Search Results

The Cordis BRITECROSS Support Catheters are indicated to guide and support a guide wire during access to the peripheral vasculature, allow for exchange of guide wires, and provide a conduit for the delivery of saline solutions or diagnostic contrast agents.

The BRITECROSS Support Catheter is a flexible single lumen catheter that is intended to cross lesions to facilitate guidewire access and/or the delivery of saline/contrast during peripheral vascular interventions. The subject device is designed to allow for fluoroscopic visualization of the catheter. The radiopaque distal tip allows for accurate placement of the tip relative to the lesion. Further, there are two (2) radiopaque marker bands incorporated along the shaft to provide the clinician with a length reference facilitating approximation of the lesion length. On the proximal end, the hub has an integrated strain relief and a standard female luer to connect with a standard syringe. The BRITECROSS Catheter is available in various lengths and diameters and the size is printed on the hub for quick identification. The device is sterile and is for single use.

The provided text describes a 510(k) premarket notification for a medical device called the "Cordis BRITECROSS Support Catheter." This is a regulatory filing that aims to demonstrate that a new device is as safe and effective as an already legally marketed device (the predicate device).

Crucially, this document focuses on the substantial equivalence of a new medical device to a predicate device based on performance testing and predicate device comparison, not on the evaluation of an AI/ML algorithm. The provided text does not contain information about an AI/ML device, its acceptance criteria, or a study proving that an AI/ML device meets those criteria.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves an AI/ML device meets the acceptance criteria using the provided text. The device described, the Cordis BRITECROSS Support Catheter, is a physical medical device (a catheter) and not an AI/ML algorithm.

The "Performance Data" section lists various physical, mechanical, and biological tests conducted on the catheter (e.g., dimensional, mechanical, in-vitro testing, biocompatibility, sterilization), which are typical for physical medical devices to demonstrate their safety and efficacy. It explicitly states "No clinical data was required" and "No animal performance data was required," further indicating that this is not an AI/ML study.

Ask a specific question about this device

Cardiopulmonary Bypass (CPB): Bio-Medicus Life Support catheters are peripheral-access catheters used to perfuse vessels or organs in conjunction with extracorporeal cardiopulmonary bypass (CPB) procedures. The catheter introducer is intended to facilitate proper insertion and placement of the appropriately sized catheter within the vessel. Catheter models with tip lengths of 18 cm (7.09 in), 50 cm (19.7 in), or 55 cm (21.7 in) and without additional side holes may be used as either drainage or reinfusion catheters. This product is intended for use in adult and pediatric patients for up to 6 hours.

Extracorporeal Membrane Oxygenation (ECMO) and Extracorporeal Life Support (ECLS): The Bio-Medicus Life Support catheters and introducers are single-lumen drainage or reinfusion peripheral-access catheters to be used in ECMO or ECLS with an extracorporeal circuit intended for use in adult and pediatric patients with acute respiratory 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 Bio-Medicus Life Support™ catheter is a single-lumen catheter used to drain or reinfuse blood. The introducer facilitates proper insertion and placement of the appropriately sized catheter over a guidewire within the vessel. These devices are intended to perfuse vessels or organs in conjunction with extracorporeal support, including cardiopulmonary bypass (CPB), Extracorporeal Membrane Oxygenation (ECMO) and Extracorporeal Life Support (ECLS). Catheter models with tip lengths of 18 cm (7.09 in), 50 cm (19.7 in), or 55 cm (21.7 in), with and without additional side holes may be used as either drainage or reinfusion catheters.

These devices are sterile, nonpyrogenic, disposable, intended for single use only. Do not store the product above 25℃ (77°F).

The provided text is a 510(k) summary for the Medtronic Bio-Medicus Life Support Catheter and Introducer. It details the device, its intended use, comparison to a predicate device, and performance testing. However, it does not describe acceptance criteria for an AI-powered device, nor does it detail a study proving such a device meets acceptance criteria.

The information provided pertains to a traditional medical device (a catheter and introducer) with a material formulation change, and the "performance testing" described is bench testing and biocompatibility assessments to demonstrate substantial equivalence to a predicate device. There is no mention of AI, machine learning, or software performance in terms of diagnostic accuracy or effect on human readers.

Therefore,Based on the provided text, it is not possible to describe the acceptance criteria or a study that proves a device meets acceptance criteria for an AI-powered device. The document pertains to a traditional medical device (catheter and introducer), specifically addressing a material change to a component (luer cap). There is no mention of AI, machine learning, or any form of algorithm-driven performance evaluation.

The "Summary of Performance Testing" section focuses on demonstrating substantial equivalence of the modified luer cap through risk-based testing, functional testing, and biocompatibility assessment, which are standard for physical medical devices.

