Search Results

The device is intended for the spatial positioning and orientation of instruments holders or tool guides to be used by trained neurosurgeons to guide standard neurosurgical instruments (biopsy needle, stimulation or recording electrode, endoscope). The device is indicated for any neurosurgical procedure in which the use of stereotactic neurosurgery may be appropriate.

The ROSA One Brain application device is a robotized image-guided device that assists the surgeon during brain surgeries. It provides quidance of any surqical instruments compatible with the diameter of the adaptors supplied by Medtech. It allows the user to plan the position of instruments or implants on medical images and provides stable, accurate and reproducible guidance in accordance with the planning. The device is composed of a robot stand with a compact robotic arm and a touchscreen positioned close the operating table. Different types of instruments may be attached to the robot arm and changed according to the intended surgical procedure. For Brain applications, these neurosurgical instruments (e.g. biopsy needle, stimulation or recording electrode, endoscope) remain applicable for a variety of procedures as shown below in Figure 1 for the placement of recording electrodes. The touchscreen ensures the communication between the device and its user by indicating the actions to be performed with respect to the procedure. Adequate quidance of instruments is obtained from three-dimensional calculations performed from desired surgical planning parameters and registration of spatial position of the patient.

The provided text describes the ROSA ONE Brain application, a robotized image-guided device for neurosurgery. It's an FDA 510(k) submission seeking substantial equivalence to a previously cleared version of the same device. The submission focuses on non-clinical performance data to demonstrate this equivalence.

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

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

The document doesn't explicitly state "acceptance criteria" for each test in a formal table with pass/fail. However, it does outline the tests performed and the results, implying that the predicate device's performance levels define the acceptance criteria for the new version. The most specific performance metric provided is for accuracy.

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

• System applicative accuracy: The text states "Performance bench Testing in compliance with internal Medtech/Zimmer Biomet robotics procedures." No specific sample size (number of tests or cases) for this in vitro testing is mentioned. The data provenance is internal company testing.
• For other tests (Electrical safety, EMC, Biocompatibility, Cleaning- and Sterilization Validation), the testing was largely performed on the predicate device. The subject device (ROSA ONE Brain application v. 3.1.7.0) was then evaluated against these predicate testing results, implying a comparison or re-evaluation rather than new, extensive testing on a new sample set for clinical endpoints.
• For Software Verification and Validation Testing, testing was performed on the subject device. No specific sample size (number of test cases or runs) is provided.

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 studies listed are non-clinical (bench testing, software testing, electrical safety, biocompatibility, cleaning/sterilization), which do not typically involve experts establishing ground truth in the same way clinical studies with image interpretation or patient outcomes do.

4. Adjudication method for the test set

This information is not applicable as the studies are non-clinical performance and engineering tests, not involving human interpretation of data 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

No MRMC comparative effectiveness study was done. The document explicitly states: "Clinical data were not required to support the safety and effectiveness of ROSA ONE Brain application. All validation was performed based on non-clinical performance tests." Therefore, there is no information about human reader improvement with or without AI assistance.

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

While the device is a "robotized image-guided device," the performance data presented is for the entire system's accuracy and various engineering aspects. The "Software Verification and Validation Testing" does cover the algorithm's performance within the broader software system. The statement that "Robot arm positioning accuracy <0.75 mm RMS Device applicative accuracy <2mm" can be considered a standalone performance metric for the device's mechanical and software-guided capabilities, demonstrating its ability to meet a precision target independently of a human's final surgical action. However, it's not an "algorithm-only" performance in the sense of an AI diagnostic tool.

7. The type of ground truth used

• System applicative accuracy: The ground truth would be precise, known physical measurements and positions in a controlled bench test environment.
• Electrical safety and EMC: Ground truth is defined by the absolute limits and requirements of the IEC 60601-1 and IEC 60601-1-2 standards.
• Biocompatibility testing: Ground truth is established by the specified biological responses (e.g., cell viability for cytotoxicity, skin reaction for irritation) determined according to ISO 10993-1.
• Software Verification and Validation Testing: Ground truth is defined by the software requirements and design specifications, against which the software's behavior is verified and validated.
• Cleaning- and Sterilization Validation: Ground truth is defined by the absence of viable microorganisms or acceptable residual soil levels, determined according to standards like ISO 17665-1, ISO 17664, ANSI/AAMI ST79, and AAMI TIR 12.

8. The sample size for the training set

This information is not provided and is not applicable to this submission. The device is a robotized stereotaxic instrument, not an AI/ML device that requires a distinct "training set" for model development. The software verification and validation are against pre-defined requirements, not derived from a training dataset.

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

This question is not applicable as there is no mention of a training set for an AI/ML model in this submission.

Ask a specific question about this device

The device is intended for the spatial positioning and orientation of instruments holders or tool guides to be used by trained neurosurgeons to guide standard neurosurgical instruments (biopsy needle, stimulation or recording electrode, endoscope). The device is indicated for any neurosurgical procedure in which the use of stereotactic neurosurgery may be appropriate.

