Knee+ is a stereotaxic system including an intraoperative software as a medical device and surgical instruments. Knee+ is intended for primary Total Knee Replacement, to assist the surgeon in determining reference alignment axes in relation to anatomical landmarks, in order to position the cutting computed mechanical axis. The Knee+ includes smart glasses as a Head Mounted Device (HMD) for displaying information to the user intraoperatively. The smart glasses should not be relied upon solely and should always be used in conjunction with traditional methods.

Knee+ is a navigation system dedicated to orthopaedic kneePlus software and KneeTools reusable surgical instruments.

The main purpose of Knee+ is to assist the surgeon during primary Total Knee Arthroplasty (TKA) interventions.

Knee+ provides information to help locate and orientate the main femoral and tibial cutting planes as required during TKA. Knee+ allows the surgeon to adjust the orientation of the cutting plane orientation and the level of resection by collecting anatomical references during the TKA procedure using surgical instruments. The software frame the instruments which include markers. All collected coordinates are treated by software algorithms to provide the surgeon with relevant orientation and location of the tracked cutting guide. Knee+ software is installed on a wearable Head Mounted Device (HMD) which includes a camera, a computer and displays intraoperative information to the user. A near-eye display allows the HMD screen when needed.

The provided document [K243975](https://510k.innolitics.com/search/K243975) is a 510(k) Premarket Notification from Pixee Medical for their device, Knee+. This document claims substantial equivalence to a previously cleared version of the same device (K233899). As such, it does not detail a new study proving the device meets new acceptance criteria, but rather demonstrates that modifications to the device do not negatively impact its performance or raise new safety/effectiveness concerns, maintaining the performance established by the predicate.

Therefore, much of the requested information regarding "acceptance criteria" and "the study that proves the device meets the acceptance criteria" in the context of a new clinical study for FDA clearance is not present, as this is a 510(k) submission showing substantial equivalence of a modified device.

However, based on the non-clinical testing summaries provided, I can infer and construct answers to some of your questions relevant to the performance demonstration for the modified device in comparison to the predicate, and how its established performance was maintained.

Here's an attempt to answer your questions based on the available information:

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

The document states: "Precision and accuracy of the device remain unchanged compared to previous version when measured according to the same methods." It also mentions "Bench testing was conducted in order to demonstrate that Knee+ performs according to its requirements and specifications. In particular, repeatability and accuracy were tested according to ASTM F2554."

Since this is a 510(k) for a modified device, the "acceptance criteria" would primarily be maintaining the performance established by the predicate. Explicit numerical acceptance criteria and reported device performance for these specific modifications are not provided in this public summary. However, the statement "All performance testing demonstrates that Knee+ performs according to its specifications and functions as intended" implies that the device met internal specifications.

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

The document does not specify test set sample sizes for the non-clinical bench testing (e.g., how many measurements were taken for repeatability and accuracy). It primarily relies on bench testing and human factors testing.

• Non-Clinical Testing Providence: France (Pixee Medical is based in Besançon, France). The testing performed is described as "Bench testing" and "Human factors." These are typically prospective tests.
• Clinical Data: "Clinical testing is not applicable." This indicates no new clinical studies were conducted for this 510(k) submission as the device is substantially equivalent to its predicate.

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

Not applicable for this 510(k) as the submission primarily relies on non-clinical bench testing and human factors assessment, not on a new clinical study requiring ground truth established by medical experts for performance evaluation.

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

Not applicable. As this is a 510(k) submission based on substantial equivalence, there's no mention of a clinical study that would require adjudication of expert opinions for a test set.

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

No, an MRMC comparative effectiveness study was not done. The device is a stereotaxic system for guiding Total Knee Replacement, not a diagnostic AI system requiring reader studies. Clinical testing was deemed "not applicable" for this 510(k).

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

The performance testing described (repeatability and accuracy via ASTM F2554) would be considered a standalone assessment of the device's measurement capabilities. However, this is for the surgical guidance aspect, not an AI algorithm generating a diagnostic output to be evaluated independently in isolation from clinical context. The device is intended to be used with human clinicians: "The Knee+ includes smart glasses as a Head Mounted Device (HMD) for displaying information to the user intraoperatively. The smart glasses should not be relied upon solely and should always be used in conjunction with traditional methods."

