Search Results

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

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 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

CorMatrix(R) Cor Patch is intended for epicardial tissue support and repair.

CorMatrix Cor Patch is intended for epicardial tissue support and repair.

CorMatrix Cor Patch is derived from the same multi-laminate SIS-ECM material as the CorMatrix Tyke (2-ply, non-pressed). The CorMatrix® Cor Patch will be supplied as a 4-ply, lyophilized, sterilized sheet of SIS-ECM. With the exception of the differing layer counts and a change to the manufacturing process for the Cor Patch which does not result in a change to the fundamental technology of the device, the device design and construction are identical to the FDA-cleared CorMatrix® Tyke™ (K152127).

This document is a 510(k) premarket notification for a medical device called CorMatrix Cor Patch. It describes the device, its intended use, and argues for its substantial equivalence to a previously cleared predicate device, the CorMatrix Tyke.

However, this document does not contain the information required to answer your specific questions regarding acceptance criteria and a study proving a device meets these criteria in the context of an AI/ML medical device.

Here's why and what's missing:

• Device Type: The CorMatrix Cor Patch is a biological patch made from porcine extracellular matrix material for epicardial tissue support and repair. It is a physical medical device, not an AI/ML algorithm or software.
• Study Type: The "Non-clinical Testing" section describes material property testing (tensile strength, suture retention, burst strength) to demonstrate adequate material properties, not a clinical study involving human or even simulated human-in-the-loop performance with an AI system.
• Acceptance Criteria: The document mentions that the testing "demonstrates that the sterile SIS-ECM of the Cor Patch possesses adequate material properties for use in the indicated applications" and "exceeds the biomechanical requirements for its intended use." However, it does not provide a specific table of acceptance criteria with quantitative thresholds for AI performance metrics (like sensitivity, specificity, AUC, human reader improvement).
• Ground Truth, Experts, Adjudication, MRMC, Standalone Performance: These concepts are relevant to the evaluation of AI/ML algorithms, where the performance of the algorithm is compared against a "ground truth" established by human experts, pathology, or outcomes data. This document does not describe such studies because the device is a physical patch.
• Sample Size (for AI training/test sets): The document refers to "testing" but does not specify sample sizes in the context of test or training sets for an AI algorithm.
• Data Provenance: Not applicable in the context of material property testing for a physical device.

In summary, the provided text is about a physical medical device (a tissue patch) and its material properties, not about an AI/ML medical device and its performance evaluation against established acceptance criteria.

Therefore, I cannot extract the requested information from this document. If you provide a document that describes the development and validation of an AI/ML medical device, I would be happy to help answer your questions.

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) summary for the PhotoFix Decellularized Bovine Pericardium. It describes the device, its indications for use, and its substantial equivalence to predicate devices based on comparative testing of biomechanical properties. However, it does not contain the specific information required to complete the table or answer the detailed questions regarding acceptance criteria and study particulars for a device performance study in the way a clinical or AI-based diagnostic device submission would.

This document focuses on biomechanical performance testing comparing the new device to existing predicate devices, not on a human-in-the-loop or standalone algorithm performance study typical for AI/ML medical devices.

Therefore, many of the requested fields cannot be filled from the provided text.

Here is the information that can be extracted or deduced:

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

Note on Acceptance Criteria: The document states that testing demonstrated that PhotoFix is substantially equivalent to the identified predicate devices for the biomechanical properties. This implies that the implicit acceptance criterion was meeting a comparable performance standard to these predicate devices, which are already legally marketed. Quantitative acceptance criteria are not explicitly listed in this summary.

Regarding the study that proves the device meets the acceptance criteria:

The study described is a comparative biomechanical testing study.

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

  • Sample Size: Not specified in the provided summary. The study involved comparative biomechanical testing of the PhotoFix device against two predicate devices (XenoSure and CorMatrix). The "test set" would refer to the number of PhotoFix samples tested for each biomechanical property.
  • Data Provenance: Not explicitly stated but clinical data provenance (e.g., country of origin, retrospective/prospective) is not applicable as this was a laboratory biomechanical testing study, not a clinical study. It's an in-vitro/ex-vivo material property study.

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

  • Not applicable. This was a laboratory-based biomechanical performance test, not a study requiring expert consensus for ground truth. The "ground truth" would be the measured physical properties of the materials.

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

  • Not applicable. This was a laboratory-based biomechanical performance test.

• 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 type of study is for diagnostic devices, particularly AI/ML-based ones. This document describes a tissue patch for surgical repair.

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

  • No. This is not an AI/ML algorithm.

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

  • The "ground truth" for this type of study would be the measured physical and mechanical properties of the PhotoFix device and the predicate devices, obtained through standardized laboratory testing (e.g., force transducers, tensile testers, etc.). It is not clinical or expert-derived ground truth.

• 8. The sample size for the training set:

  • Not applicable. This is 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 not an AI/ML algorithm.

Ask a specific question about this device

The bovine pericardial vascular patch is intended for use as a surgical patch material for: vascular reconstruction and repairs; peripheral vascular reconstruction and repairs; and suture-line buttressing.

The pericardial patch is comprised of a piece of bovine pericardium that has been preserved in a phosphate buffered glutaraldehyde solution. The Duravess patch comes in three sizes and configurations for vascular reconstruction and repair purposes. Model DP08X8: 0.8 cm x 8 cm, rectangular with round corners and a tapered end Model DP1X6: 1 cm x 6 cm, rectangular with round corners Model DP2X9: 2 cm x 9 cm, rectangular with round corners

The provided text describes the 510(k) premarket notification for the Duravess Bovine Pericardial Vascular Patch. It does not contain information about acceptance criteria for a device's performance that would typically be evaluated in a study with metrics like sensitivity, specificity, or reader performance. Instead, it focuses on demonstrating substantial equivalence to a predicate device through shared characteristics and successful functional and performance testing.

