Search Results

The Merci Retriever is intended to restore blood flow in the neurovasculature by removing thrombus in patients experiencing ischemic stroke. Patients who are ineligible for treatment with intravenous tissue plasminogen activator (IV t-PA) or who fail IV t-PA therapy are candidates for treatment. The Merci Retriever is also indicated for use in the retrieval of foreign bodies misplaced during interventional radiological procedures in the neuro, peripheral and coronary vasculature.

Like the predicate devices, the design of the modified Merci Retrievers consists of a flexible, tapered Nitinol core wire. This distal end is shaped into a helix and a platinum coil is threaded over and attached to the distal end. Polymer filaments are attached to the distal end. The core wire proximal to the helix is coated with a hydrophilic coating. A torque device is provided with Retriever to facilitate manipulation. An insertion tool is provided with Retriever to introduce Retriever into Microcather during the procedure. Merci Retrievers with "DOC" Compatible" shown on product label are compatible with the Abbott Vascular DOC® Guide Wire Extension.

This 510(k) premarket notification for the Merci Retriever focuses on a device modification and does not include a study describing acceptance criteria and device performance in the way a clinical trial or performance study for a new diagnostic or prognostic device typically would.

The document indicates that the device modification is for the Merci Retriever, which is an endovascular thrombus retriever. The modified device's intended use and materials are the same as the predicate devices. The substantial equivalence determination is based on the modified device having the same intended use and materials as previously cleared devices. Therefore, the information typically requested about acceptance criteria and study design for proving performance is not present in this type of submission.

Here's an breakdown of the requested information, indicating why it's not applicable or present in this specific 510(k) submission:

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

Not applicable/provided. This 510(k) is for a device modification, relying on substantial equivalence to predicate devices for its safety and effectiveness. It does not present new performance data against specific acceptance criteria for a novel device. The "performance" is implicitly considered equivalent to the predicate devices.

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

Not applicable/provided. No new clinical or performance study involving a test set is detailed in this 510(k) for the modified device.

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/provided. There is no new test set or ground truth establishment described for this device modification.

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

Not applicable/provided. No new test set or adjudication process is 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/provided. This device is a mechanical thrombus retriever, not an AI-assisted diagnostic or prognostic tool for human readers.

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

Not applicable/provided. This device is a mechanical thrombus retriever, not a standalone algorithm.

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

Not applicable/provided. No new ground truth is established for this device modification.

8. The sample size for the training set

Not applicable/provided. This is a mechanical device, not a machine learning model, so there is no "training set."

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

Not applicable/provided. Not applicable as this is not a machine learning model.

Summary:

This 510(k) submission (K090085) for the Merci Retriever is a "Special 510(k): Device Modification." Such submissions typically demonstrate substantial equivalence to a predicate device based on design, materials, and intended use remaining largely the same, or minor changes not affecting safety or effectiveness. They do not usually include new clinical studies or elaborate performance data as would be found for an entirely new device or one requiring significant performance validation. The FDA's substantial equivalence determination ("We have reviewed your Section 510(k) premarket notification... and have determined the device is substantially equivalent...") confirms this approach.

Ask a specific question about this device

The Merci® Retriever is intended to restore blood flow in the neurovasculature by removing thrombus in patients experiencing ischemic stroke. Patients who are ineligible for treatment with intravenous tissue plasminogen activator (IV t-PA) or who fail IV t-PA therapy are candidates for treatment. The Merci Retriever is also indicated for use in the retrieval of foreign bodies misplaced during interventional radiological procedures in the neuro, peripheral and coronary vasculature.

Like the predicate device, the design of the modified Merci Retriever consists of a flexible, tapered Nitinol core wire. This distal end is shaped into a helix and a platinum coil is threaded over and attached to the distal end. Polymer filaments are attached to the distal end. The core wire proximal to the helix is coated with a hydrophilic coating. A torque device is provided with Retriever to facilitate manipulation. An insertion tool is provided with Retriever to introduce Retriever into Microcatheter during the procedure.

The provided text describes a 510(k) submission for a modified Merci Retriever, a medical device used for removing thrombus in ischemic stroke patients and retrieving foreign bodies. However, this document primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a performance study with detailed acceptance criteria and supporting data as one would expect for a novel device or a clinical trial.

