This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Efficacy of Ostom-i Alert System at Decreasing Dehydration Related Complications (NCT02694757), a na na study. The primary outcome is Change in Readmission Rate.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT02694757 |
| Phase | NA |
| Condition | Ileostomy - Stoma |
| Allocation | Not applicable (single group) |
| Design model | Single Group |
| Masking | None (open label) |
| Enrollment | 3 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Massachusetts General Hospital |
| Results posted | Yes |
2. Clinical Question
Population
Patients with new ileostomies. The condition is listed as Ileostomy - Stoma. The registry does not report further eligibility details or describe the characteristics of the enrolled participants.
Intervention
The Ostom-i device was to be worn over the ostomy bag underneath the participant’s clothing. Output was to be monitored daily through the Ostom-i application.
Comparator
No comparison group is listed. This is a single-group study, and the registry does not identify a control intervention or usual-care arm.
Primary question
The study aimed to evaluate whether using the Ostom-i device would decrease readmission rates during the first 30 days after surgery. The registry lists change in readmission rate as the primary outcome, but says no outcomes were measured because the study was terminated.
This is a question about a device-supported monitoring approach and readmission, not a randomized comparison of the device with another strategy. The study description says daily output monitoring was intended, while its stated purpose concerns readmission in the postoperative period. The registry does not report how device use was expected to affect readmission, what threshold or definition would count as a readmission, or how the rate was to be calculated.
These distinctions matter when interpreting a clinical question. A monitoring procedure can be described without establishing that monitoring changed patient outcomes. To assess an effect on readmission, a study needs measured readmission data and an appropriate basis for comparison. Neither an outcome measurement nor a completed analysis is recorded. The record therefore establishes the study’s aim and planned device use, but not an answer to its efficacy question.
3. Trial Design
The registry describes a pilot study of the Ostom-i device in patients with new ileostomies. Its design is listed as single group, with no allocation method and no masking. The study has no listed control arm, so it is not a like-for-like comparison between participants receiving the device and participants receiving another approach. The registry identifies the intervention as a device and names Massachusetts General Hospital as the sponsor. The phase is listed as NA.
The planned device use involved wearing it over the ostomy bag underneath clothing, with output monitored daily through the application. The study’s stated purpose was to evaluate readmission rates during the first 30 days after surgery. Its primary outcome is titled change in readmission rate, with a timeframe of 30 days post-operation. However, the record explicitly states that no outcomes were measured because of termination and that no analysis was completed.
Enrollment is recorded as 3. The registry lists the study as terminated, with a start date of 2017-08-01 and a primary completion date of 2019-03-04. It does not give a reason for termination, so the reason should not be inferred. Nor does the record explain whether recruitment was complete, how long participants used the device, or what follow-up procedures were carried out.
In a single-group study, observations from participants using an intervention can describe what happened in that group, but they do not by themselves separate an intervention effect from other explanations. Here, the limitation is more fundamental: the registry reports no measured primary outcome and no analysis. The design and enrollment information describe the study structure, not evidence that the device changed readmission.
4. Participant Flow and Accounting
The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.
Overall Study
| Stage | Ostom-i Device |
|---|---|
| STARTED | 3 |
| COMPLETED | 0 |
| NOT COMPLETED | 3 |
Reasons for not completing this period:
| Reason | Ostom-i Device |
|---|---|
| Lack of Efficacy | 3 |
Analysis population for the primary outcome, as defined in the registry: No analysis was completed due to termination of 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.
Population: Because none of the study participant completed the study, there are no participant data to anaylze
| Characteristic | Unit | Ostom-i Device |
|---|---|---|
| Participants analysed | 3 | |
| Age, Categorical: <=18 years | Participants | 0 |
| Age, Categorical: Between 18 and 65 years | Participants | 3 |
| Age, Categorical: >=65 years | Participants | 0 |
| Age, Continuous | years | 39 (23 to 55) |
| Sex: Female, Male: Female | Participants | 3 |
| Sex: Female, Male: Male | Participants | 0 |
| Race (NIH/OMB): American Indian or Alaska Native | Participants | 0 |
| Race (NIH/OMB): Asian | Participants | 0 |
| Race (NIH/OMB): Native Hawaiian or Other Pacific Islander | Participants | 0 |
| Race (NIH/OMB): Black or African American | Participants | 0 |
| Race (NIH/OMB): White | Participants | 3 |
| Race (NIH/OMB): More than one race | Participants | 0 |
| Race (NIH/OMB): Unknown or Not Reported | Participants | 0 |
6. Primary Endpoint
The registry lists the primary outcome as Change in Readmission Rate, measured over 30 days post-operation.
| Element | Registry entry |
|---|---|
| Result type | N/A |
| Measure of spread | not applicable |
| Unit | not stated |
| Endpoint classification | not reduced to a single comparison |
The primary outcome is titled “Change in Readmission Rate” and has a timeframe of 30 days post-operation. Readmission is a clinically relevant endpoint for a study whose stated purpose is to evaluate readmissions after surgery. In general, a rate or proportion of readmission can describe how often the outcome occurs in a defined group over a specified observation period. To interpret such a measure, the outcome definition, denominator, follow-up rules, and method of analysis need to be clear.