Therefore, many of the requested sections about acceptance criteria, detailed study design, ground truth establishment, and expert involvement are not applicable to the information provided in this document.

Here's a breakdown of what can be extracted and what cannot:

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

The document does not specify quantitative acceptance criteria in terms of performance metrics (e.g., specific thresholds for tensile strength, burst pressure, etc.) that the device must meet, nor does it present device performance in a numerical format against such criteria. It states:

• Acceptance Criteria (Implied): The device successfully pass functional and performance testing demonstrating that it satisfies the same performance requirements as the predicate device.
• Reported Device Performance: "The Duravess bovine pericardial vascular patch has successfully passed functional and performance testing, demonstrating that the subject device satisfies the same performance requirements as the predicate device."

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

This information is not provided in the document. The document refers to "functional and performance testing" but does not detail the sample sizes, data provenance, or study design for these tests.

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

This information is not provided as the type of "test set" and "ground truth" typically associated with expert review (e.g., for diagnostic AI devices) is not applicable here. The testing referenced is likely material science and biocompatibility testing.

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

This information is not provided.

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 type of study is not applicable to a vascular patch device. The document describes a biological implant, not an AI or imaging diagnostic tool that would involve human readers.

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

This is not applicable to this device.

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

The document does not detail specific "ground truth" as it relates to clinical outcomes or expert diagnoses. For a vascular patch, "ground truth" for performance would be established through laboratory testing based on predetermined specifications or standards for material properties (e.g., tensile strength, burst pressure, suture retention) and biocompatibility, as well as potentially animal studies. The text states it "successfully passed functional and performance testing."

8. The sample size for the training set

This is not applicable as this is not an AI/ML device requiring a training set.

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

This is not applicable as this is not an AI/ML device requiring a training set.

Summary of available information regarding the "study" (functional/performance testing):

• Device Tested: Duravess Bovine Pericardial Vascular Patch
• Purpose of Testing: To demonstrate that the device satisfies the same performance requirements as the predicate device (Edwards bovine pericardial patch; K082139) to establish substantial equivalence.
• Outcome: "successfully passed functional and performance testing."
• Details Not Provided:
  • Specific quantitative acceptance criteria or performance results.
  • Details of the functional and performance tests performed.
  • Sample sizes used for testing.
  • Specific methodologies for establishing "ground truth" beyond meeting predefined performance requirements.
  • Information related to expert involvement or clinical study design, which are not relevant for this type of device's 510(k) submission focused on substantial equivalence to a predicate.

Ask a specific question about this device

CardioCel 3D is indicated for use as a patch in pericardial closure and the repair of cardiac and vascular defects including intracardiac defects; septal defects, valve and annulus repair; great vessel reconstruction, peripheral vascular reconstruction and suture line buttressing.

The CardioCel 3D 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. It is offered in a 4 x 6 cm size with a 60° curve.

The provided document is a 510(k) premarket notification for a medical device called CardioCel 3D. This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving the device meets specific acceptance criteria through a clinical study. Therefore, the document does not contain the detailed information typically found in studies designed to establish device performance against predefined acceptance criteria for AI algorithms.

Here's an analysis based on the information provided, highlighting why certain questions cannot be answered from this document:

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

This document does not specify "acceptance criteria" in the sense of performance metrics for an AI algorithm (e.g., sensitivity, specificity, AUC). Instead, it describes verification and validation testing performed on the physical device.

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

This information is not applicable and therefore not provided. The document describes laboratory verification and validation testing of the physical properties and characteristics of the CardioCel 3D device. It is not presenting data from a "test set" in the context of an AI 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):

This question is not applicable to this document. "Ground truth" and "experts" in this context typically refer to establishing diagnostic certainty for an AI algorithm's performance, which is not what this document addresses. The "ground truth" for the device's physical properties would be established by validated measurement standards and laboratory methods.

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

This is not applicable to this document as no expert adjudication of diagnostic outcomes is involved.

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

This is not applicable to this document. An MRMC study is relevant for evaluating the impact of AI on human interpretation of medical images or data, which is not the purpose of this 510(k) submission for a tissue patch.

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

This is not applicable to this document. There is no algorithm being evaluated in this submission.

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

The "ground truth" for the physical device would be established through scientific measurement standards and validated laboratory methodologies (e.g., precise calipers for dimensional verification, standardized tensile testing equipment and protocols for tensile strength, calibrated burst pressure testers, etc.). This is implicitly assumed for "verification and validation testing."

8. The sample size for the training set:

This is not applicable to this document as no AI algorithm is being trained or evaluated.

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

This is not applicable to this document as no AI algorithm is being trained or evaluated.

Summary of the document's content regarding device performance:

The document indicates that the CardioCel 3D device underwent "Verification and validation testing" which included:

• Dimensional verification
• Crosslink stability
• Tensile testing
• Burst pressure testing

Additionally, a risk assessment evaluated:

• Biocompatibility
• Sterility
• Packaging
• Shelf life

Conclusion: The results of these tests and the risk assessment "demonstrated that the design outputs of the modified device meet the design inputs in conformance with established design controls." This forms the basis for the FDA's determination of substantial equivalence to the predicate device (CardioCel K130872). The key difference from the predicate is that CardioCel 3D holds a curved shape due to a manufacturing change during crosslinking, while maintaining identical intended use, raw materials, tissue processing, sterilization, packaging, and principles of operation.

Ask a specific question about this device