RIGHT: Rhythm ID Going Head-to-Head Trial: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for RIGHT: Rhythm ID Going Head-to-Head Trial (NCT00148954), a randomized phase 4 study. The primary outcome is Number of Patients With Inappropriate Ventricular Tachycardia (VT)/Ventricular Fibrillation (VF) Therapy (Shock or Antitachycardia Pacing [ATP]) After the Pre-Discharge Visit.

2. Clinical Question

This question concerns a device-classification and treatment outcome: whether a delivered therapy was considered inappropriate after review of the rhythm episode. The study description says that events with delivered ventricular tachycardia or ventricular fibrillation therapy and a stored electrogram were reviewed by an independent adjudication committee. The committee assessed whether the device had classified the rhythm appropriately and whether the subsequent therapy was appropriate.

The primary outcome is a count of participants meeting the endpoint, rather than a count of all therapy episodes. The registry timeframe begins at the pre-discharge visit and continues until a minimum of 12 months of follow-up, ending at study closure. The record does not give a participant-level follow-up distribution or an exact common follow-up duration. The central comparison is therefore the posted participant counts in the VITALITY 2 and Medtronic Family groups, alongside the separate sponsor-reported time-to-event analysis.

3. Trial Design

RIGHT was a randomized, prospective, two-arm, parallel-group study. The registry lists the trial as Phase 4, with no masking. Participants were assigned to receive either the VITALITY 2 ICD or a selected Medtronic family ICD. The record lists Boston Scientific Corporation as the sponsor and tachycardia as the condition under study.

The registry reports an enrollment of 1962. The posted primary outcome counts are 246 participants among 985 assigned to VITALITY 2 and 187 among 977 assigned to the Medtronic Family group. These are the reported group sizes and event counts for this endpoint; they do not establish details of the randomization procedure or of any analysis population. Those details are not reported in the registry record.

The study start is listed as 2005-07, primary completion as 2009-03, and status as completed. The brief summary describes the study as assessing differential efficacy of VITALITY 2 devices using Rhythm ID versus selected Medtronic ICDs. The record lists one sponsor-reported analysis for the primary outcome, described as regression and Cox analysis, and three secondary outcomes. Those secondary outcomes concern time to first inappropriate shock, positive predictive value of the devices’ ventricular tachycardia or fibrillation discrimination algorithms, and time to first inappropriate therapy following inappropriate episode classification.

The registry does not report the original sample-size justification, details of allocation concealment, the randomization method, or a full statistical analysis plan. It also does not describe the specific Medtronic models or establish that all participants had the same length of follow-up. These omissions limit the detail with which the planned design can be reconstructed from the record.

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

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 Patients With Inappropriate Ventricular Tachycardia (VT)/Ventricular Fibrillation (VF) Therapy (Shock or Antitachycardia Pacing [ATP]) After the Pre-Discharge Visit, measured over From date of pre-discharge until a minimum of 12 months follow-up until study closure.

The primary endpoint counts participants with inappropriate ventricular tachycardia or ventricular fibrillation therapy after the pre-discharge visit. Therapy could be a shock or antitachycardia pacing. The registry defines an inappropriate therapy as ventricular tachycardia or ventricular fibrillation therapy delivered for a supraventricular tachycardia. The endpoint timeframe starts at the pre-discharge visit and continues through a minimum of 12 months of follow-up, until study closure.

This outcome is used to assess whether the device’s rhythm classification and resulting therapy were appropriate for the observed episode. The record says that all events for which such therapy was delivered and a stored electrogram existed were reviewed by an independent adjudication committee. That review addressed both the appropriateness of the device’s rhythm classification and the subsequent therapy. The description does not state how events without a stored electrogram were handled beyond limiting this review to events with one.

The reported primary outcome is a participant count, not an episode count. A participant with more than one event is not described as contributing multiple times to this endpoint; the registry title specifies the number of patients with the outcome. The record does not provide the timing or number of repeat events, or a detailed rule for classifying participants with multiple episodes. The separate sponsor analysis uses a time-to-event method, but the registry’s brief description does not give enough detail to reconstruct its event-time and censoring rules.

7. Results Posted in the Registry

• Medtronic Family: 19.1% (187/977) versus 25.0% (246/985) on control; risk difference -5.8 percentage points (95% CI -9.5 to -2.2), risk ratio 0.77 (0.65–0.91); unadjusted two-proportion z-test p = 0.002.

8. Statistical Interpretation

9. Statistical Methods Explained

General: Statistical methods summarize how observed outcomes differ between groups and how uncertain an estimate is. The method must match the type of outcome and the information recorded. A participant count with an event can be summarized as a proportion or as a difference between group proportions. A time-to-event analysis additionally uses the timing of events and the period during which participants are observed. The registry reports both a recalculated comparison based on participant counts and a sponsor analysis described as regression and Cox.

