Search Results

SynVitro® Hyadase is for the removal of the cumulus complex and corona radiata surrounding the oocyte in preparation for ICSI.

SynVitro® Hyadase is a modified version of the prior cleared SynVitro® Hyadase device and is used for removal of cumulus and corona radiata cells surrounding the oocytes (denudation) prior to intracytoplasmic sperm injection (ICSI).

SynVitro® Hyadase is a clear non-viscous hyaluronidase enzyme solution contained in a 2 ml transparent plastic bottles (containing 1 ml solution) with caps and provided in cardboard boxes containing five bottles. This product has a one-year shelf-life when stored as recommended and can be used for up to seven days after opening.

This document describes the acceptance criteria and the study that demonstrates the performance of the SynVitro® Hyadase device.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state the specific "sample size" for each test in terms of number of units or replicates. For the Mouse Embryo Assay (MEA), the acceptance criterion mentions "at least 80% of the one-cell stage control embryos" which implies a set of embryos were used, but the exact number is not provided.

The data provenance is not specified. It is likely internal testing conducted by ORIGIO a/s, a CooperSurgical Company, given they are the manufacturer and submitter of the 510(k). The document does not indicate country of origin for data or if it was retrospective or prospective.

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

This document describes the testing of a medical device (reproductive media) against established physical, chemical, and biological performance specifications, not an AI or diagnostic device that requires expert adjudication of images or clinical data. Therefore, the concept of "experts used to establish the ground truth" in the context of image interpretation or clinical diagnosis does not apply here. The "ground truth" for each test is the established scientific/regulatory standard or a biological outcome (e.g., embryo development to blastocyst stage).

4. Adjudication Method for the Test Set

Not applicable. As explained in point 3, this is not a study requiring expert adjudication of data or images. The tests described are laboratory analyses with objective endpoints.

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

No, an MRMC comparative effectiveness study was not done. This device is a reproductive media (hyaluronidase enzyme solution) and not a diagnostic or AI-assisted interpretation device that would involve human readers.

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

No, this is not an algorithm or AI-based device. The device itself is a chemical solution. The performance testing is a standalone evaluation of the solution's properties and efficacy as intended.

7. The Type of Ground Truth Used

The ground truth used for the tests is based on:

• Established scientific/regulatory standards: For pH (USP ), Osmolality (USP ), Sterility (USP ), and Endotoxin (USP ). Aseptic processing validation adheres to ISO standards.
• Biological efficacy defined by a specific outcome: For the Mouse Embryo Assay (MEA), the ground truth is the development of one-cell mouse embryos to the blastocyst stage within 96 hours.
• Quantitative measurement of active ingredient: For Hyaluronidase enzyme activity, the ground truth is the measured activity falling within a specified range (40-120 IU/ml), with the device specified at 80 IU/ml.

8. The Sample Size for the Training Set

Not applicable. This is not an AI or machine learning device that requires a "training set." The performance testing described evaluates the chemical and biological properties of the manufactured product.

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

Not applicable. Same as point 8.

Ask a specific question about this device

VitriGuard is intended for use as a cryopreservation storage device in vitrification procedures and indicated to contain and maintain human oocytes (MII), 4-8 cell embryos and blastocyst stage embryos.

VitriGuard is a sterile, single-use device that is intended for use as a cryopreservation storage device in vitrification procedures. The device consists of a two-piece polystyrene assembly that includes a hexagonal-shaped stick and cap. As part of the vitrification procedure, the oocytes or embryos are loaded on the tip of the stick is capped prior to plunging the device in liquid nitrogen and for subsequent storage. The tip has a trough area for loading, maintaining and securing oocytes or embryos. The stick and cap include a taper design that create a seal when assembled. Black markings at the end of the stick and the tip of the device provide visual aid for proper device orientation. All VitriGuard devices have a blue cap and the sticks are available in eight (8) translucent colors: clear, blue, green, yellow, lime green, purple, orange and pink.

