Search Results

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

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.

Ask a specific question about this device

The VitalFlow™ Centrifugal Pump is intended to pump blood through the extracorporeal circuit for circulatory support up to 48 hours, in adult 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 VitalFlow™ Centrifugal Pump is driven by the VitalFlow™ Console and Drive Motor, or the Emergency Handcrank.

The VitalFlow Centrifugal Pump is a sterile, single-use centrifugal blood pump. It is a non-invasive, nonpyrogenic device designed to move blood through the extracorporeal circuit by centrifugal force. The pump is the disposable portion of the pumping system and it is electromagnetically coupled to an instrument that monitors and displays the flow and pressure of the blood. Blood enters the inlet port of the pump, where a cone with impeller blades within the pump housing rotates and the blood is gently accelerated toward the outlet of the pump.

The VitalFlow Centrifugal Pump can be driven through magnetic coupling by an External Drive Motor or the Emergency Handcrank.

The provided document is a 510(k) Summary for the VitalFlow™ Centrifugal Pump, a Class II medical device. It details the device's indications for use, description, and studies conducted to demonstrate its substantial equivalence to predicate and reference devices.

Here's an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" with quantitative targets in the way one might expect for a diagnostic AI device (e.g., target specificity, sensitivity). Instead, the acceptance criteria are framed within the context of demonstrating substantial equivalence to predicate devices and meeting specific "Special Controls" outlined in 21 CFR 870.4100. The performance is assessed through various bench, animal, and real-world clinical data.

Therefore, the table below summarizes the Special Controls as acceptance criteria and how the device's performance, as reported, addresses them.

2. Sample Size Used for the Test Set and Data Provenance

The document describes several types of studies:

• Bench Performance Evaluations: No specific sample size is given for individual tests, but it states "Design verification studies were performed by the original manufacturer... and supplemented by MC3 bench performance testing, including long-term characterization." This implies multiple samples were tested for each characteristic.
• Animal Studies (In vivo evaluation): A sample size of 13 sheep was used for the 96-hour study. The data provenance is a controlled research environment.
• Clinical Performance (Real-world evidence): This utilized 1048 reports from the ELSO.org registry for the Affinity CP Centrifugal Blood Pump (AP40 group). The document states this is a "summary of real-world evidence," implying retrospective data extraction from an international registry. The country of origin for the data isn't explicitly stated but the ELSO registry collects data internationally. The comparison group ("All Other Pumps") involved 51,032 reports.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

This device is not an AI diagnostic device that relies on expert interpretation of images or signals to establish a "ground truth" in the traditional sense. The "ground truth" for its performance is established through objective measures in bench testing (e.g., flow, pressure, mechanical integrity), physiological parameters in animal studies (e.g., presence/absence of clots, functionality), and reported clinical outcomes in the ELSO registry.

Therefore, there is no mention of "experts" establishing ground truth in the context of adjudication for a test set. Design verification and animal study results would be assessed by engineers, veterinarians, and researchers involved in those studies. Clinical outcomes in the ELSO registry are reported data.

4. Adjudication Method for the Test Set

Given that this is not an AI diagnostic device evaluating, for example, medical images requiring consensus on findings, there is no adjudication method (e.g., 2+1, 3+1) mentioned or applicable for the test sets described.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not done. This type of study typically assesses the performance of human readers (e.g., radiologists) with and without AI assistance for tasks like diagnosis or detection. The VitalFlow™ Centrifugal Pump is a mechanical device, not an AI diagnostic tool, so such a study is not relevant.

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

No, a standalone (algorithm-only) performance study was not done, as the VitalFlow™ Centrifugal Pump is a physical medical device. The "standalone" performance here would refer to the device's function outside of a human-in-the-loop context, which is effectively what the bench and animal studies demonstrate regarding its mechanical integrity and ability to pump blood.

7. The Type of Ground Truth Used

The "ground truth" for evaluating the VitalFlow™ Centrifugal Pump's performance is multi-faceted:

• Bench Testing: Engineering specifications and performance metrics (e.g., pressure-flow curves, durability, wear, integrity, blood trauma data).
• Animal Studies: Direct observation of device functionality, physiological parameters, and absence of adverse events like clot formation in a living system over a defined period (96 hours).
• Clinical Performance (Real-world evidence): Reported clinical outcomes and complication rates from a large patient registry (ELSO.org), providing real-world data on pump failure, hemolysis, circuit changes, and other adverse events. This relies on the accuracy of data submitted to the registry.