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

For the non-clinical bench testing for accuracy and repeatability, the "ground truth" would be established by the precise measurements of a calibrated reference system or phantom used in the testing (e.g., known distances or angles on a test fixture). This is standard for evaluating the accuracy of navigation or measurement systems.

8. The sample size for the training set

Not applicable. This document is for a medical device (stereotaxic instrument), not a machine learning/AI algorithm that requires a training set in the conventional sense for a diagnostic output. While the device does use "software algorithms" to process collected coordinates, there's no indication of a machine learning model that requires an external training dataset in the context typically discussed for AI/ML-driven medical devices.

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

Not applicable, as there's no mention of a training set for an AI/ML model for which "ground truth" would need to be established in this context.

Ask a specific question about this device

Knee+ is a stereotaxic system including an intraoperative software as a medical device and surgical instruments. Knee+ is intended for primary Total Knee Replacement, to assist the surgeon in determining reference alignment axes in relation to anatomical landmarks, in order to position the cutting computed mechanical axis. The Knee+ includes smart glasses as a Head Mounted Device (HMD) for displaying information to the user intraoperatively. The smart glasses should not be relied upon solely and should always be used in conjunction with traditional methods.

Knee+ is a navigation system dedicated to orthopaedic knee surgery. It includes KneePlus software and KneeTools reusable surgical instruments.

The main purpose of Knee+ is to assist the surgeon during primary Total Knee Arthroplasty (TKA) interventions.

Knee+ provides information to help locate and orientate the main femoral and tibial cutting TKA. Knee+ allows the surgeon to adjust the orientation of the cutting plane orientation and the level of resection by collecting anatomical references during the TKA procedure using surgical instruments. The software locates in a 3D reference frame the instruments which include markers. All collected coordinates are treated by software algorithms to provide the surgeon with relevant orientation and location of the tracked cutting guide. Knee+ software is installed on a wearable Head Mounted Device (HMD) which includes a camera and displays intraonerative information to the user. A near-eye display allows the HMD screen or the field of view when needed.

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

1. Table of Acceptance Criteria and Reported Device Performance:

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

The document mentions "Bench testing was conducted" to evaluate repeatability and accuracy according to ASTM F2554. However, it does not specify the sample size used for this test set nor the data provenance (e.g., country of origin, retrospective or prospective nature of data).

For human factors testing, it states "Test participants representing the intended in the human factor validation testing." Again, the exact number of participants (sample size) is not provided.

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

The document does not explicitly state the number of experts used or their qualifications for establishing ground truth for any of the test sets.

4. Adjudication Method for the Test Set:

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for the test set.

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

The document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done. The device (Knee+) is described as assisting the surgeon, and the smart glasses "should not be relied upon solely and should always be used in conjunction with traditional methods," implying a human-in-the-loop scenario. However, no specific comparative study with and without AI assistance quantifying human reader improvement is mentioned.

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

The document focuses on the device's performance within the surgical workflow as an assisting tool. While software verification and validation were performed, there is no explicit mention of a standalone algorithm-only performance study independent of human interaction or the "Head Mounted Device (HMD)." The emphasis is on the integrated system providing information to the user.

7. The Type of Ground Truth Used:

The document describes the ground truth in terms of:

• Engineering Specifications/Requirements: For repeatability and accuracy, the ground truth is defined by the device's ability to "perform according to its requirements and specifications" in accordance with ASTM F2554.
• Regulatory Standards/Guidance: For cleaning, sterilization, and biocompatibility, the ground truth is established by adherence to specific AAMI, ISO, and FDA guidance documents.
• User Understanding/Safety & Effectiveness: For human factors, the ground truth is based on "observational data" and "assessment of their understanding of essential information through the interview," confirming safety and effectiveness for intended users.

There is no mention of ground truth established through pathology or outcomes data.