Here's a breakdown of why the requested information cannot be provided from the given text:

• No AI Component: The device described (Bio-Medicus Life Support Catheter and Introducer) is a physical medical device. The document explicitly states the "device modification was made to the predicate device: Luer cap material formulation change (vented connector models)." This is a hardware change, not a software or AI change.
• No Diagnostic or Classification Task: The device's function is to facilitate extracorporeal support procedures (CPB, ECMO, ECLS), not to interpret data, diagnose conditions, or assist human readers in a diagnostic capacity.
• No Performance Metrics for AI: The "performance testing" described is for the physical integrity and biocompatibility of the luer cap ("functional testing and biocompatibility assessment"), which are not the types of metrics (e.g., sensitivity, specificity, AUC, human reader improvement) that would be used for AI device acceptance criteria.

To directly answer your request based on the provided text, I must state that the information is not present:

1. A table of acceptance criteria and the reported device performance: Not applicable. The document describes bench testing to qualify a material change, not AI performance metrics.
2. Sample sized used for the test set and the data provenance: Not applicable. The "test set" here refers to physical components for bench testing, not a dataset for AI evaluation.
3. Number of experts used to establish the ground truth... and qualifications: Not applicable. Ground truth as typically defined for AI validation (e.g., for image interpretation) is not established for this physical device.
4. Adjudication method: Not applicable. There is no interpretive task requiring adjudication.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: No. This type of study is for AI-assisted human performance, which is not relevant to this device.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable. There is no algorithm.
7. The type of ground truth used: Not applicable.
8. The sample size for the training set: Not applicable. There is no training set for an AI model.
9. How the ground truth for the training set was established: Not applicable.

In conclusion, the provided FDA document is for a traditional medical device (catheter) and does not contain any information related to AI acceptance criteria or AI performance studies.

Ask a specific question about this device

SINC Support Catheters are intended to be used in conjunction with steerable guidewires to access discrete regions of the peripheral vasculature. They may be used to facilitate placement and exchange of guidewires and other interventional devices, and provide a conduit for delivery of saline solutions or diagnostic/ therapeutics agents.

The SINC™ (Selective Interventional Navigation Catheter) Support Catheters are single lumen catheters designed to access peripheral vasculature. These catheters are available in a variety of lengths and offer a side port. Each configuration has a braided support matrix and hydrophilic coating on the distal segment of the catheter. The distal tip is clearly distinguished by a radiopaque gold coated tip.

The SINC Support Catheters will also allow for exchange of guidewires and other interventional devices and provide a conduit for delivery of saline solutions or diagnostic contrast.

The provided text is a 510(k) summary for the Reflow Medical SINC Support Catheter. It outlines the device description, indications for use, and a comparison to a predicate device. However, it does not include information about a study proving the device meets acceptance criteria related to a standalone AI algorithm's performance, human-in-the-loop performance, or the nuances of AI model development (training/test sets, ground truth establishment, expert adjudication).

The document focuses on the physical and mechanical performance of the catheter itself, demonstrating substantial equivalence to a predicate device through non-clinical laboratory testing. The types of tests mentioned are:

• Simulated Use Testing
• Dimensional Verification
• Leak Testing
• Bond Integrity
• Component Integrity
• Corrosion Testing
• Kink Resistance
• Torque Testing
• Particulate
• Catheter Flow Rate and Burst Testing
• Lubricity Characterization
• Packaging Testing
• Design Validation

These tests are standard for medical devices like catheters to ensure their mechanical safety and functionality, not for AI/ML performance.

Therefore, I cannot provide accurate answers to most of your questions as they pertain to an AI/ML device study, which is not described in the given text.

However, I can extract information relevant to the device's mechanical performance to show what "acceptance criteria" and "performance" are mentioned for this type of device:

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

The document states: "The SINC™ Support Catheter met all specified criteria and did not raise new safety and performance questions." While specific quantitative acceptance criteria and reported values for each test (e.g., "Kink Resistance: Passed 1N force without kinking") are not detailed in this summary, the general statement indicates successful performance against pre-defined criteria for each test listed.

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

This information is not applicable to the non-clinical, mechanical testing described. The "test set" here refers to the physical units of the SINC Support Catheter used for the various lab tests (e.g., a certain number of catheters were subjected to torque testing, burst testing, etc.). The document does not specify the number of units tested for each category, nor is "data provenance" (country/retrospective/prospective) relevant to lab-based mechanical tests.

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)

This is not applicable. "Ground truth" in this context refers to the successful completion or failure of mechanical tests according to engineering specifications, not expert interpretation of medical images or patient outcomes. The "experts" would be the engineers and technicians conducting and evaluating the specified physical/mechanical tests according to established international standards (like ISO 10555-1, referenced in the document). Their qualifications would be in engineering, materials science, or related fields, not medical imaging.

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

Not applicable. Adjudication methods like 2+1 or 3+1 are used for establishing consensus on medical image interpretations or clinical outcomes, typically when ground truth is subjective or challenging to obtain. For mechanical tests, the results (e.g., pass/fail, measurable physical properties) are typically objective and determined by the test protocol itself.

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. No MRMC study was performed as this is a medical device (catheter), not an AI-assisted diagnostic tool.

