Search Results

For implantation to reinforce soft tissue where weakness exists, in patients requiring soft tissue repair, or reinforcement in plastic or reconstructive surgery.

Restrata Soft Tissue Reinforcement (STR) is an electrospun fiber matrix intended for implantation to reinforce soft tissue where weakness exists, in patients requiring soft tissue repair, or reinforcement in plastic or reconstructive surgery. Restrata Soft Tissue Reinforcement is composed of resorbable synthetic fibers engineered from biocompatible materials. The fibers comprising Restrata STR are produced from polyglactin 910 (PGLA 90:10) and polydiaxonone (PDO). Contents of the package are provided sterile. The device is intended for one-time use.

The provided text is a 510(k) clearance letter for the Restrata Soft Tissue Reinforcement (STR) device. While it states that nonclinical testing was performed, it does not provide the specific acceptance criteria, reported device performance, or details about the studies that demonstrate the device meets these criteria.

Therefore, many of the requested items cannot be extracted from this document.

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

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

• Cannot be created. The document mentions "benchtop flexural stiffness, tensile, suture pullout, burst, and tear resistance testing, as well as a comparative animal study," but it does not specify what the acceptance criteria were for these tests or what the reported performance outcomes were.

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

• Cannot be determined. The document mentions a "comparative animal study" but does not provide details of its design, sample size, or provenance.

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

• Not applicable / Cannot be determined. This type of information is typically relevant for studies involving human interpretation (e.g., image analysis by radiologists). For a physical medical device like surgical mesh, "ground truth" would be established through objective physical and biological measurements, not expert consensus on interpretations. Even for the animal study, the mechanism for establishing "ground truth" (e.g., histological analysis, clinical observation) is not detailed, nor is the involvement of "experts" in establishing it.

4. Adjudication method for the test set

• Not applicable / Cannot be determined. 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

• Not applicable. This device is a physical surgical mesh, not an AI-assisted diagnostic or interpretative tool. Therefore, an MRMC study is not relevant.

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

• Not applicable. This device is a physical surgical mesh, not an algorithm.

7. The type of ground truth used

• Cannot be determined with specific detail. For the benchtop tests, the ground truth would be the physical properties measured (e.g., force required for tear, burst pressure) against material specifications. For the animal study, the ground truth would likely involve histological analysis, physical integrity of the implant in vivo, and biocompatibility observations, but this is not explicitly stated.

8. The sample size for the training set

• Not applicable. This device is not an AI/ML algorithm that requires a training set in the conventional sense. The "training" for a physical device would refer to its development process, which isn't described in terms of a "training set."

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

• Not applicable. See point 8.

In summary, the provided FDA clearance letter attests to the device's substantial equivalence based on a review of provided data, but it does not contain the detailed study information (specific criteria, performance results, study design details etc.) that would typically be found in the full 510(k) submission or a peer-reviewed publication.

Ask a specific question about this device

Restrata® MiniMatrix is intended for use in the management of wounds, including: Partial and full thickness wounds, pressure sores / ulcers, venous ulcers, chronic vascular ulcers, tunneled / undermined wounds, surgical wounds (e.g., donor site / grafts, post-laser surgery, post-Mohs surgery, podiatric wounds, dehisced wounds), trauma wounds (e.g., abrasions, lacerations, partial thickness burns, skin tears), and draining wounds.

Restrata MiniMatrix is a sterile, single use device intended for the local management of wounds. Restrata MiniMatrix is a form of Restrata Matrix that can be dispersed at the wound site during application. The device is made from synthetic biocompatible materials and was designed to include a fibrous structure with high porosity similar to native extracellular matrix. Restrata MiniMatrix completely degrades via hydrolysis. The device does not contain any human or animal materials or tissues.

Restrata MiniMatrix is supplied in a nested pouch configuration, placed within a shelf-box. The product is terminally sterilized. Contents of the package are guaranteed sterile and non-pyrogenic unless the package has been opened or damaged.

