Search Results

Numen™ Coil Embolization System is intended to endovascularly obstruct or occlude blood flow in vascular abnormalities of the neurovascular and peripheral vessels. Numen™ Coil Embolization System is indicated for endovascular embolization of:

• . Intracranial aneurysms
• Other neurovascular abnormalities such as arteriovenous malformations and . arteriovenous fistulae
• . Arterial and venous embolizations in the peripheral vasculature

NumenFR™ Detachment System is intended for use with MicroPort NeuroTech Numen™ Coil Embolization System in the embolization of intracranial aneurysms and other vascular abnormalities of the neuro and peripheral vasculature.

The Numen™ Coil Embolization System is composed of two parts as described below:

• An introducer sheath: The function of the introducer sheath is to facilitate introduction . of the coil into the microcatheter.
• . The coil system: The coil system is composed of a pusher and coil implant. The coil is a permanent implant intended to occlude blood flow in vascular abnormalities. The pusher is used to deliver the coil implant to the target lesion.

The MicroPort NeuroTech NumenFR™ Detachment System is a sterile, handheld, singlepatient use device designed for use with the MicroPort NeuroTech Numen™ Coil Embolization System. The device is operated by two pre-loaded batteries.

The provided text describes a 510(k) premarket notification for a medical device called the "Numen Coil Embolization System" and "NumenFR Detachment System." This type of submission is for demonstrating substantial equivalence to a legally marketed predicate device, rather than proving enhanced performance or efficacy through extensive clinical studies. Therefore, much of the information typically sought in a study proving a device meets acceptance criteria (like MRMC studies, effect sizes, detailed ground truth establishment for AI models, and training set details) will not be present.

Based on the document, here's what can be extracted regarding acceptance criteria and performance:

The acceptance criteria are implicitly defined by the "Pass" result for each non-clinical bench test. The study proving the device meets these criteria is the Performance Testing section (Section 4).

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

Note: The document states "pre-specified acceptance criteria" for some tests, but the specific numerical values or detailed parameters of these criteria are not provided within the scope of this FDA letter.

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

The document does not specify exact sample sizes (e.g., number of coils or devices) used for each bench test. It refers to "test units representative of final finished devices." Given that this is a 510(k) submission primarily relying on bench testing to demonstrate substantial equivalence for a modification (new coil type), detailed clinical test set provenance (country of origin, retrospective/prospective) is not applicable here, as it's not a clinical study.

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 describes non-clinical bench testing, not a study involving human experts establishing ground truth for performance.

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

Not applicable. As described above, this is bench testing, not an expert-adjudicated 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

Not applicable. This is a medical device (coil embolization system) and not an AI-assisted diagnostic device. Therefore, no MRMC study or AI assistance evaluation was performed or is relevant to this submission.

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

Not applicable. This is a physical medical device, not a standalone algorithm.

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

For the bench tests, the "ground truth" or reference for evaluating performance would be the predefined engineering specifications and performance targets for each test, as derived from relevant standards (e.g., ISO 11070 for Flexing and Fracture Tests) and internal product design requirements.

8. The sample size for the training set

Not applicable. This document describes testing for a physical medical device. The concept of a "training set" is relevant for machine learning models, which are not involved here.

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

Not applicable, as there is no training set for a machine learning model.

Ask a specific question about this device

The Optima Coil System is intended for the endovascular embolization of intracranial aneurysms and other neurovascular abnormalities such as arteriovenous malformations and arteriovenous fistulae. The Optima Coil System is also intended for vascular occlusion of blood vessels within the neurovascular system to permanently obstruct blood flow to an aneurysm or other vascular malformation and for arterial and venous embolizations in the peripheral vasculature.

The Optima Coil System is a series of specialized coils that are inserted into the vasculature under angiographic visualization to embolize intracranial aneurysms and other vascular anomalies. The system consists of an embolization coil implant comprised of platinum and tungsten, affixed to a delivery pusher to facilitate insertion into the hub of a microcatheter. The system is available in various shapes, lengths, and sizes. The devices are to be placed into aneurysms to create blood stasis, reducing flow into the aneurysm and thrombosing the aneurysm. Upon positioning coils into the aneurysm, the coils are detached from the delivery pusher in a serial manner until the aneurysm is occluded.

