Improvement of Patient Satisfaction and Overall Outcomes Using HealthLoop: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Improvement of Patient Satisfaction and Overall Outcomes Using HealthLoop (NCT03481595), a randomized na study. The primary outcome is Percentage of Participants Reporting a Problem Across al PPE-15 Domains.

2. Clinical Question

3. Trial Design

The study is registered as a randomized, parallel-group trial with no masking. Group A received standard, routine medical care; Group B received the HealthLoop mobile application in addition to standard, routine medical care. The intervention description identifies the app as a device. Since the record states that masking was absent, it does not describe participants or care teams as blinded to assignment.

The registry lists enrollment as 294 and the study status as completed. The recorded start date is 2018-04-17, and the primary completion date is 2020-06-17. The sponsor is The Cleveland Clinic. The record lists the phase as not applicable. It does not report a separate trial site count, allocation ratio, sequence-generation method, allocation-concealment method, or detailed eligibility criteria.

The primary outcome was assessed 90 days after index surgery. It measured the mean percentage of participants reporting a problem across the PPE-15 domains. Secondary outcomes included patient satisfaction measured by a visual analog scale, length of hospital stay, discharge destination, readmission, emergency department visits, outpatient visits, telephone calls to the surgical team, and reoperation. The registry record also contains result data for patient satisfaction, length of stay, and discharge to home; results for the other listed secondary outcomes are not reported in the registry record.

The outcome-level participant counts are reported separately by group. For the primary outcome, the record gives 143.0 for Group A and 127.0 for Group B. Why those outcome counts differ from the enrollment figure, including whether this reflects exclusions, missing responses, or another analysis population, is not reported in the registry record. The analysis population and participant flow are also not reported in the registry 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 Percentage of Participants Reporting a Problem Across al PPE-15 Domains, measured over 90 days after index surgery.

The primary endpoint is the percentage of participants reporting a problem across the PPE-15 domains, measured 90 days after index surgery. The questionnaire has 15 items. Each response is categorized as a problem or a non-problem, and the endpoint is the percentage of respondents reporting a problem averaged across all PPE-15 domains.

This construction turns responses into a summary of reported problems across the patient experience domains included in the questionnaire. A lower group mean corresponds to a lower average percentage of respondents reporting a problem across those domains; it does not show whether every domain moved in the same direction. The registry record does not report domain-by-domain results, so the overall mean cannot identify which aspects of the experience contributed most to the group summaries.

A patient-reported experience endpoint is relevant to a study asking whether a communication app is associated with differences in patient experience and satisfaction. It captures reported problems rather than a direct clinical event such as readmission or reoperation. The endpoint is presented as a mean and standard deviation, with a mean difference between groups. These summaries describe the observed group results; they do not by themselves establish why any difference arose.

The endpoint is specified at a fixed follow-up of 90 days after surgery. The record does not report how questionnaire nonresponse was handled, how many participants completed the questionnaire, or whether the planned endpoint definition changed during the trial.

7. Results Posted in the Registry

• Group B: mean 9.50 versus 12.60 on control; difference -3.10 (95% CI -6.50 to 0.30), standardized effect d = -0.22; z-test p = 0.074.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Visual Analog Scale (VAS) for Patient Satisfaction

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Group B: mean 91.00 versus 91.00 on control; difference 0.00 (95% CI -3.73 to 3.73), standardized effect d = 0.00; z-test p = 1.000.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group B and the control. The interval gives the range of effects that remain compatible with the data.

Length of Hospital Stay

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Group B: mean 1.20 versus 1.40 on control; difference -0.20 (95% CI -0.39 to -0.01), standardized effect d = -0.25; z-test p = 0.040.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Group B than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Number of Participants Discharged to Home

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Group B: 92.9% (118/127) versus 90.9% (130/143) on control; risk difference 2.0 percentage points (95% CI -4.5 to 8.5), risk ratio 1.02 (0.95–1.10); unadjusted two-proportion z-test p = 0.548.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group B and the control. The interval gives the range of effects that remain compatible with the data.

The secondary endpoints broaden the outcome picture beyond the PPE-15 problem measure. They include patient satisfaction, hospital stay, discharge destination, readmission, emergency visits, outpatient visits, calls to the surgical team, and reoperation. The registry record reports result data for patient satisfaction, length of stay, and discharge to home. Results for the other listed endpoints are not reported in the registry record.