The provided text describes data regarding the Restrata® MiniMatrix wound dressing, which is a medical device. However, it does not contain any information about an AI/ML-driven medical device, nor does it present acceptance criteria or a study proving performance for such a device.

The document is an FDA 510(k) clearance letter and its summary for a medical device (wound dressing). The studies mentioned (biocompatibility, sterilization, wound healing animal model) are typical for assessing the safety and efficacy of a medical device, especially when seeking substantial equivalence to a predicate device, but they are not related to AI/ML performance.

Therefore, I cannot fulfill your request for the following information based on the provided text, as it describes a non-AI medical device:

1. A table of acceptance criteria and the reported device performance: Not applicable for an AI device. The document discusses performance in terms of biocompatibility, sterilization, and wound healing in an animal model, not AI metrics.
2. Sample sizes used for the test set and the data provenance: Not applicable in the AI context. The document mentions a "full thickness porcine wound model" but not a test set for an AI model.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable.
4. Adjudication method for the test set: Not applicable.
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.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.
7. The type of ground truth used: Not applicable in the AI context. The ground truth for this device's evaluation would be biological outcomes (e.g., wound healing progression in the animal model) and material properties.
8. The sample size for the training set: Not applicable.
9. How the ground truth for the training set was established: Not applicable.

In summary, the provided document details the FDA regulatory clearance for a wound dressing, not an AI/ML medical device. Therefore, the requested information pertaining to AI acceptance criteria and performance studies is not present.

Ask a specific question about this device

Restrata® is intended for use in the management of wounds, including: Partial and full thickness wounds, pressure sores/ ulcers, diabetic ulcers, chronic vascular ulcers, tunneled / undermined wounds, surgical wound (e.g., donor site/ grafts, post-Mohs surgery, podiatric wounds, dehisced wounds), trauma wounds (e.g., abrasions, partial thickness burns, skin tears), and draining wounds.

Restrata® is a sterile, single use device intended for use in local management of wounds. Restrata® is a soft, white, conformable, non-friable, absorbable matrix that provides a moist environment for the body's natural healing process to occur. Restrata® is made from synthetic biocompatible materials and was designed to include a fibrous structure with high porosity, similar to native extracellular matrix. Restrata® is a porous matrix with a defined rate of resorption that provides a scaffold for cellular infiltration and vascularization before completely degrading via hydrolysis. The device permits the ingress of cells and soft tissue formation in the defect space / wound bed. The device does not contain any human or animal materials or tissues. Restrata® is terminally sterilized, in a single use double peel package in a variety of sizes in non-meshed and meshed configurations. Contents of the package are guaranteed sterile and non-pyrogenic unless the package has been opened or damaged. The subject device is a modification of the predicate device to include updated product labeling, a change in product size offerings, and a change in product design offerings.

The provided text is a 510(k) Summary for the Acera Surgical Restrata® wound matrix, seeking substantial equivalence to a predicate device. This type of document focuses on demonstrating that a new medical device is as safe and effective as a legally marketed device and does not typically include detailed studies with acceptance criteria, sample sizes, expert qualifications, or MRMC studies, as would be expected for an AI/ML powered device.

The "study" in this context is the submission and review process for substantial equivalence (510(k)), which primarily relies on demonstrating that the technological characteristics and performance of the new device are equivalent to a predicate device.

Here's an attempt to answer your questions based on the provided text, while acknowledging that many of your points are not directly addressed because this is not an AI/ML device submission:

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

The document doesn't explicitly state "acceptance criteria" in the way one might for a diagnostic performance study. Instead, the "acceptance criteria" can be inferred as demonstrating substantial equivalence to the predicate device (Restrata® Wound Matrix K170300) and the reference device (PriMatrix® Dermal Repair Scaffold K153690) across various technological characteristics. The reported device performance is presented as direct equivalence.