8. The Sample Size for the Training Set:

The document does not provide any information regarding the sample size for the training set. This is likely because the submission focuses on the performance and safety of the updated device rather than the foundational machine learning model (if any) training.

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

As no training set is mentioned, there is no information provided on how its ground truth was established.

Ask a specific question about this device

Knee+ is a stereotaxic system including an intraoperative software as a medical device and surgical instruments. Knee+ is intended for primary Total Knee Replacement, to assist the surgeon in determining reference alignment axes in relation to anatomical landmarks, in order to position the cutting computed mechanical axis. The Knee+ includes smart glasses as a Head Mounted Device (HMD) for displaying information to the user intraoperatively. The smart glasses should not be relied upon solely and should always be used in conjunction with traditional methods.

The main purpose of Knee+ is to assist the surgeon during the primary Total Knee Replacement (TKR) intervention. Knee+ includes software and surgical instruments.

Knee+ provides information to help locate and orientate the main femoral and tibial cutting planes as required in knee replacement surgery. Knee+ allows the surgeon to adjust the cutting plane orientation and the resection level. This includes means for the surgeon to collect anatomical references during the TKR intervention using the surgical instruments. The software locates in a 3D reference frame the instruments which include markers. All collected coordinates are treated by software algorithms to provide the surgeon with relevant orientation of the tracked cutting guide. Knee+ software is installed on a wearable Head Mounted Device (HMD) which includes a camera and displays intraoperative information to the user. A near-eye display allows the surgeon to look at the HMD screen or the field of view when needed.

The provided text is a 510(k) summary for the medical device Knee+, documenting its substantial equivalence to a previously cleared version (K220104). The primary change in the subject device is the addition of an external camera to the Head-Mounted Device (HMD) for use under surgical helmets.

The document does not contain the detailed acceptance criteria or a comprehensive study report outlining the acceptance criteria and the performance data that proves the device meets those criteria in the format requested. While it refers to "performance data" and "acceptance criteria" from previous submissions, and mentions specific tests like ASTM F2554, it does not provide the specific numerical acceptance thresholds or the measured device performance against those thresholds in tabular format.

Therefore, I cannot fully answer your request by extracting the information directly from the provided text. The document states that "The same methods, protocols and acceptance criteria used to support the previously cleared K220104 were applied to evaluate the change." This implies that the specific details you're looking for would be in the K220104 submission, not in this K230789 summary.

However, I can extract and present the available relevant information regarding the study and testing performed to demonstrate substantial equivalence for the modifications in K230789:

Acceptance Criteria and Device Performance (Based on available information for K230789 modifications):

The document states that the same performance is still achieved with the modifications, and that "All performance testing demonstrates that Knee+ performs according to its specifications and functions as intended." While specific numerical criteria and reported performance values are not provided in this summary, the general areas of assessment and the type of criteria implicitly met are:

Study Details for K230789 (Focused on the modifications):

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

   • Sample Size: Not explicitly stated in terms of number of cases or subjects. For bench testing (ASTM F2554), it would typically involve multiple measurements or runs. For user needs validation, it would involve a group of "intended users." The exact number is not provided.
   • Data Provenance: The studies were performance bench testing and user validation studies conducted by the manufacturer, Pixee Medical. The text doesn't specify the country of origin of the data beyond "Besançon, FRANCE" as the submitter's address. The studies were likely prospective for the purpose of validating the new modification.

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

   • Number of Experts: Not specified.
   • Qualifications of Experts: For the "User needs validation," the validation was performed by "intended users." While their specific qualifications (e.g., orthopedic surgeons) are not explicitly stated, it can be inferred that they are medical professionals who would use the device (i.e., surgeons). For bench testing, the "ground truth" would be established by the highly accurate measurement tools and methods used within the testing lab.

3. Adjudication method for the test set:

   • Not specified. Given the nature of bench testing and user needs validation in 510(k) submissions for modifications, formal multi-reader adjudication methods (like 2+1 or 3+1 often seen in diagnostic AI studies) are not typically described in this context for performance of the device's measurement capabilities. User needs validation would involve assessing user feedback and observations.