Here's a breakdown of the acceptance criteria and the study information for the VitriGuard device, based on the provided text:

VitriGuard Acceptance Criteria and Study Information

The acceptance criteria are not explicitly stated as distinct pass/fail thresholds in a single table, but are instead derived from the "Substantial Equivalence Comparison" table and "Non-clinical performance testing" sections by comparing the subject device's performance to the predicate device and established standards. The reported device performance is also taken from these sections.

1. Table of Acceptance Criteria and Reported Device Performance

Note on Acceptance Criteria: The document clearly states that differences in cooling/warming rates, endotoxin specifications, materials, and sterilization method "do not raise different questions of safety and effectiveness." This implies that while the values may differ from the predicate, they are still considered acceptable based on existing scientific understanding and relevant standards. For MEA, SAL, and number of uses, the criteria are explicitly met by matching the predicate.

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

The document indicates that clinical performance was primarily supported by a published literature review on closed-system vitrification devices similar to the subject device, rather than a single, dedicated clinical trial for VitriGuard with a specific test set.

• Literature 1: 33 vitrified/warmed donated oocytes.
• Literature 2: 498 vitrified/warmed donated oocytes.
• Literature 3: 190 vitrified/warmed autologous oocytes.
• Literature 4: Not explicitly stated as a single sample size for the study; reported on "clinical experience" with varying results based on maternal age.
• Literature 5: 89 vitrified/warmed donated oocytes.
• Literature 6: 33 patients, resulting in 16 embryo transfer cycles.

Data Provenance: The provenance of the data (country of origin, retrospective/prospective) is not explicitly stated for each literature reference. These are published studies by various authors (Inoue, Pujol, Perez et al, Gook et al, Pinasco et al, Goldman et al), implying they are likely a mix of prospective and retrospective observations from different clinical settings globally, based on typical scientific publication practices. The document uses this existing literature to support equivalence, rather than conducting a new, primary clinical investigation with a defined test set.

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

This information is not provided in the document. The "ground truth" for the literature review refers to outcomes measured in published clinical studies (survival rates, fertilization rates, cleavage rates, blastocyst development rates, implantation rates, pregnancy rates, live birth rates). The interpretation of these outcomes would have been performed by the researchers of those individual studies, but details on expert qualifications for establishing ground truth are not given here.

4. Adjudication method for the test set

This information is not provided in the document. Given that the clinical evidence relies on a review of published literature rather than a new, dedicated clinical study with a specific test set and adjudication panel for the VitriGuard device, no adjudication method specific to VitriGuard's clinical performance assessment 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

This is not applicable. The VitriGuard is a physical cryopreservation storage device, not an AI or imaging diagnostic tool that would involve "human readers" or AI assistance. Therefore, an MRMC study or assessment of AI effectiveness for human readers is irrelevant to this device.

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

This is not applicable. The VitriGuard is a physical device, and does not involve an algorithm or human-in-the-loop performance in the context of AI.

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

For the non-clinical performance testing (e.g., cooling/warming rates, endotoxin, MEA), the ground truth is established through standardized laboratory assays and measurements (e.g., USP for endotoxin, ASTM standards for packaging, ISO standards for sterilization).

For the clinical evidence (literature review), the "ground truth" is derived from clinical outcomes data reported in the referenced published studies. This includes metrics such as:

• Oocyte survival rates
• Fertilization rates
• Cleavage rates
• Blastocyst development rates
• Implantation rates
• Clinical pregnancy rates
• Live birth rates

8. The sample size for the training set

This information is not applicable. The VitriGuard is a physical medical device, not a machine learning model that requires a "training set."

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

This information is not applicable. As it's not an AI model, there is no training set or ground truth established for one.

Ask a specific question about this device

VitriGuard is a cryopreservation storage device that is intended for use in vitrification procedures to contain and maintain human 4-8 cell and blastocyst stage embryos.

