Search Results

Harioculture TL-16 Time-lapse Incubator consists of the following devices with the following indications for use:

Time-lapse Incubator provides an environment with controlled temperature and gas concentrations (CO2 and O2) or mixed gas (CO2 and other gases) for the development of embryos at or near body temperature. Use of the Time-lapse Incubator is limited to five days (120 hr) covering the time from post insemination to day five of development.

The Hariomed culture dish is intended for preparing, storing, and transferring human embryos. The Hariomed culture dish must be used together with the Time-lapse Incubator.

The Harioculture-client software is intended for displaying, comparing, storing, and transferring images generated by the Time-lapse Incubator. This software includes a user annotation function for capturing information on embryo development parameters as well as a user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo selection. The Harioculture-client software does not control any hardware components in the Time-lapse Incubator.

The Harioculture-server software is intended to store, archive and transfer data. In addition, this software includes functions for managing models and performing calculations based on image data and embryo development parameters.

The Time-lapse Incubator, Harioculture-client software, and Harioculture-server software must be used together to export embryo images from the Time-lapse Incubator. The Harioculture-client software and Harioculture-server software must be used together to assist users to analyze the embryo images.

Harioculture TL-16 Time-lapse Incubator consists of the following components:

• Time-lapse Incubator,
• Harioculture-server software,
• Harioculture-client software,
• Hariomed culture dish.

The Time-lapse Incubator is a benchtop embryo incubator with a built-in microscope for time-lapse imaging intended to be used for the culture and monitoring of embryos used in Assisted Reproductive Technology (ART) procedures. It provides temperature control, gas control, and time-lapse microscopy at multiple focal planes. This device can hold up to 16 culture dishes (Hariomed culture dish) in the culture cabin. The device can be connected to the capacity expansion module which in turn can also accommodate 16 culture dishes. The capacity expansion module is similar to the main incubator and provides the same culture capacity as the incubator host. However, it cannot be run independently and needs to be used together with the Incubator host. The incubator host includes the software to control the temperature, gas concentration, imaging as well as image display on the incubator screen. The culture dishes are placed in the culture slots on the turntable in the Time-lapse Incubator. The culture slots provide direct heat transfer to the Hariomed culture dishes. The built-in microscope consists of an illumination unit (red LED, 630±5 nm) and an inverted microscope/camera unit. During image acquisition, turntable is rotated to position individual culture dishes on the microscopy system and image stacks are acquired for individual embryos in each culture dish.

The Time-lapse Incubator supports two gas control and culture modes:

• Self-mixed mode – Under the self-mixed gas culture mode, CO2, and N2 gases are supplied from medical grade gas cylinders. These gasses (CO2, N2 and re-flux gas) are mixed in a mixing chamber and passed through a HEPA/VOC filter prior to delivery to the culture cabin. This culture mode does not allow for humidification of the chamber (dry-culture mode).
• Pre-mixed mode – Under the pre-mixed gas culture mode, the gas is supplied from standard premixed medical gas cylinders. Pre-mixed gas passes through the HEPA/VOC filter and a humidification box to form a humidified gas which then enters the culture cabin. The humidification box is sterile, single-use component with a sterility assurance level (SAL) of 10-6 and a shelf-life of two years. The pre-mixed culture mode allows humidification of chamber (wet-culture mode).

The Hariomed culture dish is a single use, single-patient, polystyrene, radiation sterilized culture dish intended for preparing, storing, and transferring human embryos. The Hariomed culture dish is intended for use only with Harioculture TL-16 Time-lapse Incubator and includes two culture ponds. Each culture pond has eight microwells and a total of 16 embryos from a single patient can be cultured on one dish. Each dish includes four rinsing wells for rinsing and handling the embryos before or after incubation. The dishes have area for unique barcode labels that can be printed through the Harioculture-client software. The barcode labels provide patient identification information. The Hariomed culture dish has a sterility assurance level (SAL) of 10-6 and a shelf-life of two years.

The Harioculture-client software is intended for displaying, comparing, storing, and transferring images generated by the Time-lapse Incubator. The data that can be viewed using this software includes embryo images, incubation details, alarms, log files and other instrument parameters. This software also includes a user annotation function for capturing information on embryo development parameters as well as a user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo selection. The Harioculture-client software does not control any hardware components in the Time-lapse Incubator.

The Harioculture-server software allows users to update and view common data. The server acts as the central unit, which stores data and controls the data flow to and from the connected devices. The server can be connected to multiple Time-lapse incubators and computers with the Harioculture-client software.

It's important to note that the provided FDA 510(k) clearance letter and summary do not describe a clinical study involving human patients or complex AI-driven diagnostic decisions. Instead, the document focuses on the performance and safety validation of a medical device (Time-lapse Incubator) and its associated hardware and software components. The "acceptance criteria" and "study" described in the document are primarily for bench testing, in-vitro assays (like Mouse Embryo Assay), and engineering validation, not a comparative clinical trial for an AI-assisted diagnostic tool in the traditional sense (e.g., comparing AI-assisted radiologist performance to unassisted radiologist performance).

Therefore, some of the requested information regarding "AI performance," "human readers," "effect size," "ground truth establishment" for training data, and "adjudication methods" as one might see in the validation of a diagnostic AI algorithm will not be directly applicable or available in this document.

However, I can extract and structure the information that is present in the document in a way that aligns with your request's format, while highlighting the type of studies actually performed.

Device Description: Harioculture TL-16 Time-lapse Incubator System

The Harioculture TL-16 Time-lapse Incubator system is a medical device designed for Assisted Reproductive Technology (ART) procedures. It comprises:

• Time-lapse Incubator: Provides a controlled environment (temperature, CO2/O2) for embryo development, with a built-in microscope for time-lapse imaging.
• Hariomed culture dish: A single-use, radiation-sterilized polystyrene dish for culturing human embryos within the incubator.
• Harioculture-client software: Displays, compares, stores, and transfers images from the incubator, and includes user annotation and user-defined modeling functions to aid in embryo selection. It does not control hardware.
• Harioculture-server software: Stores, archives, and transfers data, manages models, and performs calculations based on image data and embryo development parameters.