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, an MRMC comparative effectiveness study was not explicitly stated or implied for this 510(k) submission. This submission focuses on demonstrating that the modified device maintains its previous performance and does not introduce new safety or effectiveness concerns, specifically regarding the addition of an external camera and use under surgical helmets. The device's primary function is to assist in surgical navigation, providing information, and the study did not aim to measure human reader improvement with AI assistance.

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

   • The document implies that standalone performance was assessed for the tracking system technology and accuracy of cut orientation and resection level through "Bench testing." This type of testing evaluates the algorithm's performance and the system's accuracy independent of a complex human interaction scenario, although it's within a controlled test environment.

6. The type of ground truth used:

   • For accuracy and repeatability (bench testing): The ground truth would be established by highly precise measurement instruments and reference standards (e.g., calibrated optical tracking systems, mechanical fixtures) that are part of the ASTM F2554 testing methodology.
   • For user needs validation: The ground truth is the qualitative assessment of safety, effectiveness, and usability by the intended users in simulated or actual usage scenarios.

7. The sample size for the training set:

   • Not applicable / Not provided. The document describes a 510(k) submission for a modification to an already cleared device. It does not contain information about the training set size for the underlying algorithms, as this would have been established during the development and clearance of the original (K220104) or even earlier versions. The current submission focuses on verifying that the modification does not negatively impact existing performance.

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

   • Not applicable / Not provided. As mentioned above, this information pertains to the original algorithm's development, not the current modification's validation.

Ask a specific question about this device

Knee is a stereotaxic system including an intraoperative software as a medical device and surgical instruments. Knee is intended for primary Total Knee Replacement, to assist the surgeon in determining reference alignment axes in relation to anatomical landmarks, in order to position the cutting guide regarding computed mechanical axis. The Knee includes smart glasses as a Head Mounted Device (HMD) for displaying information to the user intraoperatively. The smart glasses should not be relied upon solely and should always be used in conjunction with traditional methods.

The main purpose of Knee* is to assist the surgeon during the primary Total Knee Replacement (TKR) intervention. Knee* includes software and surgical instruments.

Knee* provides information to help locate and orientate the main femoral and tibial cutting planes as required in knee replacement surgery. Knee* allows the surgeon to adjust the cutting plane orientation and the resection level. This includes means for the surgeon to collect anatomical references during the TKR intervention using the surgical instruments. The software locates in a 3D reference frame the instruments which include markers. All collected coordinates are treated by software algorithms to provide the surgeon with relevant orientation of the tracked cutting guide. Kneet software is installed on a wearable Head Mounted Device (HMD) which includes an embedded camera and displays intraoperative information to the user. This near-eve display allows the surgeon to look at the HMD screen or the field of view when needed.

The provided text describes the regulatory clearance of a medical device named "Knee+" but does not contain the specific acceptance criteria or the study details proving the device meets those criteria in the format requested.

The document primarily focuses on demonstrating substantial equivalence to a predicate device (K202750) rather than presenting a detailed performance study against predefined acceptance criteria. It mentions that "All performance testing demonstrates that Knee* performs according to its specifications and functions as intended," and lists types of non-clinical performance data, but does not disclose the specific criteria or the quantitative results from those tests.

Therefore, most of the requested information cannot be extracted from the provided text.

Here's an attempt to answer what can be inferred from the document, along with explanations for what cannot be found:

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

• Cannot be provided. The document does not list specific numerical acceptance criteria (e.g., accuracy thresholds) or the quantitative performance results (e.g., reported accuracy values) for the Knee+ device in a table format. It generally states that "overall system repeatability and accuracy were tested" and that "all performance testing demonstrates that Knee* performs according to its specifications and functions as intended," but without specifics.

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

• Cannot be provided specifically for accuracy/performance testing. The document mentions "Bench testing was conducted" to evaluate repeatability and accuracy, but it does not specify the sample size used for these tests. Data provenance (country, retrospective/prospective) is also not mentioned for this bench testing.
• For Human Factors testing: "Test participants representing the intended users of the device were included." The exact number of participants is not specified.