The ROSA One Brain application device is a robotized image-guided device that assists the surgeon during brain surgeries. lt provides guidance of any surgical instruments compatible with the diameter of the adaptors supplied by Medtech. It allows the user to plan the position of instruments or implants on medical images and provides stable, accurate and reproducible guidance in accordance with the planning. The device is composed of a robot stand with a compact robotic arm and a touch screen. Different types of instruments may be attached to the robot arm and changed according to the intended surgical procedure. For Brain applications, these neurosurgical instruments (e.g. biopsy needle, stimulation or recording electrode, endoscope) remain applicable for a variety of procedures as shown below in Figure 1 for the placement of recording electrodes. The touchscreen ensures the communication between the device and its user by indicating the actions to be performed with respect to the procedure. Adequate guidance of instruments is obtained from three-dimensional calculations performed from desired surgical planning parameters and registration of spatial position of the patient.

The provided text describes the 510(k) summary for the ROSA ONE Brain Application (K214065), a robotized image-guided device assisting in brain surgeries. The document highlights the substantial equivalence of the new version (v.3.1.6.0) to its predicate device (v.3.1.3.2) (K200511).

However, the provided document does not contain information about acceptance criteria or a study that proves the device meets specific performance criteria beyond general safety and equivalence. Instead, it refers to performance testing completed for the predicate device and states that the subject device was evaluated against that predicate testing and determined to be "substantially equivalent."

Therefore, I cannot provide a table of acceptance criteria or details about a study proving the device meets those criteria directly from the provided text, as the document explicitly states: "All validation was performed based on non-clinical performance tests." and "Clinical data were not required to support the safety and effectiveness of ROSA ONE Brain application."

Based on the provided document, here's what can be inferred and what cannot:

1. Table of Acceptance Criteria and Reported Device Performance

The document presents the following performance data as part of the summary, largely relying on the predicate device's testing and then asserting equivalence for the new device. It does not explicitly state "acceptance criteria" but rather "results" from testing.

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

• Test Set Sample Size: The document does not specify a quantitative "sample size" for a test set in the traditional sense of a clinical or human-in-the-loop study. The performance data presented are primarily from bench testing and evaluations related to software, electrical safety, biocompatibility, and cleaning/sterilization. These tests are generally conducted on representative units of the device or its components.
• Data Provenance: The document does not explicitly state the country of origin for the data for all tests. It mentions "internal Biomet Medtech/Zimmer robotics procedures" for a system accuracy test. The studies mentioned (biocompatibility, electrical safety, software V&V, cleaning/sterilization, and system accuracy) are non-clinical performance tests. They are retrospective in the sense that they refer to data typically collected during product development and validation phases, rather than prospective clinical trials.

3. Number of Experts and Qualifications for Ground Truth

• Not Applicable: The document describes non-clinical performance tests. There is no mention of human experts being used to establish ground truth for a test set in the context of image interpretation or diagnostic accuracy, as this is a device for surgical guidance, not diagnostic interpretation.

4. Adjudication Method for the Test Set

• Not Applicable: As there's no mention of human experts establishing ground truth for a test set for diagnostic or interpretative purposes, adjudication methods are not relevant here.

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

• No: The document explicitly states: "Clinical data were not required to support the safety and effectiveness of ROSA ONE Brain application." Therefore, no MRMC comparative effectiveness study was performed.

6. Standalone (Algorithm Only) Performance

• Not Applicable in the traditional sense: The device is a robotized surgical guidance system. Its "performance" is inherently tied to its mechanical and software accuracy in positioning. The software verification and validation is a standalone assessment of the software's functionality, but there isn't an "algorithm only without human-in-the-loop performance" study in the way one would assess an AI diagnostic algorithm's standalone performance. The system's output is guidance for a human surgeon.

7. Type of Ground Truth Used

• Engineering/Physical Ground Truth: For the system applicative accuracy, the ground truth would be established by precise measurements using metrology equipment on a bench setup, comparing the device's guided positions against known, true positions or planned trajectories. For other tests (biocompatibility, electrical safety, software, cleaning/sterilization), the "ground truth" is compliance with established international standards and internal protocols.

8. Sample Size for the Training Set

• Not Applicable: The ROSA ONE Brain Application is a robotized surgical guidance system, not an AI/ML model that would typically have a "training set" in the context of machine learning. The software is developed through standard engineering practices (design, coding, unit testing, integration testing, verification, validation) rather than being "trained" on a dataset like a deep learning model.

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

• Not Applicable: As there's no "training set" in the machine learning sense, this question is not relevant based on the provided document. The device's "knowledge" or functionality is engineered and programmed, not learned from a dataset.

Ask a specific question about this device

The device is intended for the spationing and orientation of instruments holders or tool guides to be used by trained neurosurgeons to guide standard neurosurgical instruments (biopsy needle, stimulation or recording electrode, endoscope). The device is indicated for any neurosurgical procedure in which the use of stereotactic neurosurgery may be appropriate.

The ROSA One Brain application device is a robotized image-quided device that assists the surgeon during brain surgeries. It provides guidance of any surgical instruments compatible with the diameter of the adaptors supplied by Medtech. It allows the user to plan the position of instruments on medical images and provides stable, accurate and reproducible guidance in accordance with the planning. The device is composed of a robot stand with a compact robotic arm and a touch screen. Different types of instruments may be attached to the robot arm and changed according to the intended surgical procedure. For Brain applications, these neurosurgical instruments (e.g. biopsy needle, stimulation or recording electrode, endoscope) remain applicable for a variety of procedures as shown below in Figure 5.1 for the placement of recording electrodes. The touchscreen ensures the communication between the device and its user by indicating the actions to be performed with respect to the procedure. Adequate guidance of instruments is obtained from three-dimensional calculations performed from desired surgical planning parameters and registration of spatial position of the patient.