The system's client and server software assist users in analyzing embryo images, and the primary "AI-like" function is the "user-defined modeling function" which combines annotated information to aid in embryo selection. This suggests a user-configurable scoring or selection model rather than a pre-trained deep learning AI model for image interpretation.

Acceptance Criteria and Reported Device Performance

The "acceptance criteria" and "reported device performance" in this context refer to the engineering specifications and the results of non-clinical bench and in-vitro testing, rather than clinical endpoints from a human study.

Table of Acceptance Criteria and Reported Device Performance

Study Details (Based on the provided non-clinical information)

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

• Sample Sizes: The document does not specify exact sample sizes for each bench test (e.g., how many incubators were tested for temperature accuracy, or how many culture dishes for MEA). However, it implies that sufficient samples were tested to meet the specified standards and guidances.
• Data Provenance: The tests are non-clinical, primarily conducted as bench performance testing and in-vitro assays. Therefore, "country of origin of the data" generally refers to the location of the testing facility, not patient data origin. The document does not specify the testing facility's location, but the applicant company is in China. The data (results) are retrospective relative to the 510(k) submission date.

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

• Not Applicable in the traditional sense for this device. Given that the studies are primarily bench performance testing, in-vitro biological assays (MEA, Endotoxin), and engineering validations (electrical safety, EMC, software V&V), "ground truth" is established by adherence to recognized international standards (e.g., ISO, IEC, ASTM, USP) and FDA guidances. The "experts" would be the qualified personnel performing these standardized tests and the internal experts validating compliance to design specifications. Their qualifications would be in engineering, microbiology, quality assurance, etc., as appropriate for each specific test. There is no mention of a ground truth established by medical experts (e.g., radiologists) for image interpretation.

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

• Not Applicable. Adjudication methods like 2+1 or 3+1 are typically used in clinical studies where multiple human readers assess medical images or data, and their disagreements need to be resolved to establish a definitive "ground truth" (e.g., presence or absence of a disease). Since this document describes non-clinical engineering and in-vitro performance testing of a device hardware and software, such adjudication methods are not relevant.

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 such study was done or described. The device includes a "user-defined modeling function" to aid in embryo selection, but there is no mention of a clinical MRMC study evaluating the effectiveness of human embryologists assisted by this software feature compared to unassisted embryologists. The validation focuses on the safety and performance of the incubator's physical parameters, image acquisition, and software functionalities (display, storage, basic user annotation/modeling), not a clinical outcome related to increased human reader performance.

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

• No "standalone algorithm performance" in the typical diagnostic AI sense. The document describes software functions for displaying, storing, and users annotating/modeling, and performing calculations based on image data. This implies a tool to aid the user, not a standalone AI algorithm that provides a diagnosis or makes a definitive embryo selection recommendation without human intervention. The performance testing for the software was "Software verification and validation per the 2023 FDA Guidance Document, 'Content of Premarket Submissions for Device Software Functions'," which assures the software functions as intended and is safe, but not a standalone evaluative study of an AI's diagnostic accuracy.

6. The type of ground truth used:

• For the physical parameters of the Incubator (temperature, gas, imaging): The "ground truth" is based on engineering specifications and measurements conforming to established industry standards (e.g., accuracy, stability, recovery times).
• For the Hariomed culture dish and humidification box: The "ground truth" is established through biological assays (MEA, Endotoxin) and sterilization validation according to a priori acceptance criteria defined by regulatory standards (e.g., ≥80% blastocyst development, ≤0.5 EU/device endotoxin, SAL 10^-6).
• For software: The "ground truth" is established through software verification and validation testing against its design specifications and functional requirements to ensure it performs as intended and is safe.

7. The sample size for the training set:

• Not Applicable. This document does not describe the development or training of a machine learning or deep learning model. The "user-defined modeling function" implies that users define criteria/models based on their expert knowledge and annotated data, rather than a system trained on a large dataset. Therefore, there is no "training set" in the context of an AI algorithm described here.

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

• Not Applicable (as there is no described AI training set). If the "user-defined modeling function" were to incorporate any form of machine learning in its development (which is not explicitly stated in the summary), the ground truth for such hypothetical training would typically come from expert embryologist annotations of embryo development parameters and correlation with clinical outcomes. However, the provided document does not delve into this level of detail. The emphasis is on the software being a tool for user annotation and modeling, not an internally generated AI recommendation.

Ask a specific question about this device

The Embryo Real-time Incubator (TLS301) is intended to provide an environment with controlled temperature and mixed gas (CO2 and other gases) for the development of embryos. The Embryo Real-time Incubator (TLS301) has an integrated camera and optics for imaging and viewing embryos during incubation, for a maximum time of 120 hours.

The Embryo Real-time Culture Dish (MC 2004) is intended for preparing, storing and transferring human embryos. It is intended to be used only with the Embryo Real-time Incubator (TLS301).

Embryo Realtime 2S Software and Embryo Realtime 3E Software accessories for the Embryo Real-time Incubator (TLS301).

The Embryo Realtime 2S Software is intended to store, archive and transfer data. In addition, the Embryo Realtime 2S Software includes functions for managing models and performing calculations based on image data and embryo development parameters.

Embryo Realtime 3E Software is intended for viewing and recording embryo development events from images captured using the Embryo Real-time Incubator (TLS301). Embryo Realtime 3E Software includes a user annotation for capturing information on embryo development parameters and a user-defined modeling function that allows the user to combine annotated information on embryo development parameters to aid in embryo selection.

Embryo Realtime 2S Software and Embryo Realtime 3E Software do not control any hardware components in the Embryo Real-time Incubator (TLS301). Embryo Realtime 2S Software and Embryo Realtime 3E Software are provided in different software package and must be used together.

