Search Results

OptiVu™ ROSA® MxR is indicated for displaying surgical workflow images from the ROSA® RECON platform in Mixed Reality. It includes functions for viewing the same surgical workflow steps and 2D visualizations as presented on the existing ROSA RECON platform user interface. When accessing ROSA® MxR from a stereoscopic head mounted display (HMD), images viewed are for informational purposes only and are not intended for diagnostic use.

OptiVu™ ROSA® Mixed Reality (ROSA® MxR) is indicated for displaying surgical workflow images from the ROSA® RECON Platform and the corresponding ROSA® clinical applications intra-operatively during orthopedic surgeries. It is intended to provide an additional means of display where the ROSA® RECON Platform user interface is duplicated into a Mixed Reality see-through environment. OptiVu™ ROSA® MxR allows the ROSA® RECON Platform user interface and corresponding ROSA® clinical applications (ROSA Knee, ROSA Partial or ROSA Hip) to be streamed through a compatible head-mounted display (HMD) (e.g. HoloLens 2). The subject device's main purpose is to place the duplicated virtual ROSA® user interface at a convenient location to provide the following functionalities: ● Mixed Reality visualization solution Wireless connectivity between a HMD (e.g. HoloLens 2) . and the ROSA® RECON Platform Interaction with the duplicated user interface and ● RECON Platform (e.g. voice, eye gaze and hand gestures)

The provided text describes a 510(k) premarket notification for the OptiVu™ ROSA® MxR device. However, it does not contain the specific details required to complete your request, such as a table of acceptance criteria, reported device performance, sample sizes, expert qualifications, or details of standalone or MRMC studies.

The document states that a "subsequent performance and integration test was performed regarding the active command functions and is described in the Section 11- Design Control Activities Summary," but this section is not included in the provided text.

Therefore, I cannot provide the requested information about acceptance criteria, study details, and performance metrics as they are not present in the given document.

Image /page/0/picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the square are the words "U.S. FOOD & DRUG" in blue, with the word "ADMINISTRATION" below it.

Ask a specific question about this device

The Signature™ ONE System is indicated, based on patient-specific radiological images with identifiable placement anatomical landmarks, to assist in pre-operative planning and/or intra-operative guiding of surgical instruments for shoulder replacement surgical procedures on patients not precluded from being radiologically scanned.

The Signature™ ONE System is to be used with the glenoid components of the following shoulder implant systems in accordance with their indications and contraindications: Zimmer® Trabecular Metal™ Reverse Plus Shoulder, Comprehensive® Total Shoulder System, Comprehensive® Reverse Shoulder System, Comprehensive® Reverse Augmented Baseplates and Alliance™ Glenoid System.

The Signature™ ONE Guides and bone models are intended for single use only.

The Signature™ ONE System is developed to assist in preoperative planning of the glenoid component for Total Shoulder Arthroplasty (using the Signature™ ONE Planner) and to accurately transfer a pre-operative plan to orthopedic surgical procedures (using the Signature™ ONE Guides) if desired. Both anatomic and reverse (TSA and RSA respectively) approaches are supported.

The Signature ONE Guides and Bone Model are designed and manufactured of polyamide (nylon) using additive manufacturing (selective laser sintering), based on the approved/finalized pre-surgical plan and shipped prior to surgery. The guides and bone models are provide nonsterile and sterilized at the hospital. They are used intraoperatively to assist the surgeon in reproducing the plan. The Signature ONE System surgical technique remains close to the conventional shoulder arthroplasty to allow converting to standard surgical technique at any time if needed during the operation.

The Signature™ ONE System uses the Zimmer Biomet Drive Portal for the interaction with external users (i.e. imaging technician and the surgeon). The internal users (i.e. the Zimmer Biomet operators) use manufacturing software applications to prepare the patient cases for the surgeon.

Modifications have been made to include guides and bone models for the Alliance Glenoid System, to the planning application and user interface, and the inclusion of an additional glenosphere size for the Comprehensive Reverse Implant System within the Signature™ ONE planning software application. The overall planning process, manufacturing process, materials, sterilization methods, principal of operation, have not changed from previous predicates.