The unadjusted recalculation compares the posted event counts and group sizes without adjustment for other variables. The risk difference is stated in the direction Medtronic Family minus VITALITY 2, and the estimate is -0.058. A risk difference expresses the difference between two proportions on the proportion scale. A value below zero in this direction means the observed proportion was lower in the Medtronic Family group. The interval from -0.095 to -0.022 describes a range of values compatible with the recalculation’s uncertainty procedure. Its confidence level is not reported in the registry record. The associated unadjusted p-value is 0.002.

General: A confidence interval describes uncertainty around an estimate under the assumptions of the method used. It is not a guarantee that the true effect lies in the interval, and its width reflects both the data and the calculation method. A p-value is a measure of how unusual the data would be under a specified null hypothesis and model assumptions. It is not the probability that the null hypothesis is true, and it does not indicate the probability that an individual participant will experience the endpoint.

The recalculation also reports a risk ratio of 0.766, with bounds of 0.648 and 0.907, and an odds ratio of 0.711, with bounds of 0.574 and 0.882. A risk ratio compares group proportions as a ratio; an odds ratio compares odds. These measures use different scales, so their numerical values are not read in the same way as a risk difference. The confidence level for these recalculated bounds is not reported in the registry record. They are unadjusted summaries based on the posted group counts, not substitutes for the sponsor’s separate model-based result.

The sponsor analysis is described as regression and Cox and reports a hazard ratio of 1.34, with a 95% confidence interval from 1.11 to 1.62 and p = 0.003. General: A hazard ratio compares event rates over time among participants still under observation and event-free, as represented by a time-to-event model. It is not the same measure as a ratio of endpoint proportions. The model can use differences in event timing and follow-up, but its interpretation depends on the contrast coding, event definition, censoring, and model specification. These details are not reported in the registry record. The hazard ratio’s contrast orientation is also not stated, so the value should not be used to infer which group had the higher event rate without that information.

General: Over-dispersion matters when data contain more variability than a model assumes. It can lead a model to understate uncertainty if that extra variability is ignored. For a participant-level binary outcome, clustering or repeated events may also call for methods that account for dependence. The registry does not report whether repeated episodes were analyzed, whether any over-dispersion assessment was performed, or whether clustering was relevant to the sponsor model. The participant-count recalculation treats the posted group counts as the inputs and does not incorporate event-level information.

The reported analysis method does not reveal all implementation choices. The registry does not report the covariates included in the regression, the specific Cox model form, any checks of model assumptions, or the approach to censoring and incomplete follow-up. It also does not state whether the primary analysis followed intention-to-treat, per-protocol, or another analysis population. These omissions mean the sponsor’s model cannot be independently reconstructed from the reported summary alone.

The trial has one sponsor-reported analysis entry for this primary outcome, but that does not establish whether the study used interim analyses, additional unreported analyses, or a particular multiplicity adjustment. Such information is not reported in the registry record. The registry lists three secondary outcomes in addition to the primary outcome. When several outcomes are tested, the interpretation of individual p-values can depend on whether and how multiplicity is handled; no such approach is reported for this trial.

General: Randomization is intended to support fair comparison of assigned groups by limiting systematic differences at allocation. It does not ensure that every group characteristic is exactly balanced, nor does the word randomized supply details of allocation concealment or implementation. The record identifies the study as randomized but does not give those procedural details. Statistical results should consequently be read in light of the posted design description and the limits of the analysis information, rather than assuming unreported methods.

10. Confidence Intervals and Precision

The recalculated risk difference is -0.058, with an interval from -0.095 to -0.022. The interval endpoints are both below zero, which is consistent with the direction of the point estimate under the stated subtraction order, Medtronic Family minus VITALITY 2. The confidence level for this recalculated interval is not reported in the registry record, so it should not be labeled as a particular confidence level.

The sponsor-reported hazard ratio is 1.34, with a 95% confidence interval from 1.11 to 1.62. This interval is above 1, the null value for a hazard ratio, but the registry does not state the contrast orientation. Its direction therefore cannot be translated into a group-specific description from the reported value alone. The time-to-event estimate and the risk-difference estimate also concern different summaries and may differ because of their methods and information used.

General: Precision concerns the uncertainty around an estimate, not whether an outcome is important or whether a result applies beyond the participants studied. A wider interval allows a broader range of compatible values; a narrower interval indicates more precision under the method’s assumptions. Confidence intervals do not account automatically for limitations such as missing data, model misspecification, or unreported analysis choices.

