Search Results

The HARBOR Occlusion Device is indicated for arterial embolization in the peripheral vasculature.

The HARBOR Occlusion Device is a self-expanding braided nitinol arterial embolization implant (Figure 1) supplied with components used for implantation (Figure 2). The Device has a radiopaque marker band attached to the proximal end of the implant. The implant is packaged collapsed within an Introducer sheath and attached to a Delivery System provided within a hoop dispenser.

The provided FDA 510(k) clearance letter and summary for the HARBOR Occlusion Device outlines the device's technical specifications and the testing performed to demonstrate its substantial equivalence to predicate devices, rather than a clinical study establishing performance criteria in relation to human interpretation or outcomes. Therefore, several requested sections (e.g., sample size for test set, data provenance, number of experts for ground truth, adjudication method, MRMC comparative effectiveness) are not applicable to the information provided.

However, the document does detail the acceptance criteria (implicitly, "Pass" for each test) and the studies (bench and animal) that prove the device meets these criteria in the context of its substantial equivalence submission.

Here's a breakdown of the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly "Pass" for each test listed, indicating that the device must perform acceptably in those areas to demonstrate substantial equivalence.

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

Test Set Sample Size:

• Bench Tests: Not explicitly stated for each test, but implied to be sufficient for meeting ISO and ASTM standards.
• Animal Study: Not explicitly stated, but the study was described as "GLP Animal Study."

Data Provenance: Not explicitly stated. The document refers to "pre-clinical testing" and "GLP animal study," which are typically conducted in a controlled laboratory environment but the country of origin is not specified. The studies are prospective in nature, as they were conducted specifically for this device's submission.

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

Not applicable. This document describes the technical and biological performance of a medical device (an occlusion device) rather than an AI/CADe system or a diagnostic imaging device that would typically involve expert readers for establishing ground truth on image interpretation. The "acceptance criteria" here relate to the device's physical and biological functioning.

4. Adjudication method for the test set

Not applicable. As above, this is not a study assessing observer performance or diagnostic accuracy.

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 document does not describe an AI-enabled device or an MRMC study. It pertains to a physical medical device.

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

Not applicable. This describes a physical medical device, not an algorithm.

7. The type of ground truth used

The "ground truth" for the performance tests is established by:

• Engineering specifications and standards: For bench testing (e.g., specific tensile strength values, radial force, dimensions, nickel ion release limits).
• Biological responses: For biocompatibility tests (e.g., absence of cytotoxicity, irritation, sensitization, pyrogenicity, hemolysis, complement activation as per ISO 10993 standards).
• Physiological and pathological observations in an animal model: For the GLP animal study (e.g., direct observation of delivery, acute complications, vessel recanalization, foreign body reactions, device migration, and effectiveness of occlusion).

8. The sample size for the training set

Not applicable. This device is not an AI/ML algorithm or system that requires a "training set."

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

Not applicable. No training set exists for this type of device.

Ask a specific question about this device

The Prestige Coil System is indicated for arterial and venous embolizations in the peripheral vasculature.

The Prestige Coil System is intended for use in the peripheral vasculature to endovascularly obstruct or occlude blood flow in vascular abnormalities of the peripheral vessels.

The Prestige Coil System is a product family of embolic coils with associated delivery system components. These devices are angiographically delivered through the vasculature to embolize peripheral vascular abnormalities. The devices are to be permanently placed in the peripheral vessels to create blood stasis, reducing flow into the anomaly, and thrombosing the target site.

The provided FDA 510(k) Clearance Letter for the Prestige Coil System (Prestige Packing Coil Line Extension) does not describe a study involving an AI/Machine Learning device, human readers, or image interpretation. Instead, it describes a vascular embolization device and its mechanical and physical performance testing.

Therefore, many of the requested points in your prompt are not applicable to this document, as they relate to studies of AI performance or human reader studies in diagnostic imaging, which is not the subject of this 510(k) clearance.

However, I can extract the relevant information from the provided text regarding the device's acceptance criteria and the performance testing conducted.