The provided text describes a 510(k) premarket notification for the Signature™ ONE System, a device used for pre-operative planning and intra-operative guiding in shoulder replacement surgery. However, the text does not contain the specific details required to answer all parts of your request regarding acceptance criteria and a study proving the device meets those criteria.

Specifically, the document lacks a table of acceptance criteria with reported device performance metrics, sample sizes for test and training sets, details about ground truth establishment (number/qualifications of experts, adjudication methods), and information about MRMC studies or standalone algorithm performance.

The document primarily focuses on explaining the device's indications for use, its substantial equivalence to predicate devices, and the general types of testing performed (engineering analysis, performance tests, system validation, and software verification/validation).

Here's what can be extracted and what is missing based on your prompt:

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

• Missing. The document states that "Performance Tests- Design verification tests were O documented to ensure the performance of the implemented features and verify related design inputs" but does not provide specific acceptance criteria or the measured performance outcomes.

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

• Missing sample size for the test set.
• Missing data provenance details. The document mentions "Cadaveric validation performed" but doesn't specify the number of cadavers or their origin. It also doesn't specify if other data used for software testing was retrospective or prospective, or its geographic origin.

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):

• Missing. The document does not describe how ground truth was established for any performance testing, nor does it mention the involvement of experts in defining a gold standard.

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

• Missing. No information on adjudication methods for establishing ground truth is provided.

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:

• Missing. The document does not mention any MRMC studies or comparative effectiveness studies involving human readers with and without AI assistance. The device is described as assisting in planning and guiding, implying human interaction, but no such study details are provided.

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

• Implicitly yes, partially, but no metrics are provided. The software verification and validation would involve algorithm-only testing to ensure its functionality. However, specific standalone performance metrics (e.g., accuracy of anatomical landmark identification by the algorithm alone) are not reported. The device's function is to "assist" which suggests a human-in-the-loop system.

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

• Not explicitly stated. For the "Cadaveric validation," the ground truth would likely be based on physical measurements or surgical outcomes on the cadavers, but this is not detailed. For software testing, the ground truth for image processing tasks would typically be pre-annotated data, but the source or method of annotation is not mentioned.

8. The sample size for the training set:

• Missing. The document does not provide any information about a training set since it focuses on verification and validation of a cleared device, not the development or training phase of an AI model per se. While the device has "planning application" and "user interface" modifications, and "overall workflow remains unchanged from the predicate devices," it isn't explicitly stated that a "training set" in the machine learning sense was used for this particular submission.

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

• Missing. As no training set information is provided, no details on how its ground truth was established are present.

In summary, the provided document is a regulatory approval letter and a summary of the 510(k) submission, confirming substantial equivalence. It outlines the device's purpose and general testing activities but does not delve into the detailed performance study methodology, acceptance criteria, and specific results you've requested for an AI/ML device. This level of detail is often found in the full 510(k) submission or associated study reports, which are typically not included in the public-facing FDA clearance letter.

Ask a specific question about this device

The Signature™ ONE System is indicated, based on patient-specific radiological images with identifiable placement anatomical landmarks, to assist in pre-operative planning and/or intra-operative guiding of surgical instruments for shoulder replacement surgical procedures on patients not precluded from being radiologically scanned.

The Signature™ ONE System is to be used with the glenoid components of the following shoulder implant systems in accordance with their indications and contraindications: Zimmer® Trabecular Metal™ Reverse Plus Shoulder, Comprehensive® Total Shoulder System, Comprehensive® Reverse Shoulder System, Comprehensive® Reverse Augmented Baseplates and Alliance™ Glenoid System.

The Signature™ ONE Guides and bone models are intended for single use only.

The Signature™ ONE System is developed to assist in preoperative planning of the glenoid component for Total Shoulder Arthroplasty (using the Signature™M ONE Planner) and to accurately transfer a pre-operative plan to orthopedic surgical procedures (using the Signature™ ONE Guides) if desired. Both anatomic and reverse (TSA and RSA respectively) approaches are supported.