The provided text describes a 510(k) premarket notification for a medical device called the Optima Coil System (OptiBlock Line Extension). This submission focuses on demonstrating substantial equivalence to a predicate device (Optima Coil System, K223386) for which it is a modification or line extension.

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

1. Table of acceptance criteria and the reported device performance:

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

The document explicitly states "The following non-clinical bench testing was performed to evaluate the device changes and to demonstrate substantial equivalence...". It mentions "test samples" but does not specify the sample size for either of the tests performed. The data provenance is from bench testing for a medical device line extension, not involving human subjects or clinical data in this submission. Therefore, country of origin is not applicable in the context of clinical data.

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. Given that the studies are non-clinical bench tests, the "ground truth" would be established by engineering specifications and objective measurements rather than expert consensus on clinical cases.

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

This information is not provided and is generally not applicable to non-clinical bench testing. Adjudication methods are typically used in clinical studies where expert consensus is needed to establish ground truth for ambiguous cases.

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 the described device is a neurovascular embolization coil system, not an AI software or a device that assists human readers in interpreting medical images. There is no mention of AI in the document.

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

This information is not applicable for the same reasons as point 5. The device is a physical medical implant, not an algorithm.

7. The type of ground truth used:

For the "Visual Inspection, Dimensional Inspection, and Resistance Check," the ground truth would be engineering specifications and manufacturing tolerances. For "Simulated Use," the ground truth would be pre-defined performance criteria within a clinically relevant model, also based on engineering and functional specifications for the device's intended operation. There is no mention of expert consensus, pathology, or outcomes data being used to establish ground truth for these non-clinical tests.

8. The sample size for the training set:

This information is not provided and is not applicable given that this is not an AI/machine learning device. The concepts of "training set" and "ground truth for the training set" are relevant to machine learning model development, not for a physical medical device.

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

This information is not provided and is not applicable for the reasons stated in point 8.

Ask a specific question about this device

Target Detachable Coils are intended to endovascularly obstruct or occlude blood flow in vascular abnormalities of the neurovascular and peripheral vessels.

Target Detachable Coils are indicated for endovascular embolization of:

• Intracranial aneurysms
• Other neurovascular abnormalities such as arteriovenous malformations and arteriovenous fistulae
• Arterial and venous embolizations in the peripheral vasculature

Stryker Neurovascular Target Detachable Coils are comprised of the following coil types: Target 360 Nano, Target Helical Nano, Target 360 Ultra, Target Helical Ultra, Target 360 Soft, Target 3D, Target 360 Standard, Target XXL 360, Target XL 360 Soft, Target XL 360 Standard, Target XL Helical, Target Tetra. All Target Coils are stretch resistant coils. Target Coils incorporate a length of monofilament stretch resistant fiber or in the case of the Target Tetra, multi-strand material through the center of the coil designed to help resist stretching. Target Coils are designed for use with the Stryker Neurovascular InZone® Detachment System (sold separately). Each Target Coil type consists of a platinum-tungsten alloy coil attached to a stainless-steel delivery wire.

I am sorry, but based on the provided text, there is no information about acceptance criteria, device performance, sampling sizes, ground truth establishment, or clinical study results for the Target Detachable Coils.

The document appears to be a 510(k) premarket notification for the consolidation of instructions for use and patient information leaflets, along with other minor changes, for existing Target Detachable Coils. It asserts that the modifications do not alter the intended use, indications for use, or fundamental scientific technology of the predicate devices. Therefore, a comparative clinical study is not detailed here.

The document states:

• "This 510(k) requests clearance for the consolidation of three separate Target Instructions for Use (IFUs) into a single shared IFU and consolidates two separate Target Patient Information Leaflet (PIL) with Patient Information Card (PIC), making it a single PIL with PIC for all Target Detachable Coils, in addition to other changes made since the last 510(k) clearance resulting in a cumulative assessment that a new 510(k) is required."
• "The subject devices utilize the same design and materials of existing Target Coils, and the same manufacturing, packaging and sterilization processes."
• "The modified Stryker Neurovascular Target Detachable Coils have the same intended use/indications for use as the predicate Target Detachable Coils. The modifications do not alter the intended use, indications for use, or the fundamental scientific technology of the Predicate Devices."
• "Because the subject modifications do not alter the intended use or indications for use of the predicate devices, or the fundamental scientific technology of the predicate devices; and because the risk assessment of the modifications raise no new questions of safety and effectiveness, Stryker Neurovascular has determined the modified Target Detachable Coils to be substantially equivalent to the predicate device."