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

The document does not describe a "test set" in the context of a statistical study for device performance. It refers to the predicate device (Restrata® Wound Matrix K170300) and a reference device (PriMatrix® Dermal Repair Scaffold K153690). The "data" provenance for asserting equivalence comes from prior approvals and testing related to these predicate and reference devices, not new patient data or a specific test set for the subject device. The submission focuses on changes to the predicate device (updated labeling, new smaller size, and meshed design options) and argues these changes do not alter fundamental safety and effectiveness.

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

Not applicable. The ground truth here is the established safety and effectiveness of the predicate device, as determined by its original 510(k) clearance process. No new expert adjudication for a test set is reported for this specific submission, as it relies on equivalence to existing devices.

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

Not applicable. No new test set requiring expert adjudication is described.

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

Not applicable. This device is a wound matrix, not an AI/ML-powered diagnostic or assistive tool.

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

Not applicable. This device is a wound matrix, not an AI/ML algorithm.

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

For this 510(k) submission, the "ground truth" is that the predicate device is safe and effective. The subject device demonstrates substantial equivalence by showing that its technological characteristics are the same or adequately similar to the predicate, and any differences (like new sizes or meshed configuration) do not raise new questions of safety or effectiveness. This is supported by relying on previously submitted and reviewed non-clinical testing (mechanical, biocompatibility) for the predicate device.

8. The sample size for the training set

Not applicable. No training set is involved as this is not an AI/ML device.

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

Not applicable. No training set is involved.

Ask a specific question about this device

The Cerafix Dura Substitute is indicated as a dura substitute for the repair of dura mater. This device is indicated for defects of 4.9 in2 (31.7cm2) or less in area. For example, 4.0 in x 1.2 in (10.0 cm x 3.1 cm) would be an acceptable defect size.

Cerafix® Dura Substitute is a resorbable implant for repair of dural defects. The device can be applied as an onlay matrix or sutured in place. Cerafix® Dura Substitute is a soft, white, pliable, nonfriable, porous polymer matrix. Cerafix® Dura Substitute is available in a variety of sizes and is supplied sterile and nonpyrogenic in a single-use nested pouch configuration, which is enclosed within a protective chipboard envelope.

The provided text describes the Cerafix® Dura Substitute, a medical device for dura mater repair, and its equivalence to predicate devices, particularly focusing on expanding its indicated defect size and application method. The document, however, does not contain a detailed study proving acceptance criteria for an AI/ML device. Instead, it discusses the substantial equivalence of the Cerafix® Dura Substitute based on technological characteristics and animal studies, which is typical for a 510(k) submission for a non-AI medical device.

Therefore, many of the requested points regarding AI/ML device acceptance criteria and studies cannot be answered from this document. I will focus on the information that is present regarding the non-AI device.

Acceptance Criteria and Device Performance (Based on the non-AI device context):

The document describes "Indications for Use" and "Technological Characteristics" which serve as the de facto acceptance criteria for the expanded use of the Cerafix® Dura Substitute via a 510(k) submission. The "reported device performance" is primarily demonstrated through equivalence to a predicate device and side-by-side animal studies.

Regarding AI/ML Specific Information (points 2-9):

The provided document describes a 510(k) submission for a physical medical device (Cerafix® Dura Substitute), not an AI/ML driven software device. Therefore, the following points are not applicable to this submission based on the provided text:

2. Sample size used for the test set and the data provenance: Not applicable, as this is a physical device, not an AI/ML algorithm requiring a test set for performance evaluation in the described manner.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for an AI/ML algorithm's predictions is not relevant here.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable.
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 not an AI-assisted diagnostic tool.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not applicable in the context of AI/ML ground truth. The "ground truth" for this physical device's performance is derived from biological/physiological responses in animal models and comparison to known predicate device performance.
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.

Summary of Relevant "Study" for the physical device:

• Study Type: Side-by-side animal implantation studies.
• Model: Canine duraplasty model.
• Procedure: Dural defects (18 mm x 25 mm) created. Both the subject device (Cerafix® Dura Substitute) and the predicate device were implanted without the use of suture (onlay).
• Outcome Measured: "Equivalent safety and performance" between the subject and predicate devices.
• Conclusion: This animal study supported the expanded indication for onlay application and reinforced the safety and performance for dura repair. The justification for the increased defect size (from 4.4 in² to 4.9 in²) is stated as "Data included in this submission to justify defect increase," but the specific data from that justification is not detailed in this summary.