The Signature ONE Guides and Bone Model are designed and manufactured of polyamide (nylon) using additive manufacturing (selective laser sintering), based on the approved/finalized pre-surgical plan and shipped prior to surgery. The guides and bone models are provide nonsterile and sterilized at the hospital. They are used intraoperatively to assist the surgeon in reproducing the plan. The Signature ONE System surgical technique remains close to the conventional shoulder arthroplasty to allow converting to standard surgical technique at any time if needed during the operation.

The Signature™ ONE System uses the Zimmer Biomet Drive Portal for the interaction with external users (i.e. imaging technician and the surgeon). The internal users (i.e. the Zimmer Biomet operators) use manufacturing software applications to prepare the patient cases for the surgeon.

Modifications have been made to Planning application to include Alliance™ Glenoid implant system as a Pure Planning option (i.e. no Guides and Bone Models). In addition, modifications have been made to the user interface of the overall planning application. The planning process, manufacturing process, materials, sterilization methods, principal of operation, have not changed from previous predicates.

This FDA 510(k) premarket notification for the Signature™ ONE System does not contain the specific acceptance criteria, detailed study results, and statistical information typically required to fully answer your request regarding device performance and its proof. This document primarily focuses on demonstrating substantial equivalence to predicate devices, rather than presenting a standalone study proving the device meets predefined clinical acceptance criteria.

However, based on the provided text, here's what can be extracted and inferred:

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

The document does not explicitly state quantitative acceptance criteria (e.g., accuracy thresholds, precision ranges) or corresponding reported device performance metrics in a table format for clinical efficacy. The "Device Performance Testing" section mentions "Engineering Analysis" to "ensure the performance of the implemented features and verify related design inputs" but does not provide details on what these performance metrics were or their targets.

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 any sample size for a test set for clinical performance evaluation. It mentions "patient-specific radiological images" are used for planning, but no details about a dedicated test set of patients or images for validation are provided. Therefore, data provenance (country of origin, retrospective/prospective) is also not available here.

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 provided. The application is for a planning and guiding system, where the ground truth regarding surgical accuracy would typically be established by comparing the planned outcome to the actual intraoperative or post-operative outcome, often involving expert surgeons. However, no such study details are present.

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

This information is not provided as there is no described test set of clinical images or cases requiring ground truth adjudication.

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

There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study. The device is a planning and guiding system, not an AI diagnostic tool where human reader performance would typically be enhanced.

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

The document describes the Signature™ ONE System as assisting in "pre-operative planning and/or intra-operative guiding of surgical instruments." This inherently implies a human-in-the-loop system (the surgeon). The "planning application" is a software component, but its performance is not described in a standalone, algorithm-only context of clinical efficacy in this document. The "Software Verification and Validation Testing" addresses the software's compliance with regulations like IEC 62304 and its concern level ("moderate"), implying testing of its functionality and reliability, but not its clinical performance as a standalone entity in terms of accuracy against ground truth.

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

This information is not provided. For a surgical planning and guidance system, ground truth would ideally come from direct measurements of surgical accuracy and alignment post-procedure, or potentially surrogate measures confirmed by expert assessment.

8. The sample size for the training set

This information is not provided. While the system uses "patient-specific radiological images" for planning, the document does not discuss a "training set" in the context of an AI/ML model where a large dataset is used to train an algorithm. The system appears to be based on computational algorithms for planning rather than a deep learning model trained on a vast image dataset.

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

This information is not provided as there is no discussed training set.

Summary of what is present:

• Software Verification and Validation Testing: This was conducted to satisfy FDA guidance and IEC 62304 for medical device software. The software is classified as "moderate" level of concern.
• Engineering Analysis: Performed to ensure performance of implemented features and verify design inputs.
• Usability Engineering: Addressed user interactions.

In conclusion, this 510(k) notification focuses on the substantial equivalence of the Signature™ ONE System to previously cleared predicate devices, asserting that its modifications (like adding Alliance™ Glenoid system compatibility) do not raise new questions of safety and effectiveness. It provides a general overview of verification and validation activities (software, engineering, usability) but lacks the detailed performance study results and specific acceptance criteria that you requested for a comprehensive understanding of the device's proven clinical effectiveness.

