INVSENSOR00027 Clinical Performance Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for INVSENSOR00027 Clinical Performance Study (NCT03650192), a na na study. The primary outcome is Sensitivity of INVSENSOR00027's Posture Change Detection.

2. Clinical Question

In statistical terms, the primary question concerns detection sensitivity against the observer notes used as the reference. It is not a comparison of outcomes between randomized treatment groups, and the registry record does not describe a test of whether the sensor changes a clinical outcome. The planned evaluation also included respiratory-rate detection as a secondary outcome; the brief summary additionally names heart rate and position and posture detection as study interests. Results for these measures are not reported in the registry record.

3. Trial Design

The registry record describes the INVSENSOR00027 Clinical Performance Study as a completed, single-group clinical performance study of a device. The listed condition is healthy, the intervention is the INVSENSOR00027 investigational sensor, and the registry lists enrollment as 40. The study began on 2018-08-15, had a primary completion date of 2018-09-18, and is marked completed. The phase and allocation are listed as NA, and masking is listed as none.

Subjects were enrolled into a test group and received the investigational sensor. The primary endpoint description says sensor position-detection output was compared with observer notes at each turn. This reference comparison is part of endpoint measurement; it does not create a concurrent randomized control arm. The record itself cautions that this is not a randomized comparison and that the arms are not a like-for-like control comparison.

The stated study purpose is to assess sensor performance for detection of subjects’ position and posture in bed, along with heart rate and respiratory rate. The primary outcome is sensitivity of posture-change detection, with a timeframe of 1-5 hours. Respiratory Rate Detection is listed among the secondary outcomes. The record lists 4 outcome measures, but does not report their individual results in the information available for interpretation.

The sponsor is Masimo Corporation. The registry record does not report additional protocol details such as the setting, subject-level eligibility criteria, sensor placement procedures, or the process for training or blinding observers. It also does not report a control group, randomization procedure, or masking of outcome assessment. These omissions limit how fully the measurement process and potential sources of bias can be assessed from the registry record alone.

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 Sensitivity of INVSENSOR00027's Posture Change Detection, measured over 1-5 hours.

The primary endpoint is titled “Sensitivity of INVSENSOR00027's Posture Change Detection.” It measures the proportion of observer-noted posture changes that the sensor correctly detects. The endpoint description classifies a correctly detected position change as a true positive and a missed detection as a missed detection. Sensitivity is defined as true positives divided by the sum of true positives and missed detections, and is expressed as a percent.

This measure is useful for describing how often the sensor detects changes that are present according to the chosen reference. In general, sensitivity focuses on missed detections among reference-positive events. It does not, by itself, describe false alarms, agreement across all observations, or how well the sensor distinguishes among different positions. Those questions require other measures and definitions, which are not reported for this primary endpoint in the registry record.

The reference is the observer’s notes at each turn of the subject, and the stated timeframe is 1-5 hours. The record does not report how observer notes were resolved if they disagreed with sensor output, how many posture changes were observed, or whether all subjects contributed comparable observation periods. Most importantly, the observed sensitivity value and any uncertainty interval are not reported in the registry record. The endpoint definition therefore explains what the study intended to measure, but does not establish the sensor’s observed performance.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The central statistical measure is sensitivity. For the primary endpoint, the registry defines a true positive as a posture change correctly detected by INVSENSOR00027 and a missed detection as a posture change that was not detected. Sensitivity is the number of true positives divided by the number of true positives plus missed detections, expressed as a percent. This definition treats the observer’s notes at each turn as the reference for deciding whether a change occurred.

What does sensitivity describe?

In general, sensitivity describes the proportion of reference-positive events that a measurement method identifies. It is conditional on events being present according to the reference. It does not count reference-negative observations in its denominator, so it does not answer how often the sensor reports a change when the observer does not. Other performance measures can address different aspects of detection, but the registry record does not define those as the primary endpoint.

The distinction between a subject and an event is important for this endpoint. Enrollment is listed as 40, while the endpoint is defined at each turn and is based on posture changes. The number of enrolled subjects is not the same as the number of posture changes assessed. The registry record does not report the event count or the distribution of events across subjects, so the amount of information contributing to the sensitivity estimate cannot be assessed.

Why can repeated observations matter?

As a general statistical consideration, repeated measurements from the same subject may be related rather than independent. If a subject contributes multiple posture changes, those observations may share characteristics, such as the subject’s movement pattern or the conditions of measurement. Treating every event as independent when events are correlated can make uncertainty appear smaller than it is. Appropriate analysis may account for clustering or repeated measurements, but the registry record does not report an analysis method or explain how repeated turns were handled. This is a general issue to consider, not a claim that a particular method was used or that the study’s data had a particular correlation structure.