VitriGuard is a cryopreservation storage device that is intended for use in vitrification procedures to contain and maintain human 4-8 cell and blastocyst stage embryos. It is single-use, disposable, and provided sterile. The device consists of a two-piece polystyrene assembly that includes a hexagonalshaped stick and cap. As part of the vitrification procedure, the embryos to be stored are loaded on the tip, and capped prior to plunging the device in liquid nitrogen and for subsequent storage. The tip has a trough area for loading, maintaining, and securing the embryos. The stick and cap include a taper design that creates a seal when assembled. Markings at the end of the stick and the tip of the device provide visual aid for proper device orientation.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Note on Cooling/Warming rates: While listed as "Specifications," the document does not explicitly state them as "acceptance criteria" where a threshold needs to be met for the study. They are presented as inherent characteristics of the device. However, for the purpose of demonstrating device performance, they are included here. The MEA is the only one explicitly stated as meeting "predetermined acceptance criteria."

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

• Sample size: Not explicitly stated. The text mentions "VitriGuard devices" and "One-cell mouse embryos" without specifying a number per test.
• Data provenance: Not explicitly stated. However, given it's a pre-market submission, the study was likely conducted specifically for this submission and would be considered prospective for the device's regulatory approval. The study uses mouse embryos, which are a biological model, not human data from a specific country.

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 the Mouse Embryo Assay (MEA) is established based on the biological outcome of embryo development (percent blastocyst formation), not through expert consensus or interpretation of images/data. Therefore, no "experts" were required to establish ground truth in this context.

4. Adjudication method for the test set

Not applicable. As noted above, the ground truth for the MEA is a direct biological outcome, not a subjective assessment requiring adjudication.

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; it is a physical cryopreservation storage device. 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 not an algorithm or AI system.

7. The type of ground truth used

The ground truth for the key performance test (Mouse Embryo Assay) was biological outcome data, specifically the successful development of mouse embryos to the blastocyst stage.

8. The sample size for the training set

Not applicable. This device is a physical product, not a machine learning model. There is no "training set" in this context.

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

Not applicable. As there is no training set, there is no ground truth established for it.

Ask a specific question about this device

ORIGIO® Handling™ is intended for in vitro procedures involving handling and micromanipulation of gametes and embryos outside the CO2 incubator.

Indication includes oocyte retrieval including follicle flushing, gamete (oocyte/sperm) and embryo washing, and micromanipulation procedures including Intra Cytoplasmic Sperm Injection (ICSI), assisted hatching and trophectoderm biopsy.

ORIGIO® Handling™ is a non-viscous, ready-to-use solution providing supporting conditions for human gametes and embryos during in vitro Assisted Reproduction Technology (ART) procedures taking place outside the CO2 incubator. This product can also be used for oocyte retrieval including follicle flushing.

ORIGIO® Handling™ consists of amino acids, glucose, physiological salts, calcium lactate, sodium pyruvate, vitamins, sodium bicarbonate MOPS/HEPES, human serum albumin, and gentamicin sulfate. This product is supplied with phenol red (Cat. No. 8311) or without phenol red (Cat. No. 8310).

ORIGIO® Handling™ is a single-use device that is aseptically filled into sterilized bottles (60 and 125 ml) and has a sterility assurance level (SAL) of 103. The product is stored at 2-8℃, and if not warmed, the product can be used for up to seven days after bottle opening. Prior to use, ORIGIO® Handling™ must be pre-warmed to 37℃, except for sperm washing procedures where the product is pre-warmed to room temperature before use.

The provided document describes the ORIGIO® Handling™ reproductive media, but it does not contain information about an AI/ML device.

Therefore, I cannot fulfill your request to describe the acceptance criteria and study proving an AI/ML device meets them based on the provided text. The document describes a traditional medical device (reproductive media) and its non-clinical performance testing.

Here's why I cannot provide the requested information:

• No AI/ML Component: The text describes the reproductive media's composition, use, and validation through standard laboratory tests (pH, osmolality, mouse embryo assay, human sperm survival assay, biocompatibility, sterility, endotoxin). There is no mention of an algorithm, artificial intelligence, machine learning, or any computational component that would require acceptance criteria related to its performance on data.
• No "Device Performance" Table for AI: The "reported device performance" in the document refers to validation test results for the media itself (e.g., pH range, osmolality range, MEA blastocyst development rate). It does not report metrics like accuracy, sensitivity, specificity, AUC, or other common performance indicators for AI/ML models.