Here's the breakdown based on the provided document:

Device: Prestige Coil System (Prestige Packing Coil Line Extension)

Type: Vascular Embolization Device (mechanical medical device)
Purpose: Arterial and venous embolizations in the peripheral vasculature.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The document repeatedly mentions "test samples" but does not specify the exact number of samples used for each test (Visual Inspection, Dimensional Inspection, Resistance Check, and Simulated Use).
• Data Provenance: Not applicable in the context of clinical data. This refers to bench testing involving physical device samples. No specific country of origin or retrospective/prospective data collection is mentioned as this relates to device manufacturing and testing, not patient data.

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

• Not Applicable. "Ground truth" in this context refers to the defined engineering specifications and performance characteristics of the device. These are established through design controls, manufacturing standards, and engineering principles, not through expert consensus on medical image interpretation. The "experts" would be engineers and quality control personnel involved in the device's design and testing.

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

• Not Applicable. This is a concept related to consensus building among human readers (e.g., radiologists) for establishing ground truth in image-based studies. For physical device bench testing, the "adjudication" is based on objective measurements against pre-defined engineering specifications and Pass/Fail criteria. No multi-reader adjudication method applies here.

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 describes a vascular embolization device, not an AI/Machine Learning diagnostic device. Therefore, no MRMC study or AI assistance was involved.

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

• Not Applicable. This is a mechanical device, not an algorithm. Standalone performance refers to the device's inherent functional capabilities as demonstrated in the bench tests, which are independent of a human operator's actions beyond following the instructions for use during the test.

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

• The "ground truth" for this device's performance testing is based on pre-established engineering specifications, design requirements, and manufacturing tolerances for the physical device. The device passes if its measured physical and functional characteristics meet these objective, pre-defined criteria. There is no biological "ground truth" (like pathology or outcomes data) in this specific submission, as it focuses on demonstrating the substantial equivalence of a modified mechanical device through bench testing.

8. The sample size for the training set

• Not Applicable. This applies to AI/Machine Learning models, not physical medical devices undergoing bench testing. The device itself is not "trained."

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

• Not Applicable. As above, this applies to AI/Machine Learning models.

Ask a specific question about this device

Embosphere Microspheres are indicated for use in the embolization of:

• Hypervascular tumors, including symptomatic uterine fibroids
• Prostatic arteries for symptomatic Benign Prostatic Hyperplasia (BPH)
• Arteriovenous malformations
• Blood vessels to occlude blood flow to control bleeding/hemorrhaging in the peripheral vasculature

Embosphere Microspheres are small, compressible, hydrophilic, biocompatible spheres made of acrylic polymer and porcine-derived gelatin. The microspheres are packaged in 0.9% saline and are provided sterile and non-pyrogenic in a vial or in a syringe.

The product is provided in seven size ranges to allow physicians to choose the appropriate size necessary for the vessel being embolized. The size ranges available are:
• 50-100 microns
• 40-120 microns
• 100-300 microns
• 300-500 microns
• 500-700 microns
• 700-900 microns
• 900-1200 microns

The principles of operation for the subject device Embosphere Microspheres are the same as the predicate device Embosphere Microspheres (K181300). Embosphere Microspheres are permanent implantable devices and are designed for controlled, targeted embolization. All indications for Embosphere Microspheres; uterine arteries, arteriovenous malformations, hypervascular tumors and prostate arteries all involve arterial embolization. The procedure of arterial embolization is similar for all arteries. Appropriately sized microspheres for target vessel occlusion are chosen by the trained interventional radiologist. The delivery procedure involves arterial access through an artery, using a guidewire and microcatheter under fluoroscopic guidance. Once the catheter tip is placed in the artery(ies) supplying the targeted tissue, Embosphere Microspheres mixed with a non-ionic contrast agent are delivered in a controlled manner under visualization to occlude the feeding vessel(s) to interrupt artery blood flow to the targeted area. The device is intended for single use.

I am sorry, but the provided text is an FDA 510(k) Clearance Letter for a medical device (Embosphere Microspheres). It details the regulatory clearance process, the device's intended use, and its equivalence to a predicate device.

This document does NOT contain information about any AI/ML model, its acceptance criteria, or a study proving that an AI/ML device meets those criteria.

Therefore, I cannot extract the information required to answer your request regarding the acceptance criteria and the study proving the device meets them, as it pertains to an AI model. The provided text describes a physical medical device and its regulatory review, not a software or AI-driven diagnostic tool.

Ask a specific question about this device

The Nitinol Enhanced Device (NED) is intended for arterial and venous embolization in the peripheral vasculature. This device is not intended for neurovascular use.