The recalculated interval is based on posted counts, whereas the sponsor interval comes from the reported regression and Cox analysis. The registry does not report enough detail to verify all assumptions behind the sponsor interval, and it does not give a confidence level for the recalculated risk-difference bounds. Precision should therefore be considered separately for each analysis rather than treating their intervals as directly comparable.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm for 80% power and participants per arm for 90% power. They are not total events. The assumptions listed for the planning illustration are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. The trial’s original sample-size assumptions and justification are not reported in the registry record.

For planning for 100% of the observed effect, the figures are 792 participants per arm for 80% power and 1,060 participants per arm for 90% power. For planning for 75% of the observed effect, they are 1,442 participants per arm for 80% power and 1,929 participants per arm for 90% power. For planning for 50% of the observed effect, they are 3,317 participants per arm for 80% power and 4,440 participants per arm for 90% power.

In plain terms, 80% power describes a planning target for detecting the specified effect under the stated assumptions; 90% power uses a higher target for detecting that effect. Smaller effects require more participants under these assumptions, as illustrated by the progressively larger figures for the smaller fractions of the observed effect. These figures are planning illustrations based on the observed effect, not observed power and not evidence about the trial’s original design.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.250; treatment proportion p₁ = 0.191; average p̄ = 0.221.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5864 = 1.1493.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5849 = 0.4923.
4. n = (1.1493 + 0.4923)² / (-0.0583)² = 791.6, rounded up to 792 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
p0 <- 0.249746192893401                          # control proportion
p1 <- 0.191402251791198                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(148954)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 792 (80% power), 1,060 (90% power)
 75% of observed effect: n per arm = 1,442 (80% power), 1,929 (90% power)
 50% of observed effect: n per arm = 3,317 (80% power), 4,440 (90% power)
power.prop.test: 791.6 
Simulated power at n = 792 per arm: 0.795 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Analyses Reported by the Sponsor

The sponsor-reported analysis uses regression and Cox methods and gives a hazard ratio of 1.34, a 95% confidence interval from 1.11 to 1.62, and p = 0.003. The recalculation uses the posted participant counts and group sizes to estimate an unadjusted risk difference of -0.058, with an interval from -0.095 to -0.022 and p = 0.002. The registry reports no discrepancy between the two analyses.

The estimates are not identical measures. The recalculation compares endpoint proportions using the posted summary counts. The Cox analysis is a time-to-event model and can use the timing of events and follow-up. The registry does not report the sponsor model’s covariates, censoring rules, or contrast orientation. In particular, it does not clarify which group is in the numerator of the hazard ratio. The positive hazard ratio should therefore not be read as contradicting the negative risk difference without first knowing the contrast coding and recognizing the difference in estimands.

The sponsor’s result is the reported model-based analysis, while the recalculation is a simple, unadjusted comparison of posted summaries. They answer related but distinct statistical questions. The available registry entries do not permit full reproduction of the sponsor analysis or a direct numerical reconciliation of the two estimates.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome and three secondary outcomes. The secondary outcomes concern time to first inappropriate shock, positive predictive value of ventricular tachycardia or fibrillation discrimination algorithms, and time to first inappropriate therapy following inappropriate episode classification. The record does not report a multiplicity adjustment, a hierarchy among outcomes, or a prespecified strategy for interpreting results across these analyses. Without those details, the reported p-values should be understood as results for their stated analyses, not as evidence that family-wise testing across outcomes was controlled.

The record does not report how missing outcome data were handled, how participants lost to follow-up were treated, or whether any imputation was used. The primary timeframe specifies a minimum of 12 months of follow-up until study closure, but no distribution of follow-up duration, censoring information, or missingness summary is reported. The handling of episodes without a stored electrogram is not described beyond stating that all events with delivered therapy and a stored electrogram were reviewed by the independent adjudication committee.

The registry does not identify the analysis population as intention-to-treat, per-protocol, or another defined group. It also does not describe exclusions after randomization or crossovers between assigned groups. The posted counts are 985 for VITALITY 2 and 977 for Medtronic Family, but the record does not explain the relationship between those denominators and the enrolled population or the analysis population used in the sponsor model.

These omissions affect how completely readers can assess risk of bias and reproduce the analysis. A randomized design is informative, but interpretation still depends on how outcomes, follow-up, exclusions, and incomplete records were handled. Details of interim analyses, if any, and the full statistical analysis plan are not reported in the registry record.

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

The posted primary outcome counts show 246 participants with inappropriate therapy among 985 in the VITALITY 2 group and 187 among 977 in the Medtronic Family group. The unadjusted risk difference, defined as Medtronic Family minus VITALITY 2, is -0.058. The recalculated interval runs from -0.095 to -0.022, and the unadjusted p-value is 0.002. These statistics describe the recorded comparison under the recalculation’s assumptions; they do not establish the consequences for an individual participant.