If you have a document describing an AI/ML medical device, please provide that, and I would be happy to help with your request.

Ask a specific question about this device

The product is intended for in vitro culture of human embryos following fertilization until Day 5/6 of development. The media can also be used for embryo transfer.

SAGE 1-Step™ GM-CSF with HSA and SAGE 1-Step™ GM-CSF with SPS are assisted reproduction embryo culture media products consisting agents, physiological salts, energy substrates, amino acids, antibiotics, protein supplements (HSA or SPS), and granulocyte-macrophage colony-stimulating factor (GM-CSF, 2 ng/ml). These devices are aseptically filtered (sterility assurance level of 10 %), and supplied in 3 ml glass vials. They are tested for pH, osmolality, embryotoxicity, endotoxin, sterility, and GM-CSF concentration and potency before lot release. These devices have a shelf-life of 16 weeks, and can be used for up to seven days after vial opening when stored at 2-8°C.

Here's an analysis of the acceptance criteria and study information based on the provided text, focused on the SAGE 1-Step™ GM-CSF with HSA and SAGE 1-Step™ GM-CSF with SPS devices:

This document is a 510(k) summary for a medical device that appears to be an embryo culture media, not an AI/ML powered device, therefore some of the requested information (like multi-reader multi-case studies, AI impact, human-in-the-loop, training set sizes, and expert qualifications for ground truth in the context of diagnostic performance) are not applicable. The evaluations are primarily focused on the chemical, physical, and biological properties of the media itself.

Acceptance Criteria and Reported Device Performance

Study Information

1. Sample Size used for the test set and the data provenance:

   • Sample Size: The document does not specify a numerical sample size for individual tests like pH, osmolality, endotoxin, sterility, or GM-CSF concentration/potency beyond "real-time" shelf-life testing. For the Mouse Embryo Assay (MEA), it states "One-cell mouse embryos were exposed...", but the exact number of embryos or replicates is not provided.
   • Data Provenance: The studies were performed as part of the regulatory submission by ORIGIO a/s (Denmark). The data is generated from non-clinical laboratory testing (in vitro), not human patient data. It is inherently "prospective" in the sense that the tests were conducted specifically for this submission on the manufactured media.

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

   • This question is not applicable as the device is not an AI/ML diagnostic or image analysis tool. Ground truth in this context refers to established laboratory standards and measurement techniques (e.g., pH meters, osmometers, ELISA, cell assays, microscopic assessment of embryo development against a standard). The "ground truth" is determined by the output of these standardized assays, not by expert consensus on complex diagnostic cases.

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

   • This is not applicable for this type of device and study. Adjudication methods like 2+1 are typically used for reconciling disagreements among human readers/annotators in diagnostic studies. The results here are based on objective laboratory measurements.

4. 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, a MRMC comparative effectiveness study was not done. This type of study is relevant for diagnostic devices that involve human interpretation, often assisted by AI. This device is an embryo culture media, not a diagnostic tool requiring human reader interpretation in its intended use.

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

   • This is not applicable. There is no algorithm or AI component in this medical product. The performance is the inherent biological and chemical properties of the media itself.

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

   • The "ground truth" for the performance specifications relies on established laboratory methodologies and reference standards:
     • Standardized Analytical Measurements: pH meters, osmometers, spectrophotometers (for ELISA), LAL assays for endotoxin.
     • Biological Assays: Mouse Embryo Assay (MEA) results (percentage of embryos reaching blastocyst stage), TF-1 cell assay for GM-CSF potency. These assays have predefined criteria for success and are considered objective measures of the media's biological suitability.
     • Sterility Testing: USP standards for microbial growth.

7. The sample size for the training set:

   • This is not applicable as this device is not an AI/ML product. There is no "training set" in the context of machine learning. The media's formulation is developed based on scientific understanding of embryo biology.