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

Not applicable. No standalone algorithm performance was assessed as this is a medical device (catheter), not an AI algorithm.

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

For the mechanical tests listed, the "ground truth" is defined by the pass/fail criteria of the specified engineering and performance tests, often based on international standards (like ISO 10555-1 mentioned in the document) and the device's design specifications. For example, a "kink resistance" test would have an objective threshold for what constitutes a "kink" and the maximum force the catheter must withstand without kinking.

8. The sample size for the training set

Not applicable. This device does not involve a "training set" in the machine learning sense. The "training" for such a device involves its design, manufacturing processes, and quality control.

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

Not applicable.

In summary, the provided document details the regulatory clearance of a physical medical device (a catheter) and its mechanical performance testing. It does not describe an AI/ML device or a study involving AI performance metrics or human-AI interaction.

Ask a specific question about this device

The SOFIA EX Intracranial Support Catheter is indicated for general intravascular use, including the neuro and peripheral vasculature. The SOFIA EX Intracranial Support Catheter can be used to facilitate introduction of diagnostic agents or therapeutic devices. The SOFIA EX Intracranial Support Catheter is not intended for use in coronary arteries.

The SOFIA™ EX Intracranial Support Catheter is a single-lumen, flexible catheter equipped with coil and braid reinforcement. The distal segment is designed to facilitate vessel selection with 55-65cm of distal shaft hydrophilic coating for navigation through the vasculature. The radiopaque marker is located at the distal end of the catheter for visualization under fluoroscopy. The catheter is placed in a dispenser tube (HDPE) and is placed on a packaging card (polyethylene) that is provided in a sterile barrier Tyvek pouch and placed in a carton box.

Here's an analysis of the provided text regarding the acceptance criteria and study for the MicroVention, Inc. SOFIA EX Intracranial Support Catheter:

Summary of Acceptance Criteria and Device Performance for SOFIA EX Intracranial Support Catheter (K230775)

The provided document describes the SOFIA EX Intracranial Support Catheter as being substantially equivalent to its predicate device (SOFIA EX Intracranial Support Catheter, K182602). This means that the acceptance criteria and performance are largely benchmarked against the predicate device, implying similar performance expectations.

The document focuses on bench testing to demonstrate this equivalence.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state the sample sizes used for each specific bench test (e.g., number of catheters tested for simulated use, kink resistance, or particulate testing). The data provenance is bench testing, meaning it was conducted in a laboratory setting, not on patient data. No country of origin for the data is specified, but it can be assumed to be related to MicroVention, Inc.'s operations, likely within the US, given the FDA submission. The nature of the testing is prospective in the sense that new samples of the subject device were manufactured and tested according to a predefined protocol.

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

Not Applicable (N/A) for this submission. The ground truth for these bench tests is based on objective measurements and predefined engineering specifications, not expert interpretation of diagnostic data.

4. Adjudication Method for the Test Set

Not Applicable (N/A). Adjudication methods like 2+1 or 3+1 are typically used for clinical studies involving human interpretation or agreement on outcomes. Bench tests rely on precise measurements and adherence to specifications.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No. The document explicitly states: "No animal or clinical studies were conducted because bench testing was determined sufficient for verification and validation purposes." Therefore, no MRMC study was performed, and no human reader improvement effect size is available.

6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop)

Not Applicable (N/A). This device is a medical catheter, a physical product, not an AI algorithm. Therefore, the concept of "standalone algorithm performance" does not apply.

7. Type of Ground Truth Used

The ground truth for the bench tests is based on objective engineering measurements and predefined specifications. For example:

• Simulated Use/Lubricity: Successful navigation through a tortuous model, visual inspection for damage, and measurement of friction/lubricity metrics.
• Kink Resistance: Mechanical testing to observe and quantify resistance to kinking under specified bending conditions.
• Particulate Testing: Quantitative measurement of particle count and size using standard laboratory methods.
• Biocompatibility: Demonstrated through adherence to ISO 10993-1 standards, which were previously met by the predicate device (same materials, processing, sterilization).

8. Sample Size for the Training Set

Not Applicable (N/A). This is a medical device, not an AI/ML algorithm. There is no "training set" in the context of this submission. The device's design is based on engineering principles and validated through bench testing, not machine learning.

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

Not Applicable (N/A). As there is no training set for an AI/ML algorithm, this question does not apply.

Ask a specific question about this device

Rubicon Control Support Catheter is intended to facilitate placement and support of guidewires and other interventional devices within the peripheral vasculature and to allow for exchange of guidewires, and provide a conduit for the delivery of saline or contrast solutions.