Therefore, the requested information regarding acceptance criteria and a study proving device performance is not present in the provided text.

Ask a specific question about this device

Numen™ Coil Embolization System is intended to endovascularly obstruct or occlude blood flow in vascular abnormalities of the neurovascular and peripheral vessels.

Numen™ Coil Embolization System is indicated for endovascular embolization of:

-Intracranial aneurysms

-Other neurovascular abnormalities such as arteriovenous malformations and arteriovenous fistulae -Arterial and venous embolizations in the peripheral vasculature

NumenFR™ Detachment System is intended for use with MicroPort NeuroTech Numen™ Coil Embolization System in the embolization of intracranial aneurysms and other vascular abnormalities of the neuro and peripheral vasculature.

MicroPort NeuroTech has developed the Numen™ Coil Embolization System and NumenFR™ Detachment System. The Numen™ Coil Embolization System is designed to be used in conjunction with the NumenFRTM Detachment System (sold separately) for endovascular embolization of vascular abnormalities described in the intended use.

The Numen™ Coil Embolization System is composed of two parts as described below:

• . An introducer sheath: The function of the introducer sheath is to facilitate introduction of the coil into the microcatheter.
• . The coil system: The coil system is composed of a pusher and coil implant. The coil is a permanent implant intended to occlude blood flow in vascular abnormalities. The pusher is used to deliver the coil implant to the target lesion.

The MicroPort NeuroTech NumenFRTM Detachment System is a sterile, handheld, single-patient use device designed for use with the MicroPort NeuroTech Numen™ Coil Embolization System. The device is operated by two pre-loaded batteries.

The provided text describes a 510(k) premarket notification for a medical device, the Numen™ Coil Embolization System and NumenFR™ Detachment System. The document details the device, its intended use, comparison to a predicate device, and performance testing. However, it does not describe acceptance criteria for a study proving the device meets those criteria in the context of an Artificial Intelligence/Machine Learning (AI/ML) powered medical device.

The "Performance Testing" section (page 6) outlines bench testing conducted to evaluate device changes and demonstrate substantial equivalence to a predicate device. This is typical for traditional (non-AI/ML) medical devices, focusing on physical and functional properties, rather than AI performance metrics like sensitivity, specificity, or reader agreement.

Therefore, I cannot fulfill your request to describe acceptance criteria and a study demonstrating an AI/ML device's performance based on the provided text, as the text pertains to a different type of medical device assessment.

If you can provide a document that discusses the evaluation of an AI/ML medical device, I would be happy to analyze it according to your requested criteria.

Ask a specific question about this device

Axium™ Detachable Coil:

Axium™ Detachable Coils are intended for the endovascular embolization of intracranial aneurysms. Axium™ Detachable Coils are also intended for the embolization of other neuro vascular abnormalities such as arteriovenous malformations and arteriovenous fistulae.

Axium™ Prime Detachable Coil:

(Models: APB-X-Y-3D-ES, APB-X-Y-3D-SS, APB-X-Y-HX-ES, APB-X-Y-HX-SS)

The Axium™ Prime Detachable Coils are intended for the endovascular embolization of intracranial aneurysms. The Axium™ Prime Detachable Coils are also intended for the embolization of other neuro vascular abnormalities such as arteriovenous malformations and arteriovenous fistulae.

Axium™ Prime Detachable Coil:

(Models: FC-X-Y-3D)

The Axium™ Prime Detachable Col is intended for the endovascular embolization of intracranial aneurysms and other neurovascular abnormalities, such as arteriovenous malformations and arteriovenous fistulae. The Axium™ Prime Detachable Coils are also intended for arterial and venous embolizations in the peripheral vasculature.

The Axium™ Detachable Coil and Axium™ Prime Detachable Coil consist of a platinum embolization coil attached to a composite implant delivery pusher with a radiopaque positioning marker and a hand-held Instant Detacher (I.D.) which when activated detaches the coil from the delivery pusher tip. The I.D. is sold separately.