The NED system is comprised of polymer-based occlusion devices intended for embolization procedures in 3-6 mm vessels of the peripheral vasculature. It is intended to be used with 0.027" labeled microcatheters. The NED consists of three components: the NED implants (framing and packing), the delivery system, which is supplied engaged with the implant, and the transfer/removal tool.

The NED framing and packing implants are permanently implanted and include a 0.016" diameter polymer filament which compacts upon delivery. The implants work together to obstruct blood flow in the vessel. The framing implant is deployed first to form the initial pack and create a backing for additional implants to be deployed in accordance with physician discretion. The deployment of the framing implant is followed by the deployment of packing implants, the quantity of which is determined by the physician based on vessel size and occlusion. The physician also has the option to finish the implant pack with another framing implant. The UHMWPE braid on the implants and the nylon 6,6 tails on the packing implant provide a scaffold for thrombus to form and attach. The combination of the mechanical obstruction of blood flow and the formation of thrombus result in vessel occlusion.

The delivery system is comprised of two components: the implant pusher and the introducer. The NED delivery system comes with the NED implant pre-loaded in its package, sterile and ready for use. The pusher is a 180 cm long 0.022" diameter single super-elastic nitinol wire with a 30 cm PTFE jacket and a platinum/iridium radiopaque marker near its distal end. The nitinol pusher coupler is located on the distal end of the pusher, which as described above, serves to engage with the coupler on the implant's proximal end. The NED pusher allows the physician to reposition the NED to ensure preferred vessel positioning prior to detachment. Further, the detachment mechanism provides the physician the ability to completely withdraw the NED before detachment, should a condition result that necessitates its removal. The introducer is a PTFE tube used to protect the implant and maintain coupling between the implant and pusher prior to use (as described in Section 2.1). Once the implant and pusher are transferred into the delivery microcatheter, the introducer is discarded.

The transfer/removal tool is a disposable accessory included with the device that attaches to the hub of the delivery microcatheter prior to inserting the implant. The purpose of the transfer/removal tool is to facilitate the transfer of the implant from the device introducer into the delivery microcatheter hub and to facilitate the removal of the implant from the delivery microcatheter if necessary. The transfer/removal tool is designed to fit 0.027" labeled microcatheters. The tool is comprised of an ABS and PC Luer adapter assembly bonded with medical grade Dymax 1162-M UV adhesive. The tool utilizes a spring-loaded 300 series stainless steel tube to form the lumen.

This FDA 510(k) clearance letter pertains to a physical medical device, the Nitinol Enhanced Device (NED), not a device that relies on algorithms/AI in a way that necessitates the detailed criteria requested. Therefore, many of the requested fields are not applicable or cannot be extracted from the provided document.

The document primarily focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance testing for a vascular embolization device. It does not involve AI or software-driven performance assessment, and thus lacks information on acceptance criteria for AI performance, human expert evaluation, MRMC studies, or training/test set specifics for algorithms.

However, I can extract the relevant non-clinical performance data and the study details that were provided to demonstrate the device meets its requirements for substantial equivalence.

Acceptance Criteria and Study for Nitinol Enhanced Device (NED)

The Nitinol Enhanced Device (NED) is a physical medical device, specifically a vascular embolization device. The provided FDA 510(k) clearance letter does not describe an AI/software-driven device, therefore, many of the typical acceptance criteria and study details associated with such devices (e.g., AI performance metrics, expert adjudication, training/test set sizes for algorithms) are not applicable to this submission.

Instead, the device's acceptance criteria are met through a series of non-clinical performance tests designed to demonstrate the device's safety, functionality, and substantial equivalence to a legally marketed predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

As this is a physical medical device without explicit AI performance metrics, the "acceptance criteria" are generally implied by successful completion of various engineering, biocompatibility, and functional tests according to established standards. The "reported device performance" refers to the successful outcome of these tests.

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

This information is not detailed in the provided 510(k) summary. For physical device testing, sample sizes are typically determined based on statistical requirements for each specific test (e.g., number of units tested for tensile strength, number of animals in GLP studies). The document only states that the device "passed all testing."

• Test Set Sample Size: Not specified for individual tests.
• Data Provenance: The GLP Safety Study (Acute Ovine Study) and GLP Subchronic Ovine Product Validation Study were conducted using ovine (sheep) models. Details on the origin of the animals or whether these were prospective studies are not provided, but GLP (Good Laboratory Practice) studies are inherently prospective and controlled. The in-vitro and bench testing would have been conducted in a laboratory setting.