The Rubicon™ Control Support Catheter is a sterile, single use, single lumen, over the wire (OTW) device designed for use in the peripheral vasculature. The catheter is designed to facilitate placement and support of guidewires and other interventional devices, to allow for exchange of guidewires and provide a conduit for the delivery of saline or contrast solutions. The shaft design is a tri-layer extrusion with a braided middle layer. There are three (3) radiopaque markerbands spaced equally along the distal most markerband is approximately 2 mm away from the distal end of the catheter tip to aid in positioning the system during the procedure. The distal 40 cm portion of the catheter is coated with a hydrophilic coating to aid device insertion through the guide sheath or guide catheter is available with a straight tip and an angled tip. The catheter is available in shaft lengths 65 cm, 90 cm, 135 cm, and 150 cm compatible with 0.014'' (0.356 mm), 0.018'' (0.457 mm), and 0.035'' (0.889 mm) guidewires. The 0.035' support catheter is compatible with 5Fr sheath; the 0.014" and 0.018" are compatible with 4Fr sheath.

There are no accessories supplied with the device.

The provided text describes the 510(k) summary for the Rubicon™ Control Support Catheter. This document focuses on demonstrating substantial equivalence to a predicate device, primarily through bench testing (mechanical and biocompatibility). It does not involve a study related to AI/algorithm performance, human-in-the-loop performance, or the analysis of medical images for diagnostic purposes.

Therefore, many of the requested criteria (e.g., acceptance criteria for AI performance, sample size for AI test sets, number of experts for ground truth, MRMC studies, standalone AI performance) are not applicable to this type of medical device submission.

Here's an analysis based on the information available:

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

The document does not provide a table with quantitative acceptance criteria and reported performance values for each mechanical test. It states that "Non-clinical performance evaluations support substantial equivalence," implying that the device met the internal acceptance criteria for these tests. The types of mechanical tests performed are listed under "Mechanical testing":

• Simulated use testing
• Catheter Bond Strength
• Catheter Body Burst Pressure
• Contrast Flow Rate
• Tip Pull Test
• Torque Strength
• Particulate Evaluation
• Coating Integrity
• Shelf Life and Packaging

For Biocompatibility, the document states the evaluation was conducted to ensure the device meets "recommended biocompatibility endpoints as outlined in ISO 10993-1," listing the following tests:

• Cytotoxicity
• Sensitization
• Irritation
• Systemic toxicity
• Hemolysis
• Pyrogen Testing

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

This information is not detailed in the provided summary. The tests performed are primarily bench tests on the physical device, not on clinical data. Therefore, concepts like country of origin or retrospective/prospective data provenance are not relevant here. The sample sizes for the mechanical and biocompatibility tests are not specified.

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)

This is not applicable. The "ground truth" for this device's performance is established through physical measurements and chemical analyses in a lab setting, not through expert radiology reads or similar clinical interpretations.

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

This is not applicable. Adjudication methods are relevant for subjective assessments, particularly in clinical image interpretations. For mechanical and biocompatibility testing, standard laboratory protocols and quantitative measurements are used.

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 is not applicable. An MRMC study is relevant for evaluating the impact of an AI system on human reader performance, typically in diagnostic imaging. This submission concerns a physical medical device (catheter) and its mechanical/biocompatibility performance, not an AI algorithm.

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

This is not applicable. There is no AI algorithm component being evaluated in this submission.

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

The "ground truth" for this device is based on physical and chemical measurements against established engineering and biocompatibility standards (e.g., ISO 10993-1). It's not derived from expert consensus, pathology, or outcomes data.

8. The sample size for the training set

This is not applicable. There is no "training set" as this is not an AI/machine learning model.

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

This is not applicable as there is no training set for an AI model.

Ask a specific question about this device

The Vericor Support Catheter is intended for use in small vessel or superselective anatomy for diagnostic and interventional procedures, including peripheral use.

The Vericor Support Catheter with hydrophilic coating is a braided, kink-resistant catheter designed to facilitate wire guide exchange, wire guide support and to provide a conduit for the delivery of saline solutions or diagnostic contrast agents. The Vericor Support Catheter will be available in three catheter lengths which are 90 cm, 135 cm and 150 cm. The proposed device is a single-lumen catheter. The hub of the catheter incorporates standard luer adapter to facilitate the attachment of accessories. The outer surface of the distal catheter has a hydrophilic coating. The catheter has three radiopaque markers at the distal end to facilitate fluoroscopic visualization. The device is provided in single use and sterile.

This document, a 510(k) Summary, describes the Vericor Support Catheter and its substantial equivalence to a predicate device. This is a medical device, not an AI/ML product, so the questions regarding AI/ML clinical studies are not applicable.

Here's the breakdown of the acceptance criteria and the study (non-clinical) that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA 510(k) Summary details numerous non-clinical tests. The column "Test Method Summary" indirectly describes the acceptance criteria by outlining what the test aims to demonstrate (e.g., "To demonstrate that the device meets the corrosion resistance"). The "Results and Conclusion" column reports that the device met these criteria.

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

The document does not explicitly state the sample sizes for each non-clinical test. It generally states that "Non clinical tests were conducted to verify that the proposed device met all design specifications." The data provenance is not applicable in terms of country of origin or retrospective/prospective for these non-clinical, laboratory-based tests. The tests were performed on the Vericor Support Catheter itself.

