Search Results

The PeriBeam® Pericardial Membrane is indicated for the reconstruction or repair of the pericardium.

PeriBeam® is an ion-irradiated, expanded polytetrafluoroethylene (ePTFE) membrane used for reconstruction or repair of the pericardium. This device is intended for use as a temporary or permanent prosthesis for repair of pericardium

The provided FDA 510(k) clearance letter for the PeriBeam® Pericardial Membrane does not contain the detailed acceptance criteria and study results typically required to fully answer your request.

The document primarily focuses on the regulatory clearance process, device description, indications for use, and a general overview of the performance, animal, and biological/toxicological safety testing conducted. It does not provide the specific quantitative acceptance criteria or the reported performance data against those criteria. It also doesn't present an MRMC study or details on ground truth establishment for a standalone algorithm performance test, as this type of device (a physical membrane) would not involve AI or image analysis.

Therefore, I cannot create a table of acceptance criteria and reported device performance, nor can I elaborate on sample sizes for test sets, expert involvement, adjudication methods, MRMC studies, or training set details as these are not relevant for the type of device described.

However, I can extract the information that is present:

Summary of Information Available in the Provided Text:

Device Type: The PeriBeam® Pericardial Membrane is a physical medical device (an ion-irradiated, expanded polytetrafluoroethylene (ePTFE) implant) for reconstruction or repair of the pericardium. It is not an AI algorithm, diagnostic imaging software, or a device that would typically involve acceptance criteria related to classification metrics (e.g., sensitivity, specificity, AUC) or human reader performance.

Therefore, questions pertaining to AI/software performance (e.g., "effect size of how much human readers improve with AI vs without AI assistance," "standalone algorithm performance," "number of experts for ground truth," "adjudication method," "sample size for training set," "how ground truth for training set was established") are not applicable to this device.

The "Performance Testing" section describes types of tests conducted, but not the acceptance criteria or specific results.

1. Table of Acceptance Criteria and Reported Device Performance:

• Not Available in the provided text. The document lists types of performance tests (Tensile Strength, Suture Strength, Accelerated Fatigue, Fibrin Glue, Burst Strength) but does not provide the specific quantitative acceptance criteria for each or the measured performance values.

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

• Nonclinical Performance Testing: The specific sample sizes for tests like Tensile Strength, Suture Strength, Fibrin Glue, and Burst Strength are not explicitly stated, although ISO 2859-1 (Sampling procedures for inspection by attributes) is referenced. This standard relates to sampling plans for quality control, not necessarily the sample size of unique test cases (e.g., patient data).
• Animal Study:
  • Sample Size: "Ten (10) pigs divided into three (3) groups for eight (8) weeks."
  • Data Provenance: Not explicitly stated (e.g., country of origin), assumed to be a controlled laboratory animal study (prospective).

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

• Not Applicable. This is a physical implant device, not an AI or diagnostic device requiring expert interpretation for ground truth establishment. The "ground truth" for its performance relates to its physical, mechanical, and biological properties, which are assessed through laboratory tests and animal studies.

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, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No. This is a physical implant device, not a diagnostic or AI-powered device. MRMC studies are not relevant for this product.

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

• No. This is a physical implant device. Standalone algorithm performance is not relevant.

7. The Type of Ground Truth Used:

• For nonclinical performance testing, the "ground truth" is established through standardized engineering and materials testing methods (e.g., ISO, JIS, ASTM standards for tensile strength, burst strength, etc.).
• For the animal study, "ground truth" was established through direct observation (health condition, feeding, respiration, feces), weight measurement, ultrasonography, macroscopic observations at autopsy (adhesions, effusions, infection, discharge), and histopathology (cellular infiltration, fibroblast amount, fibrosis, bacteria). These are direct biological and pathological assessments.

8. The Sample Size for the Training Set:

• Not Applicable. This is a physical device, not an AI model that requires a training set.

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

• Not Applicable. See point 8.

In conclusion, while the document provides evidence of various tests performed, it does not include the detailed quantitative acceptance criteria and the corresponding measured performance data within the provided sections. The nature of the device (a physical pericardial membrane) means that many of the AI/software-related questions are not applicable.