The provided text describes the ROSA ONE Brain application and its substantial equivalence to a predicate device. However, it does not include detailed acceptance criteria and a study proving the device meets those criteria in the way typically expected for an AI/ML medical device submission (e.g., performance metrics like sensitivity, specificity, AUC for a diagnostic algorithm).

Instead, this document focuses on demonstrating substantial equivalence based on engineering and quality control tests rather than clinical performance of an AI algorithm making diagnostic or treatment recommendations. The "performance data" section primarily discusses electrical safety, EMC, software verification, and biocompatibility, along with a statement about system applicative accuracy derived from the predicate device's testing.

Given the information provided, here's a breakdown of what is and is not available in the document regarding your request:

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

Based on the document, the primary "performance data" that could be interpreted as a performance criterion is the "System applicative accuracy."

Note: The document explicitly states: "Testing were performed on the predicate device. The subject devices were evaluated against the predicate testing and determined to be substantially equivalent." This implies that the current device is expected to meet these same performance levels, rather than providing new, independent test results for the current device's accuracy.

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

This information is not available in the provided text. The accuracy testing was "in vitro" and performed on the predicate device, not necessarily on a "test set" of clinical cases or data in the context of an AI/ML algorithm.

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

This information is not available. The document does not describe the establishment of ground truth by experts in the context of clinical image interpretation or AI performance evaluation. The accuracy testing mentioned is an engineering performance bench test.

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

This information is not available. Adjudication methods are typically relevant for clinical studies involving human readers or expert consensus on clinical data, which is not described here.

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 information is not available. The document explicitly states "Clinical data were not required to support the safety and effectiveness of ROSA ONE Brain application. All validation was performed based on non-clinical performance tests." Therefore, an MRMC comparative effectiveness study was not performed.

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

A standalone performance test in the typical AI/ML sense (e.g., evaluating an algorithm's diagnostic accuracy on images) was not done or at least not described. The "System applicative accuracy" is a standalone test of the robot's physical positioning capabilities, not an AI algorithm's interpretive performance.

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

For the "System applicative accuracy," the ground truth would be precise physical measurements or a known, highly accurate reference system on a test bench. It is not based on expert consensus, pathology, or outcomes data in a clinical sense.

8. The sample size for the training set

This information is not available. The device describes a "robotized image-guided device" that assists surgeons; it does not explicitly mention an AI algorithm that is "trained" on a dataset in the way a diagnostic AI would be. The software verification and validation are for the overall embedded software system, not specifically for an AI model's training.

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

This information is not available, for the same reasons as point 8. No specific AI training set or its ground truth establishment is described in this document.

Summary of the Study that Proves the Device Meets Acceptance Criteria:

The "study" referenced in the document is a series of non-clinical performance tests, primarily conducted on the predicate device, and the new device (ROSA ONE 3.1.3.2) was evaluated for substantial equivalence against these established tests and performance levels.

• System Applicative Accuracy In vitro testing: This was a performance bench test designed to evaluate the physical accuracy of the robotic arm's positioning. The results stated were "<0.75 mm RMS" for robot arm positioning accuracy and "<2mm" for device applicative accuracy. These tests were performed on the predicate device, and the subject device was deemed substantially equivalent. The specific methodology would involve measuring the robot's ability to reach planned targets with precision using specialized measurement tools, but the details of the "Medtech/Zimmer robotics procedures" are not provided.
• Electrical safety and electromagnetic compatibility (EMC): Testing against IEC 60601-1 and IEC 60601-1-2 standards.
• Biocompatibility testing: Evaluation according to ISO 10993-1, including cytotoxicity, sensitization, irritation, and acute systemic toxicity performed on the predicate device.
• Software Verification and Validation Testing: Conducted according to FDA guidance and IEC 62304 standards, with the software designated as "major" concern level. This involved code inspections, unit tests, integration tests, and verification tests against requirements, followed by validation against user needs.
• Cleaning- and Sterilization Validation: Performed according to FDA guidance and ISO/AAMI standards.

In essence, the document confirms that the ROSA ONE Brain application (v.3.1.3.2), as a stereotactic instrument, relies on demonstrating its performance through engineering and quality control tests, showing substantial equivalence to a previously cleared predicate device, rather than a clinical study evaluating an AI's interpretive performance.

Ask a specific question about this device

The device is intended for the spatial positioning and orientation of instrument holders or tool guides to be used by surgeons to guide standard surgical instruments during spine surgeries.

Guidance is based on an intraoperative plan developed with three dimensional imaging software provided that the required fiducial markers and rigid patient anatomy can be identified on 3D CT scans. The device is intended for the placement of pedicle screws in vertebrae with a posterior approach in the thoracolumbar region.

The subject ROSA ONE Spine application is identical to the most recent clearance (K182848) with the exception of an additional calibration step (software) and stand-alone arrays (instrumentation).

The ROSA One device is a robotized image-guided device that assists the surgeon during spine surgeries.

It provides quidance of any surgical instruments compatible with the diameter of the adaptors supplied by Medtech. It allows the user to plan the position of instruments or implants on medical images and provides stable, accurate and reproducible guidance in accordance with the planning.

The device is composed of two stands positioned around the operating table:

• a robot stand with a compact robot arm and a touchscreen .
• a camera stand with an optical navigation system and a touchscreen .

Different types of instruments may be attached to the robot arm and changed according to the intended surgical procedure.