Therefore, many of the requested sections (acceptance criteria, specific study details, ground truth, expert involvement, MRMC study, sample sizes for training/test sets) cannot be extracted from the provided text because the document does not contain this type of performance study. The core of this submission is a "Testing Summary" stating that "Results of design verification and validation testing performed on the modified Merci Retriever confirm that the device conforms to the required specifications and establish substantial equivalence to the predicate device." This suggests that the evaluation was likely focused on engineering specifications and direct comparison to a previously cleared device, not a clinical performance study with defined acceptance criteria for metrics like sensitivity, specificity, etc.

Here's a breakdown of what can and cannot be provided based on the input:

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

• Explanation: The document does not specify quantitative acceptance criteria for device performance (e.g., successful clot retrieval rates, recanalization rates) or present data from a clinical study to demonstrate such performance. The submission aims to establish substantial equivalence based on design verification and validation testing, not a clinical outcome study against predetermined performance metrics.

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: Not applicable / Not available. The document refers to "design verification and validation testing," which typically involves bench testing, material testing, and potentially animal studies, rather than human clinical trials with a "test set" in the context of AI or diagnostic device performance evaluation.
• Data Provenance: Not applicable / Not available. No clinical data or human subject data is described.

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 / Not available. The concept of "ground truth" established by experts for a test set is relevant to studies evaluating diagnostic accuracy or AI performance. This document does not describe such a study.

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

• Not applicable / Not available. Adjudication methods are used to establish ground truth in studies involving human interpretation or clinical endpoints. This information is not present.

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 study was not done. This device is an endovascular retriever, 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. This device is a physical medical instrument, not a software algorithm.

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

• Not applicable / Not available. The document describes a physical medical device and its substantial equivalence to a predicate device, focusing on engineering and material specifications rather than clinical outcomes with a defined "ground truth."

8. The sample size for the training set

• Not applicable / Not available. There is no mention of a "training set" as this is not an AI/machine learning device.

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

• Not applicable / Not available. There is no mention of a "training set" or "ground truth" in the context of device performance in the provided document.

Summary of what the document does state regarding acceptance/testing:

The submission focuses on "substantial equivalence" to a predicate device (Merci® Retriever, K081305). The "Testing Summary" on page 1 states:

"Results of design verification and validation testing performed on the modified Merci Retriever confirm that the device conforms to the required specifications and establish substantial equivalence to the predicate device."

And then explicitly lists:

"The modified Merci Retriever is substantially equivalent to the predicate device with regard to intended use, operating principal, design concept, materials, shelf life, packaging and sterilization processes."

This indicates that the "acceptance criteria" were met by demonstrating that the modified device's specifications (design, materials, functionality) were sufficiently similar to the predicate device, or met internal engineering requirements, to justify an equivalence claim rather than requiring new clinical performance data against specific endpoints.

Ask a specific question about this device

The Merci® Retriever is intended to restore blood flow in the neurovasculature by removing thrombus in patients experiencing ischemic stroke. Patients who are ineligible for treatment with intravenous tissue plasminogen activator (IV t-PA) or who fail IV t-PA therapy are candidates for treatment. The Merci Retriever is also indicated for use in the retrieval of foreign bodies misplaced during interventional radiological procedures in the neuro, peripheral and coronary vasculature.

Like the predicate device, the design of the modified Merci Retriever consists of a flexible, tapered Nitinol core wire. This distal end is shaped into a helix and a platinum coil is threaded over and attached to the distal end. Polymer filiaments are attached to the distal end. The core wire proximal to the helix is coated with a fordrophilic coating. A torque device is provided with Retriever to facilitate manipulation. An insertion tool is provided with Retriever to introduce Retriever into Microcatheter during the procedure.

I am sorry, but the provided text does not contain information about acceptance criteria and the results of a study as you requested. The document describes a 510(k) submission for a modified Merci Retriever device, focusing on its substantial equivalence to a predicate device. It briefly mentions "design verification and validation testing" confirming conformity to "required specifications," but it does not detail these specifications as acceptance criteria or present specific outcomes of a study that would demonstrate the device meets them.

Therefore, I cannot populate the table or provide answers to the specific questions regarding acceptance criteria, study details, sample sizes, expert qualifications, or ground truth establishment.