The document provided focuses on the substantial equivalence of the "Axium™ Detachable Coil" and "Axium™ Prime Detachable Coil" with the addition of fluorosafe markers. The primary purpose of the submission is to demonstrate that these changes do not raise new questions of safety and effectiveness compared to the predicate devices. Therefore, the "device" in question is not an AI/ML powered diagnostic device, but rather a neurovascular embolization device with a minor design change.

As such, many of the typical acceptance criteria and study details relevant to AI/ML powered devices, such as sample size for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, and training set details, are not applicable or provided in this document. The provided text describes bench testing and biocompatibility testing for the physical device itself.

However, I can extract the relevant "acceptance criteria" and "reported device performance" as presented for the specific tests conducted for this submission.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not explicitly stated for each test, but standard for device verification and validation. For biocompatibility, animal models were used (guinea pig, rabbit, mice). For bench tests, "devices" (plural) were evaluated, implying a sample size greater than one but not specified numerically.
• Data Provenance: Not applicable in the context of AI/ML data sets. These are laboratory tests on physical devices.

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. The "ground truth" for this device modification is established through physical and objective measures against predefined specifications and recognized international standards (e.g., ISO 10993, USP 151) and user needs (for marker visibility). The "clinical users" who evaluated fluorosafe marker visibility are mentioned, but their number and specific qualifications are not detailed.

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

• Not applicable. Adjudication methods are typically for subjective assessments (e.g., image interpretation). These tests involve objective measurements and evaluations against specified criteria and standards.

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 submission is for a physical medical device (embolization coil) with a minor design change (adding fluorosafe markers), not an AI-powered diagnostic tool. No MRMC study was conducted.

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

• Not applicable. This is not an algorithm or AI device.

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

• The "ground truth" here is based on objective measurements against established engineering specifications, chemical/biological compatibility standards (ISO 10993, USP 151), and documented user needs. For example, meeting the criteria for "non-cytotoxic" or demonstrating "no corrosion."

8. The sample size for the training set

• Not applicable. There is no "training set" as this is not an AI/ML device.

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

• Not applicable. There is no "training set."

Ask a specific question about this device

The Penumbra LP Coil System is indicated for the embolization of:

• · Intracranial aneurysms
• · Other neurovascular abnormalities such as arteriovenous malformations and arteriovenous fistulae
• · Arterial and venous embolizations in the peripheral vasculature

The Penumbra LP Coil System is comprised of the Penumbra LP Coil, a platinum embolization coil attached to a composite delivery pusher with a radiopaque positioning marker and the Penumbra LP Coil Detachment Handle.

The coil/delivery pusher is packaged separately from the Penumbra LP Coil Detachment Handle. Penumbra LP Coil includes the following coil configurations:

• Ruby Coil LP ●
• Packing Coil LP ●
• PTC Coil LP ●
• Helical Coil LP ●
• Hybrid Coil LP ●

The provided text is a 510(k) summary for the Penumbra LP Coil System. This document focuses on demonstrating substantial equivalence to a previously cleared predicate device, rather than proving the device meets specific acceptance criteria through an independent study with a defined ground truth, a test set, or expert adjudication.

Therefore, many of the requested data points (sample size of test set, data provenance, number of experts for ground truth, adjudication method, MRMC study, standalone performance, training set sample size, ground truth for training set) are not applicable to this type of submission.

Here's an analysis based on the information provided:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes bench-top testing performed to evaluate the physical and mechanical properties of the subject device and demonstrate substantial equivalence to the predicate device. For each attribute, the "Specification" acts as the acceptance criteria, and the "Results" indicate the device met these criteria.

Additionally, the document states:

• Biocompatibility Testing: The Penumbra LP Coil System was determined to be biocompatible according to the requirements of ISO 10993-1. Specific tests for the Detachment Pusher (Cytotoxicity, Hemocompatibility) and Introducer Sheath (Cytotoxicity, Sensitization, Irritation, Systemic Toxicity, Hemocompatibility, Material-Mediated Pyrogenicity) were performed.
• Sterilization Testing: The device was tested to be sterile using identical acceptance criteria and testing methods as the predicate device in accordance with ISO 11135 and ISO 10993-7. The Sterilization Assurance Level (SAL) requirement is ≥10-6.