The touchscreen ensures the communication between the device and its user by indicating the actions to be performed with respect to the procedure.

Adequate guidance of instruments is obtained from three-dimensional calculations performed from desired surgical planning parameters and registration of spatial position of the patient.

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

1. Table of Acceptance Criteria and Reported Device Performance

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

The provided text describes non-clinical performance tests. Therefore, there isn't a "test set" in the traditional sense involving patient or human subject data.

• System Applicative Accuracy: Performance bench testing was conducted in compliance with internal Medtech/Zimmer Biomet robotics procedures. The specific sample size (e.g., number of tests, repetitions) is not detailed.
• Electrical Safety & EMC: Testing was conducted on the device. Specific sample size (e.g., number of units tested) is not detailed.
• Biocompatibility: Tests were performed on the predicate device. The subject device was then evaluated against these predicate test results. No specific sample size for the predicate testing is provided within this document.
• Software Verification and Validation: Software tests were conducted. The specific number of test cases or test runs is not detailed.
• Cleaning and Sterilization Validation: Validation was performed using two cycles.

Data Provenance: The tests are described as non-clinical and conducted by Medtech/Zimmer Biomet, implying internal lab testing. No country of origin for test data or retrospective/prospective status is relevant in this non-clinical context.

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

This information is not applicable as the studies are entirely non-clinical performance tests measuring device specifications against engineering and regulatory standards, not against "ground truth" established by clinical experts.

4. Adjudication Method for the Test Set

This is not applicable as there is no human-in-the-loop assessment or expert review for establishing ground truth in these non-clinical performance tests.

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

No, an MRMC comparative effectiveness study was not done. The submission explicitly states: "Clinical data were not required to support the safety and effectiveness of ROSA ONE Spine application. All validation was performed based on non-clinical performance tests."

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

The device itself is a robotized image-guided surgical device that assists the surgeon. While its performance (e.g., accuracy) is measured independently in non-clinical settings ("robot arm positioning accuracy," "device applicative accuracy"), these are measures of its mechanical and computational precision, not of a standalone diagnostic algorithm's performance. Therefore, a standalone "algorithm only without human-in-the-loop performance" study in the typical AI/diagnostic sense was not performed because it's an assistive surgical device, not a diagnostic algorithm.

7. The Type of Ground Truth Used

The "ground truth" in this context refers to established engineering specifications and compliance with recognized standards.

• System Applicative Accuracy: Ground truth is defined by the target accuracy specifications (e.g., < 0.75 mm RMS for robot arm positioning, < 2mm for device applicative accuracy).
• Electrical Safety & EMC: Ground truth is compliance with international standards (IEC 60601-1, IEC 60601-1-2) and FDA guidance.
• Biocompatibility: Ground truth is compliance with ISO 10993-1.
• Software Verification and Validation: Ground truth is compliance with FDA Guidance for software and IEC 62304 standard.
• Cleaning and Sterilization Validation: Ground truth is compliance with FDA Guidance and standards ISO 17665-1, ISO 17664, and AAMI TIR 12.

8. The Sample Size for the Training Set

This information is not applicable. The ROSA ONE Spine application is a robotized surgical assistance device, not a machine learning or AI algorithm that requires a "training set" in the conventional sense. Its "intelligence" comes from programmed algorithms and controls, validated through engineering means, not trained on large datasets.

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

This information is not applicable for the same reasons as above. The device doesn't use a "training set."

Ask a specific question about this device

The device is intended for the spatial positioning and orientation of instrument holders or tool guides to be used by surgeons to guide standard surgical instruments during spine surgeries.

Guidance is based on an intraoperative plan developed with three dimensional imaging software provided that the required fiducial markers and rigid patient anatomy can be identified on 3D CT scans. The device is intended for the placement of pedicle screws in vertebrae with a posterior approach in the thoracolumbar region.

The ROSA One device is a robotized image-guided device that assists the surgeon during spine surgeries.

It provides quidance of surgical instruments compatible with the diameter of the adaptors supplied by Medtech. It allows the user to plan the position of instruments or screws on medical images and provides stable, accurate and reproducible guidance in accordance with the planning.

The device is composed of two stands positioned around the operating table:

• a robot stand with a compact robot arm and a touchscreen .
• . a camera stand with an optical navigation system and a touchscreen

Different types of instruments may be attached to the end of the robot arm and changed according to the intended surgical procedure.

The touchscreen ensures the communication between the device and its user by indicating the actions to be performed with respect to the procedure.

Adequate guidance of instruments is obtained from three-dimensional calculations performed from desired surgical planning parameters and registration of spatial position of the patient.

The provided text describes the ROSA ONE Spine application, a robotized image-guided device intended to assist surgeons during spine surgeries. The information focuses on its substantial equivalence to a predicate device (ROSA SPINE, K151511) and the non-clinical performance data supporting this claim.

Here's an analysis of the acceptance criteria and study proving device performance, based only on the information provided in the document:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify sample sizes for any of the non-clinical tests (e.g., how many robots/devices were tested for accuracy, how many phantom/cadaver units for in vitro studies).

The data provenance is stated as non-clinical performance tests.

• Country of Origin: Not explicitly stated for testing, but Medtech S.A. is located in Montpellier, France.
• Retrospective or Prospective: Not specified, but given these are performance tests (not clinical trials), they are inherently experiments designed to prospectively test specific parameters.