Ask a specific question about this device

The Modified Merci Retriever is intended to restore blood flow in the neurovasculature by removing thrombus in patients experiencing ischemic stroke. Patients who are ineligible for treatment with intravenous tissue plasminogen activator (IV t-PA) or who fail TV t-PA therapy are candidates for treatment. The Modified Merci Retriever is also indicated for use in the retrieval of foreign bodies misplaced during interventional radiological procedures in the neuro, peripheral and coronary vasculature.

Like the predicate device, the Modified Merci Retriever consists of a flexible, Nitinol core wire with shaped loops at the distal end. A radiopaque coil covers the tip allowing visualization under fluoroscopy.

The Retriever is placed distal to the thrombus or foreign body through a microcatheter. The Retriever and microcatheter are pulled back to engage the thrombus or foreign body in the loops of the Retriever. The Retriever, the thrombus or foreign body, and the microcatheter are then removed from the body.

The provided text describes a 510(k) premarket notification for the "Modified Merci Retriever" device. However, it does not contain any information about acceptance criteria, device performance metrics, or a study proving the device meets specific criteria.

The document states:

• "All devices met the required specifications for the completed tests." within the "Testing Summary" section.
• "The Modified Merci Retriever is substantially equivalent to the predicate device. The indications for use, function, and materials used are equivalent." in the "Summary of Substantial Equivalence" section.

This indicates that internal testing was performed, and the device met its internal specifications. However, the document does not provide details about what those specifications (acceptance criteria) were, what the "reported device performance" was, or the methodology of any studies conducted to demonstrate this.

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance, nor can I provide details about sample sizes, ground truth establishment, expert qualifications, adjudication methods, or comparative effectiveness studies, as this information is not present in the provided text.

The 510(k) summary focuses on establishing substantial equivalence to a predicate device (Merci Retriever) based on similar indications for use, function, and materials. It does not include a detailed scientific study report with the specific information you are requesting.

Ask a specific question about this device

The Merci® Retriever is intended to restore blood flow in the neurovasculature by removing thrombus in patients experiencing ischemic stroke. Patients who are ineligible for intravenous tissue plasminogen activator (IV t-PA) or who fail IV t-PA therapy are candidates for treatment. The Merci® Retriever is also indicated for use in the retrieval of foreign bodies misplaced during interventional radiological procedures in the neuro, peripheral and coronary vasculature.

Like the predicate devices, the modified Merci Retriever consists of a flexible, Nitinol core wire with shaped loops at the distal end. A radiopaque coil covers the tip allowing visualization under fluoroscopy.

The Retriever is placed distal to the thrombus or foreign body through a microcatheter. The Retriever and microcatheter are pulled back to engage the thrombus or foreign body in the loops of the Retriever. The Retriever, the thrombus or foreign body, and the microcatheter are then removed from the body.

The provided documents describe a 510(k) submission for a modified Merci Retriever, a device used to remove thrombus in ischemic stroke patients and retrieve foreign bodies. However, this submission focuses on demonstrating substantial equivalence to predicate devices rather than a study proving the device meets specific acceptance criteria based on performance metrics.

Here's a breakdown based on the information provided and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

• Indications for Use
• Function
• Materials used | "The modified Merci Retriever is equivalent to the predicate devices. The indications for use, function, and materials used are substantially equivalent." | This is the primary "acceptance criterion" for a 510(k) submission, not performance metrics. No specific quantitative performance criteria (e.g., success rates, complication rates) are provided. |
  | Material Suitability | "All materials used... are suitable for the intended use." | "All materials used in the manufacture of the Retriever are suitable for the intended use of the device and have been used in numerous previously cleared products." | This is a qualitative statement, not a specific, measurable criterion with associated performance data. |
  | Required Specifications (General) | Met required specifications for completed tests. | "All devices met the required specifications for the completed tests." | This is a general statement. The specific tests and their required specifications are not detailed in the provided text. It likely refers to bench testing (e.g., mechanical, biocompatibility) rather than clinical performance. |

Missing Information:

• Specific, quantitative performance-based acceptance criteria (e.g., a target success rate for thrombus retrieval, a maximum allowable device-related complication rate, specific mechanical test thresholds).
• Detailed results of the "completed tests" that led to the statement "All devices met the required specifications."

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

This information is not provided in the given text.