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

The document does not specify a "test set" in the context of clinical data or images for an AI/CAD/software device. The tests performed are bench-top mechanical, chemical, and biological evaluations. The sample size for each bench-top test is not explicitly mentioned.

Data Provenance: Not applicable in the context of clinical data for this type of submission. The data is from laboratory testing (bench-top, biocompatibility, sterilization).

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

Not applicable. This submission is for a physical medical device (embolization coil system), not a diagnostic device relying on expert interpretation of images or clinical data. Ground truth, in this context, refers to established engineering specifications and international standards (e.g., ISO 10993-1, ISO 11135, ISO 10993-7).

4. Adjudication Method for the Test Set

Not applicable. There is no "test set" in the sense of clinical cases requiring expert adjudication. The "Pass" results for bench-top tests indicate compliance with predefined engineering specifications.

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 physical medical device; it is not an AI/CAD/software device intended to assist human readers.

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

Not applicable. This is a physical medical device; it is not a standalone algorithm.

7. The Type of Ground Truth Used

For the bench-top testing, the "ground truth" or reference for evaluating performance was engineering specifications, product specifications, and relevant international standards (e.g., ISO 10993-1 for biocompatibility, ISO 11135 and ISO 10993-7 for sterilization).

8. The Sample Size for the Training Set

Not applicable. This is a physical medical device; there is no "training set" in the context of machine learning or AI.

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

Not applicable. There is no training set.

Ask a specific question about this device

Target Detachable Coils are intended to endovascularly obstruct or occlude blood flow in vascular abnormalities of the neurovascular and peripheral vessels.

Target Detachable Coils are indicated for endovascular embolization of:

• Intracranial aneurysms
• . Other neurovascular abnormalities such as arteriovenous malformations and arteriovenous fistulae
• Arterial and venous embolizations in the peripheral vasculature

Stryker Neurovascular Target Detachable Coils are comprised of the following coil types: Target 360 Nano, Target Helical Nano, Target 360 Ultra, Target Helical Ultra, Target 360 Soft, Target 3D, Target 360 Standard, Target XXL 360, Target XL 360 Soft, Target XL 360 Standard, Target XL Helical, Target Tetra (Subject Device). All Target Coils are stretch resistant coils. Target Coils incorporate a length of multi-strand material through the center of the coil designed to help resist stretching. Target Coils are designed for use with the Stryker Neurovascular InZone® Detachment System (sold separately). Each Target Coil type consists of a platinum-tungsten alloy coil attached to a stainless steel delivery wire. For Target Coils with the Tetrahedral shape, the distal end of the main coil is formed such that the diameter of the distal loop is approximately 75% that of the overall secondary outer diameter (OD) size.

The provided text describes a 510(k) premarket notification for the "Target Tetra Detachable Coils" (K222533), a neurovascular embolization device. The document focuses on demonstrating substantial equivalence to predicate devices through bench testing and biocompatibility testing. It does not describe an AI/ML-based device or a study involving human readers or AI assistance. Therefore, information related to AI/ML acceptance criteria, ground truth establishment for AI, sample sizes for AI training/test sets, expert adjudication, or MRMC studies is not present in the provided document.

The document does provide information on the performance data collected to support the substantial equivalence claim for this medical device.

Here's an analysis of the provided text, extracting the relevant information within the scope of the original request, focusing on the device performance and acceptance criteria where applicable to the physical medical device described:

Acceptance Criteria and Device Performance

The document states that the "Target Tetra Detachable Coils" are substantially equivalent to their predicate devices. The performance data is primarily from bench testing and biocompatibility testing.

1. Table of Acceptance Criteria and Reported Device Performance (Non-AI/ML):

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

• Test Set Sample Size: The document does not specify the exact number of units tested for each bench test. It generally states that "performance bench testing has demonstrated" the results.
• Data Provenance: This is a physical medical device. The data comes from bench tests conducted by Stryker Neurovascular. The document does not specify the country of origin for the testing, but the company is based in Fremont, California, USA. The data is prospective in the sense that these tests were conducted specifically for this 510(k) submission.

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

• Not Applicable. This is a physical medical device, not an AI/ML device requiring clinical expert ground truth for interpretation. Performance is measured against engineering specifications and physical properties.

4. Adjudication Method for the Test Set:

• Not Applicable. See point 3.