Ask a specific question about this device

PERI-GUARD is intended for repair of pericardial structures. PERI-GUARD is also intended for use as a patch for intracardiac defects, great vessel, septal defects and annulus repair, and suture-line buttressing.

SUPPLE PERI-GUARD is intended for use as a prosthesis for pericardial closure.

PERI-GUARD Repair Patch (PERI-GUARD) and SUPPLE PERI-GUARD Repair Patch (SUPPLE PERI-GUARD) are derived from bovine pericardium procured from cattle originating in the United States. The pericardium is crosslinked with glutaraldehyde and treated with 1 molar sodium hydroxide for a minimum of 60 minutes at 20-25°C (68-77°F).

PERI-GUARD and SUPPLE PERI-GUARD are terminally sterilized using gamma irradiation and packaged within a sterile double-pouch system. The contents of the unopened, undamaged outer pouch are sterile.

PERI-GUARD and SUPPLE PERI-GUARD are MR Safe.

PERI-GUARD and SUPPLE PERI-GUARD utilize animal tissue; patient must be informed prior to any procedure.

This is a 510(k) premarket notification for the PERI-GUARD Repair Patch and SUPPLE PERI-GUARD Repair Patch. This document describes the device, its intended use, and the performance data provided to demonstrate substantial equivalence to predicate devices. The submission focuses on changes to packaging and sterilization parameters, with a reliance on historical data for many performance aspects.

Here's the breakdown of the acceptance criteria and the study information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" with numerical targets and corresponding "device performance" results for each criterion in the typical sense of a clinical or standalone performance study. Instead, it lists various performance tests conducted to support substantial equivalence. The "reported device performance" is implicitly that the devices "meet" or "demonstrate equivalence" to the predicate devices.

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

The document does not specify exact sample sizes for each performance test. It mentions "aging testing" for shelf life, but without a specific sample size. The studies are non-clinical (laboratory/bench testing, in vitro), not based on patient data. Therefore, questions about country of origin and retrospective/prospective nature are not applicable in this context.

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

Not applicable. This is a submission for a medical device (a patch), and the evaluation is based on non-clinical performance data and substantial equivalence to existing devices, not on diagnostic accuracy against a "ground truth" established by human experts.

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, 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, not an AI/software as a medical device (SaMD) that involves human readers or AI assistance.

6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done

Not applicable. This is a physical medical device, not an algorithm or AI.

7. The Type of Ground Truth Used

Not applicable in the context of diagnostic accuracy. For the performance tests listed, the "ground truth" or reference standards are the established industry standards, test methodologies (e.g., ASTM, ISO), and the performance characteristics of the predicate devices. For example, for "Burst Strength," the "ground truth" would be the measurement obtained using a validated testing procedure, and the performance would be compared to that of the predicate.

8. The Sample Size for the Training Set

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

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

Not applicable. This is a physical medical device, not an AI/ML algorithm.

Ask a specific question about this device

VASCU-GUARD Vascular Repair Patch is used in peripheral vascular reconstruction including the carotid, renal, iliac, femoral, profunda and tibial vessels and arteriovenous access revisions.

VASCU-GUARD Vascular Repair Patch (VASCU-GUARD) is derived from bovine pericardium procured from cattle originating in the United States. The pericardium is cross-linked with glutaraldehyde and treated with 1 molar sodium hydroxide for a minimum of 60 minutes at 20-25° (68-77°F). VASCU-GUARD is terminally sterilized using gamma irradiation and packaged within a sterile double-pouch system. The contents of the unopened, undamaged outer pouch are sterile. VASCU-GUARD is MR Safe. VASCU-GUARD utilizes animal tissue; patient must be informed prior to any procedure.

The provided text is a 510(k) summary for the VASCU-GUARD Vascular Repair Patch. It describes the device, its intended use, and comparison to predicate devices, along with performance data. However, this document does not contain information about acceptance criteria or specific studies that demonstrate the device meets those criteria in the context of an AI/ML medical device.