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

Not Applicable. This device is not an AI/software device requiring human expert ground truth for image interpretation or similar tasks. The "ground truth" for this device's performance is established by objective measurements against engineering specifications, biological responses in animal models, and adherence to established standards.

4. Adjudication Method for the Test Set

Not Applicable. There was no human expert adjudication of results as there were no subjective clinical assessments of AI performance or image interpretation involved. Performance was assessed through objective measurements and compliance with standards.

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

No, an MRMC study was not done. This type of study is relevant for AI-assisted diagnostic or interpretative devices. The NED is a physical embolization device.

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

Not Applicable. The NED is a physical medical device; there is no 'algorithm only' component to evaluate.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is based on:

• Engineering Specifications: Successful completion and meeting pre-defined requirements for mechanical properties (e.g., tensile strength, detachment force), delivery characteristics, and material compatibility.
• Established Standards: Adherence to national and international standards (e.g., ASTM, ISO 10993-1) for material properties (corrosion, biocompatibility) and functional tests.
• Biological Outcomes: In vivo studies (Acute Ovine Study, Subchronic Ovine Product Validation Study) provided ground truth on the biological response to the implanted device, including safety and product validation in a living system.

8. The Sample Size for the Training Set

Not Applicable. There is no 'training set' as this is not an AI/machine learning device.

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

Not Applicable. There is no 'training set' or associated ground truth establishment process for this type of device.

Ask a specific question about this device

The Ruby XL System is indicated for arterial and venous embolizations in the peripheral vasculature.

The Ruby XL System is comprised of a platinum embolization coil attached to a composite delivery pusher, and the Penumbra Detachment Handle. The coil/delivery pusher is packaged separately from the Penumbra Detachment Handle.

The provided document is a 510(k) Pre-Market Notification for the Ruby XL System, a vascular embolization device. This type of submission is for demonstrating substantial equivalence to a legally marketed predicate device, not for proving a device meets specific acceptance criteria based on a clinical or performance study in the way an AI/ML device would.

Therefore, the requested information regarding "acceptance criteria" and "study that proves the device meets the acceptance criteria" in the context of an AI/ML device (e.g., sample size, data provenance, expert ground truth, MRMC study, standalone performance) is not applicable to this document.

This submission focuses on bench-top performance testing, biocompatibility, and shelf-life, establishing substantial equivalence based on the device's physical characteristics, materials, and mechanical performance compared to a predicate embolization coil system. No AI/ML components are mentioned or evaluated in this regulatory filing.

Here's a breakdown of what is provided and why the AI/ML-specific questions are not applicable:

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

• This document does not present acceptance criteria in the typical sense of numerical thresholds for AI/ML performance metrics (e.g., sensitivity, specificity, AUC). Instead, it lists various bench-top performance tests (Dimensional/Visual, Packaging, Radiopacity, Friction, Fatigue Resistance, Torsional Resistance, Stiffness, Simulated Use, Corrosion, Tensile, MRI Compatibility) and states that these tests were "used in support of the subject device to determine substantial equivalence."
• No specific reported numerical performance values are given for these tests beyond the general statement that they substantiate the device's performance.

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

• Not applicable as no AI/ML test set was used. The "test set" here would refer to the physical devices undergoing bench-top testing. Data provenance is not relevant for physical device testing in this context.

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. Ground truth, in the AI/ML context, refers to expert labeling or an objective standard against which an algorithm's output is compared. For this device, "ground truth" would be the established physical and mechanical properties and material standards. No human experts are described as defining a "ground truth" for a test set of images or data to evaluate an algorithm.

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

• Not applicable. Adjudication methods are relevant for resolving discrepancies in expert labeling for AI/ML ground truth, which is not part of this submission.

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 physical medical device (embolization coil system), not an AI/ML diagnostic or assistive tool. MRMC studies are not relevant.

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

• No. This is a physical medical device.

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

• Not applicable for an AI/ML context. The "ground truth" for this device's performance is established engineering and material science standards and physical measurements.

8. The sample size for the training set

• Not applicable as no AI/ML algorithm was trained.

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

• Not applicable as no AI/ML algorithm was trained.