Those operational details are not reported in the registry record. It does not clarify what counted as a readmission, whether the outcome included any readmission or a particular type, or how a “change” was to be determined. It also provides no observed readmission result. The primary outcome description says no outcomes were measured due to termination of the study, and the population description says no analysis was completed.
Thus, the endpoint identifies what the investigators intended to assess and the stated assessment timeframe, but it does not supply an estimate of readmission or its change. A named endpoint is not itself evidence of an outcome. Without measured data and a completed analysis, the registry cannot show whether readmission was more frequent, less frequent, or unchanged in the study group.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The main interpretive point is that the registry records an intended efficacy question but no efficacy result. The study aimed to evaluate readmission rates after surgery among patients with new ileostomies using the Ostom-i device. Yet the primary outcome description states that no outcomes were measured because the study was terminated, and the population description states that no analysis was completed. There is therefore no posted estimate of a change in readmission rate to interpret.
Enrollment is recorded as 3, but that figure does not substitute for outcome information. It does not tell readers whether any participant was readmitted, how follow-up proceeded, or what the outcome would have been under another approach. The registry does not report the reason for termination or provide a comparison group. Even if outcomes had been reported for the single group, a comparison with no control arm would not, by itself, isolate the effect of the device from other influences.
The result cannot be described as evidence that the device reduced readmission, nor as evidence that it did not. An absent outcome estimate is not an estimate of no effect. The registry’s account is that outcome measurement and analysis did not occur, not that a completed analysis found no difference. This distinction prevents a null result from being confused with an unavailable result.
Precision also cannot be assessed for the primary outcome. A confidence interval ordinarily indicates the range of effects compatible with the observed data under a statistical model. Since no primary outcome was measured or analyzed, the record supplies no efficacy estimate or confidence interval. It is not possible to assess how precisely the study estimated a readmission effect, or whether any hypothetical effect would be compatible with a clinically important benefit or harm.
The listed safety entries are separate from the primary efficacy question. They record zero serious events, zero other events, and zero deaths among the listed group, with three at risk for each event category. These entries do not supply evidence about readmission, and they should not be treated as proof that the device is safe. The small enrollment and lack of reported outcome detail also limit what can be concluded from the safety entries.
Any planning illustration based on an observed effect needs an observed effect as its starting point. The registry says that no outcomes were measured and no analysis was completed, so it supplies no observed primary effect to interpret. Illustrative sample-size calculations, where presented, are planning exercises under stated assumptions; they are not observed power and do not turn missing study results into evidence of efficacy.
9. Statistical Methods Explained
What does a single-group design tell us?
In general, a single-group study records observations among participants who receive the same intervention. It can describe whether an outcome was observed in that group, provided that outcome data are collected and reported. Without a concurrent comparison group, however, it cannot directly show what would have happened to similar participants under another intervention or under usual care. Changes over time may reflect the intervention, but they may also reflect differences in participants, clinical care, follow-up, or other circumstances.
That general limitation applies to the design recorded. The study is listed as single group, allocation is NA, and no control arm is identified. More importantly, the registry says the primary outcome was not measured and no analysis was completed. Consequently, there are no study observations from which to describe the primary efficacy endpoint, let alone compare outcomes across strategies.
What does an outcome estimate represent?
In general, an outcome estimate is a numerical summary of observed data, defined for a particular outcome, population, and follow-up period. For a readmission endpoint, the interpretation depends on the exact definition of readmission and on who is included in the denominator. It also depends on whether all participants have comparable follow-up and how incomplete follow-up is handled. The registry names change in readmission rate and states a 30-day post-operation timeframe, but it does not report the detailed outcome definition or a numerical estimate.
A confidence interval is a general way of expressing statistical uncertainty around an estimate. It indicates which values are reasonably compatible with the observed data and the analysis assumptions. A narrower interval generally indicates greater precision, while a wider interval indicates more uncertainty. No efficacy estimate or confidence interval is reported for this trial, because no outcome was measured and no analysis was completed. It would be inappropriate to invent an interval or infer precision from the study’s enrollment entry.