8. The Sample Size for the Training Set

The document is for a traditional medical device (centrifugal pump), not an AI/Machine Learning device. Therefore, there is no "training set" in the context of AI model development that would typically have a distinct sample size. The design verification, bench testing, and animal studies serve as part of the overall development and validation process.

9. How the Ground Truth for the Training Set Was Established

As there is no AI training set, this question is not applicable. The "ground truth" for the device's design and engineering would be based on established medical and engineering principles, material science, and regulatory requirements, which are then verified through rigorous testing, as mentioned above.

Ask a specific question about this device

The VitalFlow™ Console controls the VitalFlow™ Centrifugal blood pump during extracorporeal cardiopulmonary life support for adult 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 VitalFlow Centrifugal pump is driven by the VitalFlow Motor Drive or the VitalFlow Emergency Handcrank.

The VitalFlow Console provides control of blood pumping through an extracorporeal circuit during extracorporeal life support (ECLS) procedures. The console powers the VitalFlow motor drive unit which provides rotation of the VitalFlow Centrifugal pump. Pump motor speed (RPM) can be adjusted by the user and flow and bubble detection is provided by an ultrasonic flow probe and displayed on the touchscreen. The touchscreen display allows users to set alarm limits for all measured parameters. The device will alarm visually and audibly when limits are exceeded. Status indicators, power / battery life and secondary RPM indicator is provided. Data download and data streaming from the console is available for ECLS circuit data only; no patient data are stored or exported.

The VitalFlow Emergency Handcrank (drive unit) can be used in emergency situations to manually drive the centrifugal pump in the case of console and or motor drive failure.

The provided text describes the VitalFlow™ Console, an extracorporeal circuit component, and its FDA 510(k) clearance (K230364). The document outlines the device's indications for use, description, and the performance evaluations conducted to demonstrate substantial equivalence to a predicate device.

However, the document does not contain the detailed information necessary to answer all parts of your request, specifically regarding acceptance criteria for an AI/ML model, sample sizes for test sets in an AI context, expert ground truth establishment, MRMC studies, or training set details for an AI model. This is likely because the VitalFlow™ Console is a mechanical/electronic medical device, not an AI/ML-driven diagnostic or assistive device that would typically undergo such evaluations.

The "Bench Performance Evaluations" section lists various studies (Hydraulic performance, Reliability, EMC, Electrical Safety, Software Validation, Usability Studies), but these are standard engineering and regulatory tests for hardware and software functionality, not AI model performance.

Therefore, I cannot provide a table of acceptance criteria for an AI model or details about AI-specific testing from this document.

If you are looking for information regarding an AI/ML-driven medical device, this document does not seem to pertain to such a device.

From the provided text, I can infer the following about the device and its testing:

• Device Type: The VitalFlow™ Console is an extracorporeal circuit and accessories for long-term respiratory/cardiopulmonary failure (Product Code: QNR, Regulation Number: 21 CFR 870.4100). It controls features like pump motor speed (RPM), flow, and bubble detection.
• Purpose of Studies: The studies were conducted to demonstrate "substantial equivalence" of the VitalFlow™ Console to a predicate device (TandemHeart Escort Controller, K202751) and to meet the "Special Controls" described in 21 CFR 870.4100.
• Nature of Studies: The studies were primarily "Bench Performance Evaluations" and included aspects like hydraulic performance, reliability, EMC, electrical safety, software validation, and usability studies. These are typical engineering and functional performance tests for a physical device.
• Ground Truth: For a physical device like this, "ground truth" would be established through calibrated instruments and established engineering principles for parameters like flow rate, RPM, pressure, and electrical safety. It's not based on expert consensus on image interpretation or pathology.
• No AI Component: There is no mention of an AI/ML component or algorithm within the VitalFlow™ Console. Therefore, concepts like training sets, test sets for AI models, expert adjudication, or MRMC studies are not applicable to the information provided.

In summary, the provided document does not contain the information requested about AI/ML device acceptance criteria and study details because the VitalFlow™ Console appears to be a physical medical device, not an AI-driven one.

Ask a specific question about this device

The MC3 Crescent™ Jugular Dual Lumen Catheter is a single use, dual lumen catheter that provides both venous drainage and reinfusion of blood via the jugular vein and is indicated for use in adult and pediatric patients with acute respiratory failure requiring Veno-Venous Extracorporeal Membrane Oxygenation, where other available treatment options have failed and continued clinical deterioration is expected or the risk of death is imminent.