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/Cannot be provided. The document describes "Bench testing" for accuracy and repeatability, implying these were engineering tests rather than clinical studies requiring expert-established ground truth on patient data. No mention of experts or their qualifications for establishing ground truth is present.

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

• Not applicable/Cannot be provided. Given the nature of the described "bench testing," adjudication methods for expert consensus on a test set are not relevant and are not mentioned.

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. The document does not describe an MRMC comparative effectiveness study involving human readers or AI assistance in that context. The device is a "stereotaxic system" that assists surgeons, and the performance testing mentioned (bench testing, software V&V, instrument functional tests) is not of this type.

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

• Implicitly yes, in part. The document states "overall system repeatability and accuracy were tested" as part of bench testing. While the "system" includes the software, the listed tests sound like standalone engineering performance tests, rather than human-in-the-loop performance. However, there are no specific results provided to detail this standalone performance.

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

• Inferred: Mechanical/Metrological standards or reference measurements. For "overall system repeatability and accuracy" during bench testing, the ground truth would typically be established by highly precise mechanical or optical measurement systems, or by comparison to known physical standards, rather than expert consensus, pathology, or outcomes data, which are relevant for diagnostic or prognostic devices. No specific details are given.

8. The sample size for the training set

• Not applicable/Cannot be provided. The document doesn't discuss machine learning or AI model training. The device is described as a "stereotaxic system including an intraoperative software" that "treats collected coordinates by software algorithms." This implies rule-based or conventional algorithmic software rather than a system trained on a large dataset. Therefore, there is no mention of a "training set."

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

• Not applicable/Cannot be provided. As there is no mention of a training set, the method for establishing its ground truth is also not discussed.

Ask a specific question about this device

FX SPS is intended to be used as an information tool to assist in the preoperative surgical planning and visualization of a primary total shoulder replacement.

FX SPS is a preoperative standalone web-based medical software used for the planning of primary shoulder replacement from CT-images. It comprises a secure database which enables the patient's cases management and the access to the planning interface. Preliminary to the planning, a manual segmentation needs to be performed from the patient's CT-images. The segmentation process consists in building 3D bone models of the patient's shoulder and positioning anatomic landmarks on it. Once these data are generated, their compliance is checked. They are then imported into the FX SPS's database making the planning available for the surgeon. The planning step involves virtually positioning of the shoulder prosthesis on the 3D reconstruction of the patient's shoulder. On that purpose, the surgeon chooses implants from a library of implants. Afterwards, he selects the size of the implant more suitable to the joint and he can move prosthesis components in all directions. Once the positioning of the implant is satisfying, he validates the planning to generate a planning report. During surgery, he will have at its disposal the planning report comprising preoperative and planned parameters.

The provided text describes the 510(k) summary for the Pixee Medical FX SPS device, focusing on its substantial equivalence to a predicate device (e-ortho Shoulder Software). While it details the device's function, intended use, and comparison to the predicate, it does not contain information about acceptance criteria or a specific study proving the device meets those criteria with detailed performance metrics.

The "Non-Clinical Performance Data" section generically states that:

• "Software verification and validation testing were conducted as required by IEC 62304..."
• "All performance testing demonstrated that FX SPS performs according to its specifications and functions as intended."
• "Concerning the angle or gap measurements, software verification and validation testing were conducted. All performance testing demonstrated that FX SPS performs according to its specifications and functions as intended to ensure the required angle accuracy of 1 degree and gap measurement accuracy of 1 mm."
• "User needs validation The software was validated with intended users through a human factor test series to ensure the user needs and intended use requirements were met, in accordance with IEC 62366-1. All requirements were met and no new issues of safety or effectiveness were raised."

This summary indicates that testing was performed and the device met its specifications, but it does not provide the specific "acceptance criteria" table and "reported device performance" as requested in the prompt, nor does it detail a specific study with sample sizes, data provenance, ground truth establishment, or expert involvement.