The performance data listed (Visual, Suture retention, Dimensional, Burst strength, Collagenase digestion, Denaturation Temperature, Water Permeability, Pliability, Chemical and heavy metal residuals, Bioburden, Pyrogenicity/Endotoxins, Temperature Excursion Testing, Biocompatibility Assessment) are for physical and material properties of the vascular repair patch itself, not for an AI/ML algorithm's diagnostic or predictive performance.

Therefore, I cannot provide the requested information regarding acceptance criteria, device performance, sample sizes, ground truth, expert qualifications, adjudication methods, or MRMC studies for an AI/ML device, as the supplied text pertains to a physical medical device (a vascular repair patch) and not an AI/ML product.

Ask a specific question about this device

CardiaMend™ Pericardial and Epicardial Reconstruction Matrix is intended for pericardial reconstruction and repair and for epicardial support and repair.

CardiaMend™ Pericardial and Epicardial Reconstruction Matrix is a porous acellular matrix derived from fetal bovine dermis designed to provide soft tissue reinforcement, repair, and reconstruction. The single-layer (1 ply) device is not chemically crosslinked and consists of a naturally woven network of collagen fibers. The single use device is supplied terminally sterilized via ethylene oxide and is available in a variety of sizes to be trimmed by the physician to meet individual patient needs.

The provided text describes a 510(k) premarket notification for a medical device called CardiaMend™ Pericardial and Epicardial Reconstruction Matrix. This type of submission relies on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving independent safety and effectiveness through extensive clinical trials as an AI/ML medical device would typically require.

Therefore, the document does not contain the specific information requested about acceptance criteria and a study proving the device meets those criteria in the context of an AI/ML algorithm evaluation. Specifically, there is no mention of:

• Acceptance criteria in terms of AI/ML performance metrics (e.g., sensitivity, specificity, AUC).
• A "study that proves the device meets the acceptance criteria" in the context of AI/ML, such as a test set evaluation.
• Sample sizes for test sets or training sets, data provenance, ground truth establishment methods (expert consensus, pathology, outcomes data), number or qualifications of experts, adjudication methods, or MRMC comparative effectiveness studies.

The "Performance Data" section (Section VII) details various non-clinical tests performed to support substantial equivalence, including:

• Sterilization validation/re-qualification
• EO/ECH residuals per ISO 10993-7
• Packaging validation and shelf-life per ISO 11607-1 and ISO 11607-2
• Device Characterization Testing (Dimensional verification, Tensile Strength, Tensile Stiffness/Elastic Modulus, Burst Strength, Suture Pullout Strength, Cellular Infiltration, Porosity, Collagen Denaturation)
• Design Validations (Usability Validation)
• GLP Study in an Ovine Model (animal study evaluating performance and safety compared to a predicate device)

In summary, the provided document does not contain the information relevant to the performance evaluation of an AI/ML-based medical device as detailed in your request. It pertains to a Class II medical device (a collagen matrix) that uses a 510(k) pathway, which focuses on demonstrating substantial equivalence to existing devices through non-clinical performance data and an animal study, not AI/ML algorithm performance.

Ask a specific question about this device

Vascutek Cardiovascular Fabric is indicated for vascular repair whenever knitted polyester fabrics are normally indicated.

Due to its particularly high strength. Gelseal is especially suitable for thoracic use whereas the softer handle of the Gelsoft makes it ideal for peripheral use. The Thin Wall fabric is designed for endaterectorny, particularly of the carotid arteries.

The Vascutek Cardiovascular Fabric are a range of gelatin sealed, knitted, polyester patch fabrics. The range consists of three different patch fabrics which are manufactured using identical materials, processes and procedures but which, because of slight differences in the pattern of the base fabric, exhibit different physical characteristics. This range of products is provided in order to give the implanting surgeon a choice of several different fabrics from which they can chose the most suitable according to their own preferences and according to specific demands of any given surgical situation.

