Cirrhosis Medical Home: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Cirrhosis Medical Home (NCT04581369), a randomized na study. The primary outcome is Enrollment Rate.

2. Clinical Question

3. Trial Design

The Cirrhosis Medical Home study is listed as a randomized, triple-masked, parallel-group trial. Its phase is recorded as not applicable. The registry lists Indiana University as the sponsor, a start date of 2020-09-17, a primary completion date of 2023-05-31, and a status of completed. The record lists enrollment as 44. The relationship between that enrollment figure and the outcome denominators is not reported in the registry record.

The main patient comparison is between Direct Intervention and Standard of Care. The direct-intervention description says a care coordinator would review the hospital discharge plan, seek physician approval to co-manage care, and arrange a visit after discharge. The standard-of-care description says the coordinator would identify the primary care and/or hepatology provider and help ensure follow-up appointments at discharge. The descriptions available in the record are incomplete, so the full intervention protocols and the extent of their delivery are not reported in the registry record.

Caregivers are described separately: they were enrolled and completed assessments at baseline, 3 months and 6 months. This is distinct from the patient comparison. The record does not explain the randomization sequence, allocation concealment, which people were masked, or whether masking was maintained. It also does not report the recruitment setting beyond the hospital-discharge context in the intervention descriptions, nor does it give detailed inclusion and exclusion criteria.

The primary endpoint is an enrollment-process measure, while the posted secondary outcomes include acute health care utilization, quality of life, depression symptoms and physical performance. Results are not posted for every listed outcome in the information available for this analysis. The record lists 23 outcome measures and 20 posted secondary outcomes; the analyses reported field contains no analyses. Specific analysis populations and the handling of participants who did not complete follow-up are 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.

Before assignment: The protocol allowed for up to 40 caregivers to enroll in this trial. We enrolled 4 caregivers. The protocol called for 40 participants with liver disease to be enrolled and we enrolled 40. Total enrollment is 44.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Participants were screened prior to being approached for enrollment. Only after informed consent was obtained were participants randomized to a group. The numbers reported are in the aggregate for those with liver disease only and not for a particular group. Data for caregivers were not tracked.

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 Enrollment Rate, measured over Time of Enrollment.

The primary endpoint is titled Enrollment Rate and is measured at the time of enrollment. The description says the proportion of screened patients eligible, approached and enrolled would be calculated. It characterizes this as an internal assessment of department-specific metrics, not an assessment of participant health or response to treatment. Such a measure can describe how a recruitment and enrollment process is functioning. It does not, by itself, measure symptom change, quality of life, health care use or clinical benefit.

The posted outcome values are counts of participants, with 20 reported in each labeled group and denominators of 67 in each. The endpoint population description, however, says that the numbers are aggregate for people with liver disease and not for a particular group. It also says caregivers were not tracked for this measure. The record does not explain how those aggregate data relate to the group-labeled results. This limits the interpretation of the primary comparison: the numerical estimate can be described as posted, but its connection to the endpoint definition is unclear.

Enrollment measures can be useful when evaluating the feasibility of identifying and recruiting people into a study or service model. Their meaning depends on the population counted at each stage, including who was screened, eligible, approached and enrolled. The registry does not provide separate counts for each of those stages, nor does it report a detailed definition of eligibility. As a result, the posted results do not allow the reader to evaluate each step of the enrollment pathway independently.

7. Results Posted in the Registry

• Direct Intervention: 29.9% (20/67) versus 29.9% (20/67) on control; risk difference 0.0 percentage points (95% CI -15.5 to 15.5), risk ratio 1.00 (0.60–1.68); unadjusted two-proportion z-test p = 1.000.

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.

Acute Health Care Utilization

• 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:
  • Direct Intervention: 85.0% (17/20) versus 90.0% (18/20) on control; risk difference -5.0 percentage points (95% CI -25.4 to 15.4), risk ratio 0.94 (0.75–1.19); unadjusted two-proportion z-test p = 0.633.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Direct Intervention and the control. The interval gives the range of effects that remain compatible with the data.

Health Related Quality of Life: Medical Outcome Study Short Form (SF-36)

• 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 errors.
• Result:
  • Direct Intervention: mean 56.00 versus 58.00 on control; difference -2.00 (95% CI -3.94 to -0.06), standardized effect d = -0.64; z-test p = 0.043.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Direct Intervention than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Depression Symptoms

• 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:
  • Direct Intervention: mean 11.00 versus 14.00 on control; difference -3.00 (95% CI -3.05 to -2.95), standardized effect d = -35.81; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Direct Intervention than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists secondary outcomes spanning acute health care utilization, health-related quality of life, depression symptoms and physical performance. The posted information includes results for utilization and selected score outcomes, but it does not provide a complete account of all listed secondary outcomes in the information available for this analysis. The posted outcome summaries differ in type and timing: some concern participant counts, while others are scores measured at enrollment. Results from these different measures should not be treated as interchangeable evidence about one common effect.

