Search Results

The Stöckert SS System is intended to be used during cardiopulmonary bypass for procedures lasting six (6) hours or less.

The S5 System is configurable to user needs with different system components. The main configurable and optional system components consist of: Console, System Panel, Pumps, Bubble detector, Level control, Temperature monitor, Pressure control, Cardioplegia Control, Electronic gas blender, Serial Data interface, Venous line clamps (manual), Electrical venous occlude (EVO).

The provided text is a 510(k) summary for the Stöckert S5 System, a Class II medical device (Heart-Lung Machine). It describes the device, its intended use, and the non-clinical testing performed to demonstrate substantial equivalence to a predicate device.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

No specific acceptance criteria (numerical thresholds for performance metrics) or a study proving that the device meets those criteria is explicitly provided in the typical format one would expect for an AI/ML device.

The document is a 510(k) Pre-market Notification, which focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving a device meets specific performance acceptance criteria against a clinical endpoint with defined sensitivity/specificity/accuracy thresholds. The studies described are primarily verification and validation (V&V) testing to ensure the device performs as intended and is safe and effective compared to its predicate.

Therefore, the interpretation below will focus on understanding the "acceptance criteria" through the lens of substantial equivalence and the "study" as the non-clinical testing performed for this purpose.

1. Table of Acceptance Criteria and Reported Device Performance

As noted, the document doesn't provide a typical table of acceptance criteria with numerical targets (e.g., sensitivity, specificity, accuracy). Instead, the "acceptance criteria" are implied by compliance with recognized standards and successful completion of various V&V tests, demonstrating that the device functions correctly and safely. The "reported device performance" is the successful completion of these tests.

Regarding the remaining requested information, it's important to understand that this document describes a hardware/software medical device (a Heart-Lung Machine) and not an AI/ML diagnostic or prognostic algorithm. Therefore, many of the requested fields are not applicable or cannot be answered from the provided text because they relate specifically to AI/ML performance evaluation.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Not Applicable / Not Provided: The nature of the testing (electrical safety, EMC, mechanical, software V&V) does not typically involve "test sets" of patient data or data provenance in the way an AI/ML diagnostic device would. These tests are performed on the device itself or its components. The document does not specify sample sizes for these engineering tests (e.g., how many units were tested for electrical safety).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not Applicable: This type of medical device (Heart-Lung Machine) does not involve establishing ground truth from expert interpretation in the context of diagnostic or prognostic tasks. The "ground truth" for its performance is determined by meeting engineering specifications and safety standards.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not Applicable: Adjudication methods are relevant for resolving discrepancies in expert interpretations of data, typically in AI/ML performance studies. This is not described for the V&V testing of a Heart-Lung Machine.

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, a MRMC study was not done. This is a non-AI/ML device. The "multi reader multi case" paradigm and "human readers improve with AI" concepts are not applicable to the S5 System as described.

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

• Not Applicable / Not Relevant in the AI/ML sense: The device is a standalone hardware/software system designed to perform its functions. The V&V testing assesses its performance in this standalone capacity. However, this is not equivalent to a "standalone" AI algorithm performance evaluation, as it's an operational medical device with human interaction as part of its intended use.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• Engineering Specifications and Recognized Standards: The "ground truth" for the device's performance is compliance with established engineering specifications, design requirements, and recognized international standards (e.g., IEC 60601 series, IEC 62366-1, IEC 62304, ISO 14971) for safety and effectiveness.

8. The sample size for the training set

• Not Applicable: This device is not an AI/ML system that uses a "training set" of data.

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

• Not Applicable: This device is not an AI/ML system that uses a "training set" of data.

Ask a specific question about this device