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

• No. This is not an AI/ML device; therefore, an MRMC study related to readers improving with AI assistance would not be applicable. The document explicitly states: "No clinical study was conducted because bench testing was determined sufficient to support substantial equivalence to the predicate device."

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

• Not Applicable. This is a physical device, not an algorithm.

7. The type of ground truth used:

• For physical properties and mechanical performance: Engineering specifications, established test methods, and comparison data from predicate devices serve as the "ground truth" or reference for evaluating performance parameters.
• For biocompatibility: International standards (EN ISO 10993-1:2020) and FDA guidance documents serve as the ground truth.

8. The sample size for the training set:

• Not Applicable. This is not an AI/ML device that requires a "training set" in the machine learning sense. The "training" or development of the device would involve engineering design and prototyping.

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

• Not Applicable. See point 8. The "ground truth" for developing a physical medical device involves scientific principles, material properties, biomechanical considerations, and clinical needs, leading to design specifications.

Ask a specific question about this device

The Optima Coil System is intended for the endovascular embolization of intracranial aneurysms and other neurovascular abnormalities such as arteriovenous malformations and arteriovenous fistulae. The Optima Coil System is also intended for vascular occlusion of blood vessels within the neurovascular system to permanently obstruct blood flow to an aneurysm or other vascular malformation and for arterial and venous embolizations in the peripheral vasculature.

The Optima Coil System is a series of specialized coils that are inserted into the vasculature under angiographic visualization to embolize intracranial aneurysms and other vascular anomalies. The system consists of an embolization coil implant comprised of platinum and tungsten, affixed to a delivery pusher to facilitate insertion into the hub of a microcatheter. The system is available in various shapes, lengths and sizes. The devices are to be placed into aneurysms to create blood stasis, reducing flow into the aneurysm and thrombosing the aneurysm. Upon positioning coils into the aneurysm, the coils are detached from the delivery pusher in a serial manner until the aneurysm is occluded.

The provided text is a 510(k) Summary for a medical device called the "Optima Coil System." It describes the device, its intended use, and its comparison to a predicate device. It also includes a table of performance data from bench testing. However, this document does not contain information about a study involving human readers or AI assistance, or any data related to diagnostic accuracy, sensitivity, or specificity.

The "acceptance criteria" and "device performance" described are for bench testing only, which evaluates the physical and functional characteristics of the device itself, not its performance in a clinical scenario involving human interpretation or AI.

Therefore, I cannot fulfill the request for information related to:

• A table of acceptance criteria and reported device performance in a human-AI study. The provided table only covers bench tests.
• Sample size used for the test set and data provenance for a human-AI study.
• Number of experts used to establish ground truth and their qualifications for a human-AI study.
• Adjudication method for a human-AI study.
• Multi-reader multi-case (MRMC) comparative effectiveness study or effect size.
• Standalone (algorithm only) performance.
• Type of ground truth used (expert consensus, pathology, outcomes data, etc.) for a human-AI study.
• Sample size for the training set for an AI study.
• How ground truth for the training set was established for an AI study.

The document's "Performance Data - Bench" section is directly relevant to the acceptance criteria of the device's physical properties and functionality, not an AI or diagnostic performance study.

Here's the information that can be extracted from the provided text regarding device acceptance criteria and performance (bench testing):

Device Acceptance Criteria and Reported Performance (Bench Testing)

Explanation of the Bench Study (based on the provided text):

The performance data presented is from non-clinical bench testing. Its purpose was to evaluate changes made to the Optima Coil System (e.g., new coil sizes and combinations of dimensions) and to demonstrate its substantial equivalence to the previously cleared predicate device (K200030).

• Sample size: Not explicitly stated for each bench test, but implied to be "test samples."
• Data provenance: Bench testing results, implying in-house lab testing, not clinical data from patients or specific countries. It is retrospective in the sense that it evaluates a final product design.
• Experts for ground truth: Not applicable for this type of bench testing. Ground truth is based on engineering specifications, physical measurements, and performance standards.
• Adjudication method: Not applicable. Results are based on physical measurements and functional checks against pre-defined engineering criteria.
• MRMC Comparative Effectiveness Study: No, this document does not describe such a study.
• Standalone Performance: Not applicable in the context of AI; this refers to the physical device's performance.
• Type of Ground Truth: Engineering specifications, physical dimensions, material properties, and functional performance in simulated environments.
• Training Set Sample Size/Ground Truth for Training Set: Not applicable, as this document describes bench testing of a physical medical device, not the development or training of an AI algorithm.