Ask a specific question about this device

The iASSIST Knee System is a computer assisted stereotaxic surgical instrument system to assist the surgeon in the positioning of orthopedic implant system components intra-operatively. It involves surgical instruments and position sensors to determine alignment axes in relation to anatomical landmarks and to precisely position alignments and implant components relative to these axes. Example orthopedic surgical procedures include but are not limited to: Total Knee Arthroplasty.

As in the predicates, the iASSIST Knee System consists of Pods (tracking sensors), a computer system, software, and surgical instruments designed to assist the surgeon in the placement of Total Knee Replacement components. The Pods combined with the surgical instruments provide positional information to help orient and locate the main femoral and tibial cutting planes as required in knee replacement surgery. This includes means for the surgeon to determine and thereafter track each of the bones' alignment axes relative to which the cutting planes are set. The computer system and software components control and sequence the functions of the Pods per the applicable knee surgery steps via wireless communication.

The provided text describes the iASSIST Knee System, a computer-assisted stereotaxic surgical instrument system. While it outlines the system's purpose, design, and general testing, it does not include acceptance criteria or detailed results of a study demonstrating the device meets specific performance criteria.

Therefore, I cannot provide a table of acceptance criteria and reported device performance from the given text.

However, I can extract the information that is present regarding the studies and ground truth:

General Information on Performance Data:

• Device Performance Testing:

  • Physical/Performance Tests: Conducted to ensure performance of implemented features and verify related design inputs.
  • Engineering Analysis: Conducted to ensure performance of implemented features and verify related design inputs.
  • Usability Engineering: Addressed user interactions with the iASSIST Knee System.
  • Validation Lab: Performed to validate that using the iASSIST Knee System is safe and effective and that its performances are acceptable under full simulated use on cadaveric specimens.

• Software Verification and Validation Testing:

  • Conducted to satisfy requirements of the FDA Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices and IEC 62304.
  • The software is considered a "moderate" level of concern.
  • Testing demonstrates that the iASSIST Knee System does not raise any new issues of safety and effectiveness compared to predicate devices.

Specific Study Details (based on the provided text's limitations):

1. Table of Acceptance Criteria and Reported Device Performance: Not provided in the text.
2. Sample Size used for the test set and data provenance:
   • Test Set Sample Size: "cadaveric specimens" were used in the Validation Lab. The exact number is not specified.
   • Data Provenance: The Validation Lab study involved "full simulated use on cadaveric specimens." No country of origin is specified for the cadavers or data. It appears to be a prospective simulation study.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not specified in the text.
4. Adjudication method for the test set: Not specified in the 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 text. The device is a surgical instrument system, not an imaging interpretation AI.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The text mentions "computer assisted stereotaxic surgical instrument system to assist the surgeon". The validation lab involved "full simulated use on cadaveric specimens," implying human interaction is part of its intended use and testing. A "standalone" performance without human input is not described.
7. The type of ground truth used:
   • For the "Validation Lab" testing, the ground truth would likely refer to the actual anatomical alignments or target positions in the cadaveric specimens, which would then be compared against the system's measurements and guidance. However, the exact method for establishing this ground truth is not detailed (e.g., whether it relied on pre-defined anatomical markers, precise physical measurements independent of the device, or other methods).
8. The sample size for the training set: Not applicable and not mentioned. This device is a surgical navigation system, not a typical machine learning algorithm that requires a separate training set in the conventional sense. The software is verified and validated, but does not appear to be "trained" on a dataset in the way an AI diagnostic tool would be.
9. How the ground truth for the training set was established: Not applicable (see point 8).

In summary, the provided document focuses on the regulatory submission, equivalence to predicate devices, and general categories of testing performed. It lacks the specific quantitative performance metrics, acceptance criteria, and detailed study methodologies typically required to fill out the requested table for an AI/device performance study.

Ask a specific question about this device

The Signature™ ONE System is indicated, based on patient-specific radiological images with identifiable placement anatomical landmarks, to assist in pre-operative planning and/or intra-operative guiding of surgical instruments for shoulder replacement surgical procedures on patients not precluded from being radiologically scanned.

The Signature™ ONE System is to be used with the glenoid components of the following shoulder implant systems in accordance with their indications: Zimmer® Trabecular Metal™ Reverse Plus Shoulder, Comprehensive® Total Shoulder System, Comprehensive® Reverse Shoulder System and Comprehensive® Reverse Augmented Baseplates.