Therefore, for aspects related to a specific performance study (sample size, experts, ground truth, MRMC, effect size, standalone performance, training set details), the provided document does not contain this information.

Based on the information available in the document, here's what can be inferred or stated about the device's validation:

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

   • Acceptance Criteria (inferred/stated specifications):
     • Angle accuracy: 1 degree
     • Gap measurement accuracy: 1 mm
     • Software performs according to its specifications.
     • Software functions as intended.
     • User needs and intended use requirements are met (human factors).
   • Reported Device Performance:
     • "All performance testing demonstrated that FX SPS performs according to its specifications and functions as intended."
     • "All performance testing demonstrated that FX SPS performs according to its specifications and functions as intended to ensure the required angle accuracy of 1 degree and gap measurement accuracy of 1 mm."
     • "All requirements were met and no new issues of safety or effectiveness were raised."

2. Sample sizes used for the test set and the data provenance: Not specified in the provided text. The document refers to "software verification and validation testing" and "human factor test series" but does not detail the number of cases or the origin of the data (country, retrospective/prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not specified in the provided text. The "human factor test series" implies involvement of "intended users" (surgeons), but details on the number or their qualifications are not provided.

4. Adjudication method for the test set: Not specified in the provided text.

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 specified in the provided text. The device is described as an "information tool to assist in the preoperative surgical planning," but no MRMC study comparing human performance with and without the tool is detailed.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document states "software verification and validation testing were conducted," which would typically include standalone performance against internal specifications (like the angle and gap accuracy). However, detailed results of such a standalone study beyond a general statement of compliance are not provided. The device itself is described as a "standalone web-based medical software."

7. The type of ground truth used: For the stated accuracy metrics (angle and gap), the ground truth would likely be derived from precisely measured simulated data or a highly accurate reference standard established during software development and testing. For human factors, the "ground truth" would be the fulfillment of user needs and intended use requirements assessed by users. Specific details are not provided.

8. The sample size for the training set: Not applicable/Not specified. The device performs 3D reconstruction and planning based on CT images and a library of implants. It's not explicitly described as an AI/machine learning device that requires a large "training set" in the conventional sense for model building. The software development likely involved well-defined algorithms, rather than data-driven learning. If there was a machine learning component for, e.g., segmentation (though it states manual segmentation), training set details are not provided.

9. How the ground truth for the training set was established: Not applicable/Not specified, for the same reasons as point 8.

Ask a specific question about this device

Knee is a stereotaxic system including a dedicated intraoperative standalone software and surgical instruments. Knee " is intended for primary Total Knee Replacement, to assist the surgeon in determining reference alignment axes in relation to anatomical landmarks, in order to position the cutting guide regarding computed mechanical axis. The Knee includes smart glasses as a Head Mounted Device (HMD) for displaying information to the user intraoperatively. The smart glasses should not be relied upon solely and should always be used in conjunction with traditional methods.

The main purpose of Knee* is to assist the surgeon during the primary Total Knee Replacement (TKR) intervention. Knee* includes KneePlus software and reusable KneeTools instruments.

Knee* provides information to help locate and orientate the main femoral and tibial cutting planes as required in knee replacement surgery. Knee* allows the surgeon to adjust the cutting plane orientation and the resection level. This includes means for the surgeon to collect anatomical references during the TKR intervention using the KneeTools instruments. KneePlus software locates in a 3D reference frame the KneeTools instruments which include markers. All collected coordinates are treated by KneePlus algorithms to provide to the surgeon relevant orientation of the tracked cutting guide.

The KneePlus software is installed on a monocular near-eye HMD and provides the field of vision of the embedded HMD camera with additional information on an opaque 2D OLED screen. The surgeon uses this near-eye display in a very similar way he uses a traditional monitor such as the primary predicate device (Navitrack® System - OS Knee Universal, K110054): the surgeon can choose to look at the screen only when needed. The near-eye display is similar to what would be displayed on the screen of a tablet, smart phone or laptop positioned on a table next to the user.