Across the posted secondary results, the group summaries do not all tell the same statistical story: the satisfaction means are equal, length of stay has a lower Group B mean, and discharge to home is common in both group summaries. These outcomes measure different aspects of care and are not interchangeable. In particular, an outcome concerning hospital use does not directly measure the patient-reported problems captured by the primary endpoint. The secondary findings therefore add context but do not resolve the uncertainty in the primary result.

Secondary comparisons are unadjusted. When several outcomes are considered, a small p-value can occur by chance among the collection even if no single outcome has a true effect. Without a reported multiplicity plan, the p-values for secondary outcomes carry less weight than a result from a clearly prespecified, appropriately controlled analysis. This is especially important where several outcomes have been listed but result details or analyses are absent.

The registry record reports no analysis details for the other listed secondary outcomes, including readmission, emergency department visits, outpatient visits, telephone calls, and reoperation. Their inclusion in the outcome list does not show that a difference was observed, and absence of posted results cannot be interpreted as evidence of no difference. Secondary outcomes are most informative when their estimates, uncertainty, analysis methods, and missing-data handling are all available.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Visual Analog Scale (VAS) for Patient Satisfaction
• Length of Hospital Stay
• Number of Participants Discharged to Home
• Number Participants Who Were Readmitted to the Hospital
• Number Participants Who Visited the Emergency Department
• Number Participants With 0, 1, 2, or 3+ Outpatient Visits
• Number of Participants Who Made 0, 1, 2, or 3+ Telephone Calls to the Surgical Team
• Number of Participants Who Had a Reoperation

9. Statistical Interpretation

10. Statistical Methods Explained

The trial is described as randomized and parallel-group, with standard care in Group A and the app added to standard care in Group B. Random allocation can support a fair comparison when assignment is implemented as planned and outcomes are analyzed appropriately. However, the registry record does not report the sequence-generation procedure, allocation concealment, baseline characteristics, or the statistical analysis plan. Those details therefore cannot be used to assess how the comparison was implemented or whether the analysis followed a prespecified plan.

What does a mean difference represent?

For a continuous outcome, a mean difference subtracts the control-group mean from the intervention-group mean. In the primary comparison, the registry reports the mean difference for Group B versus Group A as -3.1. A negative estimate means the Group B mean is lower on the endpoint scale. The difference is descriptive of the two group means; its interpretation also depends on the outcome definition, the uncertainty interval, and the analysis assumptions.

The standard deviation describes how much participant-level observations vary around a group mean. It is not the uncertainty in the mean itself. The registry reports standard deviations for the primary outcome and for the continuous secondary outcomes. Standard errors, when included in comparison details, describe uncertainty in estimated means under the analysis used to obtain them. The primary outcome-level standard deviations are 15.3 for Group A and 13.2 for Group B.

How should the confidence interval be read?

A confidence interval gives a range of effect estimates compatible with the observed data under the statistical procedure used. A narrower interval indicates greater precision than a wider interval, all else being equal. For a difference, zero represents no difference between group means. If an interval includes zero, the data do not exclude zero at the confidence level used. This does not prove that the true difference is zero; the interval can also include meaningful differences in either direction.

The primary comparison has an interval from -6.5 to 0.300. It includes zero, so the result does not rule out no difference. The interval also spans values on both sides of zero, which reflects uncertainty about the direction and size of the group difference. The registry record does not identify the confidence level or the method used to construct the interval, so those particulars are not reported in the registry record.

What does an unadjusted p-value tell us?

A p-value measures how unusual data at least as discrepant as the observed data would be under a specified null model and its assumptions. It is not the probability that the null hypothesis is true, nor does it quantify the probability that the result is due to chance. The primary unadjusted p-value is 0.074. It is best read alongside the estimated difference and interval, rather than as a standalone verdict. The record does not report a multiplicity adjustment or a detailed model for this analysis.

“Unadjusted” also matters when interpreting the secondary outcomes. When several outcomes are tested, the chance of obtaining at least one small p-value can increase. Adjusting for multiple testing is one way to address that issue, though the appropriate approach depends on the scientific questions and analysis plan. No such approach is reported in the registry record. The secondary p-values should therefore be regarded as exploratory evidence rather than as a collection of definitive tests.

Why can variability affect interpretation?

Greater variability among participants generally makes a group mean harder to estimate precisely unless the amount of information also increases. The reported standard deviations describe the observed spread, while the confidence interval reflects uncertainty about the estimated difference. These are related but not interchangeable. A clinical measure can have a modest group mean difference alongside substantial variation between individual participants.