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

This information is not provided in the document. The tests described are primarily engineering and laboratory-based (e.g., accuracy measurements, electrical safety, software validation, cleaning/sterilization validation), which don't typically involve human expert ground truth in the same way clinical image interpretation studies do. The in vitro studies on phantom and cadaver are described, but the method of establishing "ground truth" for the thoracic spine extension is not detailed beyond "evaluation and tests were performed."

4. Adjudication Method for the Test Set

This information is not provided in the document. Adjudication methods are typically relevant for clinical studies involving human interpretation or outcome assessment, not for the technical performance tests described here.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states: "Clinical data were not required to support the safety and effectiveness of ROSA ONE Spine application. All validation was performed based on non-clinical performance tests." Therefore, there is no information on how human readers might improve with AI assistance.

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

The device is described as "a robotized image-guided device that assists the surgeon." While it has software and automated functions, its purpose is to guide human surgeons. The listed performance tests are for the device system (robot arm accuracy, electrical safety, software function), not a standalone diagnostic algorithm. The "Device applicative accuracy" test likely reflects the system's ability to guide to a target, which is a form of standalone performance for a guidance system. However, it's not an "algorithm-only" performance in the sense of an AI model making a diagnosis without human input.

7. The Type of Ground Truth Used

For the technical performance tests:

• System Applicative Accuracy: The ground truth is likely defined by the physical target points and the robot's measured position relative to those points, verified by precise measurement tools.
• Electrical Safety & EMC / Biocompatibility / Cleaning & Sterilization Validation: Ground truth is compliance with specified regulatory standards and test methods.
• Software Verification & Validation: Ground truth is compliance with software requirements and design specifications.
• In vitro studies (phantom/cadaver): The ground truth for validating the thoracic spine extension is not explicitly detailed but would likely involve comparison against pre-defined planned trajectories or anatomical landmarks in the phantom/cadaver, measured by a precision tracking system. It is not "expert consensus, pathology, or outcomes data" in the clinical sense.

8. The Sample Size for the Training Set

This information is not provided. The document focuses on performance testing for regulatory clearance, not the development or training of an AI model. While the device is "robotized" and "image-guided," the document does not elaborate on machine learning model training. The software verification mentions "Code inspections and software tests at the unit, integration and system levels" which relates to traditional software engineering, not necessarily machine learning training.

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

Since the document does not provide information about a "training set" for a machine learning model, the method for establishing its ground truth is not applicable/not provided.

Ask a specific question about this device

The device is intended for the spatial positioning and orientation of instrument holders or tool guides to be used by neurosurgeons to guide standard neurosurgical instruments (biopsy needle, stimulation or recording electrode, endoscope). The device is indicated for any neurosurgical procedure in which the use of stereotactic neurosurgery may be appropriate.

The ROSA One Brain application device is a robotized image-guided device that assists the surgeon during brain surgeries.

It provides quidance of any surgical instruments compatible with the diameter of the adaptors supplied by Medtech. It allows the user to plan the position of instruments or implants on medical images and provides stable, accurate and reproducible guidance in accordance with the planning.

The device is composed of a robot stand with a compact robotic arm and a touch screen.

Different types of instruments may be attached to the end of the robot arm and changed according to the intended surgical procedure. For Brain applications, these neurosurgical instruments (e.g. biopsy needle, stimulation or recording electrode, endoscope) remain applicable for a variety of procedures as shown below in Figure 5.1 for the placement of recording electrodes.

The touchscreen ensures the communication between the device and its user by indicating the actions to be performed with respect to the procedure.

Adequate guidance of instruments is obtained from three-dimensional calculations performed from desired surgical planning parameters and registration of spatial position of the patient.

The ROSA ONE Brain Application device is a robotized image-guided device that assists neurosurgeons during brain surgeries by providing guidance for instruments.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

• Test Set Sample Size: Not explicitly stated but inferred to be a series of physical bench tests on the device.
• Data Provenance: The studies were non-clinical performance tests conducted to support the substantial equivalence determination for the ROSA ONE Brain application. The tests are described as "Performance bench Testing in compliance with internal Medtech/Zimmer Biomet robotics procedures." No specific country of origin for the direct test data is mentioned, but Medtech S.A. is based in Montpellier, France.

3. Number of Experts and Qualifications for Ground Truth

This information is not provided in the document. Given that the studies were non-clinical performance tests for engineering specifications, a panel of clinical experts for ground truth establishment, as might be used for diagnostic AI, would likely not be applicable in the same way. The "ground truth" for these tests would be the established engineering specifications and recognized international standards.

4. Adjudication Method

An adjudication method (e.g., 2+1, 3+1) is not applicable as this study involved non-clinical performance and engineering validation tests, not clinical assessment of results by multiple human readers.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The submission explicitly states: "Clinical data were not required to support the safety and effectiveness of ROSA ONE Brain application. All validation was performed based on non-clinical performance tests." Therefore, there is no effect size reported for human readers improving with AI assistance.

6. Standalone Performance

The performance data presented are for the standalone (algorithm only without human-in-the-loop performance) of the robotic system's accuracy and compliance with various engineering and safety standards. The "System applicative accuracy" directly refers to the device's inherent precision.

7. Type of Ground Truth Used

The ground truth for the non-clinical performance tests was based on:

• Established engineering specifications (e.g., target accuracy metrics).
• Compliance with recognized international standards (e.g., IEC 60601-1, IEC 60601-1-2, ISO 10993-1, IEC 62304, ISO 17665-1, ISO 17664, ANSI/AAMI ST79, AAMI TIR 12).
• Predicate device testing results for biocompatibility, where the subject device was evaluated for substantial equivalence.