In general, a confidence interval communicates the precision of an estimate by giving a range of values compatible with the data and the stated method. Its width depends on factors including the amount of relevant information and the analysis assumptions. For this endpoint, the count of posture changes and the handling of repeated observations would be relevant to evaluating precision. No sensitivity estimate or confidence interval is reported in the registry record, so neither the observed level nor its precision can be described.

What does the record say about analyses?

The registry lists 0 analyses. It does not report a statistical analysis plan, a model for the primary endpoint, an approach to missing observations, or an adjustment for repeated measurements. It also does not report whether the analysis would use event-level or subject-level summaries. These are not interchangeable choices: an event-level summary weights observations according to the events recorded, while a subject-level summary can give subjects a more direct role in the analysis. Without the analysis details and results, it is not possible to know which approach was used.

The registry’s sample-size assumptions describe planning illustrations based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The stated effect to detect is a fraction of the observed effect; the assumptions also distinguish total events for time-to-event illustrations from participants per arm for other illustrations. These are planning conventions, not evidence about the study’s observed power or its original design. They do not match the registry’s single-group design as a randomized two-arm comparison. The record does not report the observed effect needed to interpret such illustrations, nor does it report that these assumptions formed the study’s protocol or sample-size justification.

More generally, over-dispersion occurs when variation in observed counts exceeds what a chosen model assumes. When present, it can make standard errors or confidence intervals based on a simpler model too optimistic. Whether over-dispersion is relevant depends on the data structure and analysis; the registry record does not report a count model or information that would establish whether it occurred. This is a general methodological consideration, not a result of this study.

Finally, statistical significance and practical measurement performance are different questions. A significance test addresses compatibility with a specified null hypothesis under assumptions; it does not by itself describe the size or precision of a performance estimate. The registry record reports no test statistic, p-value, estimate, or interval for the primary endpoint. No inferential conclusion can therefore be drawn from the endpoint definition alone.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 4 outcome measures and identifies Respiratory Rate Detection as a secondary outcome. The study summary describes assessment of position and posture in bed, heart rate, and respiratory rate. The primary outcome is sensitivity of posture-change detection. However, the record does not report results for these outcomes or explain which measures were analyzed, how their results were calculated, or whether any were designated for confirmatory inference beyond the listed primary endpoint.

When a study evaluates multiple outcomes or makes multiple statistical comparisons, the chance of at least one apparently notable result can increase. In general, a multiplicity strategy may specify which comparisons are primary, whether adjustment is needed, and how findings should be interpreted. The registry record does not report a multiplicity procedure, a hierarchy among all outcome measures, or a statistical analysis plan. No conclusion about adjustment or its absence in the actual analysis can be made from the registry information.

Missing-data handling is also not reported. The record does not describe whether observations could be missing, how missing sensor readings or observer notes would be treated, or how incomplete observation periods would enter the endpoint calculation. Because sensitivity depends on identifying reference-positive changes and sensor detections, the handling of incomplete or unclassifiable observations could affect both the estimate and its interpretation. No particular missing-data method should be assumed.

The analysis population is not described. Although the registry lists enrollment as 40 and the study as a single-group test, it does not say whether all enrolled subjects contributed to each outcome, whether any records were excluded, or how exclusions would be handled. The record lists 0 analyses, so it does not provide population counts linked to completed outcome analyses. These reporting gaps prevent assessment of the analysis denominator, missingness, and the relationship between enrollment and the results.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The registry reports adverse-event information for the INVSENSOR00027 Test Group. It lists 40 subjects at risk in the serious adverse-event category and 0 affected; for other adverse events, it also lists 40 at risk and 0 affected. The reported death count is 0. No serious adverse-event terms are listed.

These are registry counts, not a complete account of how safety was monitored. The record does not report detailed event definitions, collection methods, follow-up procedures, or whether events were assessed for relationship to the device. A zero in the affected field means no affected subjects were reported in that category in this registry entry; it does not establish that the possibility of an event is absent. The adverse-event information should be read as a description of what the record reports for this group, with the limits of the reporting detail kept in view.

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

The study is relevant as a registered assessment of an investigational sensor intended to detect position and posture in bed and to measure heart rate and respiratory rate. Its primary endpoint has a clear stated purpose: quantify the sensitivity of posture-change detection against observer notes. The registry also identifies respiratory-rate detection as a secondary outcome. Those details indicate what the study set out to assess.

