(23 days)
The Nautilus VF ECMO Oxygenator with integrated heat exchanger is intended to provide assisted long-term extracorporeal circulation and physiologic gas exchange (oxygenation and carbon dioxide removal) of the patient's blood for up to 48 hours in adult and pediatric adolescent patients with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent. The integrated heat exchanger is intended to heat or cool the blood as needed during use. Integrated fluid path pressure, temperature, and oxygen saturation monitoring is achieved by built-in sensor modules.
The Nautilus™ ECMO oxygenators are diffusion membrane oxygenators used in extracorporeal life support procedures to oxygenate blood, remove carbon dioxide and regulate blood temperature. Blood enters the device and passes through both the heat exchange membrane, where temperature is adjusted, and the gas transfer membrane, where oxygen is added and carbon dioxide is removed.
The Nautilus™ VF ECMO Oxygenator device contains integrated sensors that connects to the VitalFlow Console (K230364) for the display of measured parameters. The following measured parameters are measured: inlet pressure, inlet oxygen saturation, outlet oxygen saturation, and outlet blood temperature. The difference between the inlet and outlet pressure, is calculated. The device is intended to be interconnected with a VitalFlow Console device that receives digital data from the oxygenator.
The oxygenator devices are single-use, nontoxic, non-pyrogenic, and not made from natural latex rubber materials.
The provided FDA 510(k) summary for the Nautilus VF ECMO Oxygenator describes the device and its substantial equivalence to a predicate device. However, it does not contain information typically found in a study proving a device meets acceptance criteria within the context of AI/ML-powered medical devices.
This document is for a medical device (an oxygenator) and its associated monitoring components, not an AI/ML diagnostic or prognostic algorithm. Therefore, the questions related to AI/ML specific criteria (such as effect size of human readers with AI vs. without AI, ground truth establishment for training sets, number of experts for ground truth, etc.) are not applicable in this context.
Here's an analysis of the information that is present or can be inferred, formatted to address your questions where possible, and noting where information is missing or irrelevant to this type of device:
Device Acceptance Criteria and Performance
The document describes "Performance Evaluations" and "Special Controls" that were met to demonstrate substantial equivalence to the predicate device (Nautilus™ Smart ECMO Module (K191935) and Nautilus™ ECMO Oxygenator (K191935)). These act as the acceptance criteria for the device clearance.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Criteria/Evaluation | Reported Device Performance |
|---|---|---|
| Performance Evaluations | Electrical Safety/EMC | Evaluated, demonstrated substantial equivalence. |
| Software Validation | Evaluated, demonstrated substantial equivalence. | |
| Cybersecurity analysis | Evaluated, demonstrated substantial equivalence. | |
| Special Controls | Technological Characteristics | Geometry and design parameters are consistent with intended use. Compatible with other ECLS devices. Oxygenator geometry is same as predicate. Electronic module modified but demonstrated equivalent performance. |
| Biocompatibility | Demonstrated biocompatible for prolonged use per ISO 10993-1:2009 and GLP (21 CFR 58). No modifications to blood contact surfaces. | |
| Sterility and Shelf-life | Testing demonstrates sterility as provided, and maintenance of sterility, integrity, durability, and reliability over stated shelf-life. | |
| Non-clinical Performance | Substantial equivalence demonstrated by bench performance, mechanical integrity, electromagnetic compatibility, software, durability, reliability, and accuracy. Further demonstrated by EMC, software validation, and cybersecurity analysis. | |
| In vivo Evaluation | Demonstrates performance over long-term duration in a biologic test system. Summary of initial real-world clinical experience into ELSO registry was included. Original design's evaluation applicable as oxygenator design is unchanged. | |
| Labeling | Includes detailed summary of non-clinical evaluations, installation, setup, maintenance, changeout, adverse effects, and performance characteristics related to compatibility. |
2. Sample size used for the test set and the data provenance
The document mentions "bench studies" for performance evaluations, and "in vivo evaluation" using a "biologic test system" and a "summary... described the initial real-world clinical experience... into the ELSO registry."