Ask a specific question about this device

Restrata™ Wound Matrix is intended for use in the management of wounds, including: Partial and full thickness wounds, pressure sores/ ulcers, diabetic ulcers, chronic vascular ulcers, tunneled / undermined wounds, surgical wound (e.g., donor site/ grafts, post-Mohs surgery, podiatric wounds, wound dehiscence), trauma wounds (e.g., abrasions, partial thickness burns, skin tears), and draining wounds.

The Restrata™ Wound Matrix is a sterile, single use device intended for use in local management of wounds. The Restrata™ Wound Matrix is a soft, white, conformable, non-friable, absorbable matrix that acts as a protective covering for wound defects, providing a moist environment for the body's natural healing process to occur. Restrata™ is made from synthetic biocompatible materials and was designed to include a fibrous structure with high porosity, similar to native extracellular matrix. Restrata™ is a porous matrix with a defined rate of resorption that provides a scaffold for cellular infiltration and vascularization before completely degrading via hydrolysis. The device permits the ingress of cells and soft tissue formation in the defect space / wound bed. The device does not contain any human or animal materials or tissues. Restrata™ Wound Matrix is supplied terminally sterile, in a single use double peel package in a variety of sizes. Contents of the package are guaranteed sterile and non-pyrogenic unless the package has been opened or damaged.

The provided text is a 510(k) Summary for the Acera Surgical Restrata™ Wound Matrix. This document describes the device, its intended use, and its technological characteristics as part of a premarket notification to the FDA to demonstrate substantial equivalence to an already legally marketed predicate device.

Key takeaway: This document is not a study proving a device meets acceptance criteria, but rather a submission to the FDA demonstrating substantial equivalence. Therefore, much of the requested information about acceptance criteria, study details, sample sizes, expert involvement, and ground truth establishment will not be found in this type of regulatory submission. The 510(k) process focuses on demonstrating similarity to an existing device, rather than proving a device meets specific, predefined performance metrics through a clinical study with acceptance criteria.

However, I can extract the information that is present and explain why other information is not available:

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

The document does not present a table of specific, numeric acceptance criteria with corresponding device performance metrics. Instead, it demonstrates equivalence through comparative tables of characteristics and references to performance data.

From the "Technological Characteristics" section, a comparative table is provided:

Performance Data Summary:

• "The subject device has mechanical properties (tensile strength and suture pull-out strength) equivalent or superior to the reference device." (No specific numerical values or acceptance criteria are stated).
• "The subject device was also tested against a commercially available wound dressing with the same intended use in a clinically relevant full thickness porcine wound model. Analysis included an assessment of biocompatibility, along with macroscopic assessment of wound healing, planimetric measurement of wound closure, and histopathology. Test results showed that the subject device had an equivalent wound healing response compared to the control article, and exhibited no adverse tissue responses." (Again, no specific numerical outcomes or acceptance criteria are provided; the finding is "equivalent").

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

• Sample size: Not explicitly stated. The "Performance Data" section mentions a "clinically relevant full thickness porcine wound model," implying animal testing, but the number of animals or wounds tested is not specified.
• Data provenance: The performance data comes from non-clinical testing (mechanical properties and a porcine wound model). The country of origin for the data is not specified, nor is whether the study was retrospective or prospective (though animal model studies are inherently prospective).

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

• This information is not provided. Since the described tests are primarily non-clinical (mechanical and animal model), the concept of "experts establishing ground truth for a test set" in the context of human data (e.g., radiologists for imaging) does not directly apply. For the animal study, the assessment of "equivalent wound healing response" and "no adverse tissue responses" would have been made by researchers/veterinarians/pathologists, but their number and specific qualifications are not detailed in this summary.

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

• This information is not provided and is generally not applicable to the non-clinical tests described in this 510(k) summary. Adjudication methods are typically used in clinical studies involving interpretation of human data.

