatible with differences in either direction.

The registry does not list a sponsor-reported analysis for the secondary comparison. The estimate, interval, and p-value are recalculated without adjustment from the posted group summaries. They do not account for possible covariates, clustering of multiple implants within participants, or other features that a prespecified analysis might address. The analysis plan and those details are not reported in the registry record. Accordingly, the recalculation is a useful descriptive aid, but it cannot be treated as a fully specified trial analysis.

Why does the outcome type matter?

General explanation: counts may be analyzed using methods for count data, while means are commonly analyzed using methods for continuous measurements. The choice depends on how the data were collected and on assumptions about their distribution and independence. A count of implants may require particular care if one participant contributes more than one implant, because those observations could be related. The registry does not report the number of implants per participant or an analysis accounting for possible within-participant dependence.

General explanation: over-dispersion occurs when count data vary more than expected under a chosen count model. If it is present and ignored, uncertainty estimates can be too small. Whether over-dispersion is relevant to the primary outcome cannot be determined from the posted implant counts alone; no count-data model, dispersion estimate, or primary inferential analysis is reported. This is one reason not to infer a statistical comparison from the raw counts.

For the radiographic measure, the registry reports group means and standard deviations. General explanation: a standard deviation describes the spread of individual measurements around a group mean, whereas the standard error describes uncertainty in an estimated mean. They are not interchangeable. The recalculation uses the posted group summaries to estimate an unadjusted difference and its uncertainty. Its interpretation relies on the assumptions used in that approximation and does not address unreported features such as participant-level clustering or covariate adjustment.

How should the planning illustration be read?

The planning illustration is based on the observed secondary effect, with two-sided significance level 0.05, equal allocation, and a normal approximation. It gives participants per arm for 80% and 90% power under alternative assumed effect sizes expressed as fractions of the observed effect. These are planning illustrations, not the study’s actual enrollment rationale, and they are not observed power. The registry does not report the original sample-size justification or the assumptions used to plan enrollment.

Planning calculations based on an observed effect can be especially unstable when that estimate is uncertain. They should not be used to infer that the study had a particular probability of detecting an effect after the data were observed. Nor do they show that the trial was designed to answer the primary count question: the illustration is based on the secondary mean comparison. The registry does not report a sample-size calculation for the primary outcome.

Finally, the study’s randomized-allocation label does not establish that the HIV-status comparison is randomized. General explanation: randomization can help balance measured and unmeasured characteristics when an intervention is assigned, but it does not make a pre-existing group characteristic randomized merely because the registry uses a randomized-allocation label. The allocation procedure and the feature assigned are not reported in the registry record. The group comparison should therefore be interpreted with this design uncertainty in mind.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists six outcome measures, repeats the same peri-implant health and bone-maintenance wording among its secondary outcomes, and reports no analyses. It does not state which outcomes were prespecified for formal testing, whether an outcome hierarchy was used, or whether any adjustment for multiple comparisons was planned. Those details are not reported in the registry record.

General explanation: when multiple hypotheses are tested, the chance of at least one apparently unusual result can increase. Adjustment procedures can address that issue, but they may also affect the interpretation and precision of individual estimates. Because no analysis plan or multiplicity procedure is reported, the unadjusted recalculated secondary result should be treated as exploratory rather than as a definitive test. It is not possible to determine from the registry whether the repeated outcome listings correspond to separate planned analyses or duplicate entries.

Missing-data handling is also unclear. The primary outcome description states that follow-up could not be completed for 3 participants—two in the HIV-negative group and one in the HIV-positive group—and mentions one implant failure in the HIV-positive group. The registry does not explain how missing follow-up was handled in the reported counts or whether missingness affected other outcomes. It also does not give enough participant-flow detail to reconcile the enrollment, group counts, and outcome-population description.

The analysis populations are not reported in sufficient detail to determine whether results were based on all enrolled participants, participants with observed follow-up, implants with available measurements, or another defined set. The record does not report an intention-to-treat analysis, a per-protocol analysis, imputation, or a sensitivity analysis. These omissions matter because analyses restricted to observed measurements can differ from analyses that include all participants under a prespecified missing-data strategy.

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 reports zero serious adverse events and zero other adverse events in the listed safety groups, with zero deaths in each group. The stated at-risk counts are 16 for the HIV-negative group and 14 for the HIV-positive group for both serious and other adverse events. These are the denominators reported for the safety entries; they should not be assumed to match the group counts reported for the primary outcome.

Zero events in the registry means that no events are recorded in those safety fields. It does not establish that the true risk is zero, particularly when the number at risk is limited and follow-up or ascertainment details are not available. The record does not provide event-specific descriptions among the serious-event terms, and its list of top serious terms is empty. It also does not describe how adverse events were collected, how long participants were monitored for safety, or whether all participants contributed safety data.

These figures are therefore best read as registry-reported counts, not as a precise estimate of safety or a comparison capable of ruling out uncommon events. They do not support a medical recommendation.