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

This is not applicable as the studies are non-clinical, laboratory-based performance tests, not studies involving human interpretation or clinical data. Ground truth in this context is established by adherence to specified standards and measurement techniques.

4. Adjudication Method for the Test Set

Not applicable. The tests are based on objective measurements and adherence to established standards, not expert adjudication of subjective interpretations.

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. This is a conventional medical device (support catheter), not an AI/ML diagnostic or assistive device.

6. If a Standalone (i.e. algorithm only without human-in-the loop performance) Was Done

Not applicable. This device does not involve an algorithm.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

For these non-clinical tests, the "ground truth" is defined by the objective criteria within the referenced international and national standards (e.g., ISO 10993, ISO 10555-1, ASTM standards, USP). Performance is measured against these established technical specifications and benchmarks.

8. The Sample Size for the Training Set

Not applicable. This is a physical medical device, not an AI/ML system that requires a training set.

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

Not applicable. This device does not involve a training set.

Ask a specific question about this device

The Houdini Cross Support Catheter is intended to be used in conjunction with a steerable guidewire to access discrete regions of the peripheral vasculature and for guidewire exchange.

The Houdini® Cross Support Catheter is a single use, bi-lumen intravascular catheter intended for percutaneous use. The Houdini® Cross Support Catheter is intended for use in the iliac. femoral, ilio-femoral and popliteal arteries. It is designed for use in conjunction with a standard commercially available off the shelf (OTS) 0.014" - 0.018" quidewire (not included) to gain access to locations within the cardiovascular system that are remote from the site of insertion. Once accessed, guidewires may be exchanged within the catheter. In addition, the Houdini® Cross Support Catheter provides the option of distal anchoring as well as physician-controlled extension of the inner shaft (up to 2 cm) to support the OTS guidewire during advancement.

The effective length of the Houdini® Cross Support Catheter is a nominal 100 cm. The inner lumen accommodates an OTS 0.014" - 0.018" spring-tipped guidewire. The inner lumen shaft allows for visualization under fluoroscopy due to the radiopague stainlesssteel design and additionally allows for continuous clinician control of the OTS guidewire for appropriate positioning.

If distal anchoring is desired, the Houdini® Cross Support Catheter requires the use of a commercially available OTS manual inflation device (not included). Once positioned within 2 cm of the user's target location, the catheter is inflated to 6 atm using diluted radiopaque contrast media to anchor the distal end of the catheter in the blood vessel. For additional support of the quidewire, the clinician may extend the location of the inner lumen shaft up to 2 cm distally without the need to reposition the anchoring balloon.

This document is a 510(k) Premarket Notification from the FDA for a medical device called the "Houdini Cross Support Catheter." It focuses on demonstrating the device's substantial equivalence to previously cleared predicate devices.

Based on the provided text, the document describes the acceptance criteria and study proving the device meets those criteria primarily through a comparison to a predicate device and extensive bench/simulated use testing, rather than a clinical study involving human patients or AI performance metrics.

Therefore, I will extract relevant information where available and state "Not Applicable" or "Information not provided in the document" for aspects that are typically found in studies for AI/diagnostic devices but not for a catheter's 510(k) submission focused on substantial equivalence.

Here's the breakdown of the information requested:

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

The document does not present explicit "acceptance criteria" in a quantitative, tabular format as one might find for a diagnostic or AI device's performance metrics (e.g., sensitivity, specificity thresholds). Instead, the acceptance is based on demonstrating "substantial equivalence" to a predicate device and satisfying functional and safety requirements through engineering bench testing and simulated use.

The "criteria" are implicitly tied to meeting the performance characteristics of the predicate device and established international standards (e.g., ISO 10555-1, ISO 10993-1). The "reported performance" is a general statement that the device "satisfies" these requirements.

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

• Sample Size for Test Set: The document does not specify a "test set" in terms of patient data or clinical images, as this is a 510(k) for a medical catheter based on engineering and simulated use testing. For bench testing, samples of the physical device were used, but the exact number of units tested for each specific test is not provided.
• Data Provenance: The data provenance is from laboratory bench testing and simulated use. No patient data (retrospective or prospective) from specific countries or populations is mentioned because a clinical study with patients was not required for this type of device and submission.

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 document pertains to a medical catheter, not a diagnostic device or AI algorithm requiring expert interpretation of medical images or patient data to establish ground truth. Ground truth for device performance is established through engineering specifications, validated test methods (e.g., ISO standards), and comparative performance with predicate devices.

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

• Not Applicable. As there is no clinical test set requiring expert interpretation for ground truth, there is no adjudication method described.

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. This document is for a medical catheter, not an AI algorithm or a diagnostic device that would involve human readers or AI assistance.

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

• Not Applicable. This is not an AI algorithm.

