Search Results

REAL INTELLIGENCE CORI is indicated for use in surgical procedures, in which the use of stereotactic surgery may be appropriate, and where reference to rigid anatomical bony structures can be determined. These procedures include:
· unicondylar knee replacement (UKR),
· total knee arthroplasty (TKA),
· revision knee arthroplasty, and
· total hip arthroplasty (THA).

The subject of this Traditional 510(k) is REAL INTELLIGENCE CORI (CORI), a robotic-assisted orthopedic surgical navigation and burring system. CORI uses established technologies of navigation via a passive infrared tracking camera. For knee applications, CORI aids the surgeon in planning the surgical implant location and in executing the surgical plan by controlling the cutting engagement of the surgical bur.

For knee applications, CORI software controls the cutting engagement of the surgical bur based on its proximity to the planned target surface. The cutting control is achieved with two modes:

• Exposure control adjusts the bur's exposure with respect to a guard. If the surgeon encroaches on a portion of bone that is not to be cut, the robotic system retracts the bur inside the guard, disabling cutting.
• o Speed control regulates the signal going to the tool control unit itself and limits the speed of the drill if the target surface is approached.

Alternatively, the surgeon can disable both controls and operate the robotic drill as a standard navigated surgical drill.

This document, K240139, describes a 510(k) premarket notification for a modification to the REAL INTELLIGENCE™ CORI™ device. The modification integrates an image-based planning option into the Total Knee Arthroplasty (TKA) and Unicondylar Knee Replacement (UKR) applications. The provided text, however, does not include detailed acceptance criteria or a specific study proving the device meets those criteria with performance data in the format requested.

The document primarily focuses on demonstrating substantial equivalence to a predicate device (K231963) by outlining similarities in intended use, indications for use, technological characteristics, and environmental use. It mentions "Design verification and validation testing demonstrated that CORI meets all design requirements" and "Comprehensive testing demonstrated that the system meets required design inputs," but does not provide the specific quantitative acceptance criteria or performance results from these tests.

Therefore, the following points address the requested information based only on what is available in the provided text. Many points will be marked as "Not provided" or "Not applicable" due to the nature of the submission (a 510(k) for a modification focusing on substantial equivalence rather than a full de novo study with detailed performance metrics).

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Test Set: Not specified for the software verification, design verification, or image-based planning registration testing. For the summative usability validation testing, it mentions "representative users," but the number is not provided.
• Data Provenance: Not specified. (e.g., country of origin, retrospective/prospective). This is a modification of an existing device, so the testing mainly focuses on the modified functionalities.

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

• Number of Experts: Not specified.
• Qualifications of Experts: For the usability study, "surgeon users" are mentioned, implying qualified medical professionals, but specific qualifications (e.g., years of experience, specialty) are not detailed. For other testing, the method of establishing ground truth for technical performance (e.g., registration accuracy) is not explicitly described as relying on "experts" in the sense of clinical reviewers, but rather on engineering verification.

4. Adjudication Method for the Test Set

• Not applicable/Not specified. The document refers to "design verification and validation testing," "software verification testing," and "summative usability validation testing." There is no mention of an adjudication process typically associated with reviewer consensus on medical images or clinical outcomes.

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 done/Not applicable. This submission is for a surgical navigation system, not an AI-assisted diagnostic tool that would typically involve a multi-reader, multi-case study to assess human reader performance improvement. The "image-based planning option" implies the import and use of pre-operative imaging data, but the device itself is not described as an AI intended to assist human readers in image interpretation.

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

• Not applicable in the conventional sense of a diagnostic algorithm. The device, REAL INTELLIGENCE™ CORI™, is described as a "robotic-assisted orthopedic surgical navigation and burring system" with an integrated image-based planning option. Its function inherently involves human interaction (a surgeon) and mechanical components. The "standalone" performance would relate to the accuracy of its navigation and burring control, which is implied by "Comprehensive testing demonstrated that the system meets required design inputs," but specific standalone performance metrics are not given.

7. The Type of Ground Truth Used

• The type of ground truth for general "design requirements" and "design inputs" would typically be engineering specifications, physical measurements, and computational models. For the "image-based planning option," the ground truth for registration accuracy would likely be established metrologically against known anatomical landmarks or fiducials in the pre-operative image data. For usability, the ground truth is simply the ability of users to safely and effectively complete tasks, assessed through observation and user feedback. No mention of pathology or outcomes data in this context.

8. The Sample Size for the Training Set

• Not applicable/Not specified. The document does not describe the development of a machine learning or AI model with a distinct "training set." The modification is described as integrating an "image-based planning option," implying a capability to import and use image data, rather than a system trained on image data in an AI development pipeline.

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

• Not applicable. As noted in point 8, no training set for an AI model is described.

Ask a specific question about this device

CORI is indicated for use in surgical procedures, in which the use of stereotactic surgery may be appropriate, and where reference to rigid anatomical bony structures can be determined. These procedures include:

• unicondylar knee replacement (UKR),
• . total knee arthroplasty (TKA),
• revision knee arthroplasty, and
• . total hip arthroplasty (THA).