They do not establish the observed performance. The registry record does not report the primary sensitivity estimate, its numerator or denominator, or an uncertainty interval. Results for the other named sensor-performance measures are also not reported. Without those results, readers cannot determine the frequency of missed posture changes, the precision of any estimate, or how performance varied across subjects or observation conditions.

The single-group design also defines what can be inferred. Observer notes are the reference for the primary endpoint, but the study is not described as a randomized comparison with a control group. Therefore, the record does not provide a comparative estimate against another sensor or intervention. The endpoint is a detection measure, not a direct measure of a clinical outcome. No conclusion about clinical benefit or harm follows from the endpoint definition alone.

In general, sensor-performance estimates depend on the reference standard and the data collection process. If observer notes are incomplete or inconsistent, that may affect the classification of detections; the registry does not report enough detail to evaluate that possibility. In addition, sensitivity alone does not describe false detections, so it cannot fully characterize overall detection performance.

The appropriate interpretation is therefore bounded: the record describes a completed study in healthy subjects, its investigational sensor, and its planned primary measure, but it does not report the numerical outcome needed to judge observed sensitivity. The listed adverse-event counts are also limited to the information recorded and do not establish the absence of all safety risks.

13. Why This Trial Matters Statistically

This trial matters statistically because it illustrates the difference between a clearly defined endpoint and a reported result. The registry gives a specific sensitivity definition based on true positives and missed detections, and identifies observer notes at each turn as the reference. That makes the intended measurement understandable. Yet, without the observed estimate, the event counts, or an uncertainty interval, the endpoint cannot be used to quantify performance.

It also highlights the importance of matching the analysis to the unit of observation. Enrollment is recorded at the subject level, while posture changes are assessed at turns. In general, multiple observations from the same subject may be correlated, and the analysis should account for the data structure when appropriate. The registry record does not report whether this issue was addressed, so the statistical handling cannot be evaluated.

The record further shows why a performance measure should be interpreted in context. Sensitivity describes detection among events identified by the reference; it does not describe false detections or all aspects of agreement. A complete evaluation may require additional measures and clear reporting of the reference method, observation process, and denominators. Those details and results are not reported in the registry record.

Finally, planning calculations should not be mistaken for observed evidence or original design justification. The described planning assumptions involve equal allocation between two arms, whereas this study is listed as single-group and not a randomized comparison. Such planning illustrations cannot substitute for a reported analysis of the study’s data. The key statistical lesson is that design, endpoint definition, analysis method, and result are separate pieces of evidence; the registry record supplies some of the first two, but not the latter results.

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 registry record does not report the observed sensitivity for posture-change detection, the count of true positives, the count of missed detections, or an uncertainty interval. It therefore does not permit a quantitative assessment of the primary endpoint or its precision. Results for the other outcomes are not reported either, despite the listed outcome measures and the study summary’s stated performance interests.

The endpoint uses observer notes as its reference, but the record does not describe observer training, agreement procedures, adjudication, or whether observers were masked to sensor output. It also does not specify how posture changes were defined operationally or how sensor and observer timestamps were aligned. These are unreported details, not evidence that a particular procedure was or was not used.

The record does not provide event counts, subject-level contributions, or the analysis method for repeated turns. It therefore does not show how dependence among observations from the same subject was handled, whether any observations were excluded, or how missing observations would affect the endpoint. The analysis population and missing-data approach are not reported in the registry record.

The study is single-group and unmasked, with no like-for-like control comparison reported. Its performance findings, if reported elsewhere, would need interpretation within that design and against the observer-note reference. The registry information alone does not allow assessment of generalizability beyond the described healthy-subject population or the stated 1-5 hours timeframe. The record also does not report detailed safety-monitoring methods. These limitations reflect the information available in the registry record and should not be treated as evidence about unreported study procedures.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: INVSENSOR00027 Clinical Performance Study — NCT03650192.
• Registry record last updated 2021-01-29; status last verified 2021-01.
• Results first posted 2021-01-29.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

NCT03650192 is the completed INVSENSOR00027 Clinical Performance Study, sponsored by Masimo Corporation. The registry lists enrollment as 40, the condition as healthy, allocation as NA, and masking as none. The study dates are 2018-08-15 for start and 2018-09-18 for primary completion.

The single-group study evaluated an investigational sensor. Its primary outcome was sensitivity of posture-change detection, comparing sensor output with observer notes at each turn during a timeframe of 1-5 hours. Respiratory Rate Detection is listed as a secondary outcome. The registry lists 4 outcome measures and 0 analyses.

The primary result and other outcome results are not reported in the registry record. Adverse-event entries list 0 affected subjects for serious and other adverse events and 0 deaths in the test group. The record does not provide further outcome-analysis or safety-monitoring detail.