Search Results

Sensometrics Software is intended for use by a qualified nurse or physician to display variables from existing legally marketed primary measuring devices used to monitor neurosurgical and neurological patients. The parameters displayed by the Sensometrics Software include intracranial pressure, arterial blood pressure, oxygen, core/cerebral temperature, and these are continuously trended in charts. The presentation of both measured parameters and the relationships between them is intended as an adjunct to the information provided by existing primary monitors. The Sensometrics® Software should not be used alone as the sole basis for decisions as to diagnosis or therapy.

Sensometrics® Software is a secondary display system that collects together on a single large color display screen the measured pressure variables relevant to the multimodality monitoring of the patient in a neurosurgical intensive care unit. It receives digital inputs from primary monitors used in the measurement of intracranial pressure, arterial blood pressure and cerebral temperature. The Sensometrics® Software displays the measured and derived variables in digital trace form and can store and display trends over periods of up to 240 hours.

Here's an analysis of the provided text regarding the Sensometrics® Software's acceptance criteria and the study that proves its performance:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly state numerical acceptance criteria for the Sensometrics® Software in terms of accuracy or precision. Instead, the "acceptance criteria" are implied by the objective of demonstrating equivalence to predicate devices and performing "according to specifications." The reported performance is a qualitative statement of equivalence.

2. Sample Size Used for the Test Set and Data Provenance:

The document mentions a "performance comparison test" where the Sensometrics® Software was compared with the Phillips and Integra devices. However, it does not specify the sample size used for this test set (e.g., number of patients, number of data points).

The data provenance is also not explicitly stated. It's not clear where this performance comparison test was conducted (country of origin) or if the data was collected retrospectively or prospectively.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:

The document does not mention the use of experts to establish ground truth for the test set. The comparison test seems to rely on the outputs of the predicate devices themselves as the reference for "equivalence."

4. Adjudication Method for the Test Set:

No adjudication method is described, as the ground truth appears to be established by the predicate devices rather than human expert consensus.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done:

No, an MRMC comparative effectiveness study was not done. The study described is a performance comparison between the software and primary measuring devices, not a study evaluating human reader performance with and without AI assistance. Therefore, no effect size of human readers improving with AI vs. without AI assistance is provided.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done:

Yes, a standalone performance evaluation was done in the sense that the "Sensometrics® Software" itself was compared directly to the predicate devices' outputs. The software's performance describes its ability to compute and display parameters in a way that is equivalent to existing primary monitors. The intended use emphasizes it's an adjunct and not for sole diagnosis, but the performance testing described is of the algorithm/software's output.

7. The Type of Ground Truth Used:

The ground truth used for the performance comparison test was the measurements/outputs from the legally marketed predicate devices (Phillips IntelliVue Mp40 and Integra MPM-1). The assumption is that these predicate devices are accurate and provide reliable measurements for Mean ICP, Mean ABP, systolic pressure output, diastolic pressure output, and cerebral temperature output.

8. The Sample Size for the Training Set:

The document does not specify a sample size for a training set. The software's development life cycle included various levels of testing (Module/Unit, Subsystem, Integration, V&V, Final Acceptance), but there is no mention of a separate training phase or dataset in the context of machine learning, which the Sensometrics® Software submission does not appear to be. It's a display system, not an AI/ML algorithm that requires a training set in the typical sense.

9. How the Ground Truth for the Training Set Was Established:

As there is no explicit mention of a training set in the context of typical machine learning models (which this device is not presented as), there is no information provided on how ground truth for a training set was established. The software's "specifications" and the outputs of the primary monitors serve as the reference points for its design and verification.

Ask a specific question about this device