The endpoint concerns whether a shock or antitachycardia pacing was delivered for a supraventricular tachycardia, with event review by an independent adjudication committee when a stored electrogram was available. It is a specific device-related classification and therapy outcome. It does not, by itself, describe the severity of each event, all device performance, or every possible clinical outcome. The registry also lists secondary outcomes, but their numerical results are not reported in the record.

The sponsor’s time-to-event analysis reports a hazard ratio of 1.34, a 95% confidence interval from 1.11 to 1.62, and p = 0.003. Because the registry does not state the hazard-ratio contrast orientation or the model details, this estimate cannot be translated into a definite group-direction statement from the posted information alone. It should be kept distinct from the unadjusted comparison of participant proportions.

The results do not establish that a device is preferable for a particular person, nor do they provide medical advice. They describe outcomes in the studied randomized comparison. Eligibility criteria, detailed participant characteristics, exact device models within the selected Medtronic family, and full follow-up distributions are not reported in the registry record. Those limits matter when considering how far the findings can be generalized.

16. Why This Trial Matters Statistically

Statistically, RIGHT illustrates why outcome definition and analysis scale matter. The primary endpoint counts participants with an inappropriate therapy after the pre-discharge visit, while the sponsor analysis is described as a Cox time-to-event analysis. A proportion-based risk difference and a hazard ratio summarize different features of the data. They cannot be compared as if they were the same estimand, and the missing contrast orientation for the hazard ratio makes its group direction particularly important to clarify.

The record also demonstrates the distinction between a sponsor-reported analysis and an unadjusted recalculation from posted summary counts. The recalculation is transparent in its inputs and subtraction direction, while the sponsor model may use event timing and follow-up. Yet the model’s covariates, censoring details, and other implementation choices are not reported, limiting independent reproduction. Statistical interpretation is strongest when the endpoint definition, estimand, population, and model are all sufficiently described.

Finally, the study’s randomized parallel-group design supplies a comparative framework, but the registry record leaves important design and analysis details unresolved. The original sample-size justification, multiplicity plan, missing-data handling, and analysis population are not reported. The planning illustration based on the observed effect is useful as a sensitivity-oriented planning exercise, but it is not the trial’s design justification or observed power. These distinctions help readers assess what the posted numbers can support without extending the claims beyond the registry record.

17. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The registry record does not report detailed eligibility criteria, participant characteristics, the randomization procedure, allocation concealment, or the specific Medtronic models selected. These gaps make it difficult to assess how participants were selected, how assignment was implemented, and how closely the enrolled groups represent other populations or device configurations.

Follow-up is described as a minimum of 12 months until study closure, but the record does not give exact participant follow-up times, censoring rules, or loss-to-follow-up information. It also does not describe missing-data handling, analysis population, post-randomization exclusions, or crossover handling. Since the sponsor analysis uses a Cox method, the absence of event-time and censoring details limits interpretation and independent reproduction of that analysis.

The primary endpoint depends on adjudication of delivered therapy for episodes with a stored electrogram. The record does not explain how episodes without a stored electrogram were classified or handled in the endpoint analysis, or how multiple events in a participant were treated beyond defining the outcome as a number of patients. The listed secondary outcome results are not reported in the record, limiting assessment of other device-performance measures.

The registry does not report the original sample-size justification, a full statistical analysis plan, multiplicity handling, or interim-analysis details. The risk-difference interval’s confidence level is not reported, and the hazard-ratio contrast orientation and model specification are not stated. These limitations do not erase the posted counts, but they restrict how completely the analyses can be checked and interpreted.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: RIGHT: Rhythm ID Going Head-to-Head Trial — NCT00148954.
• Registry record last updated 2012-01-12; status last verified 2012-01.
• Results first posted 2011-12-26.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

21. Record Summary

RIGHT is a completed, randomized, prospective, parallel-group Phase 4 study with no masking, sponsored by Boston Scientific Corporation. The registry lists an enrollment of 1962, a start of 2005-07, and primary completion in 2009-03. It compared the VITALITY 2 ICD with a selected Medtronic family ICD.

The primary outcome was the number of participants with inappropriate ventricular tachycardia or ventricular fibrillation therapy after the pre-discharge visit. The posted counts are 246 of 985 for VITALITY 2 and 187 of 977 for Medtronic Family. The unadjusted recalculated risk difference is -0.058, with an interval from -0.095 to -0.022 and p = 0.002. The sponsor-reported regression and Cox analysis gives a hazard ratio of 1.34, a 95% confidence interval from 1.11 to 1.62, and p = 0.003.

The registry lists three secondary outcomes. Details on the original sample-size rationale, multiplicity, missing-data handling, analysis population, and important model specifications are not reported in the registry record.