Across the available secondary results, the estimates do not form a single, straightforward pattern that can be read as confirmation of the primary enrollment result. The primary endpoint concerns a recruitment process, whereas the secondary measures concern patient experience or health care use. A similar or different direction across those domains would not, by itself, validate the enrollment comparison. The registry does not report a prespecified hierarchy linking the primary and secondary outcomes or an overall interpretation that integrates them.

In general, secondary outcomes can help describe a trial's broader findings, but each additional comparison creates more opportunities for a result to appear notable by chance. An unadjusted p-value evaluates a comparison without correcting for the number of outcomes or comparisons. The registry does not report a multiplicity adjustment or a plan specifying which secondary outcomes should carry the most weight. Therefore, individual unadjusted secondary results are exploratory signals, not independent confirmation of a treatment effect.

The record also lacks reported analyses for the outcomes as a set. It does not document how repeated measures were handled, whether baseline values were used in models, or how missing outcome data affected the results. Those details matter particularly when outcomes are collected at different times or use different scales. The secondary evidence should be read as descriptive and provisional, and it should not be used to resolve the uncertainty in the primary enrollment endpoint.

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

• Acute Health Care Utilization
• Health Related Quality of Life: Medical Outcome Study Short Form (SF-36)
• Health Related Quality of Life: Medical Outcome Study Short Form (SF-36)
• Health Related Quality of Life: Medical Outcome Study Short Form (SF-36)
• Depression Symptoms
• Depression Symptoms
• Depression Symptoms
• Physical Performance

9. Statistical Interpretation

10. Statistical Methods Explained

The primary comparison is expressed as a risk difference. In general, a risk difference subtracts the event proportion in one group from the event proportion in another. A value of zero corresponds to equal proportions; positive and negative values indicate the direction of the contrast according to the stated group order. For this endpoint, the posted estimate is 0.0. The registry also posts a confidence interval and an unadjusted p-value. The precise statistical test or model used for the sponsor's analysis is not reported in the registry record.

The posted primary values are counts, not means or scores. The outcome is labeled as a count of participants, and the result gives group denominators as well as counts. In general, binary outcomes can be summarized as the number of participants meeting an event definition and the number assessed. A proportion is formed from those quantities, and a group contrast can then be expressed as a risk difference, risk ratio or odds ratio. The registry posts some of these comparison measures, but the risk difference is the primary contrast. Because the endpoint description says the data are aggregate rather than group-specific, the meaning of the group denominators remains uncertain.

The posted unadjusted p-value is a measure of how compatible the observed data are with a specified null hypothesis under the assumptions of the statistical test. In general, a p-value is not the probability that the null hypothesis is true, and it does not measure the size or practical importance of an effect. It is also not a substitute for a confidence interval. The record does not report a prespecified significance threshold or identify the test used for the primary comparison.

Several secondary outcomes are continuous scores. For a continuous outcome, a mean difference compares the group averages on the outcome's scale. The registry reports a mean difference for the posted quality-of-life and depression measures, along with confidence intervals and unadjusted p-values. Those summaries are not adjusted estimates according to the information available. The record does not report a model that accounts for baseline scores, repeated measurements, or other covariates.

The posted quality-of-life outcome is described as a mean with standard error. In general, a standard error describes uncertainty in an estimated mean, rather than the spread of individual participant scores. A standard deviation, by contrast, describes variation among individual observations. Those measures are not interchangeable. The registry's depression outcome is described with a standard deviation, while the comparison information includes very small dispersion values and a standardized effect estimate. This combination yields an unusually large standardized estimate and an extremely narrow interval. The registry does not explain how the scale and dispersion values were derived. That pattern merits caution rather than a claim that the result is precisely established.

The record includes planning illustrations based on observed effects. These are not the trial's original design calculations and do not represent observed power. The stated illustration assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and a target effect set to a stated fraction of the observed effect. In general, such planning calculations ask how many participants per arm a future study might need under those assumptions. Their estimates depend strongly on the chosen effect size and on whether the observed effect is a reasonable planning target. A small study can produce an unstable observed effect, so planning directly from it can be misleading.

The depression planning illustration reports participants per arm for 80% and 90% power as 1 for each displayed fraction of the observed effect. These values arise alongside the unusual dispersion information. They should not be read as a reliable recommendation for a future study or as evidence that the current study had adequate power. The record does not report the original sample-size justification, the anticipated effect used for the study design, or any interim analyses.