Two of the patches, Gelseal™ and Gelsoft™, are based on fabrics which are currently used in Vascutek's range of tubular vascular prostheses, which have received Premarket approval from the FDA. The only difference between the cardiovascular fabrics and the tubular grafts is that the patches are produced in flat, patch formats (i.e. square or rectangular) and have not been subjected to the crimping process which is used in the production of the tubular prostheses. With this single exception, the manufacturing facilities, equipment, processes and the quality control processes and procedures are identical to those used in the manufacture of the Gelseal™ and Gelsoft™ vascular prostheses.

The third type of patch, the Thin Wall Carotid Patch, is also manufactured using the identical materials, processes and procedures as the other cardiovascular patches but with a slightly modified knit pattern. This new structure has been developed in order to maintain the physical characteristics necessary for general cardiovascular patching but with a reduced wall thickness and characteristics which make it ideally suited to use for parching carotid arteries after endarterectomy procedures.

This is a 510(k) premarket notification for a medical device, not a study evaluating an AI algorithm. Therefore, the requested information about acceptance criteria, study design, expert involvement, and ground truth for an AI device is not available in the provided text.

The document describes the Vascutek Gelseal Patch, Vascutek Gelsoft Patch, and Vascutek Thin Wall Carotid Patch, which are cardiovascular fabric patches. The FDA has determined these devices are substantially equivalent to legally marketed predicate devices.

The "study" referenced in the document is a series of nonclinical tests performed to demonstrate that the device is safe and effective when compared to predicate devices. These tests included:

• Physical testing
• Biocompatibility testing
• Chemical characterization
• An animal performance study

The purpose of these tests was to show that the new devices, with a change in the gelatin supplier, perform as well as the previously approved devices.

Since this is not an AI device, the specific questions about acceptance criteria related to AI performance metrics (like sensitivity, specificity, or AUC), sample sizes for AI training/test sets, expert adjudication, or MRMC comparative effectiveness studies are not applicable and therefore cannot be answered from the provided text.

Ask a specific question about this device

The ADAPT® Tissue is indicated for use as a patch in the repair of cardiac defects including intracardiac defects, septal defects, valve and annulus repair.

The ADAPT® Tissue medical device is a bovine pericardial patch prepared from glutaraldehyde-crosslinked bovine pericardium using the ADAPT® TEP technology. It is a sterile, light yellow to beige colored, moist, pre-cut sheet of acellular collagen. The products range in size from 4cm² to 84cm² and can range in thickness from 0.25-0.80mm.

This document is a 510(k) Pre-Market Notification from Admedus Regen PTY LTD for their ADAPT® Tissue device. It primarily focuses on establishing substantial equivalence to previously cleared predicate devices (CardioCel and VascuCel) rather than presenting new performance data for the ADAPT® Tissue itself.

Therefore, many of the typical acceptance criteria and study details for an AI/ML device would not apply here. The key criteria for this submission are focused on demonstrating that "ADAPT® Tissue" is essentially the same device as the "CardioCel", with a minor labeling change (refining the indications for use).

However, I can extract the relevant information based on the document's content:

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

Since this is a substantial equivalence submission based on an existing device (CardioCel), the "acceptance criteria" here are that the ADAPT® Tissue should be functionally equivalent to CardioCel. The reported performance refers to the nonclinical testing already performed for CardioCel.

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

This information is not provided in the document as no new human clinical study was performed for the ADAPT® Tissue's specific submission. The submission relies on "nonclinical testing performed in support of the general intended use for CardioCel." Details about the sample size, provenance, and type of study for the original CardioCel testing are not included in this summary.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This is not applicable as this is not an AI/ML diagnostic or image analysis device relying on expert interpretation for ground truth. It's a biocompatibility and performance assessment of a surgical patch.

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

Not applicable for the reasons stated above.

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 device is a surgical patch, not an AI-assisted diagnostic tool.

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

Not applicable. This device is a surgical patch, not an algorithm.

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

For the "performance" verification of such a device, the "ground truth" would typically involve:

• Biocompatibility testing: In vitro and in vivo studies (animal models) to assess tissue integration, immune response, and toxicity, with outcomes often measured by histological analysis, inflammatory markers, and gross observations.
• Mechanical property testing: Laboratory tests to evaluate tensile strength, elasticity, and suture retention.
• Degradation studies: In vitro and in vivo studies to assess how the material degrades over time in a physiological environment.
• Sterility testing: Laboratory verification of sterility.