The Embryo Real-time Incubator (TLS301) consists of the following components:

• Embryo Real-time Incubator, integrated with temperature control system, gas supply control system and time-lapse imaging system.
• Image capture software
• Workstation, composed of server and workstation software.
• Embryo Real-time Culture Dish (MC 2004)

The Embryo Real-time Incubator (TLS301) is a benchtop tri-gas (CO2, N2, and air) embryo incubator with a built-in microscope for time-lapse imaging intended to be used for the culture and monitoring of embryos used in Assisted Reproductive Technology (ART) procedures. It provides temperature control, gas control, and time-lapse imaging at multiple focal planes. The incubator chamber has the capacity to hold up to ten Embryo Real-time Culture Dishes (MC 2004). Each chamber contains a heating plate to maintain chamber temperatures. Gas (CO2, N2, and air) is mixed in a mixing chamber and passed through a HEPA/VOC filter prior to delivery to the incubation chamber. The built-in microscope consists of an illumination unit (red LED, 635 nm) and an inverted microscope/camera unit. The imaging system is mobile and is controlled through moving guide rail to automatically position the camera to the designated culture plate/well. The camera can acquire images in multiple focal planes. The time-lapse imaging system in the incubator along with the image capture software capture timelapse images of the embryos and transmit captured images to the computer for display and storage. The image capture software also reads the patient labels on the Embryo Real-time Culture Dish (MC 2004) and incorporates patient information into the imaging record.

The workstation includes a server and workstation software (Embryo Realtime 3E Software). It includes graphical user interface and receives and stores images. It also supports query, retrieval and display of the embryo images. The workstation software allows for manual annotation of the series of images obtained through time-lapse imaging into a user-defined model for the assessment of embryo's development. In addition, the server software (Embryo Realtime 2S Software), that does not include a graphical user interface, is designed to archive, transfer and store images of embryos from the time lapse incubator and performs user model management and calculations based on image data and user inputted embryo development parameters. The two software are used together.

The Embryo Real-time Culture Dish (MC 2004) is a single use, single-patient, polystyrene, radiation sterilized culture dish intended for preparing, storing, and transferring human embryos. It is intended to be used only with the Embryo Real-time Incubator (TLS301). It contains two types of wells for rinsing and handling the embryos before or after incubation and 16 wells for culturing the embryos during incubation. Each culture well is used to culture one embryo and a total of 16 embryos from a single patient can be cultured on one dish. The culture and rinsing wells have a volume of 30 µL and 50 µL, respectively. There is a central depression in the center of each culture well, where the embryo resides. The Embryo Real-time Culture Dishes (MC 2004) has a label area for unique identification of the culture dish.

The provided text pertains to the FDA 510(k) premarket notification for the "Embryo Real-time Incubator (TLS301)" and "Embryo Real-time Culture Dish (MC 2004)" and their associated software.

Based on the provided information, the acceptance criteria and study details are primarily focused on the non-clinical performance and substantial equivalence to a predicate device, rather than a clinical study evaluating diagnostic accuracy or reader performance with AI. The device does not appear to be an AI-based diagnostic tool in the typical sense, but rather an incubator with an integrated imaging system and software that aids in embryo selection.

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

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes various performance tests and their acceptance criteria, predominantly for the hardware components (incubator, optics, culture dish) and basic software functionalities.

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

The document describes non-clinical bench testing.

• Sample Size: Not explicitly quantified for each specific test in terms of individual units. The "Mouse embryo assay (MEA)" involved embryos, but a specific number is not given.
• Data Provenance: The studies are described as "Non-clinical bench testing." There is no mention of human clinical data, retrospective or prospective studies, or country of origin for such data. The MEA, by its nature, would use animal (mouse) embryos.

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

This type of information is generally relevant for AI/diagnostic devices that require expert human labels for ground truth. The provided document describes non-clinical bench testing to verify hardware and software performance against specifications. As such, there is no mention of experts establishing a "ground truth" in the diagnostic sense, nor their qualifications. The closest would be implicit expertise in conducting the various standardized tests (e.g., electrical safety, sterility, MEA).

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set:

Not applicable. The tests described are objective non-clinical performance and safety tests, not subjective interpretations requiring adjudication among experts.

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 comparative effectiveness study was mentioned. The device's software (Embryo Realtime 3E Software) includes a "user-defined modeling function that allows the user to combine annotated information on embryo development parameters to aid in embryo selection." However, the document does not describe any study evaluating the comparative effectiveness or improvement in human reader performance (e.g., embryologists) with or without this AI assistance. The focus is on the software's functionality and validation rather than its clinical impact on human decision-making.

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

The document does not describe a standalone performance evaluation of the "user-defined modeling function" or any other algorithm. The software functions aid in embryo selection, implying a human-in-the-loop process. The "Embryo Realtime 2S Software... includes functions for managing models and performing calculations based on image data and embryo development parameters," but no standalone performance metrics are provided for these calculations.

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

For the specific tests mentioned:

• Hardware and Software Performance: Ground truth is defined by objective engineering specifications and scientific standards (e.g., temperature ranges, gas concentrations, electrical safety standards, image quality parameters, sterility levels, endotoxin limits, mouse embryo development rates).
• Mouse Embryo Assay (MEA): The "ground truth" for this test is the biological outcome of mouse embryo development to blastocyst (≥80% development in 96 hours), an accepted standard for assessing device biocompatibility.

8. The Sample Size for the Training Set:

The document does not describe any machine learning or AI model training. Therefore, there is no mention of a training set sample size. The software's "user-defined modeling function" suggests that users create or define models based on annotated information, rather than the device coming with a pre-trained model.

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

Not applicable, as no machine learning training set or associated ground truth establishment process is described.

Ask a specific question about this device

The Geri Embryo Incubator is intended to provide an environment with controlled temperature and mixed gas (CO2 and other gases) for the development of embryos. The Geri Embryo Incubator has an integrated camera and optics for imaging and viewing embryos during incubation, for a maximum time of 120 hours.

Geri Connect and Geri Assess are optional software accessories for the Geri Embryo Incubator. Geri Connect is intended for access and review of time-lapse data generated by the Geri Embryo Incubator on a local area network. Geri Assess is intended for viewing and recording embryo development events from images captured using the Geri Embryo Incubator. Geri Assess includes a user annotation for capturing information on embryo development parameters and a userdefined modeling function that allows the user to combine annotated information on embryo development parameters to aid in embryo selection. Geri Connect and Geri Assess do not control any hardware components in the Geri Embryo Incubator. Geri Connect and Geri Assess are combined in the same software package and must be used together.