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

   • This is not applicable as there is no training set for an AI/ML algorithm. The "ground truth" for the media's development and validation would stem from scientific literature on embryo development, established laboratory protocols, and regulatory standards for reproductive media.

Ask a specific question about this device

The Transem and EchoGen™ are catheters with angled or spherical tips for embryo transfer into the uterine cavity in the treatment of infertility.

The Transem Stylets are intended to assist the insertion of the Transem or EchoGen™ catheters where the passage through the cervix is impeded.

The Transem and EchoGen™ are Embryo Transfer Catheters with various angled or spherical tips and various lengths. The EchoGen™ variants are designed to be visible under ultrasound imaging. Stylets to aid in the insertion of the embryo catheters are also available.

This document describes the safety and effectiveness of the Transem and EchoGen™ Embryo Transfer Catheters through various performance evaluations, without directly referencing an AI/ML algorithm or its performance. Therefore, I cannot provide details related to acceptance criteria or studies proving device performance from an AI/ML perspective.

However, I can extract information related to the device's performance data and criteria described in the document for its physical and biological characteristics:

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

Regarding the AI/ML-specific questions, based solely on the provided text, there is no information available:

2. Sample size used for the test set and the data provenance: Not applicable as no AI/ML study is mentioned.
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 (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.
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 consensus, pathology, outcomes data, etc.): Not applicable.
8. The sample size for the training set: Not applicable.
9. How the ground truth for the training set was established: Not applicable.

This document pertains to the 510(k) premarket notification for traditional medical devices (catheters), which typically focus on material biocompatibility, sterility, physical performance, and similarity to predicate devices, rather than AI/ML algorithm performance.

Ask a specific question about this device

VitriGuard is a cryopreservation storage device that is intended for use in vitrification procedures to contain and maintain human 4-8 cell and blastocyst stage embryos.

VitriGuard is a cryopreservation storage device that is intended for use in vitrification procedures to contain and maintain human 4-8 cell and blastocyst stage embryos. The VitriGuard device is composed of a two-piece polystyrene assembly that includes a hexagonal shaped stick and cap. As part of the vitrification procedure, the embryos to be stored are loaded on the tip, also referred to as the leaf, and capped with a pre-cooled cap for subsequent storage following vitrification. The leaf has a trough area for loading. maintaining, and securing the embryos. The stick and cap include a taper design that creates a hermetic seal, forming a closed system. Markings at the stick and the tip of the device provide visual aid for proper device orientation. The device is provided sterile and is for single use only. The VitriGuard has been designed as a cryopreservation storage device to maintain the integrity of human 4-8 cell and blastocyst stage embryos throughout the cooling. storage, and warming processes.

Here's the information about the acceptance criteria and the study that proves the device meets them, extracted from the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state the specific numerical sample size (e.g., number of embryos or devices) used for each test. However, it indicates that "various mouse embryos" were used for the Mouse Embryo Survival and Development evaluations.

The data provenance is not explicitly detailed in terms of country of origin. The studies appear to be prospective in nature, as they involve conducting tests on the VitriGuard device according to specified protocols to evaluate its performance.

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

The document does not mention the use of human experts to establish ground truth for the test set. The ground truth for the performance tests (e.g., survival rates, development rates, integrity checks) is established by direct measurement against predefined criteria or by observation of biological outcomes (mouse embryo survival/development).

4. Adjudication Method for the Test Set

Not applicable, as the evaluation methods described are objective measurements or biological assays rather than subjective human assessments requiring adjudication.

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

No, an MRMC comparative effectiveness study was not done. The studies described are performance tests of the device itself, comparing its physical and biological performance characteristics to predefined criteria and to a predicate device.

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

This question is not applicable. The VitriGuard is a cryopreservation storage device, not an AI algorithm. Its performance is evaluated through non-clinical laboratory testing.

7. The Type of Ground Truth Used

The ground truth used for the performance studies is a combination of:

• Direct Measurement/Objective Criteria: For parameters like cooling/warming rates, endotoxin levels, sterility, and physical integrity (e.g., no leakage, no cap expulsion).
• Biological Outcomes Data: Specifically for the Mouse Embryo Assay (MEA), Mouse Embryo Survival Evaluation, and Mouse Embryo Development Evaluation, where the "ground truth" is the observed biological response (e.g., percentage of blastocyst formation, survival rate). These are quantitative biological endpoints.