The Signature™ ONE Guides and bone models are intended for single use only.

The Signature™ ONE System is developed to assist in pre-operative planning of the glenoid component for Total Shoulder Arthroplasty (using the Signature™ ONE Planner) and to accurately transfer a pre-operative plan to orthopedic surgical procedures (using the Signature™ ONE Guides) if desired. Both anatomic and reverse (TSA and RSA respectively) approaches are supported.

The Signature ONE Guides and Bone Model are designed and manufactured of polyamide (nylon) using additive manufacturing (selective laser sintering), based on the approved/finalized pre-surgical plan and shipped prior to surgery. The guides and bone models are provide nonsterile and sterilized at the hospital. They are used intraoperatively to assist the surgeon in reproducing the plan. The Signature ONE System surgical technique remains close to the conventional shoulder arthroplasty to allow converting to standard surgical technique at any time if needed during the operation.

The Signature™ ONE System uses the Zimmer Biomet Drive Portal for the interaction with external users (i.e. imaging technician and the surgeon). The internal users (i.e. the Zimmer Biomet operators) use manufacturing software applications to prepare the patient cases for the surgeon.

The provided text describes the 510(k) premarket notification for the Signature™ ONE System, a device intended to assist in pre-operative planning and intra-operative guiding for shoulder replacement surgery. However, the document does not contain specific acceptance criteria, detailed study results proving device performance against those criteria, or information regarding AI/algorithm performance metrics.

It primarily focuses on demonstrating substantial equivalence to predicate devices based on intended use, technological characteristics, and principles of operation, rather than providing a detailed performance study with quantitative acceptance criteria and results.

Therefore, many of the requested details cannot be extracted from this document.

Here's an attempt to answer the questions based only on the provided text, indicating where information is not available:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: Not specified in the provided text.
• Data Provenance: Not specified, although testing on "cadaveric specimens" is mentioned. The country of origin of the data is not provided. It is presented as nonclinical performance data, and the general nature of such testing typically implies prospective testing on the device model.

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.

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

• MRMC Study: Not mentioned.
• Effect Size of Human Readers with AI vs. without AI assistance: Not applicable, as no MRMC study or AI performance improvement claims are detailed. The device is described as assisting in pre-operative planning and intra-operative guiding, not as an AI for reading or interpreting medical images in the context of improving human reader performance.

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

• The document implies a "human-in-the-loop" system where the surgeon reviews, modifies, and approves the plan. It states the system "assist[s] in pre-operative planning and/or intra-operative guiding" and surgeons "interact with to review, modify and approve the plan."
• No standalone algorithm-only performance is detailed.

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

The term "ground truth" is not explicitly used. However, the validation lab performed studies "under full simulated use on cadaveric specimens," implying that the performance was assessed against known anatomical structures and surgical targets within those specimens, likely guided by expert surgical opinion and established anatomical references for accuracy.

8. The sample size for the training set

Not applicable. The document describes a medical device for surgical planning and guidance, not an AI/machine learning algorithm with a distinct "training set."

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

Not applicable. See #8.

Ask a specific question about this device

The ROSA® Knee System is indicated as a stereotaxic instrumentation system for total knee replacement (TKA) surgery. It is to assist the surgeon in providing software-defined spatial boundaries for orientation to identifiable anatomical structures for the accurate placement of knee implant components.

The robotic arm placement is performed relative to anatomical landmarks as recorded using the system intraoperatively, and based on a surgical plan, optionally determined pre-operatively using compatible X-ray or MRI based surgical planning tools.

It includes a robotic arm, an optical sensor navigation system and accessories, software system, surgical instruments and accessories.

The targeted population has the same characteristics as the population that is suitable for the implants compatible with the ROSA® Knee System. The ROSA® Knee System is to be used with the following fixed bearing knee replacement systems in accordance with their indications and contraindications:

NexGen® CR, NexGen CR-Flex, NexGen CR-Flex Gender, NexGen LPS, NexGen LPS-Flex, NexGen LPS-Flex Gender, Persona® CR, Persona PS, Vanguard® CR, and Vanguard PS.