The Geri Dish is intended to be used for preparation, storage and imaging of human embryos. The Geri Dish is intended to be used only with the Geri Embryo Incubator.

The Geri Embryo Incubator is a benchtop incubator with six modular incubation chambers each with its own temperature control capability and separate gas inlet feed. Each chamber contains heating elements in its lid and base, together with an orange light source (591 nm) and camera with integrated optics that take time-lapse images of embryos and allows operators to view embryos without removing them from the incubation chamber. Inside each chamber is a filter the gas mixture entering the incubation chamber from the gas supply. The gas is supplied from standard premixed medical gas cylinders. The Geri Embryo Incubator includes firmware to control the incubator settings, and software to control patient information and settings.

The Geri Assess and Geri Connect are optional software accessories for the Geri Embryo Incubator. The Geri Connect allows the user to access the embryo data remotely, whereas the Geri Assess provides the user with a tool for analysis of embryo data. Using user defined parameters, the Geri Assess can score the embryos. However, the Geri Assess itself does not include any pre-loaded scoring assessments or perform any diagnostic functions. The Geri Connect and Geri Assess software package is provided with the Geri Embryo Incubator, but needs to be unlocked, when purchased by the end user.

The Geri Dish is intended to be used for preparation, storage and imaging of human embryos. Up to 16 embryos can be stored in one Geri Dish. Geri Dishes are supplied sterile with a sterility assurance level (SAL) of 10 %, and have a shelf-life of 12 months. The Geri Dish is intended to be used only with the Geri Embryo Incubator. Other assisted reproduction culture dishes may be used in the Geri Embryo Incubator in separate non-time-lapse positions located within each chamber.

The provided text is a 510(k) summary for the Geri Embryo Incubator with Geri Connect and Geri Assess Software. It explains the device, its intended use, and compares it to a predicate device. However, it does not contain any information about acceptance criteria or specific study results that prove the device meets those criteria, especially in relation to AI/software performance in aiding embryo selection.

The document states:

• "Software verification and validation testing was conducted on the subject device in accordance with the FDA guidance document, 'Guidance for the Content of Premarket Submissions for Software in Medical Devices' issued on May 11, 2005."
• "The Geri Assess itself does not include any pre-loaded scoring assessments or perform any diagnostic functions."
• "Geri Assess includes a user annotation function for capturing information on embryo development parameters and a user-defined modelling function that allows the user to combine annotated information on embryo development parameters to aid in embryo selection."
• "The features added by this additional software do not represent a new intended use, and are seen in other cleared devices of this type."
• "The differences in technological characteristics between subject and predicate devices do not raise different questions of safety and effectiveness."

Based on these statements, it appears the Geri Assess software provides tools for users to define and apply their own models for embryo selection, rather than itself being an AI that performs diagnostic functions or makes automated predictions based on pre-loaded algorithms. The regulatory submission likely focused on verifying the software's functionality, usability, and safety as a tool, rather than validating its performance in an AI-assisted diagnostic capacity.

Therefore, it is not possible to extract the requested information (acceptance criteria, specific study results, sample sizes, expert details, MRMC studies, AI effect size, etc.) from the provided text because these elements are not present. The document concludes that the device is substantially equivalent based on the software's functionality as a user-defined tool, rather than as a diagnostic AI requiring extensive clinical performance studies as described in the prompt.

Ask a specific question about this device

EmbryoScope+ consists of the following devices with the following indications for use:

The EmbryoScope+ incubator provides an environment with controlled temperature and gas concentrations (CO2 and O2) for the development of embryos at or near body temperature. Use of the EmbryoScope+ incubator is limited to five days (120 hr) covering the time from post insemination to day five of development.

The EmbryoSlide+ culture dish is intended for preparing, storing, and transferring human embryos. The EmbryoSlide+ culture dish must be used together with the EmbryoScope+ incubator.

The Embryo Viewer software is intended for displaying, storing, and transferring images generated by the EmbryoScope+ incubator. This software includes a user annotation for capturing information on embryo development parameters as well as a user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo Viewer software does not control any hardware components in the EmbryoScope+ incubator.

The ES Server software is intended to store, archive and transfer data. In addition, this software includes functions for managing models and performing calculations based on image data and embryo development parameters.

The EmbryoScope+ incubator, EmbryoViewer software, and ES Server software must be used together to export embryo images from the EmbryoScope+ incubator. The EmbryoViewer software must be used together to analyze the embryo images.

EmbryoScope+ consists of the following devices: EmbryoScope+ incubator, EmbryoSlide+ culture dish, EmbryoViewer software, and ES Server software.

The EmbryoScope+ incubator is a bench top embryo incubator with a time-lapse imaging function. It provides temperature control, and time-lapse microscopy at multiple focal planes. This device can hold up to 15 culture dishes (EmbryoSlide+ culture dish) in the incubation chamber. The culture dishes are placed on the dish holder in the EmbryoScope+ incubator. The holder provides direct heat transfer to the EmbryoSlide+ culture dish. The built-in microscope consists of an LED illumination unit and an inverted microscope/camera unit. During image acquisition, each culture dish located on the culture dish holder is rotated to the microscopy system and individual image stacks are acquired from all individual embryos in each culture dish.

The EmbryoSlide+ culture dish is a radiation-sterilized polystyrene culture dish containing two separate reservoirs. Each reservoir has eight culture well is used to culture one embryo. Therefore, a total of 16 embryos can be cultured on one dish. Each dish includes four special wells that are only used for rinsing and handling the embryos either before or after incubation. An adhesive barcode label printed from the EmbryoViewer software is used to mark each dish. The barcode label contains two different 2D data matrices that provide information on the patient ID, treatment ID, and insemination time). The EmbryoSlide+ culture dish has a sterility assurance level of 10° and a shelf-life of four years. This device is subject to mouse embryo assay (MEA) and endotoxin testing before lot release.