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 MRMC study was performed or described. This document is for a physical medical device (wound matrix), not an AI/software device that assists human readers.

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

• Not applicable, as this is a physical medical device, not an algorithm.

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

• For the mechanical properties, the "ground truth" would be established by standardized mechanical testing methods.
• For the porcine wound model, the "ground truth" was established through "macroscopic assessment of wound healing, planimetric measurement of wound closure, and histopathology." This is effectively a combination of direct observation, quantitative measurement, and microscopic pathology, as assessed by the researchers of that study.

8. The sample size for the training set

• Not applicable. This is a physical device being submitted via 510(k), not an AI/machine learning algorithm that requires a training set. The "testing" referred to is for device performance, not algorithm training.

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

• Not applicable, as there is no training set for a physical device.

Ask a specific question about this device

The Cerafix® Dura Substitute is indicated as a dura substitute for the repair of dura mater. This device is indicated for defects of 4.4 in2 (28.3 cm2) or less in area. For example, 4.0 in x 1.1 in (10.1 cm x 2.8 cm) would be an acceptable defect size.

Cerafix® Dura Substitute is a resorbable implant for repair of dural defects and is to be used with tensionless sutures. Cerafix® Dura Substitute is a soft, white, pliable, nonfriable, porous polymer matrix. Cerafix® Dura Substitute is available in a variety of sizes and is supplied sterile and nonpyrogenic in a single-use nested pouch configuration, which is enclosed within a protective chipboard envelope.

The provided document is a 510(k) summary for the Cerafix Dura Substitute. It describes the device, its indications for use, and a comparison to a predicate device to demonstrate substantial equivalence.

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

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

The document does not explicitly present a table of "acceptance criteria" with numerical targets and reported performance values for each criterion in the way one might expect for a diagnostic or AI device. Instead, it focuses on demonstrating "substantial equivalence" to a predicate device.

The primary "acceptance criteria" implicitly revolve around demonstrating equivalent performance to the predicate device in terms of:

• Safety and Efficacy: No significant differences in adverse events or repair outcomes.
• Biocompatibility: No new biocompatibility concerns.
• Mechanical Properties: Equivalent per unit area to the predicate.
• Neoduralization and Resorption: Similar mechanisms and timelines to the predicate.
• Absence of Complications: No CSF leaks, hydrocephalus, hemorrhage, or infection.

The reported device performance is that the subject device (new Cerafix Dura Substitute) was found to be equivalent to the predicate device (previously cleared Cerafix Dura Substitute - K153613) in all these aspects.

Key Comparison Points and Performance (Implicit Acceptance Criteria and Reported Performance):

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

• Test Set Sample Size: The "test set" was the animal study.
  • Canine Bilateral Duraplasty Model: "Each time point evaluated 3 test and 3 control animals, each with 2 defects."
  • This means a total of 6 animals per time point (3 for subject device, 3 for predicate device).
  • Since it states "at both time points" (implying at least two), it would be a minimum of 12 animals in total (6 animals x 2 time points), generating 24 defects.
• Data Provenance: The study was a "canine bilateral duraplasty model." This indicates it was a prospective animal study. The country of origin of the data is not specified.

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

• Ground Truth Establishment: For the animal study, tissue samples were processed by histopathology techniques and analyzed for dural integrity/neoduralization and local tissue reactions according to ISO 10993-6.
• Number and Qualifications of Experts: The document does not specify the exact number or qualifications of the individuals who performed the histopathology analysis or interpreted the results. It only mentions "tissue samples from each defect site were processed by histopathology techniques and analyzed."

4. Adjudication method for the test set

• The document does not describe an adjudication method for the animal study results. The histopathology analysis would likely have been performed by a qualified pathologist, but no multi-reader review or consensus method is described.

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

• No, an MRMC comparative effectiveness study was not done. This document pertains to a medical device (dura substitute), not an AI algorithm. Therefore, there is no discussion of human readers or AI assistance.