These "truths" are established through standard scientific and regulatory testing methods, not expert consensus in the diagnostic sense. The document states "The nonclinical testing performed in support of the general intended use for CardioCel also demonstrates substantial equivalence." This implies a reliance on these types of scientific evaluations performed for the predicate device.

8. The sample size for the training set

Not applicable. This is not an AI/ML device, so there is no training set in that context.

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

Not applicable. For the same reason as above.

Ask a specific question about this device

The XenoSure Biologic Patch is intended for use as a surgical patch material for cardiac reconstruction and repair, soft tissue deficiency repair and reinforcing the suture line during general surgical procedures.

The XenoSure consists of one piece of bovine pericardial tissue that has been selected for minimal tissue blemishes. The tissue is treated with a glutaraldehyde process which crosslinks the collagen fibers and minimizes antigenicity. XenoSure patch is liquid chemical sterilized and packaged in a plastic jar containing sterile glutaraldehyde storage solution.

The provided text is a 510(k) summary for the XenoSure Biologic Patch, which is a medical device. This document details the pre-clinical testing performed to demonstrate substantial equivalence to a predicate device, specifically to support a labeling change allowing the device to be exposed to temperatures below 0°C (i.e., frozen).

The request asks for information typically associated with the acceptance criteria and proof of performance for an AI/ML-driven medical device, including aspects like human reader studies, training/test set sample sizes, and ground truth establishment by experts. However, the provided document does not describe an AI/ML device; it is for a physical biologic patch used as surgical material. Therefore, information about AI-specific aspects (like MRMC studies, human-in-the-loop performance, training/test set ground truth for AI, number of experts for ground truth, etc.) is not applicable to this document.

Instead, the document details laboratory and animal studies to prove the physical and biological characteristics of the XenoSure Biologic Patch are not adversely affected by freezing.

Here's an analysis of the provided text in the context of the device's performance and acceptance criteria:

Acceptance Criteria and Study for XenoSure Biologic Patch

The study described here aims to demonstrate that a frozen XenoSure Biologic Patch is substantially equivalent to the unfrozen predicate XenoSure Biologic Patch. The acceptance criteria are based on mechanical properties and biological performance, ensuring the frozen device retains its intended function and safety.

1. Table of Acceptance Criteria and Reported Device Performance:

Ask a specific question about this device

The TigerPaw Pro is indicated for the occlusion of the left atrial appendage, under direct visualization, in conjunction with other open cardiac surgical procedures.

Direct visualization, in this context, requires that the surgeon is able to see the heart directly, without assistance from a camera, endoscope, etc., or any other viewing technology. This includes procedures performed by sternotomy (full or partial) as well as thoracotomy (single or multiple).

The TigerPaw Pro is a flexible, implantable occlusion fastener to be placed on the ostium of the left atrial appendage (LAA) during open cardiac surgical procedures. TigerPaw Pro consists of a Fastener implant that is pre-loaded onto a Delivery Tool and is for single use only. It is designed to provide an alternative to conventional suture and surgical staplers for occlusion of the ostium of the LAA. The TigerPaw Pro implantable fastener comes in two lengths; 35mm and 45mm. Surgeon judgment based on patient anatomy should determine what length fastener to apply.

The provided text does not contain information about the acceptance criteria or a study that proves the device meets specific acceptance criteria in the format requested. The document is a 510(k) summary for the TigerPaw Pro Left Atrial Appendage Occlusion Fastener and Delivery Tool, which outlines the device's indications for use, technological characteristics, and safety and performance testing conducted to demonstrate substantial equivalence to a predicate device.