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

• The "ground truth" for the device's performance is established through:
  • Engineering Specifications: The device is designed to meet specific physical and performance parameters (e.g., diameter, length, pressure resistance, guide wire compatibility).
  • International Standards: Compliance with ISO standards (e.g., ISO 10555-1 for intravascular catheters, ISO 10993-1 for biocompatibility) where the "ground truth" is adherence to these established safety and performance benchmarks.
  • Predicate Device Performance: The predicate device serves as a benchmark for "ground truth" in terms of expected functionality and safety. The new device must demonstrate that its performance characteristics are substantially equivalent.

8. The sample size for the training set

• Not Applicable. This document does not describe the development of an AI algorithm thus there is no "training set" in the machine learning sense.

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

• Not Applicable. As there is no AI training set, this question is not applicable.

Ask a specific question about this device

The Boss Crossing Support Catheter (Boss CSC) is indicated to guide and support a guidewire during access of the peripheral vasculature, allow for wire exchanges and provide a conduit for the delivery of saline or diagnostic contrast agents.

The Boss Crossing Support Catheter (Boss CSC) is intended to guide and support a guidewire during access of the peripheral vasculature, allow for wire exchanges and provide a conduit for the delivery of saline or other diagnostic contrast agents. The proposed device is intended for single use and is provided sterile using Ethylene Oxide gas. The device consists of two low profile catheters, 2.4F and 3.9F, which are compatible with 0.018" and 0.035" guidewires, respectively. Both catheter shafts are composed of a high modulus thermoplastic material in a monolithic single layer construction. The proximal end of each catheter includes a standard catheter hub with Luer fitting and a strain relief. Like the predicate, Terumo NaviCross Support catheters, the distal end of the Boss CSC catheter is equipped with an RO marker band to enable visibility under fluoroscopy. There is a hydrophilic coating on the distal portion of each catheter shaft to enhance lubricity.

The 2.4Fand 3.9F catheters are packaged together in individual spiral HDPE hoops that are secured to a HDPE card and placed inside a Tyvek Mylar pouch. There are two versions of the device offered:

1. 3.9F/90cm length catheter packaged with a 2.4F/135cm length catheter
2. 3.9F/90cm length catheter packaged with a 2.4F /150cm length catheter

As stated, the 2.4F and 3.9F catheters are packaged together. Each catheter is individually inserted into a spiral HDPE protective hoop which is then secured to an HDPE backer card. The two catheter hoops and backer card are inserted into a Tyvek/Mylar pouch that is then placed into a cardboard outer shelf box. Five (5) individual pouches are then placed in a cardboard shelf box.

The provided text describes a medical device, the Boss Crossing Support Catheter (Boss CSC), and the testing conducted to support its substantial equivalence to predicate devices. However, it does not include the specific details you've requested regarding acceptance criteria and a study that proves the device meets those criteria in the context of AI/ML performance.

The document discusses various bench tests and biocompatibility tests to demonstrate the device's physical performance, material safety, and sterility. These tests are conducted to ensure the device performs as intended and is safe for use, but they are not related to the performance of an AI/ML diagnostic or assistive device that would have metrics like sensitivity, specificity, or reader improvement.

Below is a breakdown of why this document cannot provide the information you're looking for, and where such information would typically be found for an AI/ML device:

Reason for lack of requested information:

This 510(k) submission is for a physical medical device (a catheter), not an AI/ML-driven diagnostic or assistive technology. Therefore, the concepts of "acceptance criteria" as you've defined them (e.g., sensitivity, specificity, human reader improvement), "test set sample size," "ground truth establishment," or "multi-reader multi-case studies" are not applicable to this particular submission.

What is included (and would be equivalent for a physical device):

• Acceptance Criteria & Reported Performance: The document lists various performance tests (e.g., Kink Resistance, Tensile Strength, Flow Rate, Leak Test, Hydrophilic Coating Integrity, etc.). For each of these, the "acceptance criteria" would be defined in the test protocols (e.g., "no kinks observed under X force," "tensile strength > Y N," "flow rate within Z ml/min"). The "reported device performance" would be the actual measured values from these bench tests. The document states "The Boss CSC catheters submitted in this 510(k) have demonstrated similar performance characteristics to the predicate devices" and "The performance of the Boss CSC Catheters demonstrates substantial equivalence to the performance of the predicate devices," implying these criteria were met.
• Sample Size for Test Set: For physical devices, this would refer to the number of catheters tested for each performance characteristic. The document doesn't specify the exact number of devices tested for each bench test, but it notes "Testing was performed on aged and non-aged Boss CSC catheters."
• Data Provenance: Not applicable in the AI/ML sense. Data comes from bench testing of the manufactured device.
• Experts / Ground Truth: Not applicable for physical device performance. The "ground truth" is the physical measurement itself. For example, a "kink" is a directly observable physical event.
• Adjudication Method: Not applicable.
• MRMC Study: Not applicable.
• Standalone Performance: The "standalone" performance for a physical device refers to its ability to meet its functional specifications directly, which is what the bench tests evaluate.
• Type of Ground Truth: Direct physical measurements and observations from bench testing.
• Sample Size for Training Set: Not applicable (no AI/ML model to train).
• How Ground Truth for Training Set was Established: Not applicable.