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

The posted results describe implant counts and a radiographic group summary among HIV-positive and HIV-negative participants. For the primary outcome, the registry reports counts of functioning implants but does not report a between-group estimate, confidence interval, or statistical test. Without total implants assessed and a clear account of the analysis population, those counts cannot show a comparative rate or quantify the uncertainty around a group difference.

The secondary radiographic comparison has an unadjusted recalculated mean difference close to zero, with a confidence interval that spans zero and values in both directions. This is compatible with uncertainty about the direction and size of the difference. It does not establish equivalence, prove that the groups have the same outcomes, or settle the primary clinical question.

The registry’s randomized-allocation designation is not enough to interpret HIV status as randomized. The groups are defined by HIV status, and the record does not describe what was randomized. The findings therefore should not be read as a randomized causal estimate of the effect of HIV status. The study may describe observed outcomes in the listed groups, but the record does not show whether differences in other characteristics were addressed.

The result also does not establish how implant outcomes would compare in other populations or under different follow-up and assessment practices. The protocol, full analysis plan, participant flow, missing-data methods, and detailed measurement procedures are not reported in the registry record. These uncertainties limit the strength of conclusions that can be drawn from the posted summaries. They do not negate the descriptive value of the observations, but they define what those observations can support.

13. Why This Trial Matters Statistically

This study raises several statistical issues that often arise when clinical outcomes are recorded at more than one level. The primary measure counts implants, while the participants are grouped by HIV status. If participants contribute multiple implants, observations from the same participant may be related. The registry does not state how many implants each participant contributed or whether the analysis accounted for this possible clustering. That information matters for estimating uncertainty from implant-level data.

The record also illustrates why outcome definitions and denominators are essential. A count of implants meeting functional criteria is informative as a descriptive measure, but without the number assessed it cannot be converted into a rate or a probability. The stated incomplete follow-up adds another layer: the registry identifies participants without follow-up and an implant failure, but does not explain how these observations were incorporated into the outcome results.

A further issue is the distinction between randomized allocation and a comparison by a participant characteristic. The registry labels allocation as randomized, yet the groups are defined by HIV status and both are described as receiving implants. Without a clear description of the allocation procedure, the label cannot establish that the group comparison has the protection against confounding associated with randomized assignment.

Finally, the secondary result illustrates the difference between an estimate and its precision. A point estimate near zero does not establish equivalence when the confidence interval remains compatible with differences in either direction. The absence of reported analyses, a sample-size rationale, and multiplicity procedures makes it especially important to distinguish descriptive summaries and recalculations from prespecified confirmatory findings. These are general lessons about design and interpretation, rather than conclusions that the registry does not support.

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 are specific to the record for this study. The primary endpoint is reported as counts of functioning implants, but the total number of implants assessed in each group is not reported. The record therefore does not support interpreting those counts as group-specific rates or probabilities. It also does not describe whether multiple implants from the same participant were handled as related observations in any analysis.

The enrollment and outcome descriptions are not fully reconciled. Enrollment is listed as 41, while the primary outcome reports 19 participants in each group and separately notes incomplete follow-up for 3 participants and one implant failure. The record does not explain how these statements relate to the outcome counts or define the complete analysis population.

The randomized-allocation label is difficult to interpret alongside groups defined by HIV status. The record does not report the allocation method or identify what was randomized. It also does not report masking of outcome assessors, procedures for measuring the radiographic outcome, or details of follow-up beyond the stated outcome timeframe and broad study purpose.

No sponsor-reported analyses are listed. The primary outcome lacks an inferential comparison, and the available secondary comparison is an unadjusted recalculation. The statistical plan, sample-size justification, missing-data strategy, covariate adjustments, and multiplicity approach are not reported in the registry record. The secondary outcome wording is repeated, without a clear explanation of whether the listings represent distinct analyses. Together, these gaps limit interpretation of precision, robustness, and generalizability.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Longitudinal Study of Dental Implant Therapy in HIV Positive Patients — NCT01211288.
• Registry record last updated 2020-06-02; status last verified 2020-05.
• Results first posted 2020-05-15.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

The registry describes a completed parallel-group study of dental implant therapy in HIV-positive and HIV-negative participants. It lists randomized allocation, no masking, and Astra implants. Enrollment is 41, with a recorded start of 2010-05 and primary completion on 2019-04-01.

The primary outcome is the number of functioning implants from baseline to 12 months after restoration completion. The registry reports counts for each group but no inferential comparison. The secondary radiographic outcome is summarized by group, with an unadjusted recalculated mean comparison. The registry lists no reported analyses.

Participant flow, the allocation procedure, analysis populations, missing-data methods, sample-size rationale, and statistical plan are not reported in the registry record. The posted summaries are therefore best interpreted as descriptive, with the secondary recalculation offering limited evidence about the precision of a between-group difference.