While it mentions various performance tests and an animal study, it does not provide:

1. A table of acceptance criteria and reported device performance: The document lists several performance tests (e.g., ability to completely close the fastener, tensile strength of barbs, force required to actuate, corrosion testing) but does not present specific quantitative acceptance criteria or their corresponding results in a table format.
2. Sample size, data provenance, number of experts, adjudication method, MRMC study, standalone performance, type of ground truth, training set size, or how ground truth was established for these specific criteria. The animal study details the sample size (7 canines) and that a board-certified pathologist performed the necropsy, indicating the ground truth assessment method. However, these details are for the animal study, not explicitly linked to acceptance criteria in the tabular form or for a human-in-the-loop or standalone AI performance study.

Information that is present regarding studies and their findings:

• GLP Animal Study:

  • Sample size: 7 canines.
  • Data provenance: Acute Good Laboratory Practices (GLP) animal study.
  • Ground truth experts: Board-certified pathologist for full necropsy examination of local tissues post device implantation.
  • Ground truth type: Pathology and visual assessment of the device's usability, safety, and performance during and after deployment.
  • Results: "All acceptance criteria were met for this animal study performed using the market version of this device."
  • Purpose: To evaluate the usability of the device and the risk of tissue injury on the LAA during deployment and securement of the fastener.

• Performance Testing (In-vitro):

  • Included tests such as:
    • Ability to completely close the fastener after deployment and prevent leakage from a mock LAA.
    • Tensile strength of individual fastener barbs after closure.
    • Assessment of Delivery Tool jaw component characteristics (e.g., angle measurements).
    • Force required to actuate the Delivery Tool trigger, unlock button, and torque for shaft rotation.
    • Corrosion testing (ISO 10555-1 Annex A).
    • Comparison of TigerPaw II and TigerPaw Pro's tool jaw resistance to flexure on a worst-case thickness mock LAA ostium.
    • Comparison of TigerPaw II and TigerPaw Pro's ability to deploy and secure fasteners under different worst-case rotational forces on a mock ostium.
  • Results: "The results of the in-vitro tests conducted demonstrate that the functionality and performance characteristics of the device are comparable to the previously cleared TigerPaw System II."

The document concludes that "The performance and other testing established that the TigerPaw Pro is substantially equivalent to the predicate device," but it does not provide the specific acceptance criteria and detailed quantitative results for each test in a format that directly addresses all parts of your request.

Ask a specific question about this device

The MatriStem UBM™ Pericardial Patch is intended for the reconstruction and repair of the pericardium.

The MatriStem UBM Pericardial Patch is a 4-layer multi-laminate device comprised of stacked urinary bladder matrix (UBM) sheets. The Pericardial Patch serves as a patch to reconstruct the pericardium and restore the native anatomy. The Pericardial Patch is available in three sizes: 7x10 cm, 7x15 cm, and 10x15 cm. Each device is packaged in a double peel-open pouch and an outer carton. The device is terminally sterilized using electron-beam irradiation.

This document describes the regulatory submission for the MatriStem UBM™ Pericardial Patch, a medical device intended for the reconstruction and repair of the pericardium. It is a 510(k) premarket notification, which means the manufacturer (ACell, Inc.) is seeking to demonstrate that their device is substantially equivalent to legally marketed predicate devices, and therefore does not require a full premarket approval (PMA).

The information provided covers bench testing and an animal study to support the substantial equivalence claim. However, it's important to note that this submission does not involve an AI/ML-based device and therefore the questions relating to AI-specific acceptance criteria, multi-reader multi-case studies, expert adjudication methods, and training/test set ground truth establishment for an AI algorithm are not applicable to this document. The device is a biological patch, not a diagnostic or prognostic AI tool.

Therefore, many of the requested items regarding AI/ML aspects will be answered as "Not Applicable" or "No" as the study described is for a physical medical device.

Here's the breakdown based on the provided text:

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

Since this is a physical medical device and not an AI model, the acceptance criteria are based on physical, chemical, and biological properties, and functionality in an in vivo model.

Note: Specific quantitative acceptance criteria for most bench tests are not provided in this public summary but are typically part of internal design control documentation and would have been submitted to the FDA. The document states "All acceptance criteria were met" for the animal study, indicating the successful completion of the pre-defined endpoints.