For outcomes such as counts or rates, over-dispersion is a general statistical concern when observed variability exceeds what a basic probability model assumes. A model that ignores over-dispersion can understate uncertainty. The reported primary endpoint, however, is presented as a continuous mean with a standard deviation, and the registry record does not describe a model for its analysis. It would be inappropriate to assume that an over-dispersion adjustment was or was not used.

For a binary outcome such as discharge to home, a risk difference compares the proportions in the two groups. Its interval indicates the range of plausible differences under the method used. When the interval includes zero, a difference in either direction remains compatible with the data. Risk ratios and odds ratios are alternative ways to express binary comparisons, but the record’s listed estimates should not be treated as interchangeable: they use different scales and have different interpretations.

What do standardized effects and planning figures add?

A standardized mean difference expresses a mean contrast relative to a measure of variability. It can aid comparison across continuous outcomes that use different units, but it is less directly interpretable than a difference on the original outcome scale. The planning illustrations use the observed effect as their starting point and show participant requirements under stated assumptions. They are not evidence about the probability that this completed trial detected an effect.

The record does not report the trial’s original sample-size calculation, its assumed target effect, its intended power, or whether interim analyses were planned or conducted. The planning figures are separate illustrations, not a reconstruction of the trial’s design. They should be read as conditional examples that depend on their stated assumptions, not as a judgment of whether the trial was adequately designed.

11. Confidence Intervals and Precision

The primary estimate is a mean difference of -3.1, with a confidence interval from -6.5 to 0.300. The interval crosses zero, so the estimate is not precise enough to rule out no difference under the reported interval procedure. It also permits a difference favoring either group. Its width is a reminder that the point estimate alone should not be read as the known or exact effect.

Confidence intervals describe uncertainty in an estimated group contrast, not the range containing most individual participants’ outcomes. The standard deviations of 15.3 in Group A and 13.2 in Group B describe participant-level spread around the means. They answer a different question from the interval around the mean difference. Both pieces of information are useful: the group means describe average outcomes, while variability and interval width help show how much uncertainty surrounds the comparison.

Precision also depends on outcome completeness and analysis choices. The primary outcome counts are 143.0 in Group A and 127.0 in Group B, while overall enrollment is reported as 294. The reason for the difference between enrollment and the outcome-level counts is not reported in the registry record. Missing-response handling, the confidence-interval method, and the analysis population are not reported in the registry record either. These omissions limit how fully readers can assess the source of uncertainty.

The secondary intervals give differing levels of precision. The satisfaction interval extends from -3.726 to 3.726 and includes zero. The length-of-stay interval is below zero, while the discharge-to-home interval includes zero. These intervals concern distinct outcomes and should not be used to substitute for the primary interval. Their precision and interpretation depend on each outcome’s scale and analysis.

12. 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 sample-size figures are planning illustrations, not observed power. They are expressed as participants per arm for the continuous and binary outcomes in this record; the convention of total events applies to time-to-event outcomes, and no time-to-event planning figures are listed. The assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each row uses the stated fraction of the observed effect as the effect to detect.

The 80% power column describes the number of participants per arm that a hypothetical study would require, under those assumptions, to have an 80% chance of detecting the chosen effect if that effect were the true one. The 90% power column uses a higher target chance of detection and therefore calls for more participants per arm under the same assumptions. These are prospective planning quantities; they do not describe the chance that the completed trial detected its observed result.

For the primary endpoint, the illustration lists 337 participants per arm for 80% power and 451 for 90% power when planning for 100% of the observed effect. Planning for 75% of the observed effect lists 599 and 801 participants per arm, respectively; planning for 50% lists 1,346 and 1,802. Smaller effects are harder to distinguish from random variation, so the illustrations require more participants per arm as the effect to detect becomes smaller.

The figures depend on the planning assumptions and the observed effect used as their reference. They do not show what the trial originally intended to recruit or establish that the original design had a particular power. The original sample-size justification and design assumptions are not reported in the registry record. Read the table and curve as conditional illustrations, not as observed results or a retrospective score of the trial.

13. 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, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -3.100; pooled standard deviation σ = 14.351.
2. n = 2 × (1.96 + 0.842)² × 14.351² / -3.100² = 336.4, rounded up to 337 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
delta <- -3.1                      # observed difference in means
sigma <- 14.3510127574391                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^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 (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(3481595)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 337 (80% power), 451 (90% power)
 75% of observed effect: n per arm = 599 (80% power), 801 (90% power)
 50% of observed effect: n per arm = 1,346 (80% power), 1,802 (90% power)
power.t.test: 337.4 
Simulated power at n = 337 per arm: 0.799 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-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.