Summary based on the provided document:

The Ruby XL System is a medical device (vascular embolization device), not a software/AI/ML product. The 510(k) submission demonstrates substantial equivalence to a predicate device (Penumbra Coil System and POD System) based on:

• Indications for Use: The subject device is indicated for arterial and venous embolizations in the peripheral vasculature, which is a subset of the predicate's indications.
• Design and Materials: The document states "SAME" for various material and construction attributes, coil dimensions, detachment mechanism, sterilization method, and method of supply, indicating identical or highly similar characteristics to the predicate.
• Non-Clinical Safety and Performance Data: Bench-top testing (e.g., Dimensional, Packaging, Radiopacity, Friction, Fatigue, Stiffness, Simulated Use, Corrosion, Tensile, MRI Compatibility) and Biocompatibility testing were performed. These tests are the "study" that substantiates the device's performance and safety, leading to the determination of substantial equivalence. The document explicitly states "No animal or clinical study was conducted as bench testing was determined sufficient for verification and validation purposes."

Therefore, the requested AI/ML specific criteria and study details are not relevant to this 510(k) submission for a physical medical device.

Ask a specific question about this device

Embozene Color-Advanced Microspheres are intended for embolization of arteriovenous malformations and hypervascular tumors, including uterine fibroids (UFE) and hepatoma, and for embolization of prostatic arteries (PAE) for symptomatic benign prostatic hyperplasia (BPH). The device is not intended for neurovascular use.

Embozene Color-Advanced Microspheres (hereafter may be referenced as Embozene Microspheres or Embozene) are spherical, tightly calibrated, biocompatible, non-resorbable, hydrogel microspheres coated with an inorganic perfluorinated polymer shell (Polyzene-F). The microspheres are suspended in liquid and then injected into the bloodstream to permanently occlude blood vessels. They are used to stop bleeding when the underlying lesion is not likely to heal or block arteries supplying a tumor to cause tumor necrosis and/or shrinkage. Embozene Color-Advanced Microspheres are sterile, single use devices and are supplied in pre-filled 20 ml syringes containing 2ml of microspheres in approximately 7 ml of transport solution. The Embozene Microspheres are available in 40-1300 µm sizes.

The provided text is a 510(k) Premarket Notification from the FDA regarding "Embozene Color-Advanced Microspheres". This submission focuses on demonstrating substantial equivalence to a predicate device, rather than providing efficacy study data with acceptance criteria for a new device.

Therefore, the document does not contain the requested information regarding specific acceptance criteria, a study proving the device meets those criteria, or details regarding sample sizes, ground truth establishment, expert qualifications, adjudication methods, MRMC studies, or standalone algorithm performance.

The submission confirms that:

• The device is "substantially equivalent" to a legally marketed predicate device (K180102).
• The substantial equivalence is based on the devices having "the same indications for use and the same technological characteristics."
• The only change in the subject device is an "updated syringe due to end of life of the previously used syringe."
• Non-clinical testing (mechanical performance, biocompatibility, sterility, packaging, and shelf-life) was conducted to ensure the updated device meets the specifications of the predicate device.

Ask a specific question about this device

The TEMBO Embolic System is a gelatin agent intended for use in the embolization of hypervascular tumors and blood vessels to occlude blood flow in the peripheral vasculature.

The TEMBO Embolic System consists of biocompatible, dry resorbable particles of porcine gelatin in a 10 mL syringe with a non-vented luer lock cap. The TEMBO Embolic System is a gelatin agent and a sterile, single use, medical device intended for the embolization of hypervascular tumors and blood vessels to occlude blood flow in the peripheral vasculature. The TEMBO Embolic System particles are hydrated using commercially available contrast media or contrast mixed with saline. Once hydrated, the material is injected into the target blood vessel via a commercially available microcatheter for occlusion of target vasculature. The dry TEMBO Embolic System gelatin particles are between 85 µm.

The provided text describes the TEMBO Embolic System, but it does not contain information about acceptance criteria or a study proving the device meets specific acceptance criteria in the context of clinical performance or diagnostic accuracy.