The EmbryoViewer software is used for displaying, comparing, storing, and transferring images generated by the EmbryoScope+ incubator. The data that can be viewed using this software includes embryo images, incubation details, alarms, log files and other instrument parameters. This software also includes a user annotation for capturing information on embryo development parameters as well as a user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo selection. The EmbryoViewer software neither controls any hardware components in the EmbryoScope+ incubator nor performs any diagnostics.

The ES Server software allows users to update and view common data. The server acts as the central unit, which stores data and controls the data flow to and from the connected devices. The server can be connected to multiple EmbryoScope+ incubators and computers with the EmbryoViewer software installed.

The provided text does not contain information about a "study that proves the device meets the acceptance criteria" in the format of a clinical trial or a specific comparative effectiveness study with human readers and AI assistance. Instead, it describes non-clinical performance testing conducted to support the substantial equivalence of the EmbryoScope+ device to its predicate devices.

The acceptance criteria are generally implied by the design specifications and testing standards mentioned.

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

1. Table of Acceptance Criteria and the Reported Device Performance

The text doesn't explicitly present a direct "acceptance criteria" vs. "reported performance" table for all aspects. However, it lists performance specifications for the EmbryoScope+ incubator and the results of various non-clinical tests.

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 describes non-clinical bench testing. For the Mouse Embryo Assay (MEA), the sample size is implicitly "one-cell mouse embryos" without a specific number. The data provenance is not mentioned (e.g., country of origin). The testing seems to be experimental/prospective in nature, rather than retrospective use of human patient data.

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

Not applicable. The document describes non-clinical performance and engineering testing (electrical safety, EMC, software V&V, bench performance, sterilization, package integrity, endotoxin, mouse embryo assay). These do not involve human experts establishing ground truth for a diagnostic AI system.

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

Not applicable, as this is non-clinical performance testing, not a clinical study requiring adjudication of expert interpretations.

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 comparative effectiveness study is mentioned. The device, EmbryoScope+, includes software (EmbryoViewer) with "user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo selection." However, the text details non-clinical testing for substantial equivalence, not a clinical study on human reader performance with or without AI assistance.

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

While the EmbryoViewer software includes "user-defined modeling function" to "aid in embryo selection," the substantial equivalence argument relies on comparing the entire system (incubator, software, dish) to predicate devices through non-clinical performance metrics. There is no specific mention of a standalone algorithm performance study without human involvement, particularly relating to "embryo selection" capability. The software primarily displays, stores, transfers images, and allows for user annotation and user-defined modeling, implying human-in-the-loop use. It explicitly states, "The EmbryoViewer software neither controls any hardware components in the EmbryoScope+ incubator nor performs any diagnostics."

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

For the non-clinical tests described:

• EmbryoSlide+ Culture Dish (MEA): The "ground truth" for the MEA test was defined by the biological outcome: "percent of embryos developed to the expanded blastocyst stage within 96 hours." This is an objective biological endpoint.
• Other non-clinical tests (electrical safety, EMC, metrology, etc.): Ground truth is established by adherence to engineering specifications, recognized standards (e.g., IEC, EN, ASTM, ISO, USP, ANSI/AAMI), and design specifications.

8. The sample size for the training set

Not applicable. The document does not describe a machine learning model that requires a training set in the conventional sense. The "user-defined modeling function" in the EmbryoViewer software suggests that users define their own criteria based on embryo development parameters, rather than the device itself being trained on a large dataset.

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

Not applicable, as no machine learning training set is described.

Ask a specific question about this device

The Geri Embryo Incubator is intended to provide an environment with controlled temperature and mixed gas (CO2 and other gases) for the development of embryos. The Geri Embryo Incubator has an integrated camera and optics for imaging and viewing embryos during incubation, for a maximum time of 120 hours.

The Geri Dish is intended to be used for preparation, storage and imaging of human embryos. The Geri Dish is intended to be used only with the Geri Embryo Incubator.

The Geri Embryo Incubator is a benchtop incubator with six modular incubation chambers each with its own temperature control capability and separate gas inlet feed. Each chamber contains heating elements in its lid and base, together with an orange light source (591 nm) and camera with integrated optics that take time-lapse images of embryos and allows operators to view embryos without removing them from the incubation chamber. Inside each chamber is a filter the gas mixture entering the incubation chamber from the gas supply. The gas is supplied from standard premixed medical gas cylinders. Each chamber can also contain an optional water bottle (Geri Water Bottle) to generate humidity. The Geri Water Bottle is supplied sterile with a sterility assurance level (SAL) of 10°, and has a shelf-life of three years. The Geri Water Bottle is designed to be used with the Geri Embryo Incubator only.

The embryos are maintained in Geri Dishes that are supplied separately. The Geri Dish is an optically-clear polystyrene dish designed to be compatible with the Geri Embryo Incubator. Up to 16 embryos can be stored in one Geri Dish. Geri Dishes are supplied sterile with a sterility assurance level (SAL) of 10°, and have a shelflife of 12 months.

The Geri Embryo Incubator and Geri Dish are intended to be used together for embryo imaging purposes. The Geri Dish is not compatible with other embryo time-lapse incubators. However, other assisted reproduction culture dishes may be used in the Geri Embryo Incubator in separate non-time-lapse positions located within each chamber.

The Geri Embryo Incubator includes firmware to control the incubator settings, and software to control patient information and settings.

This document, a 510(k) Summary for the Geri Embryo Incubator and Geri Dish, outlines the characteristics and testing for a medical device. It is not a document about an AI/ML-based medical device. Therefore, none of the specific questions regarding AI/ML device acceptance criteria, study design for AI/ML, sample sizes for AI/ML test and training sets, expert adjudication methods for AI/ML ground truth, or MRMC studies for AI assistance, can be answered from the provided text.

The document focuses on the substantial equivalence of the Geri Embryo Incubator and Geri Dish to a predicate device, with the main change being the addition of a humidity control system. The studies described are traditional non-clinical performance tests for an incubator and culture dish, such as electrical safety, EMC, cleaning validation, gas maintenance, temperature control, time-lapse imaging function, embryo development testing (mouse embryo assay), and sterilization validation.