In general, over-dispersion matters when the observed variation is greater than a statistical model assumes. If that extra variation is ignored, standard errors can be too small and confidence intervals too narrow, making evidence appear more precise than it is. The record does not report a dispersion model for these outcomes, and the endpoint types differ, so no single over-dispersion adjustment can be inferred. More broadly, the statistical analysis plan, missing-data procedures, and prespecified analysis populations are not reported in the registry record. These omissions constrain how far the posted summary statistics can be interpreted.

11. Confidence Intervals and Precision

The primary risk-difference estimate is 0.0, with a 95% confidence interval from -0.155 to 0.155. In general, a confidence interval describes a range of values compatible with the observed data under the method's assumptions. It is not a guarantee that the true value lies in the interval, and it does not assign probabilities to individual values after the data have been observed. The interval includes zero and also allows effects on either side of zero.

The estimate is therefore centered on no difference, but its precision is limited: the data remain compatible with a range of possible group contrasts. The registry does not report a threshold for an enrollment difference that would matter operationally, so it is not possible to classify the entire interval as unimportant or important. The interval should be considered alongside the uncertainty about whether the group-labeled values correspond to the aggregate endpoint definition.

Precision also depends on the information available for the endpoint and the validity of the analysis. The record reports 20 participants in each labeled group and denominators of 67 in each, but separately describes the primary data as aggregate and not group-specific. It lists enrollment as 44, without explaining the relationship between that figure and the outcome denominators. These inconsistencies limit confidence in what population the interval represents.

In general, a narrow confidence interval indicates greater statistical precision than a wide interval, but it cannot correct for a poorly defined endpoint, missing observations, or an inappropriate analysis. The registry does not report the method used to construct the primary interval, the handling of missing data, or an analysis population. The displayed interval is informative as a summary of the posted comparison, but those unreported details constrain its interpretation.

12. Multiplicity, Missing Data and Analysis Populations

The registry lists 23 outcome measures and 20 posted secondary outcomes. Multiple outcomes raise a multiplicity question: when many statistical comparisons are made, the chance of at least one apparently unusual result can increase. In general, a prespecified testing hierarchy or an adjustment for multiple comparisons can help control that issue. The registry does not report a multiplicity strategy, a hierarchy among outcomes, or which outcomes were intended to be confirmatory. The posted secondary p-values are unadjusted, so they should be interpreted cautiously and should not be treated as a collection of independent confirmations.

The record lists no reported analyses. It does not provide a statistical analysis plan or say whether any plan was finalized before outcome data were examined. The original sample-size justification, interim analyses, and stopping rules are not reported in the registry record. The planning illustrations based on observed effects do not fill this gap: they are labeled as planning calculations rather than the study's own design assumptions.

Missing-data handling is also not described. The registry does not report how participants with incomplete assessments were treated, whether outcome data were missing, or whether any imputation or sensitivity analyses were used. The outcome denominators and the study enrollment figure are not reconciled. For the primary endpoint, the description states that results are aggregate for people with liver disease and not specific to a group, while the posted results carry group labels. The record does not explain the discrepancy.

Analysis populations are not specified. In general, a trial may report results for everyone randomized, everyone who received an intervention, or a subset with complete data; these populations answer different questions. The registry does not identify which population underlies the posted comparisons or describe deviations from assigned groups. Randomization is listed, but sequence generation, concealment, and masking details are not reported. Without these details, it is difficult to assess the protections against bias or to determine precisely which participants the estimates represent.

13. 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 5% reporting threshold.

The adverse-event information lists zero participants affected by serious events and zero affected by other events in each of the three listed groups. It separately reports deaths: 7 in Direct Intervention, 6 in Standard of Care and 0 in the Caregiver group. The corresponding numbers described as at risk are 20, 20 and 4. These are the registry's safety figures; the record does not report event timing, causes of death, or whether events were considered related to an intervention.

These figures should be read as counts, not as proof that an intervention caused or prevented an event. The caregiver group is distinct from the patient treatment comparison, and its smaller at-risk group makes direct comparisons with the patient groups inappropriate. The registry does not clarify the relationship between these safety denominators and the enrollment figure or outcome denominators elsewhere in the record.

The serious-event terms list is empty. That means no serious-event terms are listed in the record; it does not provide additional detail about event definitions or ascertainment. The available information does not support a comparative safety conclusion, particularly without timing, attribution, follow-up, and analysis details.

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

The primary result is a posted comparison of enrollment counts between the Direct Intervention and Standard of Care labels. Its risk-difference estimate is centered on zero, and its confidence interval includes zero as well as differences in either direction. This describes the observed summary and its statistical uncertainty. It does not establish equivalence, demonstrate that the care approaches are identical, or determine whether either approach changes health outcomes.