The subject of this Special 510(k) is REAL INTELLIGENCE CORI (CORI), a robotic-assisted orthopedic surgical navigation and burring system. CORI uses established technologies of navigation via a passive infrared tracking camera. Based on intraoperatively-defined bone landmarks and known geometry of the surgical implant, the system aids the surgeon in establishing a bone surface model for the target surgery and planning the surgical implant location. For knee applications, CORI then aids the surgeon in executing the surgical plan by controlling the cutting engagement of the surgical bur.

CORI knee application software controls the cutting engagement of the surgical bur based on its proximity to the planned target surface. The cutting control is achieved with two modes:

• . Exposure control adjusts the bur's exposure with respect to a guard. If the surgeon encroaches on a portion of bone that is not to be cut, the robotic system retracts the bur inside the guard, disabling cutting.
• . Speed control regulates the signal going to the tool control unit itself and limits the speed of the drill if the target surface is approached.

Alternatively, the surgeon can disable both controls and operate the robotic drill as a standard navigated surgical drill.

The provided text describes a 510(k) submission for the REAL INTELLIGENCE™ CORI™ surgical navigation and burring system. This submission is a "Special 510(k)" which supports an update to the CORI system to allow it to be used with porous Unicondylar Knee Replacement (UKR) implants.

The core of this submission is to demonstrate substantial equivalence to a previously cleared predicate device (also REAL INTELLIGENCE™ CORI™, K221224). Therefore, the provided documentation focuses on showing that the modifications to support porous UKR implants do not impact the system's intended use, indications for use, or fundamental scientific technology, and that the device remains safe and effective.

Crucially, the document does NOT contain a detailed report of a study proving the device meets specific performance acceptance criteria for the AI component, nor does it explicitly mention an AI component as typically understood in medical image analysis (e.g., for diagnosis or prognosis). The device is described as a "robotic-assisted orthopedic surgical navigation and burring system" that uses "intraoperative data collection (image-free or non-CT data generation)" and "predefined boundaries generated during the planning process to control the motion of the surgical bur." This suggests a system for surgical precision and control, not necessarily one that employs machine learning/AI for diagnostic or predictive tasks from imaging data.

Given the information provided, it's not possible to populate all the requested fields as they pertain to a study proving an AI/ML-based device meets acceptance criteria through performance metrics like sensitivity, specificity, or reader improvement. The document focuses on demonstrating that the modified surgical control system still performs as expected and is safe and effective for its intended surgical guidance purpose.

However, I can extract information related to the closest aspects of "acceptance criteria" and "study" described, which in this context refer to verification and validation testing of the updated surgical system.

Here's an attempt to answer based on the provided text, highlighting where information is absent for an AI/ML context:

Device: REAL INTELLIGENCE™ CORI™ (K231963 Special 510(k) update)
Predicate Device: REAL INTELLIGENCE™ CORI™ (K221224)
Purpose of Submission: Update to allow use with porous Unicondylar Knee Replacement (UKR) Implants.

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

The document does not provide a quantitative table of acceptance criteria with specific performance metrics (e.g., accuracy, precision measurements for anatomical structures, or percentages for successful burring). Instead, it makes a general statement about meeting design inputs.

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

• Sample Size for Test Set: Not specified. The document mentions "verification and validation testing" and "summative usability testing," but does not provide details on the number of cadaveric specimens, phantom models, or simulated cases used.
• Data Provenance: Not specified. The studies appear to be bench and simulated use tests, not clinical data from patients.

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)

• Number of Experts: Not specified. For "summative usability testing," the document states "participating surgeons," but provides no number or qualifications beyond "surgeons."
• Qualifications of Experts: Assumed to be surgeons, but no specific professional experience or certification details are given.

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

• Adjudication Method: Not specified.

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

• MRMC Study: Not applicable/not mentioned. This device is a surgical navigation and burring system, not an AI for diagnostic image interpretation that would typically involve an MRMC study comparing human readers with and without AI assistance. The "AI" in "REAL INTELLIGENCE" appears to refer more broadly to advanced computational control/guidance rather than a diagnostic AI algorithm.

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

• Standalone Performance: Not explicitly detailed as a separate "algorithm only" study. The system provides "software-defined spatial boundaries" and "controls the motion of the surgical bur." The testing mentioned is for the integrated system's performance (human-in-the-loop operation, or mechanical performance of the robotic arm/burring based on software control), not a standalone AI algorithm validating its own output without physical action.

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

• Type of Ground Truth: Not explicitly stated but implied to be based on:
  • Design Inputs: The system's performance is verified against its predefined engineering design specifications for spatial accuracy and burring control.
  • Simulated Surgical Environment: For usability testing, the "ground truth" would be the successful and safe completion of the simulated surgical task according to established surgical principles and desired outcomes for UKR implant placement. This would likely involve measuring accuracy of bone cuts against a planned target.

8. The sample size for the training set

• Sample Size for Training Set: Not applicable/not mentioned. This document describes an update to a surgical system, not the development of a new machine learning model. The system uses "intraoperative data collection (image-free or non-CT data generation) to create a model of the patient's femur and/or tibia" and "predefined boundaries." This implies real-time data capture and processing based on established anatomical models and surgical plans, rather than a system trained on a large dataset of patient images to learn patterns.

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

• Ground Truth for Training Set: Not applicable/not mentioned. As per point 8, there's no indication of a machine learning training set in the conventional sense. The "ground truth" for the system's operational principles would be based on anatomical science, biomechanics, engineering specifications, and surgical planning principles.

Ask a specific question about this device