Therefore, I cannot provide the requested information as the provided text relates to a medical device that does not appear to be an AI/ML device.

Ask a specific question about this device

The Geri Embryo Incubator is intended to provide an environment with controlled temperature and mixed gas (CO2 and other gases) for the development of embryos. The Geri Embryo Incubator has an integrated camera and optics for imaging and viewing embryos during incubation, for a maximum time of 120 hours.

The Geri Dish is intended to be used for preparation, storage and imaging of human embryos. The Geri Dish is intended to be used only with the Geri Embryo Incubator.

The Geri Embryo Incubator is a benchtop incubator with six modular incubation chambers each with its own temperature control capability and separate gas inlet feed. Each chamber contains heating elements in its lid and base, together with an orange light source (591 nm) and camera with integrated optics that take time-lapse images of embryos and allows operators to view embryos without removing them from the incubation chamber. Inside each chamber is a filter the gas mixture entering the incubation chamber from the gas supply. The gas is supplied from standard premixed medical gas cylinders.

The Geri Embryo Incubator includes firmware to control the incubator settings, and software to control patient information and settings.

The embryos are maintained in Geri Dishes that are supplied separately. The Geri Dish is an optically-clear polystyrene dish designed to be compatible with the Geri Embryo Incubator. Up to 16 embryos can be stored in one Geri Dish. Geri Dishes are supplied sterile with a sterility assurance level (SAL) of 10-9, and have a shelf-life of 12 months.

The Geri Embryo Incubator and Geri Dish are intended to be used together for embryo imaging purposes. The Geri Dish is not compatible with other embryo time-lapse incubators. However, other assisted reproduction culture dishes may be used in the Geri Embryo Incubator in separate non-time-lapse positions located within each chamber.

The provided text is a 510(k) summary for the Geri Embryo Incubator and Geri Dish. It details the device, its intended use, comparison to predicate devices, and a summary of non-clinical performance testing. However, it does not include detailed acceptance criteria tables or specific reported device performance values for the Geri Embryo Incubator and Geri Dish.

Specifically, while it mentions "Bench performance tests that met design specifications described in Section VII" and lists some parameters like "Gas maintenance testing," "Temperature control testing," and "Time-lapse testing," it generally states that these tests "met design specifications" without providing the actual acceptance criteria values (e.g., specific CO2 levels, temperature ranges, or image resolution thresholds) and the precise device performance results.

Therefore, I cannot create a table of acceptance criteria and reported device performance from the provided text. The document describes the types of tests performed and generally states that the device met the specifications, but it does not quantify those specifications or the observed performance.

Similarly, the document provides limited information on most of the other requested criteria for a study proving the device meets acceptance criteria, as it is a 510(k) summary, not a detailed study report.

Here's an assessment based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance:

• Cannot be created from the provided text. The document states that "Bench performance tests that met design specifications described in Section VII" and lists categories like "Gas maintenance testing," "Temperature control testing," and "Time-lapse testing." It also provides a specific acceptance criterion for the Geri Dish's Mouse Embryo Assay: "1-cell MEA ≥80% embryos developed to blastocyst in 96 hours." However, the actual numerical design specifications (acceptance criteria) and the measured device performance for gas, temperature, and time-lapse functions are not provided.

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

• Sample size for test set: Not explicitly stated for most tests. For the mouse embryo assays, it implies a comparative group ("in comparison with the control group"), but the number of embryos or dishes tested is not given.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). This is typically lab-based bench testing.

3. Number of Experts Used to Establish Ground Truth and Qualifications:

• Not applicable / Not specified. This document describes performance testing for an incubator and dish, which are physical devices with measurable parameters (temperature, gas, imaging). The "ground truth" for these tests would be established through calibrated instruments and established scientific principles, not typically by expert consensus in the way, for example, medical image analysis AI models use expert radiologists. The "Embryo development test" and "Mouse embryo assay" are biological assays, where the "ground truth" is typically the observed biological outcome (blastocyst development), assessed by trained laboratory personnel, but no expert qualifications or numbers are mentioned.

4. Adjudication Method for the Test Set:

• Not applicable / Not specified. Adjudication is relevant for subjective assessments, particularly in clinical studies involving interpretation. The tests described are primarily objective benchtop and biological assays.

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

• No. An MRMC study is relevant for AI-assisted diagnostic devices where human readers interpret medical images. This document describes a medical device (incubator and dish) that does not directly involve human image interpretation in its primary function, nor does it describe AI assistance to human readers.

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

• Not applicable. This device is hardware with integrated software for control and imaging; it's not a standalone AI algorithm for interpretation. Its performance is inherent to the device's function.

7. Type of Ground Truth Used:

• For physical parameters (gas, temperature, imaging functions): Measured values against design specifications using calibrated instruments.
• For biological assays (mouse embryo development): Observed biological outcomes (e.g., blastocyst formation).

8. Sample Size for the Training Set:

• Not applicable. This is a hardware device with integrated control/imaging software, not a machine learning model that requires a "training set" in the conventional AI sense for learning patterns from data. The software mentioned ("Software verification and validation testing") refers to traditional software engineering V&V, not AI model training.

9. How Ground Truth for Training Set Was Established:

• Not applicable. (As explained above, no separate training set for an AI model is described.)

Ask a specific question about this device

The COOK Vacuum Pump is intended for the aspiration of eggs (ova), during assisted reproduction procedures using low flow, intermittent vacuum.

The COOK Vacuum Pump (K-MAR-5200) is an electrically-powered, vacuum pump that is used for the collection of ova (eggs) from ovarian follicles for use in in vitro fertilization (IVF) procedures. The COOK Vacuum Pump provides vacuum levels ranging from -10 mmHg to -500 mmHg. . It is supplied non-sterile.

The disposable Vacuum Line with Hydrophobic Filter (K-DVLF-240) is an accessory to the COOK Vacuum Pump and is used to connect the vacuum pump to an ovum aspiration needle. This component has been designed and tested to withstand the maximum vacuum pressures associated with the COOK Vacuum Pump. The Vacuum Line with Hydrophobic Filter (K-DVLF-240) is provided sterile (ethylene oxide sterilization) for single use only, and has a shelf-life of three years.