- Sample Size for Bench Studies: Not specified. Bench studies typically involve a set number of device units for various tests (e.g., electrical, mechanical, software).
- Sample Size for In Vivo Evaluation: Not specified, but refers to a "biologic test system" and "initial real-world clinical experience with the first records of clinical ECMO cases entered sequentially into the ELSO registry." The exact number of cases or subjects is not provided in this summary.
- Data Provenance: The "ELSO registry" implies multi-center, international data, but the specific country of origin or whether it's retrospective/prospective is not detailed for the "real-world clinical experience" summary. The "biologic test system" would be a controlled lab setting.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not applicable and not provided for this type of medical device. The evaluation of an oxygenator focuses on its physical, chemical, electrical, and biological performance characteristics, not on diagnostic accuracy requiring expert interpretation or "ground truth" establishment in the way an AI algorithm for image analysis would.
4. Adjudication method for the test set
This information is not applicable and not provided. Adjudication methods (like 2+1, 3+1) are typically used for establishing ground truth in clinical studies involving interpretation (e.g., by radiologists) where there might be disagreements, which is not the case for an oxygenator's performance evaluation.
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
This information is not applicable as this is not an AI/ML-driven diagnostic or assistive device requiring human reader interaction.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This information is not applicable as this is not an AI/ML-driven device. The device has integrated sensors and connects to a console for display, so there's a human-in-the-loop for monitoring parameters, but it's not an AI algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For an oxygenator, "ground truth" would refer to established scientific and engineering principles, validated measurement techniques, and regulatory standards. For example:
- Biocompatibility: Established by adherence to ISO 10993 standards.
- Sterility: Validated sterilization methods and testing.
- Performance (e.g., gas exchange, heat exchange): Measured against validated laboratory methods and established clinical ranges for physiological parameters (e.g., blood oxygenation, CO2 removal).
- Safety (Electrical/EMC): Adherence to relevant IEC standards.
- In vivo: Performance in a "biologic test system" and "real-world clinical experience" as mentioned, assessed against physiological outcomes.
8. The sample size for the training set
This information is not applicable as this is not an AI/ML-driven device with a "training set" in the machine learning sense. The device is hardware with integrated sensors and software components that are validated, not trained.
9. How the ground truth for the training set was established
This information is not applicable for the same reasons as #8.
§ 870.4100 Extracorporeal circuit and accessories for long-term respiratory/cardiopulmonary failure.
(a)
Identification. An extracorporeal circuit and accessories for long-term respiratory/cardiopulmonary support (>6 hours) is a system of devices and accessories that provides assisted extracorporeal circulation and physiologic gas exchange of the patient's blood in patients with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent. The main devices and accessories of the system include, but are not limited to, the console (hardware), software, and disposables, including, but not limited to, an oxygenator, blood pump, heat exchanger, cannulae, tubing, filters, and other accessories (e.g., monitors, detectors, sensors, connectors).(b)
Classification —Class II (special controls). The special controls for this device are:(1) The technological characteristics of the device must ensure that the geometry and design parameters are consistent with the intended use, and that the devices and accessories in the circuit are compatible;
(2) The devices and accessories in the circuit must be demonstrated to be biocompatible;
(3) Sterility and shelf-life testing must demonstrate the sterility of any patient-contacting devices and accessories in the circuit and the shelf life of these devices and accessories;
(4) Non-clinical performance evaluation of the devices and accessories in the circuit must demonstrate substantial equivalence of the performance characteristics on the bench, mechanical integrity, electromagnetic compatibility (where applicable), software, durability, and reliability;
(5) In vivo evaluation of the devices and accessories in the circuit must demonstrate their performance over the intended duration of use, including a detailed summary of the clinical evaluation pertinent to the use of the devices and accessories to demonstrate their effectiveness if a specific indication (patient population and/or condition) is identified; and
(6) Labeling must include a detailed summary of the non-clinical and in vivo evaluations pertinent to use of the devices and accessories in the circuit and adequate instructions with respect to anticoagulation, circuit setup, performance characteristics with respect to compatibility among different devices and accessories in the circuit, and maintenance during a procedure.