8. Sample Size for the Training Set

The document does not specify a separate training set or its sample size. This device is a robotic surgical assistance system, and the accuracy and performance data provided relates to the hardware and software's adherence to engineering specifications and regulatory standards, rather than a machine learning model trained on a dataset. The software validation refers to verification and validation activities according to IEC 62304, which are standard for medical device software development, not necessarily the training of an AI model with a distinct training dataset.

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

As no specific "training set" for a machine learning model is mentioned, the method for establishing its ground truth is not applicable or described in this document. The ground truth for the device's overall performance validation was based on compliance with engineering specifications and regulatory standards as described in point 7.

Ask a specific question about this device

The device is intended for the spatial positioning and orientation of instrument holders or tool guides to be used by neurosurgeons to guide standard neurosurgical instruments (biopsy needle, stimulation or recording electrode, endoscope). The device is indicated for any neurosurgical procedure in which the use of stereotactic surgery may be appropriate.

The ROSA BRAIN device is a robotized platform providing guidance of any neurosurqical instruments compatible with the diameter of the adaptors supplied by Medtech (for example, a biopsy needle). The device is composed of a compact robotic arm and a touch screen mounted on a robot stand. Different types of instruments may be attached to the robot arm and changed according to the requirements of the procedure to be completed. The touch screen ensures the communication between the device and its user by indicating the actions to be done as well as by offering various commands. ROSA BRAIN is an image-quided device that assists the surgeon in planning the position of instruments or implants on preoperative images. It provides a stable, accurate and reproducible mechanical guidance in accordance with the planning. An image acquisition of the patient's head (MRI / CT images) is performed prior to surgery and loaded into the device. In the preoperative phase, the surgeon carries out the surgical planning on the patient images using the device software. The desired surgical parameters for positioning of the surgical instruments are defined (for example: target point, entry point and instrument lenath). During surgery, the device provides accurate and rigid guidance of the required instrument according to the previously completed planning. The optical distance sensor used with the ROSA BRAIN is susceptible to Electrostatic Discharge (ESD). The ROSA BRAIN device is intended to be used with anti-static sterile drapes which are designed for the device and listed in the list of compatible devices. The anti-static sterile drapes are mitigations to ROSA Brain device ESD immunity.

The provided text is a 510(k) summary for a medical device called ROSA BRAIN (v3.0.0.5), a computer-assisted surgical device (stereotaxic instrument). This document describes the device, its intended use, and the testing conducted to demonstrate its substantial equivalence to a predicate device (ROSA BRAIN v3.0.0.0).

Based on the information provided, here's a breakdown of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance:

The document focuses on demonstrating substantial equivalence to a predicate device rather than setting new, specific acceptance criteria for this version's performance at a detailed algorithmic level. The performance data provided are primarily for safety and general functional aspects, and a key 'performance' metric mentioned is system applicable accuracy.

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

The document explicitly states: "Clinical data were not required to support the safety and effectiveness of ROSA Brain. All validation was performed based on non-clinical performance tests."

Therefore:

• Test Set Sample Size: Not applicable in the context of human patient data or studies. The "test set" refers to the non-clinical bench testing conducted to verify accuracy and other engineering specifications. For physical accuracy, the entry "System applicative accuracy In vitro testing" indicates "Testing on the subject device was performed." This would imply multiple runs or repetitions, but a specific numerical sample size (e.g., number of test cases or measurements) is not provided.
• Data Provenance: Not applicable as no human data was used. The testing was in vitro (bench testing) and non-clinical. Given the manufacturer is Medtech S.A. in Montpellier, France, the testing would presumably have been conducted in a controlled lab environment at or by the manufacturer.

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

Not applicable, as no human-in-the-loop clinical or reader studies were performed, and the evaluation was based on non-clinical performance tests against engineering specifications. The "ground truth" for the accuracy test would have been established by precise measurement tools and calibration standards (e.g., coordinate measuring machines, optical tracking systems) rather than human experts in an interpretive sense.

4. Adjudication Method for the Test Set:

Not applicable, as no human-in-the-loop or interpretive studies requiring adjudication were performed.

5. MRMC Comparative Effectiveness Study:

No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done. The submission explicitly states: "Clinical data were not required to support the safety and effectiveness of ROSA Brain." The device's clearance is based on substantial equivalence to a predicate, primarily through non-clinical performance testing.

6. Standalone (Algorithm Only) Performance:

The device is a robotized platform providing guidance, not an AI algorithm that generates diagnostic outputs or interpretations. Its primary "performance" is in terms of the physical accuracy and reliability of its robotic positioning and guidance, as well as its software's ability to plan and execute these movements. The "System applicative accuracy" testing (Robot arm positioning accuracy < 0.75 mm RMS, Device applicative accuracy < 2mm) represents the standalone mechanical and software performance accuracy.

7. Type of Ground Truth Used:

For the "System applicative accuracy" test, the ground truth was metrological/engineering ground truth, established through precise physical measurements using calibrated equipment (e.g., optical tracking systems, mechanical benchmarks) in an in-vitro testing environment, and compared against predefined engineering tolerances.