Why does a comparison group matter?
In general, a comparison group helps distinguish outcomes associated with an intervention from outcomes that may have occurred without it. Random allocation, when used, can help balance participant characteristics across groups, though the quality of inference also depends on study conduct and analysis. This record does not describe a randomized comparison: allocation is listed as NA, the model is single group, and the registry identifies no control arm. The listed design therefore does not support a direct comparative treatment-effect estimate.
A before-and-after contrast can sometimes be used in a single group, but it requires defined measurements at both times and an analysis plan that addresses the limitations of such a contrast. The registry does not report that kind of analysis, baseline outcome data, or a completed endpoint assessment. It would be speculation to assume that a particular before-and-after method was planned.
How should the planning assumptions be read?
In general, sample-size calculations use assumptions about the target effect, variability, significance threshold, allocation, and statistical model. A planning calculation asks how much information a future study might need under those assumptions; it is not a result from the participants in a completed analysis. The registry’s planning description specifies a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a stated fraction of an observed effect. It also distinguishes between total events for time-to-event calculations and participants per arm for other calculations.
Those are planning assumptions, not a description of the actual single-group design. The record does not report an observed efficacy effect, and it says no outcome was measured or analyzed. Therefore, no calculated planning value can be interpreted as evidence about the device’s effect in this study. A sample-size illustration is not observed power; observed power is not a substitute for reporting an effect estimate and its uncertainty.
Why can event data be difficult to interpret?
In general, event counts carry limited information when few participants are observed, especially when the outcome is uncommon. Estimates based on sparse data can be unstable and uncertain. Methods also need to match the data structure: for example, repeated events, varying follow-up, and over-dispersion may require methods different from those for a simple binary outcome. Over-dispersion means that the observed variability exceeds what a statistical model assumes; ignoring it can make uncertainty appear too small.
These are general statistical considerations rather than methods reported for this study. The registry gives no event data for the primary readmission outcome and no statistical analysis plan or completed analysis. It is not possible to determine whether repeated events or over-dispersion were relevant, or whether any specific model was used. The appropriate reading is that those methodological details are not reported in the registry record, rather than that a particular method was applied.
10. Multiplicity, Missing Data and Analysis Populations
Multiplicity concerns arise when an analysis tests or estimates multiple outcomes, time points, subgroups, or other comparisons. In general, carrying out many statistical tests can increase the chance of a seemingly notable finding arising by chance. Researchers may address this through a prespecified primary outcome, adjustment procedures, or a clearly exploratory interpretation. The registry identifies change in readmission rate as the primary outcome, but it does not report a statistical plan describing how multiplicity would be handled. The record lists one outcome measure and no analyses, and states that no outcome was measured because the study was terminated.
Missing-data handling is also not reported in the registry record. Since no primary outcome measurement or analysis is recorded, there is no account of whether outcome data were missing, how missingness was assessed, or what approach would have been used. It would be inaccurate to assume either complete follow-up or a particular missing-data method. The record also does not describe an analysis population, such as an intention-to-treat or per-protocol population; instead, it states that no analysis was completed.
These omissions are distinct from a reported analysis that found no effect. There is no completed analysis to evaluate for multiplicity, missing-data assumptions, or analysis-population choices. The registry therefore does not allow readers to assess whether those methods were appropriate or how they might have influenced an estimated readmission effect.
11. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Ostom-i Device | 0 | 3 | 0.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Ostom-i Device | 0 of 3 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 0% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Ostom-i Device | 0 of 3 |
The registry lists an Ostom-i Device group with three participants at risk for serious events and three at risk for other events. It records zero serious events, zero other events, and zero deaths. These are the safety figures entered for the listed group; they are not the primary readmission outcome and do not describe an efficacy analysis.
In general, a count of zero observed events means no such events were recorded in the specified group and reporting category. It does not demonstrate that the underlying risk is zero. Limited enrollment and the absence of additional safety detail make it especially important not to interpret the entries as a comprehensive assessment of safety. The registry does not report further information about event definitions, follow-up completeness, or how adverse events were collected.
The study is listed as terminated, and no outcomes were measured according to the primary outcome description. The safety entries should therefore be read narrowly as registry-reported counts, not as proof that the device caused no harms or that it is safe. They also cannot be used to infer any effect on readmission.