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

• No, a standalone (algorithm only) performance study was not done. This is a hardware medical device, not an algorithm.

7. The type of ground truth used

• For the animal study, the ground truth was established through histopathology analysis (morphological and cellular evaluation of tissue samples) and clinical observations (e.g., absence of CSF leaks, neurological evaluations). These are essentially expert observations/assessments based on established scientific methods.

8. The sample size for the training set

• This device is not an AI algorithm; therefore, there is no training set in the context of machine learning. The "predicate device" study (K153613) serves as a baseline/reference, from which the current subject device draws its "equivalent" conclusions regarding mechanical and biocompatibility data.

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

• Not applicable, as there is no training set for an AI algorithm. The performance of the predicate device (K153613) was established through its own set of non-clinical and potentially animal/clinical studies, which presumably used similar ground truth methods (e.g., pathology, clinical assessment).

Ask a specific question about this device

The Cerafix® Dura Substitute is indicated as a dura substitute for the repair of dura mater. This device is indicated for defects of 1.9 in² (12.5cm²) or less in area. For example, 1.2 in x 1.6 in (3 cm x 4 cm) would be an acceptable defect size.

Cerafix® Dura Substitute is a resorbable implant for repair of dural defects and is to be used with tensionless sutures. Cerafix® Dura Substitute is a soft, white, pliable, nonfriable, porous polymer matrix. Cerafix® Dura Substitute is available in a variety of sizes and is supplied sterile and nonpyrogenic in a single-use nested pouch configuration, which is enclosed within a protective chipboard envelope.

The provided text describes the Cerafix® Dura Substitute, a medical device intended for the repair of dura mater, and its journey through FDA 510(k) clearance. The document details the device's characteristics, indications for use, and the non-clinical testing performed to establish its substantial equivalence to predicate devices.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for many of the mechanical and biological tests were framed as "Equivalent to Predicate or Reference Device" or "Meets Final Device Specification." For some, specific thresholds were mentioned.

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

The document does not specify the exact sample sizes for each mechanical test (e.g., number of samples tested for tensile strength or burst strength). It mentions "side-by-side bench testing versus the predicate or commercially available reference device" for mechanical tests, and for biocompatibility, it refers to standard ISO/ASTM tests using animals (e.g., guinea pigs, rabbits, mice) and cell cultures. The data provenance is pre-clinical testing, likely conducted in a laboratory setting. There is no mention of country of origin for the data or whether it was retrospective or prospective in the context of human data, as this is a pre-market clearance based on non-clinical data.

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

Not applicable. The "ground truth" for this device's clearance is based on established scientific principles and comparison to legally marketed predicate devices through defined acceptance criteria in mechanical and biocompatibility testing, not on expert consensus of clinical data.

4. Adjudication method for the test set

Not applicable. This device clearance relies on objective laboratory and animal testing, not human-based adjudication of clinical outcomes or images.

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 pertains to the pre-market clearance of a physical medical implant (dura substitute), not an AI-powered diagnostic or assistive technology. Therefore, no MRMC study or AI-related effectiveness is discussed.

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

Not applicable, as this is not an algorithm or AI device.

7. The type of ground truth used

The "ground truth" for this regulatory submission is a combination of:

• Predicate Device Equivalence: The primary ground truth is established by demonstrating that the Cerafix® Dura Substitute's technological characteristics, performance, and safety are substantially equivalent to a legally marketed predicate device (Ethisorb™ Dura Patch) and a reference device (DuraGen Plus™ Dural Regeneration Matrix).
• Established Scientific Standards: Compliance with ISO and ASTM standards for biocompatibility and mechanical properties (e.g., non-cytotoxic, non-pyrogenic, appropriate burst strength).
• Animal Study Outcomes: Equivalence in safety and performance based on side-by-side animal implantation studies compared to the predicate device.

8. The sample size for the training set

Not applicable. There is no "training set" in the context of this device's pre-market clearance, as it's not a machine learning model.

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

Not applicable, as there is no training set.

Ask a specific question about this device