8. Sample Size for the Training Set:

Not applicable. This device is a robotic surgical assistance system, not a machine learning model that requires a "training set" in the conventional sense of AI/ML. The software itself undergoes verification and validation, but this refers to traditional software engineering practices, not AI model training.

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

Not applicable, as there is no "training set" for an AI/ML model for this device. The software development and testing follow standard software verification and validation procedures (IEC 62304).

Ask a specific question about this device

The device is intended for the spatial positioning and orientation of instrument holders or tool guides to be used by surgeons to guide standard neurosurgical instruments during spine surgery. Guidance is based on an intra-operative plan developed with three dimensional imaging software provided that the required markers and rigid patient anatomy can be identified on 3D CT scans. The device is indicated for the placement of pedicle serews in lumbar vertebrae with a posterior approach

ROSA Spine is a computer controlled electromechanical arm providing guidance of neurosurgical instruments during spinal surgery.

ROSA Spine assists the surgeon in planning the position of instruments relative to intraoperative images.

Adequate position of the instrument holder is obtained from three-dimensional calculations performed from desired surgical planning parameters and registration of spatial position of the patient.

ROSA Spine provides a stable, accurate and reproducible mechanical guidance of neurosurgical instruments in accordance with an intraoperative planning.

While the provided document is a 510(k) premarket notification for the ROSA Spine device, it primarily focuses on establishing substantial equivalence to predicate devices rather than detailing a specific clinical study with detailed acceptance criteria and ground truth establishment for a diagnostic or AI-driven medical device. The ROSA Spine is described as a computer-controlled electromechanical arm for surgical guidance, not a device that makes diagnoses or predictions based on medical images in the way an AI algorithm might.

Therefore, many of the requested details, particularly those related to "AI improvement," "multi-reader multi-case studies," "ground truth establishment," and "training sets" are not applicable or explicitly stated for this type of surgical guidance system's 510(k) submission.

However, I can extract the relevant performance data and address the questions to the best of my ability based on the provided text, making it clear where the information is not present or not applicable.

Here's an attempt to answer your questions based on the provided document:

Device: ROSA Spine (a computer-controlled electromechanical arm for spinal surgical guidance)

1. Acceptance Criteria and Reported Device Performance

The document does not explicitly present these as "acceptance criteria" in a formal table with pre-defined thresholds the way an AI or diagnostic device might. However, it does provide performance metrics tested and reported for the device and its predicates. I will interpret "acceptance criteria" as the performance levels achieved that demonstrate equivalence and safety/effectiveness for this type of device.

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

• Sample Size for Device Performance Testing: "Testing were conducted on cadaveric specimens" - The exact number of cadaveric specimens is not specified.
• Data Provenance: The document does not explicitly state the country of origin for the cadaveric specimens or if the studies were retrospective or prospective. Given it's a 510(k) for a French company, it's plausible testing occurred in Europe or the US, but this is not stated. The context implies these were laboratory/simulated clinical environment tests.

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

• Not applicable in the sense of typical AI ground truth for image interpretation. For a surgical guidance robot, "ground truth" relates to physical accuracy. The device's accuracy was verified against physical measurements. The document does not specify if "experts" were involved in setting up or verifying the cadaveric tests beyond standard engineering and clinical personnel.

4. Adjudication Method for the Test Set

• Not applicable as it's not an AI model requiring human consensus for interpretation. The performance metrics are objectively measured.

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

• No, an MRMC study was NOT done. This type of study is typically performed for diagnostic devices, especially those involving human interpretation of medical images with or without AI assistance. The ROSA Spine is a robotic surgical guidance system, not a diagnostic imaging device.

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

• The "Performance Data" section describes "Device performance tests were performed to validate the absolute accuracy and repeatability of the robot arm, the application accuracy of the device, and the navigation accuracy according to ASTM F2554-10." This is essentially the standalone performance of the robot's mechanical and navigation capabilities, independent of a specific surgeon's skill in using it for the final instrument placement, although it is designed to guide human actions. It's not an "algorithm only" in the AI sense, but rather the robot's physical performance.

7. The Type of Ground Truth Used

• For the performance tests related to accuracy and repeatability, the ground truth was physical measurement against known standards or reference points (e.g., as per ASTM F2554-10) on cadaveric specimens. This is an objective measurement of the robot's mechanical and guidance precision.

8. The Sample Size for the Training Set

• Not applicable. This device is a robotic system; it is not an AI model that learns from a "training set" of data in the common machine learning sense. Its programming and algorithms are deterministic, based on physics and geometry.

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

• Not applicable, as there is no "training set" in the machine learning sense. The device's functionality is based on engineering principles and pre-programmed algorithms rather than data-driven learning.

Ask a specific question about this device

The device is intended for the spatial positioning and orientation of instrument holders or tool guides to be used by neurosurgeons to guide standard neurosurgical instruments (biopsy needle, stimulation or recording electrode, endoscope). The device is indicated for any neurosurgical procedure in which the use of stereotactic surgery may be appropriate.

The ROSA Brain device is a robotized platform providing guidance of any neurosurgical instruments compatible with the diameter of the adaptors supplied by Medtech (for example, a biopsy needle). The device is composed of a compact robotic arm and a touch screen mounted on a robot stand. Different types of instruments may be attached to the robot arm and changed according to the requirements of the procedure to be completed. ROSA Brain is an image-guided device that assists the surgeon in planning the position of instruments or implants on preoperative or intraoperative images. It provides a stable, accurate and reproducible mechanical guidance in accordance with the planning.