• Sample Size: No information on the number of patients or cases used for any clinical testing. The submission focuses on substantial equivalence based on device characteristics rather than new clinical data from a dedicated test set.
• Data Provenance: Not mentioned.

3. Number of Experts Used to Establish Ground Truth and Qualifications

This information is not provided. As no clinical or imaging study data is presented, there's no mention of ground truth establishment by experts.

4. Adjudication Method

This information is not provided.

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

This information is not provided. The submission does not describe a clinical study comparing human readers with and without AI assistance. This device is a physical medical device (retriever), not an AI diagnostic tool.

6. Standalone (Algorithm Only) Performance Study

This information is not applicable/not provided. The Merci Retriever is a physical medical device, not an algorithm, so a standalone algorithm performance study is not relevant.

7. Type of Ground Truth Used

This information is not provided. If bench testing was performed, the "ground truth" would be the engineering specifications. For clinical performance, it would typically be clinical outcomes or expert adjudication, but no such data is presented.

8. Sample Size for the Training Set

This information is not applicable/not provided. This is a physical device, not a machine learning algorithm, so there is no "training set."

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

This information is not applicable/not provided.

Summary of the Study Discussed (510(k) Submission):

The provided documents describe a 510(k) Premarket Notification for a modification to the Merci® Retriever. The "study" described is essentially the documentation and rationale presented to the FDA to demonstrate substantial equivalence to previously cleared predicate devices (Merci® Retriever K033736 and Modified Merci® Retriever K061059).

• Purpose of the "Study": To demonstrate that the modified Merci® Retriever is as safe and effective as existing legally marketed predicate devices, mainly by showing that its indications for use, function, and materials are substantially equivalent.
• Key Findings: The submission states that the modified device is substantially equivalent, and that "All materials used in the manufacture of the Retriever are suitable for the intended use of the device and have been used in numerous previously cleared products" and "All devices met the required specifications for the completed tests."
• Nature of the Evidence: The evidence primarily comprises:
  • Comparison of design features and materials to predicate devices.
  • Statements regarding the suitability of materials.
  • A general statement that "all devices met the required specifications for the completed tests" (likely referring to bench testing, but details are not provided).
• Clinical Data: No new clinical trial data, human subject testing, or expert reviews of clinical outcomes are detailed in the provided text for this specific 510(k) modification. This type of submission often relies on a comparison to predicate devices, and sometimes existing clinical data for the predicate device, rather than new, extensive clinical studies for minor modifications.

Ask a specific question about this device

The Modified Merci Retriever is intended to restore blood flow in the neurovasculature by removing thrombus in patients experiencing an ischemic stroke. Patients who are ineligible for treatment with intravenous tissue plasminogen activator (IV t-PA) or who fail IV t-PA therapy are candidates for treatment. The Modified Merci Retriever is also indicated for use in the retrieval of foreign bodies misplaced during interventional radiological procedures in the neuro, peripheral and coronary vascular systems.

Like the predicate device, the Modified Merci Retriever consists of a flexible, Nitinol core wire with shaped distal loops covered by a platinum coil for radiopacity. It is coated with a hydrophilic lubricious coating.

Both the Modified Merci Retriever and the predicate device are placed distal to the thrombus or foreign body using a microcatheter which is retracted to deploy the loops of the Retriever. The Retriever and microcatheter are pulled back into the thrombus or foreign body, engaging it in the loops of the Retriever. The Retriever, the thrombus or foreign body, and the microcatheter are then removed from the body.

The provided text is a 510(k) summary for the Modified Merci® Retriever. It details the device's description, intended use, and its substantial equivalence to a predicate device. However, it does not include information about specific acceptance criteria or the details of a study that proves the device meets such criteria in terms of performance metrics like sensitivity, specificity, or outcomes.

This document focuses on demonstrating substantial equivalence to a previously cleared device (Merci® Retriever X6) through materials and testing methods. It states: "The Modified Merci Retriever was tested in the same manner as the predicate device. All devices met the required specifications for the completed tests." This implies that the 'acceptance criteria' were likely internal engineering specifications for the device's physical properties and function, rather than clinical performance metrics in a study.

Therefore, most of the information requested in your prompt cannot be extracted from this document, as it pertains to clinical study design and performance evaluation, which is not present here.