The MC3 Jugular Dual Lumen Catheters are dual lumen catheters supplied with an introducer to facilitate wire guided placement into the vasculature via percutaneous (Seldinger type) vascular access methods. The introducer is designed to follow a prepositioned standard guide wire (not included) or obturator (blunt end closed tip introducer) when following a surgical placement. The catheter is wire reinforced for flexibility and kink-resistance and includes depth marks. Both the introducer and catheter are made of radiopaque materials and the catheter also includes tantalum radiopaque markers at the infusion port, proximal and distal drainage holes, and the catheter tip. The catheter body contains an integrated suture site for use during securement. An optional suture collar is provided and can be used for supplemental securement only. A dilator is also included. The dilators are the same diameter of the catheter and are designed to be used for dilation of the vessel. These catheters are provided in a variety of sizes ranging from 13Fr (8.9 cm insertable length) to 32Fr (34 cm insertable length).

This document is a 510(k) Summary for the MC3 Crescent™ Jugular Dual Lumen Catheter. It outlines the device's indications for use, description, comparison to a predicate device, and how it conforms to Class II Special Controls.

Here's an analysis of the provided text based on your request:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" with quantitative targets alongside "reported device performance" in the way one might expect for diagnostic accuracy or clinical outcomes. Instead, it discusses conformance to "Special Controls" and mentions various types of testing to demonstrate "substantial equivalence."

Based on the information provided, the "acceptance criteria" can be inferred from the "Class II Special Controls" and the general requirements for substantial equivalence. The "device performance" is described qualitatively as meeting these controls.

Important Note: The document focuses on demonstrating substantial equivalence to a predicate device (Jugular Dual Lumen Catheter K180151) rather than proving novel clinical efficacy or diagnostic accuracy as might be seen for AI-driven diagnostic devices. The performance metrics are related to safety, material compatibility, and engineering design rather than clinical outcome improvements attributable to the device itself beyond its function in ECMO.

2. Sample size used for the test set and the data provenance

The document describes various types of testing but does not provide specific sample sizes for each test mentioned (e.g., "non-clinical performance," "in vivo evaluation," "biocompatibility").

• Non-clinical Performance: Mentions "bench" testing, "mechanical integrity," and "30-day durability." No specific sample size is given.
• In vivo Evaluation: Mentions "7-day in vivo thrombogenicity evaluation." No specific sample size is given, nor is the species used.
• Biocompatibility: Refers to ISO 10993-1:2009 and GLP (21 CFR 58). These are standards for testing, but they don't specify the sample size used in this particular submission.

Data Provenance: The data is generated from various tests (bench, in vivo, etc.) conducted by the manufacturer (MC3 Incorporated). The document does not specify the country of origin for the data or if it's retrospective or prospective, as these are typically controlled laboratory and animal studies, not patient data in the context of this device.

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

This information is not provided in the document. The tests described are laboratory and animal studies, not typically involving human expert adjudication for "ground truth" in the way a diagnostic AI would.

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

This information is not provided and is not applicable to the types of engineering and biocompatibility tests described for this medical device.

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, an MRMC comparative effectiveness study was not done. This type of study is relevant for diagnostic imaging AI devices, not for a physical medical device like a catheter.

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

This question is not applicable as the device is a physical catheter, not an algorithm or AI system.

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

The concept of "ground truth" in the context of diagnostic accuracy is not directly applicable here. For the various tests performed, the "truth" is established through:

• Bench Test Results: Measured physical and mechanical properties against pre-defined specifications.
• Biocompatibility Standards: Adherence to established ISO and GLP guidelines.
• In vivo Evaluation: Biological responses (e.g., thrombogenicity) observed in an animal model, measured against expected safety profiles.

8. The sample size for the training set

This is not applicable. The MC3 Crescent™ Jugular Dual Lumen Catheter is a physical medical device, not an AI/ML algorithm that requires a training set.

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

This is not applicable as there is no training set for this type of device.

Ask a specific question about this device

The Nautilus(tm) Smart ECMO Module 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 and display.

The Nautilus(tm) 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.