The endpoint itself is about the enrollment process, not the clinical course of cirrhosis. Even a clearly estimated enrollment difference would speak most directly to recruitment or departmental processes. The registry's stated aim is to evaluate a collaborative care model for people with cirrhosis, but the primary endpoint does not measure care coordination, symptoms, quality of life, or health care utilization. Those topics appear among secondary outcomes, which require separate interpretation.

Several limitations make the primary estimate difficult to generalize. The endpoint description says the data are aggregate and not specific to a group, while the result is posted under group labels. The study enrollment figure and the outcome denominators are not reconciled. The registry does not report the analysis population, missing-data approach, randomization details, or statistical plan. These are not minor technicalities: they affect how confidently the comparison can be attributed to the randomized groups and what population it represents.

The secondary outcomes do not resolve those uncertainties. They cover different constructs and include unadjusted comparisons, with no reported multiplicity plan. The available results cannot be taken as a definitive account of benefit or harm. Similarly, the adverse-event counts do not establish that an intervention caused or prevented deaths or other events; attribution and timing are not reported.

In general, a registry result is most informative when the endpoint definition, denominator, analysis population and statistical method align clearly. Here, the posted estimate can be described, but its interpretation is constrained by unresolved inconsistencies and missing analysis details. It should be regarded as a limited statistical summary rather than a final conclusion about the clinical value of the Cirrhosis Medical Home.

15. Why This Trial Matters Statistically

This trial is statistically notable because its primary endpoint is an enrollment-process measure, while its stated clinical context concerns coordinated care for people with cirrhosis. That distinction matters: recruitment feasibility and patient outcomes answer different questions. A study can report information about enrollment without establishing whether a care model changes health, quality of life or use of services.

The record also illustrates why denominators and endpoint definitions are central to interpretation. The primary result is labeled by randomized group, but the endpoint description says the figures are aggregate and not group-specific. The listed study enrollment and outcome denominators are also not reconciled. When those elements do not align clearly, even a simple comparison can be difficult to interpret as a randomized treatment contrast.

The confidence interval adds useful context beyond the point estimate and p-value. It communicates that the result is compatible with no difference while retaining a range of possible differences. The registry does not identify an operational threshold that would make an enrollment difference meaningful, so the interval cannot be translated into a judgment about practical importance.

Finally, the secondary outcomes and planning illustrations show why analytic context matters. Unadjusted comparisons across multiple endpoints need cautious interpretation, and calculations based on observed effects are not substitutes for a trial's original sample-size justification. The unusual dispersion information for the depression outcome further illustrates how summary statistics can affect derived estimates and planning calculations. This record is a useful case for separating what a posted statistic directly says from what it cannot establish.

16. 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 available registry record. First, the primary endpoint description and its posted results do not align transparently: the description says the data are aggregate for people with liver disease and not for a particular group, while the results are labeled by intervention group. The record does not explain how the group comparison was constructed. It also lists enrollment as 44, while the primary results list denominators of 67 in each group; the relationship among these figures is not reported.

Second, the endpoint is described as a proportion of screened patients who were eligible, approached and enrolled, but the posted result gives participant counts without separate counts for each stage. The record does not report how eligibility was defined, how many people were screened or approached, or whether those steps were recorded consistently across groups. Caregiver data were not tracked for the primary endpoint, according to its population description.

Third, important design and analysis details are unavailable. The registry does not report the randomization sequence, concealment, masking roles, statistical analysis plan, analysis population, handling of missing data, or original sample-size justification. It lists no reported analyses. The relationship between the reported outcome denominators and the enrollment field is therefore unresolved.

Finally, the secondary outcomes include different types of measures and timeframes, and the record does not report a multiplicity plan. The depression summary includes very small dispersion values and a derived standardized estimate that is unusually large; the record does not explain the scale or calculation. These issues limit confidence in interpreting that summary and its planning illustration. The available information does not support a complete assessment of intervention fidelity, follow-up completeness, or safety attribution.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: Cirrhosis Medical Home — NCT04581369.
• Registry record last updated 2024-07-17; status last verified 2024-06.
• Results first posted 2024-07-17.
• 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.

20. Record Summary

The Cirrhosis Medical Home record describes a randomized, triple-masked, parallel-group study sponsored by Indiana University, with status completed. Its primary endpoint is Enrollment Rate, defined as a process measure at enrollment. The posted comparison has a risk difference of 0.0 and a confidence interval from -0.155 to 0.155. The record lists 23 outcome measures, 20 posted secondary outcomes, and no reported analyses.

The primary endpoint description says its results are aggregate rather than group-specific, although the posted values are labeled by group. The record lists enrollment as 44 and gives outcome denominators of 67 in each primary comparison group, without explaining their relationship. The analysis plan, missing-data procedures and analysis populations are not reported in the registry record. These qualifications limit interpretation of the numerical results and prevent a clear conclusion about the randomized group contrast.