The provided text is a 510(k) summary for the "Knee+" device. While it describes non-clinical performance data and mentions performance comparison studies, it does not contain a detailed study proving the device meets specific numerical acceptance criteria with a breakdown of sample sizes, ground truth establishment methods, or expert qualifications as requested.

Therefore, I cannot fully complete the requested table and answer all questions directly from the provided text. The document focuses on demonstrating substantial equivalence to a predicate device rather than a comprehensive, detailed clinical study report against pre-defined acceptance criteria.

However, I can extract the information that is present and highlight what is missing.

Missing Information

The provided document does NOT explicitly state:

• A table of specific numerical acceptance criteria.
• The reported device performance against numerical acceptance criteria.
• Details of the test set sample size, country of origin, or whether it was retrospective/prospective for the accuracy comparison.
• The number of experts or their qualifications used to establish ground truth.
• Adjudication methods for the test set.
• Whether an MRMC comparative effectiveness study was done, or the effect size of human readers improving with AI assistance.
• Whether a standalone (algorithm only) performance study was done.
• The actual "type of ground truth" used (beyond "simulated use (cadaveric specimens with orthopedic surgeon)", which implies surgical assessment rather than pathology or long-term outcomes).
• The sample size for the training set.
• How the ground truth for the training set was established.

Information Extracted from the Document

Here's a summary of the relevant information provided:

1. Acceptance Criteria and Reported Device Performance

The document states:

• "Bench testing was conducted in order to demonstrate that KneePlus software performs according to its requirements and specifications. In particular, overall system repeatability and accuracy were tested."
• "Performance comparison studies have been performed between Pixee Medical's device and the primary predicate device (Navitrack® System - OS Knee Universal) on test bench (sawbones) and simulated use (cadaveric specimens with orthopedic surgeon). The aim was to compare the accuracy of both systems and therefore assess the performance of Knee+."
• "Even though differences in technology can be noticed between the predicate device and Knee+, a comparison study between Knee+ and Navitrack® - OS Knee Universal (bench testing and cadaveric testing) confirmed that the subject device and its primary predicate have the same accuracy."

Crucially, numerical acceptance criteria for accuracy and repeatability are not provided, nor are the specific numerical results for Knee+ or the predicate device. The document only states that their accuracy was confirmed to be "the same."

2. Sample Sizes and Data Provenance

• Test Set Sample Size: Not explicitly stated. The studies involved "test bench (sawbones)" and "cadaveric specimens."
• Data Provenance: Implied to be lab-based (bench and cadaveric studies), likely in France (where Pixee Medical is located and indicated as "Besançon FRANCE"). Not specified as retrospective or prospective clinical data.

3. Number of Experts and Qualifications

• Experts: Not explicitly stated how many, but involved "orthopedic surgeon" for cadaveric studies. No specific number or years of experience mentioned.

4. Adjudication Method

• Adjudication Method: Not specified.

5. MRMC Comparative Effectiveness Study

• MRMC Study: Not mentioned or implied. The focus was on device accuracy comparison to a predicate, not human reader improvement with AI assistance.

6. Standalone Performance Study

• Standalone Performance: The non-clinical testing includes "Bench testing was conducted in order to demonstrate that KneePlus software performs according to its requirements and specifications. In particular, overall system repeatability and accuracy were tested." This implies a standalone technical performance assessment of the device/software itself, separate from human interaction, although the specific metrics and results are not provided. The cadaveric studies involved a surgeon, so that portion wasn't purely standalone.

7. Type of Ground Truth Used

• Ground Truth:
  • For bench testing: Implied to be based on precise physical measurements of known targets on sawbones.
  • For cadaveric testing: Based on the assessment made during "simulated use (cadaveric specimens with orthopedic surgeon)," which would rely on the surgeon's anatomical knowledge and surgical expertise/measurements. This isn't pathology or long-term clinical outcomes data.

8. Sample Size for the Training Set

• Training Set Sample Size: Not mentioned.

9. How Ground Truth for Training Set Was Established

• Training Set Ground Truth: Not mentioned. The document focuses on verification and validation of the device's performance, not the details of its developmental training data.

Ask a specific question about this device