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™ Smart ECMO Module device contains integrated sensors with an electronic touch screen display. The following measured parameters are visible on the electronic display: inlet pressure, inlet oxygen saturation, outlet pressure, outlet oxygen saturation, and outlet blood temperature. The difference between the inlet and outlet pressure, delta pressure, is calculated and also displayed on the screen. The touchscreen display allows users to set alarm limits for all measured parameters. The Nautilus™ Smart ECMO Module will alarm visually and audibly when the limits are exceeded.

The devices are single-use, nontoxic, non-pyrogenic, and not made from natural latex rubber materials.

The provided text describes performance evaluations for the MC3 Nautilus Smart ECMO Module and Nautilus ECMO Oxygenator. However, it does not explicitly state "acceptance criteria" in a tabulated format and then directly link each criterion to "reported device performance" in a separate column. Instead, it presents various performance evaluations and their findings.

Based on the information provided, here's a structured summary attempting to address your request as closely as possible:

1. Table of acceptance criteria and the reported device performance

While explicit acceptance criteria are not tabulated with specific numerical targets, the document implies that the device is considered acceptable if its performance is "comparable or better" than a state-of-the-art device and meets the "special controls" and standards.

• "The most common complication reported was circuit exchange in twenty percent of patients..."
• "Ten percent of patients had reports of blood infections on ECMO, which is similar to the rate of infections (11%) previously reported by others."
• "One patient suffered a CNS infarction event (5%), and another patient, a CNS hemorrhage." |
  | Compatibility with other circuit devices | Technological Characteristics: "The subject device is designed to be compatible with other extracorporeal circuit devices and accessories." |

The studies collectively show that the Nautilus device meets performance expectations by being comparable to or better than predicate/reference devices and established clinical norms, and by demonstrating safety and efficacy in various testing environments.

2. Sample size used for the test set and the data provenance

• Long-term Bench Gas Exchange testing: The sample size isn't explicitly stated as a number of devices, but it refers to "MC3 Nautilus oxygenators from accelerated age populations" and "competitive heparin coated oxygenators."
  • Provenance: In vitro, conducted according to ISO 7199:2016, using bovine blood/plasma.
• In-Vivo Study in Sheep:
  • Sample size: A total of 15 sheep. Specifically, 10 sheep were used to evaluate the Nautilus device (at either 2 or 5 L/min), and 5 control animals were studied with a state-of-the-art heparin-coated device (at 2 L/min).
  • Provenance: Prospective animal study.
• Clinical information (Real World Evidence):
  • Sample size: Not explicitly stated as a number of patients, but data were collected from patients at 7 centers in 4 countries. The average duration of ECMO support was 378.5 hours (15.8 days), with a range of 17 to 1271 hours (52.9 days). Given these durations, it implies a significant number of patient-hours of use.
  • Provenance: Retrospective, voluntarily entered into the ELSO registry from initial real-world clinical experience. Data from 7 centers in 4 countries.

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

This information is not provided in the text. The studies described are performance-based (bench, in-vivo) and real-world data collection, rather than studies requiring expert adjudication of device performance in a diagnostic sense.

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

This information is not provided in the text. The studies described (bench, animal, real-world registry data) do not appear to involve a human adjudication process for establishing a "ground truth" in the way a diagnostic algorithm might be evaluated.

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

There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study, nor any evaluation of human readers improving with AI assistance. The device is an ECMO module/oxygenator, not an AI-assisted diagnostic tool.

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

This question is not directly applicable. The device (ECMO module/oxygenator) is a medical device that physically interacts with a patient's blood, not an algorithm. The "Smart Module" has integrated sensors and an electronic display, which would operate in a "standalone" algorithmic sense for its sensor functions, but its primary function as an ECMO device is not an algorithm. The sensor accuracy was evaluated as part of "Smart Module Testing."

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

• Long-term Bench Gas Exchange testing: Ground truth for gas exchange and pressure drop was established by measurements according to the ISO 7199:2016 standard using bovine blood, providing objective scientific measurements.
• In-Vivo Study in Sheep: Ground truth for clotting was established by direct observation ("no clots in any location") and confirmation of oxygenator functionality in the animal model.
• Clinical information (Real World Evidence): Ground truth for complications and device performance in a clinical setting was derived from clinical observation and patient outcomes data voluntarily entered into the ELSO registry by clinicians at the participating centers.

8. The sample size for the training set

This information is not applicable/provided. The device is a physical medical device, not a machine learning algorithm that requires a "training set" for its operation in the way an AI diagnostic tool would.

