Search Results

The BcSs-PICNI-2000 Sensor is intended for the monitoring of variation in intracranial pressure in patients with suspected alteration of intracranial pressure (ICP) or change in brain compliance, by providing ICP waveforms for interpretation.

The BcSs-PICNI-2000 Sensor ("the Braincare Sensor") is a non-invasive device intended for the monitoring of variation in intracranial pressure, including patients with suspected alteration of intracranial pressure (ICP) or change in brain compliance. It consists of a sensor, headband, and adapter cable. The sensor contains four strain gauges situated on a metal bar that detects variations in skull deformation through tension and compression of the metal bar in response to changes in intracranial pressure. The proposed device does not measure absolute intracranial pressure values, but produces waveform morphology and its trend reflecting changes in ICP. The BcSs-PICNI-2000 Sensor and waveform output do not substitute ICP monitoring methods when measurement of the absolute value of ICP is required to make a clinical decision.

The sensor component is supported on a plastic headband worn by the patient, such that the sensor is in contact with the scalp and is perpendicularly positioned in the temporoparietal transition, 2 inches (5-6 cm) above the entrance of the external auditory canal on the coronal plane. Slight pressure is applied so that the sensor pin maintains contact with the scalp throughout the monitoring session. The sensor continuously records and transfers acquired signals through an adapter cable to a compatible multi-parameter monitor that has piezoresistive pressure transducer sensitivities of 5uV/Vex/mmHg or greater and automatic amplitude window adjustment capability. The multi-parameter monitor's inherent software interprets the signal received from the BcSs-PICNI-2000 Sensor and displays a waveform that allows for assessment of suspected intracranial hypertension or changes in brain compliance based on the characteristic Percussion (P1), Tidal (P2), and Dicrotic (P3) peaks of the ICP waveform morphology.

The BcSs-PICNI-2000 Sensor is not intended to be a standalone diagnostic tool. The waveform output does not replace a comprehensive clinical evaluation, but only provides an element for preliminary assessment. The clinician is responsible for determining the additional clinical information that may be required to make a diagnosis.

Here's an analysis of the acceptance criteria and the studies performed for the BcSs-PICNI-2000 Sensor, based on the provided document:

Acceptance Criteria and Device Performance

The document doesn't explicitly state a table of "acceptance criteria" with specific thresholds for performance metrics. Instead, it details various tests and their "Pass" or "Results" that demonstrate the device meets expected performance and safety standards, largely by showing substantial equivalence or demonstrating proper functioning. The "Results" column in the table below is derived from the Table 3 Summary of Non-Clinical Performance Data and the Study Outcomes sections of the clinical studies.

Study Details

2. Sample sizes and Data Provenance

• Animal Studies:
  • Rat Model: 7 rats. Data provenance not explicitly stated (e.g., country of origin, retrospective/prospective), but implied to be prospective due to controlled experimental setup.
  • Swine Model: 1 swine animal model. Data provenance not explicitly stated, implied to be prospective.
• Clinical Studies:
  • HIV-associated Cryptococcal Meningitis: 1 critically ill adult patient. Data provenance not explicitly stated (e.g., country of origin, retrospective/prospective), but implied to be prospective as it's an "early study" evaluating the device.
  • Traumatic Brain Injury: 7 adult patients. Data provenance not explicitly stated (e.g., country of origin, retrospective/prospective), but implied to be prospective for validation. Total acquisition time of 608 hours (337 hours analyzed).

3. Number of experts used to establish the ground truth for the test set and their qualifications

• The document implies that the "predicate device" (Codman® Microsensor Basic Kit) served as the primary reference or "ground truth" for comparison in the animal and TBI clinical studies, as it represents the "standard of care" for invasive ICP monitoring.
• For the HIV-associated Cryptococcal Meningitis study, the "patient's clinical status" and response to treatment, likely determined by treating clinicians, served as the ground truth against which the non-invasive ICP waveforms were assessed.
• No specific number of experts or their qualifications for establishing ground truth are explicitly stated beyond the use of the invasive predicate device and general clinical judgment.

4. Adjudication method

• There is no explicit mention of an adjudication method (like 2+1, 3+1, or none) for establishing ground truth in any of the studies. The comparisons are largely quantitative against the invasive predicate or qualitative against clinical observations.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No MRMC comparative effectiveness study was done. The device does not involve AI assistance for human readers; it provides waveform data for direct clinician interpretation, similar to the predicate device. The focus is on the device's ability to provide comparable waveform information.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done

• Given that the device's output is "waveform morphology and its trend reflecting changes in ICP" for "qualitative evaluation by the clinician" and "does not substitute ICP monitoring methods when measurement of the absolute value of ICP is required," the device is inherently not a standalone diagnostic tool. Its performance is validated in providing signals consistent with clinical status, with the expectation that a human clinician will interpret these waveforms in conjunction with other clinical parameters. Therefore, a standalone algorithm-only performance study, as typically understood for diagnostic AI, was not performed or applicable in this context.

7. The type of ground truth used

• Animal Studies & Traumatic Brain Injury Clinical Study: Invasive intracranial pressure (iICP) measurements obtained from the predicate device (Codman® Microsensor Basic Kit) served as the de facto ground truth against which the non-invasive ICP (nICP) signals from the BcSs-PICNI-2000 Sensor were compared. This is a form of reference standard comparison.
• HIV-associated Cryptococcal Meningitis Clinical Study: The "patient's clinical status" and response to "standard treatment," likely assessed by treating physicians and based on neurological symptoms and other clinical parameters, served as the ground truth. This can be categorized as a form of clinical outcome/expert consensus.

8. The sample size for the training set

• The document does not mention a training set or a machine learning component for the BcSs-PICNI-2000 Sensor itself. The device functions based on strain gauge sensors and mechanical principles, not through a learned algorithm or AI model that requires a discrete training set. The studies described are validation and performance testing, not model training.

9. How the ground truth for the training set was established

• As no training set is mentioned or implied for an AI/ML algorithm within the device, this question is not applicable.

Ask a specific question about this device