The document is an FDA 510(k) clearance letter and a 510(k) Summary. This type of document focuses on demonstrating substantial equivalence to a predicate device through bench testing, biocompatibility, sterility, shelf-life, and limited animal studies. It does not typically include information about clinical studies with human participants that establish diagnostic performance metrics like sensitivity, specificity, or accuracy, as would be relevant for devices that provide diagnostic output or alter human reader performance.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and reported device performance (in a clinical/diagnostic context).
• Sample size used for the test set and data provenance (for diagnostic performance).
• Number of experts used to establish ground truth and their qualifications (for diagnostic performance).
• Adjudication method (for diagnostic performance).
• MRMC comparative effectiveness study or its effect size.
• Standalone algorithm performance.
• Type of ground truth used (for diagnostic performance).
• Sample size for the training set (for an AI algorithm).
• How ground truth for the training set was established.

What the document does provide regarding performance and studies:

• Performance Data (Bench Testing and Functional Testing): The document lists several types of performance testing, including Visual Verification, Particle Size (Dry), Iodinated Contrast Media Chemical Compatibility, Delivery Ease, Embolic Persistence, Pepsin Digestion, pH of Hydrated Gelatin, Pot Life, Simulated Use Testing (Ability to Create an Embolization, Depth of Penetration, Minimal Non-target Embolization, Directed Delivery of Embolic Material, Embolic Material Withstands Confirmation Angiography, Embolic Delivery Through Microcatheter System, Ability to Start and Stop Embolic Delivery), and Compatibility with Female Luer Connections. It states, "All performance testing met predetermined specifications."
• Biocompatibility Testing: A comprehensive list of biocompatibility tests was successfully completed according to ISO 10993-1.
• Sterility: Sterilization via gamma radiation to a SAL of 10⁻⁶, with a validated bacterial endotoxins test.
• Shelf Life: Demonstrated for 6 months.
• Animal Testing:
  • One study on 11 swine evaluated the acute embolization effect in renal arteries and systemic impact over 28 days, assessing target tissue embolization and non-target embolization/device migration.
  • An additional study on 8 swine compared the embolic effect of TEMBO to EmboCube and Gel-Bead at 7 days.

Conclusion based on the provided text:

The TEMBO Embolic System is a vascular embolization device. The provided FDA submission documents demonstrate its substantial equivalence through mechanical, chemical, and biological testing, including animal studies, but do not involve any diagnostic or AI-related evaluation processes that would require acceptance criteria for reader performance, ground truth establishment by experts, or MRMC studies. The "acceptance criteria" referred to in the document pertain to engineering and biological specifications of the device itself ("predetermined specifications" for bench and functional testing).

Ask a specific question about this device

ONCOZENE Microspheres are intended for embolization of arteriovenous malformations and hypervascular tumors including hepatoma.

ONCOZENE Microspheres (hereafter may be referenced as ONCOZENE Microspheres or ONCOZENE) are spherical, tightly calibrated, biocompatible, non-resorbable, hydrogel microspheres coated with an inorganic perfluorinated polymer shell (Polyzene-F). The microspheres are suspended in liquid and then injected into the bloodstream to permanently occlude blood vessels. They are used to stop bleeding when the underlying lesion is not likely to heal or block arteries supplying a tumor to cause tumor necrosis and/or shrinkage.

ONCOZENE Microspheres are sterile, single use devices and are supplied in pre-filled 20 ml syringes containing 2ml or 3 ml of microspheres in approximately 7 ml of transport solution. The ONCOZENE Microspheres are available in 40, 75 and 100 um sizes.

The provided text is a 510(k) Premarket Notification from the U.S. Food and Drug Administration (FDA) regarding a medical device called "ONCOZENE Microspheres." The document primarily addresses the substantial equivalence of a modified device (new syringe) to a previously cleared predicate device.

Based on the provided text, the device in question is a medical device (microspheres for embolization), not an AI/software-based medical device that would require the types of studies and acceptance criteria typically associated with AI performance.

Therefore, I cannot extract information related to:

• A table of acceptance criteria and reported device performance (in the context of AI performance metrics like sensitivity, specificity, AUC). The document speaks of "acceptance criteria" but in the context of physical device testing such as mechanical performance, sterilization, biocompatibility, packaging integrity, and shelf-life.
• Sample size used for the test set and data provenance (for AI model evaluation).
• Number of experts used to establish ground truth or their qualifications.
• Adjudication method for the test set.
• Multi reader multi case (MRMC) comparative effectiveness study or human reader improvement with AI assistance.
• Standalone (algorithm only without human-in-the-loop performance) study.
• Type of ground truth used (expert consensus, pathology, outcomes data, etc.) for AI evaluation.
• Sample size for the training set (for AI models).
• How the ground truth for the training set was established (for AI models).