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

This information is not applicable/provided, as the concept of a "training set" does not apply to this type of device.

Ask a specific question about this device

Intended for single use by a trained physician to assist in vessel cannulation.

The MC3 Vascular Access Kit consists of component devices that are already cleared by FDA, as well as various sized dilator devices. The subject devices include dilators that are 13, 16, 20, 24, 26, and 28 French (FR). These dilators are all made of Colorite PVC, 9566M-RAD14. The MC3 logo and size indicator are legibly printed at the hub end of the dilator using NAZDAR VF111 Black Ink with NAZDAR VF190 Ink Thinner. These dilators are packaged together in the MC3 Vascular Access Kit with other devices already cleared by FDA in accordance with the FDA convenience kit guidance. All kit contents are sterile (EtO), nonpyrogenic, and single use only. The current FDA cleared devices of the kit include a stainless steel Guidewire; a Stepped Dilator, starting at 8Fr. on the tip transitioning to 10Fr.; a singlewall introducer needle, with protector, that is designed to introduce up to a 0.038" guidewire into the vasculature; a long handle, disposable #11 safety scalpel used for incisions during operational procedures; and a 10ml silicone double seal stopper syringe with luer slip. Peripheral access to the vein is gained using the needle, syringe, and scalpel. The guidewire is then inserted into the vessel through the needle is removed. A dilator is then chosen by the physician and inserted over the guidewire into the vessel. The dilator is then removed and the next sized dilator is inserted in the same manner until the desired dilation is achieved. The single-use devices are then disposed after use.

The provided document describes the predicate device and the studies conducted to demonstrate substantial equivalence, rather than detailing a study that proves the device meets specific acceptance criteria in the context of an AI/ML medical device. The device in question is the "MC3 Vascular Access Kit 21030," which consists of physical components like dilators, guidewires, needles, and scalpels for vessel cannulation. It is not an AI/ML device.

Therefore, many of the requested points, such as sample sizes for test/training sets, expert ground truth establishment, MRMC studies, or standalone algorithm performance, are not applicable to this physical medical device submission.

However, I can extract the relevant information regarding the acceptance criteria and the performance for this device based on the non-clinical testing performed.

Updated Information based on the provided document:

1. A table of acceptance criteria and the reported device performance:

2. Sample size used for the test set and the data provenance:
For the non-clinical tests (Buckling, Tensile Strength, Guidewire Fit, Tip Cracking/Kinking, Biocompatibility), the document states "All test articles met acceptance criteria." This implies a sample size was used for each test, but the exact number for each specific test is not explicitly stated in the provided text.
The data provenance is from non-clinical laboratory testing conducted by the manufacturer, MC3 Incorporated. It is not patient data (retrospective or prospective) from specific countries.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
This criterion is not applicable as the studies were in-vitro/lab-based non-clinical tests, not involving expert interpretation of data or images.

4. Adjudication method for the test set:
Not applicable for these types of non-clinical tests.

5. If a multi-reader multicase (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/ML 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/ML device.

7. The type of ground truth used:
For the mechanical and physical tests, the "ground truth" was established by objective engineering specifications and measurement standards. For biocompatibility, it was based on internationally recognized standards (ISO-10993).

8. The sample size for the training set:
Not applicable as this is not an AI/ML device.

9. How the ground truth for the training set was established:
Not applicable as this is not an AI/ML device.

Ask a specific question about this device

The MC3 Jugular Dual Lumen Catheter is a single use dual lumen catheter, which provides both venous drainage and reinfusion of blood via the jugular vein, that is indicated for use in patients with acute respiratory failure requiring Veno-Venous Extracorporeal Membrane Oxygenation, where other available treatment options have failed and continued clinical deterioration is expected or the risk of death is imminent.

The MC3 Jugular Dual Lumen Catheters are bi-caval dual lumen catheters supplied with an introducer to facilitate wire guided placement into the vasculature via percutaneous surgical methods (Seldinger type approach). The introducer is designed to follow a prepositioned standard 0.038" (0.97 mm) or 0.035" (0.89 mm) guide wire (not included). The introducer hub provides an area for grasping the introducer during insertion and when fully seated, indicates that the introducer is fully inserted. The catheter is wire reinforced for flexibility and kink-resistance and includes depth marks. Both the introducer and catheter are made of radiopaque materials and the catheter also includes tantalum radiopaque markers at the infusion port, proximal and distal drainage holes, and the catheter tip. The catheter body contains an integrated suture site for use during securement. An optional suture collar is provided and can be used for supplemental securement only. A dilator is also included. The dilators are the same diameter of the catheter and are designed to be used for dilation of the vessel. The catheters remain intact throughout the duration of use and withstand the forces associated with insertion, securement, connection to perfusion line, clamping, blood pressures, and removal.