12. What the Result Does, and Does Not, Mean
This record documents a pilot study intended to evaluate whether the Ostom-i device could decrease readmissions among patients with new ileostomies during the first 30 days after surgery. It describes a single-group design, the device’s intended use, enrollment, and registry status. It also lists safety event counts for the device group. These registry entries help explain what the study set out to examine and what was entered in the registry.
But the intended question is not answered by the posted results. The primary outcome is titled change in readmission rate, yet the registry says no outcomes were measured because the study was terminated. It also says no analysis was completed. Thus, there is no readmission estimate, no comparison of readmission outcomes, and no statistical uncertainty estimate to interpret. The record cannot establish a decrease, an increase, or no change in readmission.
The absence of a control group is an additional interpretive limitation. Even if the single group had outcome measurements, those observations alone would not provide a direct comparison with what might have happened under another strategy. The lack of reported outcome data means that this limitation is not merely a concern about causal attribution: the primary result itself is unavailable.
The safety counts are similarly limited. Zero recorded serious events, other events, and deaths in the listed group are counts, not proof of absence of risk. They do not answer the efficacy question and cannot support a broad safety conclusion. Enrollment and event reporting need to be read in the context of the terminated study and the missing outcome analysis.
The most defensible conclusion is therefore about the evidence record: the study’s question and intervention are described, but its primary outcome was not measured and analyzed according to the registry. No claim about the device’s effect on readmission follows from these data.
13. Why This Trial Matters Statistically
This study matters statistically because it illustrates the difference between a planned clinical question and an analyzable result. A registry can identify an intervention, a target population, a primary endpoint, and a follow-up period, yet still contain no evidence about the endpoint if the outcome was not measured. Here, the stated aim concerns readmission after surgery, but the record explicitly says no outcomes were measured and no analysis was completed.
It also highlights why design information is essential to interpretation. This is a single-group study with no listed control arm. The intended device use and the clinical question are clear at a broad level, but a single-group structure cannot directly establish what readmission would have been under an alternative approach. In this case, the missing outcome data mean that even a descriptive result for the device group is unavailable.
The record also demonstrates why zero event counts should be separated from conclusions about safety. The listed entries report no serious events, other events, or deaths, but these counts do not prove absence of risk. They should not be expanded into claims about safety, efficacy, or the study’s reason for termination.
Finally, statistical planning and statistical evidence serve different purposes. Planning assumptions can illustrate what a future study might require under specified conditions, but they cannot supply an effect estimate when the study reports no measured endpoint. Recognizing that distinction helps prevent a calculation or a named endpoint from being mistaken for a trial finding.
14. Limitations
- The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
- Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
The principal limitation is that the registry reports no measured primary outcome and no completed analysis. Consequently, there is no readmission result, effect estimate, or confidence interval. The registry does not explain why the study was terminated, so the reason cannot be linked to recruitment, feasibility, safety, or any other factor.
The design is single group, with no listed control arm and allocation recorded as NA. This limits comparative interpretation independently of the missing outcome data. The record also does not define the readmission outcome in detail, explain how the stated rate or its change would be calculated, or describe the handling of follow-up and missing observations. Those details are not reported in the registry record.
Enrollment is recorded as 3, but the registry gives no participant characteristics, account of actual device exposure, or description of follow-up completion. The safety entries are counts for the listed device group and do not provide detailed event definitions or collection procedures. The registry also does not report a statistical analysis plan, an analysis population, or a missing-data strategy.
These limitations prevent assessment of efficacy, precision, and many aspects of study conduct. They should not be recast as evidence of no effect or as evidence of an adverse effect. The record establishes that the study was terminated and that its primary outcome was not measured or analyzed; it does not establish why that happened or what a completed study would have found.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Efficacy of Ostom-i Alert System at Decreasing Dehydration Related Complications — NCT02694757.
- Registry record last updated 2020-03-19; status last verified 2020-03.
- Results first posted 2020-03-19.
- Data retrieved from ClinicalTrials.gov on 2026-11-09.
- Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
18. Record Summary
The registry describes a pilot study of the Ostom-i device in patients with new ileostomies, intended to evaluate readmission during the first 30 days after surgery. The device was to be worn over the ostomy bag, with output monitored daily through an application. The study is listed as single group, with no allocation method, no masking, enrollment of 3, and terminated status.
The primary outcome is titled change in readmission rate, with a timeframe of 30 days post-operation. The registry states that no outcomes were measured because of termination and that no analysis was completed. There is no control group or reported efficacy estimate. Safety entries list zero serious events, zero other events, and zero deaths in the device group. These counts do not establish a safety conclusion or answer the readmission question.