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

• Test Set Sample Size (Animal Study):

  • Total pigs: 12
  • Sham group (no repair): 2 pigs
  • ACell MatriStem UBM Pericardial Patch group: 5 pigs
  • Predicate CorMatrix Pericardial Patch group: 5 pigs

• Data Provenance: The study was a "90-day Good Laboratory Practices (GLP) animal study" performed in a porcine (pig) model. The country of origin is not specified but generally, GLP studies adhere to international standards. It is a prospective animal study designed to evaluate the device.

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

• Not Applicable (N/A) for an AI/ML context. This is a physical medical device.
• For the animal study, the ground truth was established through objective biological and physiological assessments:
  • Histology evaluation: Performed by pathologists.
  • Full necropsy examination: Performed by veterinary pathologists.
  • Echocardiography measurements: Performed by specialists in echocardiography (likely veterinary cardiologists or trained technicians).
  • The document implies that these assessments were performed by qualified personnel as part of a GLP study, but the specific number and qualifications of individuals are not detailed in this summary.

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

• N/A for an AI/ML context. This pertains to consensus among human readers for image interpretation, which is not relevant for this device.
• For the animal study, the "adjudication" of results would rely on standardized GLP protocols for sample collection, pathology, and data analysis to ensure consistency and objectivity. Any disagreements in interpretation (e.g., in histology slides) would typically be resolved by senior pathologists or consensus panels within the pathology group, but this is not an "adjudication method" in the AI sense.

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 is a study for a physical implantable medical device, not an AI diagnostic/assistance tool.
• The comparative effectiveness was demonstrated by comparing the subject device to a predicate device and a sham in an animal model based on biological and physiological outcomes, not human reader performance.

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

• N/A. This is a physical medical device, not an algorithm.

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

• Pathology and Outcomes Data (from an animal model).
  • Histology evaluation: Provides microscopic ground truth on tissue response, cellular infiltration, and remodeling.
  • Full necropsy examination: Provides macroscopic ground truth on device integration and tissue health.
  • Echocardiography measurements: Provides functional ground truth on cardiac performance.
  • The "ground truth" for the device's performance in vivo was established by these objective biological and physiological assessments in directly implanted animals.

8. The sample size for the training set

• N/A. This is a physical medical device. There is no "training set" in the context of machine learning.
• The development process for this device would involve extensive internal research and development, materials characterization, and process optimization, but this does not constitute a "training set" for an AI model.

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

• N/A. As there is no AI training set, this question is not applicable.

Ask a specific question about this device

PhotoFix is indicated for the following uses: intracardiac repair, suture line buttressing, pericardial closure, and vascular repair and reconstruction (for example: the carotid, iliac, femoral, and tibial blood vessels and arteriovenous access revisions).

The PhotoFix® Decellularized Bovine Pericardium ("PhotoFix") is a cardiovascular patch that is prepared from bovine pericardium, stabilized using dye-mediated photooxidation, processed using ethylene oxide, and sterilized using aseptic processing techniques. The photooxidation process creates crosslinks in the bovine tissue. No aldehyde chemistry is used during any phase of manufacturing including the tissue fixation or sterilization processes. PhotoFix is intended for single use only and cannot be resterilized. PhotoFix is supplied sterile in a sealed container with 22% buffered ethanol solution. Rinsing of the pericardium prior to implantation is not required.

This document is a 510(k) premarket notification for a medical device called PhotoFix® Decellularized Bovine Pericardium. It describes the device and claims substantial equivalence to a previously marketed device (K172085).

However, the provided text does not contain any information about acceptance criteria or a study that proves the device meets specific performance criteria, especially in the context of an AI/ML powered device. The document is a traditional medical device submission for a physical implant, not an AI/ML algorithm.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and the reported device performance.
2. Sample size used for the test set and data provenance.
3. Number of experts used to establish ground truth.
4. Adjudication method.
5. MRMC comparative effectiveness study.
6. Standalone performance.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

This document focuses on the substantial equivalence of a modified physical device (a new packaging size for an existing bovine pericardium patch) to a predicate device, based on non-clinical testing related to packaging integrity and shelf-life, not clinical performance metrics or AI/ML algorithm validation.

Ask a specific question about this device