The ROSA® Knee System is used to assist surgeons in performing Total Knee Arthroplasty (TKA) with features to assist with the bone resections as well as assessing the state of the soft tissues to facilitate implant positioning intra-operatively. The ROSA® Knee System uses a Medical Device Data System (MDDS) called the Zimmer Biomet Drive Portal which manages the creation and tracking of surgical cases. The cases reside on the portal until it is uploaded to the ROSA® Knee System before surgeries.

If the case is image-based, a 3D virtual bone model is generated pre-operatively by the PSI systems (X-PSI Knee System or CAS PSI Knee System) to create a model of the patient's femur/tibia and allows for the preparation of a pre-operative surgical plan as well as visualization of planned cuts. The pre-operative plan is then matched to the landmarks taken intra-operatively on the patient's bony anatomy. An imageless option is also available where landmarks taken intra-operatively on the patient's bony anatomy are used to create the surgical plan directly in the surgery. Accuracy of resections, knee state evaluation, and soft tissue assessment are the same between image-based and imageless options as they are always based on intra-operative landmarks.

The intra-operative workflow and surgical concepts implemented in the system remain close to the conventional TKA workflow. As such, at the time of the surgery , the system mainly assists the surgeon in (1) determining reference alignment axes in relation to anatomical landmarks, (2) planning the orthopedic implants location based on these reference alignment axes and orthopedic implant geometry (planning optionally based on a pre-operative plan using pre-operative imaging),, and (3) precisely positioning the cut guide relative to the planned orthopedic implant location by using a robotic arm.

It includes a robotic arm, an optical sensor navigation system and accessories, software system, surgical instruments and accessories.

The provided text describes a 510(k) premarket notification for the ROSA® Knee System, a stereotaxic instrumentation system for total knee replacement (TKA) surgery. However, the document primarily focuses on demonstrating substantial equivalence to predicate devices and does NOT contain information regarding:

• Specific acceptance criteria with numerical targets.
• A "study" that directly proves the device meets these acceptance criteria in the format requested (e.g., performance metrics against specific targets). The document mentions "Verification and Validation Testing" and "Software Verification and Validation Testing" but does not detail the results against quantifiable acceptance criteria for device performance.
• Sample size for test sets or data provenance.
• Number of experts or their qualifications for ground truth establishment.
• Adjudication method.
• Multi-Reader Multi-Case (MRMC) comparative effectiveness study.
• Standalone (algorithm-only) performance.
• Type of ground truth used.
• Sample size for the training set.
• How ground truth for the training set was established.

The document does mention:

• Biocompatibility testing: "The biocompatibility evaluation for ROSA Knee was conducted in accordance with ISO 10993. The evaluation reveals that the ROSA Knee device meets biocompatibility requirements." This implies an acceptance criterion of "meets biocompatibility requirements" and a study showing compliance with ISO 10993.
• Electrical Safety and Electromagnetic Compatibility (EMC): "The device complies with recognized electrical safety standards: IEC 60601-1 standard for electrical safety and IEC 60601-1-2 standard for electromagnetic compatibility." This implies an acceptance criterion of "compliance with IEC 60601-1 and IEC 60601-1-2" and a study demonstrating this compliance.
• Device Performance Testing: Mentions "Physical/Performance Tests," "Engineering Analysis," and "Validation Lab" on cadaveric specimens to "validate that using the ROSA Knee is safe and effective and that the performances of the ROSA Knee are acceptable." However, specific acceptance criteria and detailed performance results are not provided.
• Software Verification and Validation Testing: States that testing was conducted to satisfy FDA guidance and IEC 62304 for "major" level of concern software. It concludes that "The testing demonstrates that the ROSA Knee does not raise any new issues of safety and effectiveness as compared to the predicate device(s)." This implies acceptance criteria related to software safety and effectiveness, and the V&V testing serving as the study.

Conclusion:

Based on the provided text, it is not possible to fully complete the requested table and descriptions because the document, being a 510(k) summary, focuses on substantial equivalence and general statements of compliance rather than detailed performance study results against specific, quantifiable acceptance criteria.

