(256 days)
The INSPIRA™ ART100 system is intended for use in an extracorporeal perfusion circuit to pump blood during short duration cardiopulmonary bypass procedures lasting six hours or less.
The INSPIRA™ ART100 system is a device for pumping blood without direct contact in an extracorporeal blood circulation circuit. The device is prescribed (Rx) by specialists to be used in Cardiopulmonary Bypass (CPB) procedures. The INSPIRA™ ART100 system consists of the following components: Controller Unit, Pump Drive Unit, Manual Pump Drive Unit, Blood Flow and Bubble Detection Sensor, Temperature Sensor, Cable adapters for Pressure Sensors, Cable adapters for Temperature Sensor, Oxygenator and Pump Drive Holders. The system is compatible with a Non-Roller Centrifygal Pump (Capiox iCP Centrifyqal Pump). The Inspira Pump Drives are magnetically coupled exclusively with the Capiox iCP Centrifugal Pump, designed and manufactured by Terumo Cardiovascular Systems Corporation, and can be supplied by Inspira. The INSPIRA™ ART100 system is intended to be used in conjunction with other previously 510(k)-cleared devices and sterile accessories such as cannulas, catheters, oxygenators, luer connectors, pressure sensors, supplied by hospital users or other manufacturers.
The provided text describes a 510(k) premarket notification for the INSPIRA™ ART100 device. While it details the device's technological characteristics, intended use, and comparison to a predicate device, it does not include specific acceptance criteria for performance metrics (e.g., accuracy, sensitivity, specificity) or a detailed study proving the device meets these criteria in the context of an AI/human-in-the-loop system.
The device, Inspira Art100, is a cardiopulmonary bypass pump speed control system. The testing performed is related to ensuring the device functions as intended and meets safety standards, rather than evaluating specific clinical performance metrics typical of AI/ML-driven diagnostic or prognostic devices.
Therefore, many of the requested details about acceptance criteria and performance studies for an AI device cannot be extracted from this document.
However, I can extract information regarding non-clinical tests performed to demonstrate safety and effectiveness for this type of medical device:
1. Table of Acceptance Criteria and Reported Device Performance
The document states: "All testing met predetermined acceptance criteria." However, the specific acceptance criteria and detailed reported performance values for each non-clinical test are not explicitly provided in a table format. The reported performance is implicitly that the device passed these tests.
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Software Verification and Validation | Met predetermined acceptance criteria. |
| Functional Design Verification and Validation | Met predetermined acceptance criteria. |
| Electrical Safety, EMI/EMC | Met predetermined acceptance criteria and certified by accredited third-party laboratories to IEC 60601-1, IEC 60601-1-2, IEC 60601-1-8. |
| Interoperability Evaluation (with accessories/compatible devices) | Met predetermined acceptance criteria. |
| Reliability Testing | Met predetermined acceptance criteria. |
| Simulated Use Testing | Met predetermined acceptance criteria. |
| Cleaning Validation | Met predetermined acceptance criteria. |
| Packaging and Shipping Testing | Met predetermined acceptance criteria and certified to ASTM D4332-22, ASTM D4169-22. |
| Usability/Human Factors | Completed human factors validation study in accordance with IEC 62366-1, ISO 14971, and FDA guidance. All residual use-error risks evaluated and minimized; overall residual risk acceptable. |
| Risk Management | In accordance with ISO 14971:2019. |
| Software Life Cycle Processes | In accordance with IEC 62304:2006/AMD 1:2015. |
| Battery Safety/Transport | Certified to IEC / UL 62133-2:2020 Ed.1 / CSA C22.2 and UN38.3. |
2. Sample size used for the test set and the data provenance: Not applicable. The tests performed are non-clinical, bench, and simulated use tests for a pump speed control device, not a diagnostic or prognostic AI system using patient data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth as typically defined for AI models (e.g., disease presence) is not relevant for the type of device and testing described. Expert involvement would be in the design, testing, and validation of the device's engineering and safety aspects.
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: No, this type of study was not done. The device is a cardiopulmonary bypass pump speed control system, not an AI assistance tool for human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document describes standalone device testing (bench tests) for its functional and safety performance, but not in the context of an AI algorithm vs. human performance.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): For the non-clinical tests described, "ground truth" refers to engineering specifications, performance standards (e.g., for pump speed, flow rate accuracy), and compliance with recognized industry standards (e.g., IEC, ISO, ASTM).
8. The sample size for the training set: Not applicable. This device is not an AI/ML model that requires a training set of data.
9. How the ground truth for the training set was established: Not applicable.
§ 870.4380 Cardiopulmonary bypass pump speed control.
(a)
Identification. A cardiopulmonary bypass pump speed control is a device used that incorporates an electrical system or a mechanical system, or both, and is used to control the speed of blood pumps used in cardiopulmonary bypass surgery.(b)
Classification. Class II (performance standards).