Here's what can be answered based on the provided text, and what cannot:

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

• Cannot be provided. The document does not explicitly list acceptance criteria (e.g., target thrombus removal rates, recanalization success, complication rates) or reported performance metrics in a clinical context. It only states that all devices "met the required specifications for the completed tests," which refers to product-level engineering tests, not clinical performance.

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

• Cannot be provided. A clinical "test set" and its provenance are not mentioned.

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):

• Cannot be provided. This information would be relevant to a clinical study, which is not detailed in this submission.

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

• Cannot be provided. This is relevant to a clinical study.

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:

• Cannot be provided. This device is an endovascular retriever, not an AI-powered diagnostic or assistive tool for human readers. Therefore, an MRMC study related to AI assistance is not applicable.

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

• Cannot be provided. This device is a physical medical instrument, not a standalone algorithm.

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

• Cannot be provided. Ground truth is a concept for evaluating diagnostic or imaging systems against a definitive reference. This document for a physical medical device does not discuss such ground truth in relation to performance.

8. The sample size for the training set:

• Cannot be provided. This would be relevant for an AI/machine learning model, which this device is not.

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

• Cannot be provided. Not applicable to this type of device submission.

Summary of what is available from the text relevant to testing:

• Testing Approach: The Modified Merci® Retriever was tested "in the same manner as the predicate device."
• Outcome of Tests: "All devices met the required specifications for the completed tests."
• Quality System: The device was designed under the Concentric Quality System, which complies with 21CFR8820.30.

This submission relies on demonstrating "substantial equivalence" to a predicate device (Merci® Retriever X6), implying that if the new device performs comparably in engineering design and materials, and meets similar specifications, it is considered safe and effective for similar indications. The document does not contain the level of detailed clinical study data often found for new devices or AI/diagnostic tools.

Ask a specific question about this device

The Modified Merci® Retriever is intended to restore blood flow in the neurovasculature by removing thrombus in patients experiencing ischemic stroke. Patients who are ineligible for intravenous tissue plasminogen activator (IV t-PA) or who fail IV t-PA therapy are candidates for treatment. The Modified Merci® Retriever is also indicated for use in the retrieval of foreign bodies misplaced during interventional radiological procedures in the neuro, peripheral and coronary vasculature.

Like the predicate device, the Modified Merci Retriever consists of a flexible, Nitinol core wire with shaped loops at the distal end. A radiopaque coil covers the tip allowing visualization under fluoroscopy.

Both the predicate Retriever and the Modified Merci Retriever are placed distal to the thrombus or foreign body using a microcatheter which is retracted to deploy the loops of the Retriever. The Retriever and microcatheter are pulled back into the thrombus or foreign body, engaging it in the loops of the Retriever. The Retriever, the thrombus or foreign body, and the microcather are then removed from the body.

This document is a 510(k) summary for the Concentric Medical, Inc. Modified Merci Retriever. It aims to demonstrate substantial equivalence to the predicate device, the Merci® Retriever X6, rather than proving the device meets specific acceptance criteria through a clinical study. Therefore, most of the requested information regarding study design, sample sizes, expert involvement, and ground truth establishment is not present in this document.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not provide a table of specific, quantifiable acceptance criteria or reported device performance in the context of typical clinical study results (e.g., sensitivity, specificity, accuracy, workflow time, etc.). Instead, it states that the device was tested and found to meet "required specifications."

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

• Sample Size: Not specified. The document indicates "All devices" were tested, implying all manufactured units or a representative sample from a production lot were subjected to engineering/performance tests, but no test set in the context of clinical data is mentioned.
• Data Provenance: Not applicable. The testing described appears to be engineering and design verification, not clinical data from patients or a specific geographical region.

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

• Not applicable. The document describes product testing (design verification, material suitability) rather than a study requiring expert-established ground truth for clinical cases.

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

• Not applicable. There is no mention of clinical data or adjudication processes.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No. This is a 510(k) submission for a medical device (thrombus retriever), not an AI diagnostic tool. Therefore, an MRMC study related to AI performance is not relevant or included.

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 consensus, pathology, outcomes data, etc.):

• Not explicitly stated for clinical ground truth. For the engineering tests, the "ground truth" would be the predefined specifications and performance metrics for the device (e.g., tensile strength, flexibility, material composition, deployment mechanism integrity), which are internally established by the manufacturer and often align with industry standards or recognized test methods.