Hypothetical Example (if this were an AI/ML device):

If the Boss Crossing Support Catheter were, for instance, an AI-powered system designed to detect potential anatomical blockages during catheter insertion by analyzing real-time imaging, the requested information would look something like this:

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

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

• Sample Size: 500 patient cases (250 with blockages, 250 without), comprising 1500 image frames.
• Data Provenance: A multi-center retrospective dataset collected from hospitals in the United States (70%), Germany (20%), and Japan (10%).

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

• Number of Experts: 3
• Qualifications:
  • Expert 1: Interventional Radiologist, 15 years experience in peripheral vascular interventions, board certified.
  • Expert 2: Vascular Surgeon, 12 years experience, specializes in complex peripheral revascularization.
  • Expert 3: Interventional Cardiologist, 10 years experience, with a focus on peripheral artery disease.

4. Adjudication method for the test set

• Adjudication Method: 2+1 (Two experts independently reviewed each case. If they agreed, that was the ground truth. If they disagreed, a third senior expert was brought in to make the final decision).

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

• MRMC Study Done: Yes
• Effect Size: Average increase of 0.07 in ROC AUC (from 0.81 without AI to 0.88 with AI assistance) across all readers for detecting blockages, and a 15% reduction in reading time without compromising accuracy.

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

• Standalone Performance Done: Yes, as reported in the table above (Sensitivity 92.5%, Specificity 84.1%).

7. The type of ground truth used

• Type of Ground Truth: Expert Consensus (adjudicated by 3 experts based on angiographic images and clinical reports).

8. The sample size for the training set

• Training Set Sample Size: 10,000 patient cases (approximately 30,000 image frames).

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

• Ground Truth for Training Set: Established by a team of 5 clinical residents and 2 junior interventional radiologists, with periodic audits and quality checks performed by a senior interventional radiologist. Cases flagged for ambiguity were escalated for consensus review by senior staff. Pathology reports and outcomes data were sometimes used as secondary confirmation where available for specific types of blockages.

Ask a specific question about this device

The XO Cross Coronary is a support catheter intended to guide and support a guidewire during access of the peripheral or coronary vasculature, allow for wire exchanges and provide a conduit for the delivery of saline solutions or diagnostic contrast agents.

The XO Cross Coronary Support Catheter is a single-lumen support catheter designed to support a guidewire during access of the peripheral or coronary vasculature, allowing for exchange of guidewires during vascular access procedures, and providing a conduit for the delivery of saline solutions or diagnostic contrast agents. The shaft and tip are both radiopaque to track the location of the XO Cross Coronary Support Catheter within the vasculature, while under fluoroscopy. The distal end of the subject catheter is also coated with a hydrophilic coating to reduce surface friction. It is available in various lengths (90cm, 135cm, 175cm), with a diameter of 2 Fr (0.7 mm) and with a tapered polymer tip at its distal end.

The provided text describes a medical device, the XO Cross Coronary Support Catheter, and its 510(k) submission to the FDA for substantial equivalence. However, the document does not contain information about:

• Acceptance criteria for an AI/ML powered device. The device described is a physical catheter, not an AI/ML software.
• A study proving the device meets AI/ML specific acceptance criteria.
• Sample size for test sets or data provenance (these are relevant for AI/ML validation).
• Number of experts or their qualifications for ground truth.
• Adjudication methods.
• Multi-Reader Multi-Case (MRMC) comparative effectiveness studies.
• Stand-alone performance of an algorithm.
• Types of ground truth used (e.g., pathology, outcomes data).
• Sample size for training sets.
• How ground truth for training sets was established.

The document details the following for the physical catheter device:

Device Performance and Testing:

The document focuses on demonstrating substantial equivalence to a predicate device (Quick Cross Extreme Support Catheter, K092396) and a reference device (XO Cross Support Catheter, K210322). The "performance" assessment is based on functional and safety testing of the catheter, not on specific output metrics typically associated with AI/ML systems (like accuracy, sensitivity, specificity, etc.).

Biocompatibility Testing:

• Tests performed and passed: Cytotoxicity, Sensitization, Intracutaneous Reactivity, Acute Systemic Toxicity, Material Mediated Pyrogenicity, Bacterial Endotoxin LAL, Hemolysis, Complement Activation, Partial Thromboplastin Time (PTT), Blood Platelet and Leukocyte Count.
• Method: In accordance with the 2020 FDA guidance document "Use of International Standard ISO 10993-1" for an external communicating device with limited exposure (≤ 24hrs) to circulating blood. The device used the same materials and processes as the reference device, with an additional assessment for a new black polymer outer layer.

Design Verification (Performance Bench Testing):

• Tests performed or fulfilled: Tip ID Testing, Tip Tensile Testing, Distal Shaft Kink Testing, Simulated Use.
• Purpose: To ensure the catheter met applicable design and performance requirements throughout its shelf life, verify conformity to applicable standards, and demonstrate substantial equivalence.