In summary, the provided document focuses solely on the substantial equivalence of a physical neurovascular embolization device based on bench testing of its modifications. It does not contain any information related to AI performance, human-in-the-loop studies, or diagnostic efficacy.

Ask a specific question about this device

The CEREPAK™ Uniform, Uniform 3D, Heliform Soft, Heliform XtraSoft, Heliform XL, Heliform XtraSoft XL, Freeform, and Freeform Mini Detachable Coil Systems are indication of intracranial aneurysms, neurovascular abnormalities such as arteriovenous malformations and arterial and arterial and venous embolizations in the peripheral vasculature.

The CEREPAK™ Freeform XtraSoft Detachable Coil System is indication of intracranial aneurysms.

CEREPAK™ is a platform delivery system that aids in the delivery of embolic coils (or "microcoils") using standard endovascular methods to treat hemorrhagic conditions. It consists of two main components, the CEREPAK™ Detachable Coils, and the CEREPAK™ Detacher. These components will be provided sterile and sold separately. The CEREPAK™ Detachable Coils are comprised of an embolic coil implant (microcoil) attached to a delivery system. The CEREPAK™ Detacher is a mechanical accessory that aids in the detachment of the CEREPAK™ Detachable Coils.

The delivery system of the CEREPAK™ Detachable Coils consists of a long, thin hypotube (delivery tube) shaft with an attachment interface to secure the microcoil at its distal end until deployment is required. Microcoil designs are based on the microcoils present in the predicate device. The delivery tube is advanced with the microcoil through a compatible microcatheter using standard endovascular techniques until the microcoil is placed at the target lesion.

The CEREPAK™ Detacher interacts with the delivery system to detach the microcoils. Upon finger actuation, the Detacher translates (slides) a component within the delivery tube that aided in securing the microcoil. This detaches the microcoil from the delivery tube. Once the microcoil is detached at the desired location, the delivery tube can be removed and discarded.

The provided document is a 510(k) Premarket Notification for a medical device (CEREPAK™ Detachable Coil Systems), not an AI/ML device. Therefore, the questions regarding acceptance criteria and study design for AI/ML performance (e.g., sample size for test/training sets, expert ground truth, MRMC studies, standalone performance) are not applicable to this document.

The document describes non-clinical bench testing and an animal study to demonstrate substantial equivalence to a predicate device, focusing on the physical and functional performance of the embolization coils and their delivery system.

Here's an attempt to answer the applicable parts based on the document's content, focusing on what is provided:

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

The document provides a "Performance Testing Summary" (Table 5) and "Biocompatibility Test Summary" (Table 6). For all tests listed, the acceptance criteria are generally implied by the "Objective" of the test, and the reported performance is consistently a categorical "PASS." Specific quantitative acceptance criteria or detailed numerical results are not provided in this summary.

Table: Acceptance Criteria (Implied) and Reported Device Performance

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

• Test Set Sample Size: The document states that "All testing was conducted using sampling methods as required by internal procedure," but it does not specify the exact sample sizes for each bench test. For the "In-Vitro Usability Study," it mentions it was conducted with "skilled users" using a "silicone arterial model." For the "Animal Study," it mentions it was conducted "in a porcine model," again without specifying the number of animals.
• Data Provenance (Country of Origin and Retrospective/Prospective): The document does not specify the country of origin for the data or whether the data was retrospective or prospective. Given these are non-clinical bench and animal studies to support a 510(k) submission, they would inherently be prospective studies conducted by the manufacturer (Medos International, SARL). The manufacturer is based in Switzerland.

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

This question is not applicable as there is no "ground truth" to be established by experts in the context of an AI/ML model for this type of device (embolization coil system). The performance tests are largely engineering and material science evaluations against predefined specifications. The "skilled users" mentioned in the usability/animal studies would be medical professionals (e.g., interventional neuroradiologists) demonstrating the use of the device, but not establishing a "ground truth" in the sense of diagnostic interpretation for an AI.

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

Not applicable. There is no diagnostic "test set" requiring adjudication by multiple experts.