8. The sample size for the training set:

• Not applicable. There is no mention of a "training set" as this is not a machine learning or AI product.

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

• Not applicable for the same reason as above.

Summary of the Study (as described):

The "study" described in the document is a design verification and validation process for the Modified Merci Retriever. It is a comparison to a predicate device (Merci® Retriever X6) to establish substantial equivalence.

• Study Type: Design verification and validation.
• Objective: To demonstrate that the Modified Merci Retriever is substantially equivalent to the predicate device (Merci® Retriever X6) in terms of indications for use, function, materials, and safety/performance.
• Methodology: The device underwent "the same manner" of testing as the predicate device. This implies a series of internal engineering and performance tests (e.g., mechanical tests, material compatibility tests, deployment tests in a simulated environment) to ensure the device meets its design specifications and performs comparably to the predicate.
• Conclusion: The manufacturer concluded that "All devices met the required specifications for the completed tests" and that the Modified Merci Retriever is "substantially equivalent" to the predicate device.

This 510(k) summary focuses on demonstrating that the new device does not raise new questions of safety or effectiveness compared to a previously cleared device, which is the standard for 510(k) submissions. It does not provide detailed clinical trial data or performance metrics from a large patient cohort, as would be expected for a novel device or an AI clinical decision support tool.

Ask a specific question about this device

The Merci Retriever is intended to restore blood flow in the neurovasculature by removing thrombus in patients experiencing ischemic stroke. Patients who are ineligible for treatment with intravenous tissue plasminogen activator (IV t-PA) or who fail IV t-PA therapy are candidates for treatment. The Merci Retriever is also indicated for use in the retrieval of foreign bodies misplaced during interventional radiological procedures in the neuro, peripheral and coronary vasculature.

The Merci Retriever consists of a Nitinol tapered wire with a helical shaped distal tip. A platinum coil is attached over the helical distal tip. A radiopaque distal coil facilitates fluoroscopic visualization.

This document describes the 510(k) premarket notification for the Concentric Merci® Retriever Models X5 and X6. The information provided is directly from the submitted summary and FDA clearance letter.

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes the predicate device equivalence and testing, but does not explicitly state specific quantitative acceptance criteria or detailed performance metrics against those criteria. It uses language indicating that the device "met the required specifications" and that "no new issues of safety and effectiveness exist."

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

• Sample Size: The document mentions a "MERCI Clinical Study" but does not specify the sample size for this study.
• Data Provenance: The document does not explicitly state the country of origin or whether the study was retrospective or prospective. Clinical studies for medical devices typically involve prospective data collection, but this is not confirmed here.

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

The document does not provide information regarding the number of experts used or their qualifications for establishing ground truth within the MERCI Clinical Study.

4. Adjudication Method for the Test Set

The document does not specify any adjudication method used for the test set in the MERCI Clinical Study.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not mentioned in the provided document. The submission focuses on device clearance through substantial equivalence and a clinical study assessing safety and effectiveness, not direct comparison of human readers with and without AI assistance.

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

This device is a physical medical device (a catheter for thrombus retrieval), not an AI algorithm. Therefore, the concept of "standalone (algorithm only without human-in-the-loop performance)" is not applicable to this submission.

7. Type of Ground Truth Used

The document refers to a "MERCI Clinical Study" that established safety and effectiveness for "thrombus removal versus foreign body removal." This suggests that the ground truth would have been based on clinical outcomes data related to successful thrombus removal, restoration of blood flow, and potentially adverse events, as observed and documented during clinical procedures. Pathology or expert consensus on images alone would likely not be sufficient for assessing the performance of a physical retrieval device.

8. Sample Size for the Training Set

The concept of a "training set" typically applies to machine learning algorithms. Since the Merci Retriever is a physical medical device, there is no explicit "training set" in the context of AI development. The device's design, manufacturing, and preclinical testing would involve various engineering and bench testing data, but not an AI training set.

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

As explained above, there is no AI training set for this physical device. Therefore, this question is not applicable. The device's "ground truth" during its development would have been established through a combination of engineering specifications, material testing standards, and preclinical (in vitro and in vivo) performance evaluations against defined mechanical and functional requirements.

Ask a specific question about this device