This document describes the premarket notification for a medical device and provides information on its performance evaluations, but it does not contain acceptance criteria or a study proving the device meets those criteria in the context of diagnostic or AI-driven performance.

The document is a 510(k) summary for the MC3 Jugular Dual Lumen Catheter, which is a physical medical device (a catheter) used for Veno-Venous Extracorporeal Membrane Oxygenation (ECMO). The "performance evaluations" mentioned are for the physical characteristics and safety of the catheter itself (e.g., durability, flow, kink resistance, biocompatibility, sterility), not for a diagnostic algorithm or AI system's output.

Therefore, I cannot provide the requested information from the provided text, as it pertains to a different type of device and different evaluation criteria than what your questions imply (e.g., questions about ground truth, expert consensus, MRMC studies, standalone algorithm performance, training/test sets are relevant for AI/diagnostic devices, not for a physical catheter's mechanical performance).

If you have a document related to an AI/diagnostic device, please provide that.

Ask a specific question about this device

The MC3 26 Fr. QuickFlow™ Dual Lumen Catheter is a single use dual lumen catheter, which provides both venous drainage and reinfusion of blood via the femoral vein, that is indicated for use for up to 72 hours in patients with acute respiratory failure requiring partial Veno-Venous Extracorporeal Membrane Oxygenation (full hemodynamic support is not required and predicted flows needed to maintain adequate oxygenation do not exceed 31/min) where other available treatment options have failed and continued clinical deterioration is expected or the risk of death is imminent.

The MC3 28 Fr. QuickFlow™ Dual Lumen Catheter is a single use dual lumen catheter, which provides both venous drainage and reinfusion of blood via the femoral vein, that is indicated for use for up to 72 hours in patients with acute respiratory failure requiring partial Veno-Venous Extracorporeal Membrane Oxygenation (full hemodynamic support is not required and predicted flows needed to maintain adequate oxygenation do not exceed 3.5l/min) where other available treatment options have failed and continued clinical deterioration is expected or the risk of death is imminent.

The MC3 QuickFlow Dual Lumen Catheters are dual lumen catheters supplied with an introducer to facilitate wire guided placement into the vasculature by normal access techniques. The introducer is designed to follow a pre-positioned standard 0.038" (0.97 mm) or 0.035" (0.89 mm) guide wire (not included). The catheter is wire-reinforced for flexibility and kink-resistance and includes depth marks. Both the introducer and catheter are made of radiopaque materials and the catheter has radiopaque markers at the tip and most proximal set of drainage holes.

The devices are comprised of two separate thin-walled catheters made of silicone and polyurethane polymer and reinforced with a spring wire. The dual lumen design involves two catheters of different diameters joined together in a co-axial configuration. An arrangement of side holes in the outer (drainage) catheter allows for egress of blood. An open tip on the inner (return) catheter allow s for blood ingress. Unreinforced tube extensions with barbed connectors, allowing clamping and connection to the extracorporeal circuit, are joined to the wye junction. A tapered tip introducer is included to facilitate placement of the catheter into the blood vessel over a standard guide wire (not included). Securement of the device may be accomplished via a groove designed in the Y-connector to accept a suture and a suture around a 3/8" barb connector.

The provided text describes the MC3 QuickFlow Dual Lumen Catheter and its equivalency to a predicate device, focusing on its physical characteristics, intended use, and performance evaluations. However, it does not contain information related to an AI/ML device, nor does it present acceptance criteria or a study proving an AI/ML device meets such criteria.

The document is a 510(k) premarket notification for a medical device (a catheter), and the performance evaluations listed are typical for such hardware devices (durability, pressure/flow, kink resistance, etc.). There is no mention of "AI", "algorithm", "human readers", "MRMC", "ground truth" in the context of an AI-driven study, or any other terms that would suggest an AI/ML component.

Therefore, I cannot fulfill your request for information regarding acceptance criteria and a study proving an AI/ML device meets those criteria based on the provided text, as the text pertains to a non-AI medical device.

Ask a specific question about this device