14. Multiplicity, Missing Data and Analysis Populations

The registry record lists one primary endpoint and multiple secondary outcomes, but it does not report how the statistical testing was organized across outcomes. No multiplicity adjustment or hierarchy for secondary hypotheses is reported in the registry record. If many outcomes are tested, the chance of at least one apparently notable result can rise even when the outcomes are not truly affected. This general issue is why secondary p-values without a stated testing plan should be interpreted cautiously.

The record gives the number of outcome measures and indicates no reported analyses in its analysis summary. It does not provide a detailed statistical analysis plan, identify which secondary outcomes were considered confirmatory, or describe whether any outcomes were selected or changed after data collection. Those details are not reported in the registry record. As a result, the status of the secondary comparisons as prespecified or exploratory cannot be established from the record.

Missing-data information is also limited. The primary endpoint counts are 143.0 in Group A and 127.0 in Group B, while enrollment is 294. The reasons these figures differ are not reported in the registry record. The record does not report the amount or pattern of missing primary questionnaire data, whether missingness was related to participant characteristics or outcomes, or how missing responses were handled. It also does not report whether the primary result used imputation, complete cases, or another method.

The analysis population is not reported in the registry record. It is therefore unclear from the record whether participants were analyzed according to randomized group, whether any participants were excluded after assignment, or how protocol deviations were handled. The absence of this information is not proof that a particular method was or was not used. It limits assessment of potential bias and makes it harder to judge whether the reported comparison preserves the advantages expected from randomization.

For the primary and secondary comparisons, the registry does not describe adjustment for baseline factors or the method used to calculate confidence intervals and p-values. Nor does it report interim analyses or stopping rules. These omissions prevent a full assessment of the inferential procedures. The posted estimates remain useful descriptions of the registered results, but conclusions about confirmatory testing and missing-data robustness cannot be drawn from the available record.

15. 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 2% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: manipulation under anesthesia (2.4%), hyperkalemia (1.6%), bradycardia (0.8%), urinary retention (0.8%), effusions (0.8%).

The safety record lists serious adverse events affecting 11 participants in Group A and 14 in Group B. Other, non-serious adverse events are listed for 12 participants in Group A and 10 in Group B. The record reports 0 deaths in Group A and 1 in Group B. These are group-specific counts; they do not establish that the app caused or prevented an event, and the registry record does not provide an adjusted safety comparison.

The listed serious-event terms include manipulation under anesthesia at 2.4%, hyperkalemia at 1.6%, bradycardia at 0.8%, urinary retention at 0.8%, effusions at 0.8%, and gastrointestinal bleed at 0.8%. The registry record does not provide enough detail in these summaries to determine the clinical course, timing, severity beyond the serious classification, or attribution of each event. The terms and percentages should be read as reported event summaries, not as evidence that an event was related to the intervention.

Safety counts can be influenced by follow-up completeness, event definitions, and ascertainment. Those details are not reported in the registry record. A difference in counts alone is not a causal comparison, particularly without event-level context and a prespecified analysis.

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

The posted results describe a randomized comparison of adding HealthLoop to routine postoperative care versus routine care alone. On the primary patient-experience outcome, the Group B mean is lower than the Group A mean, with a reported difference of -3.1. The confidence interval includes zero, so the data do not clearly distinguish that estimate from no group difference. The result should be described as uncertain rather than as proof that the groups differ or are identical.

The primary outcome is an average across PPE-15 domains. It does not establish that every domain improved or worsened, and the registry record does not report the domain-specific summaries. Nor does a group average describe the experience of every participant. Individual experiences may vary around the group means, as reflected by the standard deviations.

The secondary summaries address satisfaction, length of stay, and discharge to home, among other listed outcomes. Their pattern is mixed and their comparisons are unadjusted. They do not independently settle the primary question, and missing results for several listed outcomes should not be interpreted as either favorable or unfavorable findings. The serious adverse event summaries are also descriptive and do not establish a causal relationship with app use.

This record does not establish that the app is beneficial or ineffective. A failure to rule out no difference is not proof of equivalence, and a point estimate in one direction is not proof of a meaningful effect. The registry does not report a threshold for a clinically important difference, so the clinical importance of the primary estimate cannot be determined from this record alone.