8. The Sample Size for the Training Set

Not applicable. The VitriGuard is a physical medical device, not an AI/machine learning algorithm that requires a training set.

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

Not applicable, as there is no training set for this device.

Ask a specific question about this device

ORIGIO® Sperm Wash is intended for washing of spermatozoa, the isolation of motile viable sperm by swim-up method, dilution of ORIGIO gradients, and holding sperm for IUI procedure

ORIGIO® Gradient™ 100, ORIGIO® Gradient™ 90 and ORIGIO® Gradient™ 40/80 are for separation of motile sperm from the ejaculate by the density gradient method.

ORIGIO® Sperm Wash and ORIGIO® Gradient™ devices are for separation of motile sperm from semen and handling of sperm. These devices are based on the same formulation, but differ in the content of Human Serum Albumin (HSA), NaCl, bicarbonate, and silane silica. The silane silica generates the density, thus it is an ingredient in the ORIGIO® Gradient™ devices only and is not present in ORIGIO® Sperm Wash. All subject devices, except ORIGIO® Gradient™ 100, contain gentamicin and HSA.

The subject devices are aseptically filtered, colorless solutions. ORIGIO® Gradient™ devices are viscous while ORIGIO® Sperm Wash is non-viscous. They are contained in transparent polyethylene terephthalate glycol (PETG) bottles with high density polyethylene (HDPE) closures, available in card board boxes, individually labeled and with instruction for use provided as a package insert.

The document provided describes the acceptance criteria and performance data for ORIGIO® Sperm Wash and ORIGIO® Gradient™ devices (100, 90, and 40/80). However, it does not describe a study involving an AI device or human readers with AI assistance. The document pertains to reproductive media and supplements, which are chemical solutions used in assisted reproductive technologies, not complex imaging or diagnostic AI systems.

Therefore, many of the requested points, such as AI-related metrics (human readers with/without AI assistance, standalone AI performance), expert qualifications, and adjudication methods, are not applicable to this submission.

Here's the information that can be extracted from the provided text, focused on the device's characteristics and its comparison to predicate devices:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document states that "The bench testing demonstrated that the subject devices met all product specifications," but it doesn't provide specific numerical results for each criterion to show how they met them, only the acceptance ranges.

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

• Test set sample size: Not explicitly stated in terms of a "test set" as would be used for an AI algorithm. The performance evaluation was conducted on "sperm separated using subject devices" for "motility, morphology, viability, purity and integrity." The number of samples/donors used for this evaluation is not provided.
• Data provenance: Not specified. The document indicates the devices are manufactured by ORIGIO a/s in Denmark, but the location of the performance testing is not mentioned. The nature of the studies appears to be laboratory bench testing rather than clinical trials with patient data.

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

• Not applicable. This relates to the evaluation of a medical device (reproductive media), not an algorithmic diagnostic or imaging tool that requires human expert interpretation for ground truth establishment. The performance evaluation involved laboratory tests on sperm characteristics.

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

• Not applicable. No adjudication method described as it's not a study involving human interpretation of data for ground truth.

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

• Not applicable. This is not an AI device or an imaging/diagnostic device that would involve human readers.

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

• Not applicable. This is not an AI device. The "standalone performance" refers to the device's ability to perform its function (sperm washing and separation) independently, which was evaluated through bench testing. The document states "The bench testing demonstrated that the subject devices met all product specifications." and "The sperm separated using subject devices were evaluated for motility, morphology, viability, purity and integrity in comparison with predicate and other cleared devices."

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

• The "ground truth" for the device's performance relies on laboratory measurements and established biological criteria for sperm characteristics (motility, morphology, viability, purity, integrity) as well as chemical and physical properties of the media (pH, osmolality, density, endotoxin levels, sterility, HSA concentration). There isn't a "ground truth" in the diagnostic sense (like a pathology report for an image).