Comparative Analysis (Substantial Equivalence):

The document presents a comparison (Table 2) between the subject device, the predicate device, and the reference device across various attributes like:

• Intended Use
• Indications for Use
• Classification Name
• Single Use
• Fundamental Scientific Technology
• Prescription (Rx Only)
• Anatomical Access
• Design
• Effective Length (cm)
• Distal Tip/Crossing Profile
• Shaft Outer Diameter
• Visibility
• Guidewire Compatibility
• Sheath / Introducer Compatibility
• Max Infusion Pressure
• Sterility
• Biocompatibility

Conclusion:

The submission concludes that the XO Cross Coronary Support Catheter is substantially equivalent in safety and effectiveness to the legally marketed predicate and reference devices. The minor design differences (longer tapered tip, modified strain relief, outer polymer layer color change, minimum kink specifications, minimum tip ID and tensile specifications) were assessed and determined to "raise no additional or different questions of safety or effectiveness."

In summary, the provided document is a 510(k) clearance letter and summary for a physical medical device (catheter), not an AI/ML-powered device. Therefore, it does not contain the specific information requested regarding AI/ML acceptance criteria and validation studies.

Ask a specific question about this device

The Bio-Medicus Life Support catheters and introducers are single-lumen drainage or reinfusion peripheral-access catheters to be used in ECMO or ECLS with an extracorporeal circuit intended for use in adult and pediatric 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 Bio-Medicus Life Support™ catheter is a single-lumen catheter used to drain or reinfuse blood. The introducer facilitates proper insertion and placement of the appropriately sized catheter over a guidewire within the vessel. These devices are intended to perfuse vessels or organs in conjunction with extracorporeal support, including Extracorporeal Membrane Oxygenation (ECMO) and Extracorporeal Life Support (ECLS). Catheter models with tip lengths of 18 cm (7.09 in), 50 cm (19.7 in), or 55 cm (21.7 in), with and without additional side holes may be used as either drainage or reinfusion catheters.

These devices are sterile, nonpyrogenic, disposable, intended for single use only. Bench studies were performed after device preconditioning including exposure (21 days) to simulated in vivo use conditions to demonstrate safety and reliability. Do not store the product above 25°C (77°F).

The provided document is a 510(k) summary for the Medtronic Bio-Medicus Life Support Catheter and Introducer. It describes a medical device, specifically a catheter and introducer for use in ECMO/ECLS, and assesses its substantial equivalence to a predicate device.

Crucially, this document is for a medical device (catheter and introducer), not an AI/ML device or a software device. Therefore, the standard acceptance criteria and study designs typically associated with AI/ML devices (e.g., standalone performance, MRMC studies, expert ground truth for image analysis, etc.) are not applicable to this submission.

The "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this context refer to the performance tests and regulatory requirements for a physical medical device. They are focused on mechanical properties, biocompatibility, sterility, shelf-life, and in vivo performance in an animal model, rather than AI/ML model performance metrics like accuracy, sensitivity, or specificity.

Therefore, I cannot populate the requested table and answer the questions in the context of an AI/ML device. The document does not contain information on:

• A table of acceptance criteria and reported device performance related to AI/ML metrics.
• Sample size for a "test set" or "training set" in the AI/ML sense.
• Number of experts for ground truth or adjudication methods for an AI/ML model.
• MRMC studies or effect sizes for human readers with/without AI assistance.
• Standalone algorithm performance.
• Type of ground truth (expert consensus, pathology, outcomes data) for an AI/ML context.
• How ground truth for a training set was established for an AI/ML model.

What the document does provide relevant to device acceptance is:

• Acceptance Criteria (Special Controls for the device type): These are outlined under "Comparison to Predicate (Special Controls)" on page 5 and include:
  • Technological Characteristics (geometry, design, compatibility)
  • Biocompatibility (ISO 10993-1:2009 compliance)
  • Sterility and Shelf-life (demonstrates sterility, integrity, durability, reliability)
  • Non-clinical Performance (bench, mechanical integrity, durability, reliability testing)
  • In vivo Evaluation (performance over 7-day duration of use)
  • Labeling (detailed summary of non-clinical and in vivo evaluations, instructions, compatibility, maintenance)
• Study Proving Device Meets Criteria (Summary of Performance Data): This is detailed on pages 5-6 under "Summary of Performance Data" and includes:
  • Pre-clinical bench testing: Used to verify performance characteristics.
    • 21-day Simulated use durability testing (Tensile strength after life conditioning, Pressure test after life conditioning)
    • Blood trauma testing
    • Kink testing
    • Birds Mouth testing
    • ID occlusion due to suture ring
    • Suture Collar Slide Force
    • Introducer removal and insertion forces
  • In vivo animal testing: 7-day GLP in vivo study.

In conclusion, the requested information pertains to AI/ML device validation, which is not the subject of this 510(k) submission. This document describes the testing and regulatory compliance for a physical medical device.

Ask a specific question about this device