The findings apply to the groups and outcomes represented in this trial record. Details needed to assess broader applicability—including eligibility criteria, the separate hip and knee surgery results, and the characteristics of participants—are not reported in the registry record. The record also does not provide enough methodological detail to fully assess missing data, analysis populations, or adjustment for multiple outcomes. These limits should shape any interpretation beyond the posted group summaries.

17. Why This Trial Matters Statistically

This trial illustrates why an estimate, its interval, and the analysis context belong together. The primary point estimate is below zero for Group B versus Group A, but the confidence interval includes zero. Focusing only on the direction of the estimate would overstate what the data establish; focusing only on whether a threshold was crossed would discard information about the estimated magnitude and uncertainty.

It also illustrates the distinction between a patient-reported experience measure and operational or clinical outcomes. A summary of reported problems across questionnaire domains, a satisfaction rating, length of stay, and discharge destination address different questions. Evidence on one cannot automatically stand in for evidence on another. A coherent interpretation considers the endpoint hierarchy and the outcomes’ separate meanings.

Randomization is an important design feature, but it does not remove the need to understand allocation, follow-up, missing outcomes, and analysis populations. Those details are not reported in the registry record. Without them, readers have limited ability to judge whether the comparison retained the benefits expected from random allocation or whether outcome availability could have affected the estimate.

The secondary outcomes also make multiplicity relevant. Several outcomes were listed, while no multiplicity strategy is reported and several result details are absent. Treating every secondary p-value as an independent confirmatory test would give an overly confident reading. The record is therefore a useful example of the difference between exploratory patterns and a prespecified inferential conclusion.

Finally, planning illustrations based on an observed effect are not a substitute for the original design calculation. They show how sample requirements change under stated assumptions and effect sizes, but they cannot recover the trial’s original target or determine retrospectively whether its design was adequate. Keeping planning, observed outcomes, and uncertainty distinct is central to sound clinical interpretation.

18. 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 trial-specific limitations follow from details absent in the registry record. The record does not report eligibility criteria, participant characteristics, or the number of participants undergoing hip versus knee replacement. The primary outcome combines both surgical populations, and there are no subgroup results by procedure in the posted data. Readers therefore cannot assess whether the overall estimate represents similar results across the two surgery types.

The primary endpoint is based on a 15-item patient experience questionnaire, but the record does not report questionnaire completion, item-level missingness, or the handling of incomplete questionnaires. The outcome-level group counts differ from the overall enrollment figure, and the reason is not reported. Without participant flow and missing-data methods, the potential effect of incomplete outcome data cannot be assessed.

The registry identifies a randomized design but does not report sequence generation, concealment, baseline balance, or analysis by randomized assignment. Masking is listed as none, which may matter for outcomes reported by patients or care teams. The record does not describe whether outcome assessors were masked or how awareness of assignment might have influenced questionnaire responses or event reporting.

Intervention adherence, app engagement, and the amount of clinical communication are not reported. The intervention was added to routine care, so the posted comparison is between care with app access and routine care, not a comparison of app use alone against no care. The record does not provide details on whether participants used the app as intended or whether usual communication differed across groups.

Finally, multiple secondary outcomes are listed, but no multiplicity plan is reported and result details are absent for several of them. The registry also does not report a statistical analysis plan or the original sample-size justification. These gaps constrain assessment of confirmatory inference, precision, and generalizability.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Improvement of Patient Satisfaction and Overall Outcomes Using HealthLoop — NCT03481595.
• Registry record last updated 2021-11-24; status last verified 2021-10.
• Results first posted 2021-11-24.
• 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.

22. Record Summary

NCT03481595 is a completed randomized, unmasked, parallel-group trial sponsored by The Cleveland Clinic. It compared standard, routine medical care with standard care plus the HealthLoop mobile application during the postoperative period for hip or knee replacement patients. The recorded enrollment was 294, with primary completion dated 2020-06-17.

The primary outcome was the mean percentage of participants reporting a problem across PPE-15 domains 90 days after index surgery. The posted Group B versus Group A mean difference is -3.1, with a confidence interval that includes zero and an unadjusted p-value of 0.074. Secondary results are available for satisfaction, length of stay, and discharge to home; other listed outcomes do not have result details in the registry record.

The record does not report the original sample-size justification, analysis population, missing-data methods, or multiplicity approach. The results are best read as group summaries and uncertain comparisons, with these omissions limiting assessment of the analyses.