The provided document is a 510(k) premarket notification for the ROSA Brain device. It does not describe a study proving the device meets specific acceptance criteria in the context of diagnostic or AI performance.

Instead, the document focuses on demonstrating substantial equivalence to a predicate device (ROSA Surgical Device K101797) based on technological characteristics and non-clinical performance data, primarily related to safety, electrical compatibility, and software validation.

Therefore, many of the requested items (e.g., table of acceptance criteria vs. reported performance, sample sizes for test/training sets, expert ground truth, MRMC study, standalone performance) are not applicable or extractable from this specific document, as it pertains to a different type of device clearance (stereotaxic instrument rather than an AI/diagnostic device).

Here's a breakdown of what can be extracted or inferred from the document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't present a table of quantitative performance acceptance criteria with corresponding device results in the way it would for an AI or diagnostic device (e.g., sensitivity, specificity, accuracy thresholds). The "performance data" provided relates to compliance with standards and successful software verification/validation.

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

Not applicable in the context of an AI/diagnostic test set. The document refers to "software tests" and "verification tests," but these are functional and safety tests, not performance evaluations against a labeled dataset for an AI algorithm.

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

Not applicable in the context of an AI/diagnostic test set. The device is a surgical guidance robot, not an AI diagnostic tool requiring expert-labeled ground truth for performance evaluation.

4. Adjudication Method for the Test Set:

Not applicable.

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

No. The document explicitly states: "The 510(k) does not contain clinical information for the ROSA Brain." and "The 510(k) does not contain animal study test results for the ROSA Brain." An MRMC study would fall under clinical information.

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

Not applicable for a surgical robotic system. The device is inherently "human-in-the-loop," assisting a surgeon. Its performance is evaluated through functional metrics and its ability to accurately position instruments, not as a standalone diagnostic algorithm.

7. The Type of Ground Truth Used:

For the software verification and validation, the "ground truth" would be the predefined functional requirements and expected outputs of the software modules. The "Conformity of software with the user needs and intended use of the device" serves as the ultimate validation.

For the mechanical and electrical performance, the ground truth is the established standards (e.g., IEC 60601-1) and the physical measurements/outputs of the device to ensure it meets specifications (e.g., accuracy of positioning).

8. Sample Size for the Training Set:

Not applicable. This device is not an AI model that undergoes "training" on a dataset in the conventional sense. The "training" in this context would be the development and testing of the software and hardware components following engineering principles.

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

Not applicable. As above, there's no "training set" in the context of an AI algorithm. The validation of the device's components and system is against design specifications, functional requirements, and established safety/performance standards. The "ground truth" for each specific test during development and verification would be defined by those specifications and the expected, correct behavior or output.

Ask a specific question about this device

ROSA Surgical Device is a computer-controlled electromechanical arm. It is intended to be used in the operating room for the spatial positioning and orientation of an instrument holder or tool guide. Guidance is based on a pre-operative plan developed with three-dimensional imaging software, and uses fiducial markers registration. The system is intended for use by neurosurgeons to guide standard neurosurgical instruments. It is indicated for any neurosurgical condition in which the use of stereotactic surgery may be appropriate.

ROSA Surgical Device is a computer controlled electromechanical arm. It is intended to be used in the operating room for the spatial positioning and orientation of an instrument holder or tool guide. Guidance is based on a pre-operative plan developed with three-dimensional imaging software, and uses fiducial markers registration. The system is intended for use by neurosurgeons to guide standard neurosurgical instruments.

The ROSA Surgical Device is a computer-controlled electromechanical arm intended for the spatial positioning and orientation of an instrument holder or tool guide in neurosurgery. Guidance is based on a pre-operative plan developed with three-dimensional imaging software and uses fiducial marker registration.

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

1. Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

The provided text does not explicitly state a sample size for the test set or the data provenance (e.g., country of origin, retrospective or prospective). It mentions "Device performance tests were performed," but no details on the specifics of these tests are given.

3. Number of Experts and Qualifications for Ground Truth

The provided text does not specify the number or qualifications of experts used to establish ground truth for any testing.

4. Adjudication Method for the Test Set

The provided text does not describe any adjudication method used for the test set.

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

There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study in the provided text. The submission focuses on the performance of the device itself, not on human-in-the-loop performance or the effect size of AI assistance on human readers.

6. Standalone Performance Study

Yes, the information implies a standalone (algorithm only without human-in-the-loop performance) study was done. The "Device performance tests" focused on validating the "accuracy and repeatability of the device" itself, suggesting an evaluation of the system's inherent performance.

7. Type of Ground Truth Used

The type of ground truth used is not explicitly stated. However, given the nature of a computer-controlled electromechanical arm for spatial positioning and orientation, it is highly likely that the ground truth for "accuracy and repeatability" would be established through precision measurements and validated spatial references within a controlled environment, rather than expert consensus, pathology, or outcomes data in the traditional sense of diagnostic AI.

8. Sample Size for the Training Set

The provided text does not state the sample size for the training set. It refers to "pre-operative planning developed with three-dimensional imaging software," which would require data for algorithm training, but no details are given.

9. How Ground Truth for the Training Set Was Established

The provided text does not describe how ground truth for the training set was established. The device uses "fiducial markers registration" and "three-dimensional imaging software" for planning, which implies that the training data would be related to accurate spatial mapping and image processing, but the method of establishing their ground truth is not detailed.

Ask a specific question about this device