8. The sample size for the training set

• Not applicable. This is not an AI device, so there is no training set in the context of machine learning.

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

• Not applicable. As above, no training set for an AI model.

Ask a specific question about this device

BlastGen™ is for the culture of embryos from the 4-8 cell stage through to the blastocyst stage. BlastGen™ can also be used for embryo transfer.

BlastGen™ is based on ORIGIO® Sequential Blast™ (K133387) with the supplement of Leukine (Sargramostim) granulocyte macrophage colony-stimulating factor (GM-CSF).

BlastGen™ is a colorless, non-viscous solution contained in 3mL transparent glass bottles with white polypropylene caps, available in a single piece card board box, individually labeled and with instruction for use provided as a package insert. BlastGen™ is a ready to use by professionals for assisted reproduction.

BlastGen™ is quality control tested before release for pH, sterility, Mouse Embryo Assay, endotoxin, osmolality, GM-CSF concentration (by ELISA), GM-CSF potency (TF-1 cell assay) and human serum albumin (HSA) concentration (by ELISA).

Here's an analysis of the acceptance criteria and study data for the BlastGen™ device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA 510(k) summary does not explicitly state formal "acceptance criteria" in a tabular format for direct comparison with reported device performance. Instead, it presents various performance and safety data points that demonstrate equivalence to a predicate device. The implicit acceptance criterion for a 510(k) is "substantial equivalence" to a legally marketed predicate device.

However, based on the non-clinical and clinical evidence provided, we can infer some performance aspects that were evaluated.

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

The primary clinical evidence mentioned is:

• Sample Size: "a prospective randomized sibling zygote pilot study (n=371 zygotes)"
• Data Provenance: Not explicitly stated (e.g., country of origin). The study is described as "prospective randomized sibling zygote pilot study." The names of authors (Nakajyo, Sjöblom) suggest international research, but the specific source country of the embryos/patients is not mentioned in this document.

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

This document describes a device (reproductive media) for culturing embryos, not a diagnostic device that requires expert-established ground truth for performance evaluation in the same way an imaging AI would. The "ground truth" for embryology outcomes (e.g., blastocyst formation, pregnancy) is typically based on biological observation and clinical outcomes. Therefore, the concept of "experts establishing ground truth for a test set" with specific qualifications (like radiologists) does not apply directly here. The "truth" is the biological outcome observed by embryologists/clinicians.

4. Adjudication Method for the Test Set

Not applicable in the context of this type of device and study. The outcomes (e.g., blastocyst formation, pregnancy) are objective biological assessments rather than subjective interpretations requiring adjudication.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done.
• This type of study is relevant for diagnostic devices where human readers interpret images or data, and the comparison is between human interpretation alone versus human interpretation with AI assistance. BlastGen™ is a culture medium, not a diagnostic imaging AI tool.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• No, a standalone "algorithm only" study was not done because BlastGen™ is a culture medium, not an algorithm or AI. Its performance is evaluated through biological outcomes in a laboratory and clinical setting, which inherently involves human embryologists and clinicians interacting with the embryos and patients.

7. Type of Ground Truth Used

The ground truth used for evaluating BlastGen's performance is biological and clinical outcomes, specifically:

• Embryo development: Blastocyst formation rate, proportion of embryos reaching the blastocyst stage.
• Embryo quality indicators: Apoptotic nuclei count, viable inner cell mass cell count.
• Clinical outcomes: Pregnancy rate, ongoing implantation rates.
• Pre-clinical tests: Mouse Embryo Assay (MEA), pH, osmolality, sterility, endotoxin, GM-CSF concentration, GM-CSF potency, and HSA concentration.

8. Sample Size for the Training Set

This information is not provided. The provided studies are performance evaluations of the final product, not related to the training of an algorithm.

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

This question is not applicable as BlastGen™ is a culture medium and not an algorithmic/AI device that requires a "training set" with established ground truth in the AI sense. Its formulation and development would be based on scientific research and biological principles, rather than machine learning training.

