Search Results

The ClearStar pump can be used for adult and pediatric patients provided the patients can tolerate a feeding range within the pump operational specifications. Those specifications are:

• • The flow rate range is 1-300 ml/hr in I mL/hr increments
• • The flow rate accuracy is ± 10% or ± 0.5 mL/hr, whichever is greater
• • The occlusion pressure limit is 26-30 psi.
    If these specifications are not appropriate for a given patient, the ClearStar pump should not be used.

The ClearStar pump raises no new questions of safety or effectiveness above those currently associated with enteral feeding pumps. The operator's manual for the ClearStar pump provides warnings regarding volume sensitive patients similar to those found in the operating manuals of the Companion and Quantum enteral feeding pumps. The pump's automatic clog clearing function has been designed to ensure that the nominal pressure exerted on a clog is in the 26 to 30 psi range. Additionally, to ensure that the patient is not underfed, the pump, if unsuccessful in clearing a clog before ten (10) minutes have elapsed, will alarm occlusion. Finally, the pump can only be in the clog clearing mode a maximum of twenty (20) minutes or ten times in any consecutive four (4) hour period. If twenty (20) minutes or ten times are exceeded, the pump will alarm occlusion.

The provided text describes the "ClearStar Enteral Nutrition Pump" and its safety and effectiveness. It outlines performance specifications and how these were designed and verified, but it does not contain information about a study proving the device meets acceptance criteria in the context of a medical AI device submission.

Therefore, I cannot fulfill your request for details on a study proving a device meets acceptance criteria, sample sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance, ground truth types, or training set information.

The document is a 510(k) summary for a medical device (an enteral feeding pump), which is a premarket notification to the FDA to demonstrate that the device is substantially equivalent to a legally marketed predicate device. This process primarily focuses on comparing the new device's indications for use and technological characteristics to an existing device, and verifying that it raises no new questions of safety or effectiveness. It does not typically involve the type of clinical performance studies and ground truth establishment methodologies that are relevant for AI/ML-based medical devices as outlined in your prompt's questions.

Here's a breakdown of what can be extracted regarding acceptance criteria and performance based on the provided text, but it's important to understand this is not in the context of an AI/ML study:

ClearStar Enteral Nutrition Pump: Acceptance Criteria and Reported Performance

The document describes the design and expected performance characteristics of the ClearStar pump, particularly concerning its clog-clearing function and pressure limits.

1. Table of Acceptance Criteria and Reported Device Performance

Information Not Available / Applicable from the Provided Text:

• 2. Sample sized used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective): Not applicable for this type of device submission. Performance is based on engineering design and bench testing, not clinical data in the sense of a test set for an algorithm.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for an enteral pump's mechanical function is based on physical measurements and engineering specifications, not expert interpretation of data.
• 4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable.
• 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: Not applicable, as this is not an AI device.
• 6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not applicable, as this is not an AI device.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the pump's mechanical characteristics, the "ground truth" would be established via engineering measurements, calibration, and pressure/flow testing against established physical standards and design specifications.
• 8. The sample size for the training set: Not applicable, as this is not an AI device.
• 9. How the ground truth for the training set was established: Not applicable, as this is not an AI device.

In summary, the provided document describes the design features and performance specifications of a mechanical medical device (an enteral pump) as part of a 510(k) submission, emphasizing its substantial equivalence to predicate devices and inherent safety features. It does not provide the type of study data, methodologies, or "ground truth" definitions relevant to an AI/ML device assessment.

Ask a specific question about this device