The document outlines the following types of performance data and their "acceptance criteria" in a general sense:

1. Non-clinical Testing: To demonstrate the design and performance met established design criteria and is substantially equivalent to the predicate device. Specifically, mechanical testing was performed to verify the Syringe Volume Identification, and results "met all related specifications."
2. Sterilization: To ensure a minimum sterility assurance level of 10⁻⁶ in accordance with ISO standards. Half and full cycles were used, and results "met all acceptance criteria."
3. Biocompatibility: In accordance with ISO 10993-1, demonstrating that patient-contacting components are biocompatible. Testing was performed for genotoxicity, hemocompatibility, cytotoxicity, implantation effects, irritation and sensitization, pyrogenicity, subacute/subchronic systemic toxicity, toxicological risk assessment of chemistry results, chemical characterization, and irritation. The text states testing "demonstrated compliance."
4. Packaging Integrity and Shelf Life: Performed in accordance with ISO 11607-1 and ISO 11607-2, supporting a three-year shelf-life. Testing included label adhesion, legibility, packaging seal integrity, bubble leak test, peel strength test, and dye penetration.

In summary of what is available in the provided text:

• Device Type: Vascular embolization device (ONCOZENE Microspheres). This is a physical medical device, not an AI/software device.
• Study Purpose: To demonstrate substantial equivalence of a device with an updated syringe to a predicate device.
• Methods: Non-clinical testing, sterilization testing, biocompatibility testing, packaging integrity, and shelf-life testing.
• Acceptance: For all listed performance data, the results "met all acceptance criteria" or "demonstrated compliance/substantial equivalence."
• Ground Truth: For these types of physical device tests, "ground truth" is typically defined by adherence to established engineering specifications, ISO standards, and regulatory requirements (e.g., a specific sterility assurance level, a certain peel strength, or passing toxicology tests).

Since the nature of the device and the provided documentation does not pertain to AI/software performance evaluation, the requested details regarding AI model acceptance criteria, test sets, expert involvement, and ground truth for AI are not applicable and thus not present in the provided text.

Ask a specific question about this device

The OBSIDIO™ Conformable Embolic is indicated for use in the embolization of:

• Hypervascular tumors
• Blood vessels to occlude blood flow for controlling bleeding/hemorrhaging in the peripheral vasculature

The OBSIDIO™ Conformable Embolic is a premixed embolic agent consisting of pre-hydrated gelatin and layered silicate, and tantalum powder (to provide for visualization under fluoroscopy). Obsidio Embolic is delivered directly through a microcatheter into the blood flow to target tissue without relying on precipitation or polymerization. The material conforms to the shape of the vessel. Obsidio Embolic is packaged in a 1 mL (1 cc) syringe. The device is supplied as a sterile, single use product.

The provided document is a 510(k) summary for a medical device called OBSIDIO™ Conformable Embolic. It states that this 510(k) submission is to implement labeling updates as part of mitigations for a recent Class I Recall and that no new safety or effectiveness issues were raised during the device testing. The document highlights that the subject device has the same intended use, indications for use, and technological characteristics as its predicate device (also OBSIDIO™ Conformable Embolic, K213385 cleared July 1, 2022).

Therefore, this document does not contain information about acceptance criteria and a study proving the device meets those criteria for the current submission, as the submission is for labeling updates and asserts substantial equivalence based on the technological identity with the predicate and prior testing. The "summary of non-clinical performance testing" refers to "use characterization analysis" to support label updates, not a new clinical or performance study to establish new acceptance criteria or device performance.

Consequently, I cannot provide the requested information. The document explicitly states:

• "No new safety or effectiveness issues were raised during the device testing."
• "This 510(k) was submitted to implement labeling updates as part of mitigations for a recent Class I Recall."
• "The subject and predicate OBSIDIO™ Conformable Embolic have the same technical characteristics."
• "Predicate and subject device intended use / indications for use are the same."

These statements confirm that no new study was conducted to establish new performance criteria or to re-evaluate the device against existing criteria in the context of this 510(k) application. The substantial equivalence is based on the device's prior clearance (K213385).

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.

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