The provided text is a 510(k) Premarket Notification from the FDA regarding the "COOK Vacuum Pump". This document primarily focuses on the device's substantial equivalence to a predicate device and does not contain information about clinical studies or performance data related to AI/algorithm-driven medical devices. Therefore, I cannot provide the requested information regarding acceptance criteria and study results for an AI device.

The document discusses the following:

• Device Name: COOK Vacuum Pump
• Indications for Use: Aspiration of eggs (ova) during assisted reproduction procedures using low flow, intermittent vacuum.
• Predicate Device: COOK Ultra Quiet Vacuum Pump & Regulator (K992070)
• Technological Characteristics: Comparison of vacuum range, boost function, controller type, and presence of software.
• Non-Clinical Performance Testing: Electrical Safety, Electromagnetic Compatibility, Software Verification and Validation, Sterilization Validation, Shelf-Life Testing.

Specifically, regarding your request, this document does not include:

• A table of acceptance criteria and reported AI device performance.
• Sample sizes, data provenance, or details of a test set for an AI algorithm.
• Information on experts used to establish ground truth for an AI test set.
• Adjudication methods for an AI test set.
• Multi-Reader Multi-Case (MRMC) comparative effectiveness studies for human readers with/without AI assistance.
• Standalone AI algorithm performance.
• Type of ground truth for an AI algorithm.
• Sample size for an AI training set.
• How ground truth for an AI training set was established.

The "Software Verification and Validation Testing" mentioned refers to the general software development lifecycle and testing process of the embedded software controlling the vacuum pump, not to artificial intelligence or machine learning model validation.

Ask a specific question about this device

To maintain the temperature of human reproductive tissue such as occytes and embryos through an assisted reproduction (AR) cycle.

The RI Witness Embryology Heated Plate is designed to maintain the temperature of embryos and other reproductive tissues placed in dishes on the surface of the device. It is typically installed in a flow hood or on a work bench and comprises of a central clear window within a solid baseplate containing the temperature controller. There are 5 heating circuits, one for the window that uses ITO coated glass and the other 4 use power resistors screwed in thermal contact to the aluminium base plate.

The provided text describes the RI Witness Embryology Heated Plate, a device designed to maintain the temperature of human reproductive tissues. However, the document does not contain information about a study that measures the device's performance against detailed acceptance criteria in the manner requested (e.g., in a clinical trial with human subjects, or a detailed analytical study with a specified sample size, ground truth, and expert involvement).

The document is a 510(k) summary for the device, focusing on demonstrating substantial equivalence to a predicate device. It details non-clinical performance data related to electrical safety, EMC, wireless technology, software verification, and bench testing. These tests are primarily focused on safety and engineering performance, rather than clinical efficacy or accuracy in the context of an AI/algorithm-driven device as implied by the request's structure.

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

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

1. Table of acceptance criteria and reported device performance:

The document lists some technical specifications and mentions various types of bench testing performed. From this, we can infer some internal acceptance criteria related to these technical specifications and tests.

• Time to reach temperature set point
• Maximum temperature
• Stability of temperature control
• Uniform distribution of temperature across the device
• Liquid ingress
• Volatile organic compound emissions
• Cable integrity up to 84°C
• Thermal Cycling Life Test
• Packaging Verification |
  | Biological Effect of Radiofrequency Exposure | Mouse embryo assay performed to measure the effects of exposure to radiofrequency. (The text states the test was done, implies acceptable results as it concludes substantial equivalence). |

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

• Sample Size: Not specified for any of the tests. The "mouse embryo assay" implies a biological sample, but the number of embryos or replicates is not mentioned.
• Data Provenance: The device is manufactured in the United Kingdom by Research Instruments Ltd. All testing appears to be non-clinical bench testing conducted by or for the manufacturer. The "mouse embryo assay" is the only test that could be considered biological, but specific details are absent.

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

• Not applicable. The tests performed are primarily engineering and safety assessments, not evaluations requiring expert human interpretation of images or clinical data.

4. Adjudication method for the test set:

• Not applicable. No expert adjudication process is described for the types of tests conducted.

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/algorithm-driven diagnostic tool that assists human readers. It is a heated plate for medical samples.

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

• Not applicable. This device is not an algorithm.

7. The type of ground truth used:

• For the engineering/safety tests: Standards (e.g., IEC 60601-1:2012, IEC 60601-1-2:2014, FDA guidance for wireless technology) and defined performance specifications (e.g., temperature accuracy, heating range).
• For the mouse embryo assay: Biological outcomes in mouse embryos, implicitly compared against a control or expected norm for viability/development. Specific details are not provided.

8. The sample size for the training set:

• Not applicable. The device is not an AI/machine learning algorithm requiring a training set in this context.

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

• Not applicable.

In conclusion, the provided document is a regulatory submission focused on substantial equivalence of a medical device (a heated plate). It describes engineering and safety tests rather than performance against acceptance criteria for an AI or imaging diagnostic device. As such, most of the requested information regarding study design, sample sizes, expert involvement, and ground truth in a clinical or AI context is not present.

Ask a specific question about this device

To provide an environment with controlled temperature, CO2 (and other gases) for the development of embryos. This model has an integrated inverted microscope and imaging system for embryo viewing. Device use is limited to five days (120 hr) covering the time from post-fertilization to day 5 of development.

Preparing, storing and transferring human embryos. To be used only with the MIRI TL device.

Not Found

This document is a 510(k) clearance letter from the FDA for two devices: AT Medical MIRI TL and AT Medical CultureCoin. It does not contain information on device acceptance criteria or a study proving that the device meets such criteria. Therefore, I cannot fulfill your request with the provided information.

Ask a specific question about this device

The EmbryoScope® time-lapse incubator (version D) provides an environment with controlled temperature, CO2 (and other gasses) for the development of embryos. This model has an integrated inverted microscope and imaging system for embryo viewing. Device use is limited to five days (120 hr) covering the time from post-fertilization to day 5 of development.