Ask a specific question about this device

EmbryoGen® is for culture of human embryos until the 2-8 cell stage. EmbryoGen® can also be used for embryo transfer at day 2 or 3.

EmbryoGen® (1204) is a modification of EmbryoGen® (1203) (K120136), where the base medium has been changed from EmbryoAssist® (K080473) to the new ORIGIO Sequential Cleav™ (K133912) medium. EmbryoGen® (1204) contains GM-CSF (Granulocyte macrophage- colony stimulating factor), in the same concentration as EmbryoGen® (1203). EmbryoGen® (1204) is an aseptically filtered, colorless, non viscous solution, which is ready to use by professionals within assisted reproduction. EmbryoGen® (1204) is contained in 3 ml transparent glass bottles with white polypropylene caps, available in a single piece card board box, individually labeled and with instruction for use provided as a package insert.

The provided document is a 510(k) Summary for a medical device called EmbryoGen® (Cat. No. 1204). This device is a reproductive culture medium used for human embryos. The document focuses on demonstrating substantial equivalence to a predicate device, EmbryoGen® (Cat. No. 1203).

The 510(k) summary does not contain acceptance criteria or details of a study designed to prove the device meets specific performance acceptance criteria in the typical sense of a clinical trial for diagnostic or interventional devices with quantifiable outcomes like sensitivity, specificity, accuracy, etc.

Instead, the submission for EmbryoGen® (1204) relies on demonstrating substantial equivalence to a legally marketed predicate device (EmbryoGen® (1203)). This means the "acceptance criteria" are effectively the characteristics and performance of the predicate device. The "study" proving the device meets these criteria is a comparison of technological characteristics and performance data between the new device and the predicate device, as well as another cleared device (ORIGIO® Sequential Cleav™).

Here's an breakdown based on the provided text, addressing your questions where possible:

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

Since this is a submission for substantial equivalence of a culture medium, the "acceptance criteria" are the established specifications and comparable performance parameters of the predicate device and other similar cleared devices. The "reported device performance" are the specifications of the new device.

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

The document does not specify a "test set" sample size for a typical clinical performance study. The "performance data" section primarily discusses laboratory tests and stability studies, which would involve samples of the culture medium itself, not biological samples from human patients in a clinical trial.

• 1-cell MEA (Mouse Embryo Assay): This is a biological assay using mouse embryos. The document states a performance criterion (≥80%) but does not specify the sample size (e.g., number of mouse embryos, number of batches tested) used to demonstrate this for EmbryoGen® (1204).
• Stability studies: These tests involved multiple batches of the product over time. The sample size (number of batches) is not explicitly stated.
• Data Provenance: Not specified as a clinical trial. The manufacturing company, ORIGIO a/s, is based in Denmark.

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 to this type of device submission. There is no concept of "ground truth" established by human experts in the context of this culture medium's substantial equivalence demonstration. The "ground truth" is essentially the established specifications and safety profile of the predicate device and the general scientific understanding of IVF media components.

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

Not applicable. There is no clinical read by human readers that would require an adjudication method.

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 culture medium, not an AI-powered diagnostic or decision support system that would involve human readers or AI assistance.

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

Not applicable. This device is a culture medium, not an algorithm.

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

The "ground truth" in this context is based on:

• Established scientific understanding and regulatory requirements for reproductive media.
• Performance specifications of the predicate device (EmbryoGen® (1203)) and another cleared device (ORIGIO® Sequential Cleav™).
• Standardized laboratory tests for pH, osmolality, endotoxin, specific protein concentrations, and biological assays like MEA (Mouse Embryo Assay), GM-CSF ELISA, and GM-CSF potency (TF-1 cell assay).
• Biocompatibility testing (cytotoxicity, sensitization, irritation) against ISO 10993-1:2009 standards.

There is no "expert consensus" or "pathology" in the sense of interpreting images or clinical findings.

8. The sample size for the training set

Not applicable. This device is a culture medium, not an AI/machine learning model that requires a training set.

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

Not applicable. As stated above, this device does not involve a training set.

Ask a specific question about this device