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 not an AI-assisted diagnostic device.

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

Not applicable. This is not an AI/ML algorithm. The device's performance is inherently tied to its physical interaction with the human body and the user.

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

The "ground truth" for this device's acceptance is based on predefined engineering specifications, material properties, and functional performance requirements of the device, derived from established standards and comparison to a legally marketed predicate device. For biocompatibility, it's based on International Standard ISO 10993-1 and FDA Guidance. For physical performance, it's based on successful operation within simulated environments and animal models ("PASS" results on specific functional tests).

8. The sample size for the training set:

Not applicable. There is no AI/ML training set.

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

Not applicable. There is no AI/ML training set.

Ask a specific question about this device

The InZone Detachment System is intended for use with all versions of Stryker Neurovascular detachable coils in the embolization of intracranial aneurysms and other vascular malformations of the neuro and peripheral vasculature.

Stryker Neurovascular's InZone® Detachment System is a sterile, handheld, single-patient use device designed for use with Stryker Neurovascular Detachable Coils. The device consists of an enclosure with a detachment button, five LED indicator lamps, a funnel inset at its distal end, and a cable connection port. The device comes pre-loaded with two AAAA (1.5 VDC) batteries.

Here's an analysis of the provided text regarding the InZone Detachment System, focusing on acceptance criteria and the supporting study:

The provided document (K212455) is a 510(k) summary for modifications to the InZone Detachment System. It does not describe a study involving human readers or AI. Instead, it focuses on bench testing and software verification to demonstrate substantial equivalence to a predicate device after firmware modifications. The device is a medical instrument used for detaching coils in neurovascular procedures, not an AI or imaging diagnostic tool. Therefore, many of the requested points related to AI, ground truth establishment, expert consensus, and MRMC studies are not applicable.

1. Table of Acceptance Criteria and Reported Device Performance

The document implicitly treats the successful completion of the listed verification tests as meeting acceptance criteria, demonstrating the modified device functions as intended and is substantially equivalent to the predicate.

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

The document does not specify a "test set" in the context of patient data or clinical images. The testing described is primarily bench-top testing of the device's firmware and physical characteristics. Therefore, there is no mention of country of origin or whether data was retrospective or prospective in the clinical sense. The "test cases" for software and bench-top testing would refer to specific scenarios and conditions the device was put through. The number of iterations or specific samples for each bench test (e.g., how many coils were detached for detachment consistency) is not provided.

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

Not applicable. This device is an instrument, not an AI diagnostic tool requiring expert interpretation of medical data for ground truth. Ground truth for the device's functionality would be established by engineering specifications, proper electrical readings, and functional verification, typically performed by engineers and technicians.

4. Adjudication Method for the Test Set

Not applicable. There is no clinical test set requiring adjudication in the context of expert review. The device's performance is objectively measured against engineering specifications.

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 not an AI diagnostic device, and no MRMC study was performed. The device is a tool used by interventionalists, and the study focuses on its functional performance, not its impact on human reader effectiveness for diagnosis.

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

This refers to the performance of the device itself (the "algorithm" being its firmware). The "Verification Testing" detailed in the table above is a standalone assessment of the device's performance. It evaluates the device's ability to perform its functions (detachment, detection, safety features) without human intervention beyond initiating the process.

7. The Type of Ground Truth Used

The ground truth used for the verification testing (standalone performance) is based on engineering specifications and expected functional outcomes. For example:

• Detachment cycle time: Should fall within a defined range.
• Max voltage/current output: Must not exceed specified limits.
• Low battery detection: Must accurately signal when battery is low.
• Fault detection: Must correctly identify and signal specified faults.
• Delivery wire compatibility and detection: Must correctly identify and interface with different coil types.

These ground truths are derived from existing design requirements, safety standards (e.g., ISO 14971, EN 62304), and the established performance of the predicate device.

8. The Sample Size for the Training Set

Not applicable. This device is not an AI system that undergoes "training" with data in the conventional machine learning sense. Its firmware is programmed based on design specifications and engineering principles.

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

Not applicable, as there is no "training set" in the context of machine learning. The "ground truth" for the device's design and programming comes from established medical device standards, functional requirements for electrolytic detachment, and the performance characteristics of the previously cleared predicate device.

Ask a specific question about this device