The EmbryoViewer™ software is an optional accessory software package for use in displaying, comparing, storing, and transferring images generated by the EmbryoScope® time-lapse incubator (Version D). The software includes a user annotation function for capturing information on embryo development parameters as well as a user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo selection. The EmbryoViewer™ software does not control any hardware components in the EmbryoScope® time-lapse incubator (Version D).

The EmbryoScope® time-lapse incubator is a tri-gas incubator, which acquires a series of unattended measurements on individual embryos during their development. The measurements include: time-lapse microscopy at multiple focal planes and logging of incubation conditions. Separate processing units control the incubation environment and data acquisition to ensure safe and reliable operation. Up to 72 embryos (6 EmbryoSlide® culture dishes with 12 embryos in each culture dish) can be incubated simultaneously.

The purpose of the EmbryoViewer™ software is to assist the embryologist in selecting embryos for transfer or freezing. This is obtained by allowing the embryologist to inspect high-resolution time-lapse images of embryo development, to use detailed annotation tools and to inspect the running conditions of the EmbryoScope® time-lapse system. The EmbryoViewer™ software does not perform any diagnostics, but only shows data from the EmbryoScope® time-lapse system and data entered by the user.

The provided text describes the 510(k) summary for the "EmbryoScope time-lapse incubator (Version D) and EmbryoViewer software." However, it does not contain specific acceptance criteria, a detailed quantitative study proving the device meets acceptance criteria, or information on human reader performance with or without AI assistance, or details about the training set.

Instead, it states that the device is considered substantially equivalent to a predicate device (K113075) based on an evaluation of tests performed on previous versions, with additional tests for new features. The document explicitly states that "No clinical testing was performed" for the EmbryoViewer software and "No clinical testing was performed" for the EmbryoScope time-lapse incubator.

Therefore, many of the requested details cannot be extracted from the provided text.

Here is an attempt to address the request based only on the information available:

1. A table of acceptance criteria and the reported device performance
   The document does not provide a table of acceptance criteria with specific quantitative targets. Instead, it relies on substantial equivalence to a predicate device (K113075). The reported "performance" for the EmbryoScope time-lapse incubator is that the "test results have been evaluated and it has been concluded to accept the test results; the EmbryoScope time-lapse incubator is substantially equivalent to the predicate device." For the EmbryoViewer software, "Test results have been evaluated and it has been concluded to accept the test results; the EmbryoViewer software is as safe, as effective and performs as well or better than the EmbryoViewer software included in the submission K113075."

   Acceptance Criteria	Reported Device Performance
   EmbryoScope time-lapse incubator (Version D):
   Substantial equivalence to predicate device (K113075) based on evaluation of tests performed on previous version (GB) and additional tests for new features (EGS).

Incubation conditions and image quality not adversely affected by changes.
New features do not raise new types of safety and effectiveness questions.
Underwent and passed electrical safety, electromagnetic compatibility, environmental, and operating performance testing in accordance with IEC 60601-1:2005. | Test results evaluated and accepted; device is substantially equivalent to the predicate device.
Incubation conditions and image quality are not adversely affected.
New features do not raise new types of safety and effectiveness questions.
Passed electrical safety, electromagnetic compatibility, environmental, and operating performance testing in accordance with IEC 60601-1:2005.
Tests with and without mouse embryos confirm gas system component (EGS) is equivalent to gas system component (GB) in predicate device. No adverse effects of image acquisition were observed. |
| EmbryoViewer™ software: | |
| Substantial equivalence to predicate device (K113075) based on evaluation of tests performed on previous version and additional tests for new features.
Fulfilling the requirements of the IEC 62304 standard according to software testing.
New features (models and Compare & Select) do not impact incubation conditions or require changes to the EmbryoScope time-lapse incubator and do not raise new types of safety and effectiveness questions. | Test results evaluated and accepted; software is as safe, as effective, and performs as well or better than the predicate device's software.
Fulfills the requirements of the IEC 62304 standard according to software testing.
New features have no impact on incubation conditions and do not raise new safety and effectiveness questions. |

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 specify a distinct "test set" in terms of number of cases (e.g., embryos or patients). The testing for substantial equivalence for both the EmbryoScope incubator and EmbryoViewer software primarily refers to "an evaluation of tests performed on previous version" with "addition of tests related to new features." There's mention of "Tests with and without mouse embryos" for the incubator, but no sample size or specific provenance for these. No information is provided about data provenance or whether any data was retrospective or prospective.

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 (N/A). The document states "No clinical testing was performed" for either device. Therefore, no ground truth was established by experts in a clinical study context for this submission.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
   Not applicable (N/A). As "No clinical testing was performed," there was no clinical test set 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
   No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The document explicitly states "No clinical testing was performed." The EmbryoViewer software includes a "user-defined modeling function" to "aid in embryo selection," but no study on its effectiveness or the improvement of human readers is presented.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
   The document describes the EmbryoViewer software's functionality, including "a user annotation function" and a "user-defined modeling function." It explicitly states that the "EmbryoViewer™ software does not perform any diagnostics, but only shows data from the EmbryoScope® time-lapse system and data entered by the user." This implies it's designed as an assistive tool for human-in-the-loop use, rather than a standalone diagnostic algorithm. No standalone performance metrics are provided.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
   Not applicable (N/A). As "No clinical testing was performed," there is no mention of ground truth types derived from studies for this submission. The EmbryoViewer software stores "patient details, treatment data and outcome data," but this refers to data input by the user and stored in the database, not ground truth used to evaluate the device itself for this submission.

8. The sample size for the training set
   Not applicable (N/A). No explicit training set is mentioned as part of the device's development or evaluation in this submission. The software's "user-defined modeling function" allows users to define models, which implies the models are user-trained or configured, but no internal training set used by the manufacturer is described.

9. How the ground truth for the training set was established
   Not applicable (N/A). As no training set is described for the manufacturer's algorithm development in this document, no information on how its ground truth was established is provided.

Ask a specific question about this device