Information that can be extracted and inferred:

1. Table of Acceptance Criteria and Reported Device Performance

The remaining sections cannot be answered with the given text.

The document is a 510(k) summary, which generally provides a high-level overview of testing and conclusions for substantial equivalence rather than granular details of specific study designs, methodologies, and raw results for performance criteria.

Ask a specific question about this device

The X-PSI Knee System is indicated as an orthopedic instrument system to assist in the positioning of knee replacement components. It involves surgical planning software used pre-operatively to plan the surgical placement of the components on the basis of provided patient radiological images and 3-D reconstructed bones with identifiable placement anatomical landmarks, and surgical instrument components that include patient specific or customized guides fabricated on the basis of the surgical plan to precisely reference the placement of the implant components intra-operatively per the surgical plan. The X-PSI Knee system is indicated for patients without severe bone deformities, such as a HKA greater than 15° or deformities due to prior fracture of the distal femur or proximal tibia.

The X-PSI Knee System is to be used with the following fixed bearing knee replacement systems in accordance with their indications and contraindications: NexGen® CR, NexGen CR-Flex Gender, NexGen LPS, NexGen LPS-Flex, NexGen LPS-Flex Gender, Persona® CR, Persona PS, Vanguard® CR and Vanguard PS.

The patient specific guide components are intended for single-use only.

The present Zimmer Biomet® X-PSI Knee System is an instrumentation system that includes customized surgical guides to mate each patient's bony and articular surface topographies to reference the location and orientation of the implant system's instruments which in turns sets the position and alignment of the femoral and tibial implant components.

It involves the following:

• A CAS X-PSI Knee Software Suite used in preparation for the surgery to sequentially construct 3-D surface models of each patient's knee joint bony structures and articular surfaces from the patient's X-Ray images, plan the location and orientation of the knee replacement implant components upon the patient's model, and create the corresponding specification models for the patient specific surgical guides (PSI Guides) with surfaces and elements to uniquely fit each patient topographical features and set or reference the placement of the implant system components per the plan,
• . The Zimmer Biomet ® X-PSI Guides (also called jigs) that are manufactured per the above models and plan, for intra-operative and single use, which include one to set the placement of the distal femoral cut guides which set the resection depth, the varus/valgus and the flexion of the distal cut and one to set the placement of the tibial cut guides which set the resection depth, the varus/valgus, and the posterior slope of the proximal cut.
• . Each patient's Zimmer Biomet ®3-D Bone Models (femur and tibia components) that are fabricated and provided along with the PSI Guides for use intra-operatively to provide the surgeon with an intra-operative visual reference of the planned location of the PSI Guides in order to help guide their locations on the patient's actual joint,
• Zimmer Biomet X-PSI Reusable Surgical Instrumentations are provided both sterile . and non-sterile and are reusable for intra-operative use, which include femoral stylus, and femoral and tibial cut block instrumentations to allow setting the resection level and performing the bone cuts as defined by the PSI Guides.
• Fixation Pins are accessories for use of the guides, these accessories are Class I devices under the classification "Orthopedic manual surgical instrument (21 CFR § 888.4540)".

The Zimmer Biomet® X-PSI Knee System is compatible for use with the following class II Zimmer Biomet Nexgen, Persona and Vanguard total knee replacement implant systems:

• . NexGen®family: NexGen CR, NexGen CR-Flex, NexGen CR-Flex Gender, NexGen LPS, NexGen LPS-Flex, NexGen LPS-Flex Gender
• . Persona® family: Persona CR, Persona PS
• Vanguard® family: Vanguard CR, Vanguard PS

Finally, the following accessories are used for the acquisition of the x-ray images:

• X-Ray Marker 3D Zimmer Biomet ® X-PSI (re-usable) ●
• X-Ray Calibration Straps, Short and Long (single-use)

The provided document is a 510(k) premarket notification for the Zimmer Biomet X-PSI Knee System. It details the device, its indications for use, and a summary of performance data used to establish substantial equivalence to predicate devices.

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

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

The document states that a non-significant risk clinical study was performed to evaluate the proper positioning of the Zimmer Biomet X-PSI Knee guides. The primary metric measured was the resulting frontal Hip-Knee-Ankle (HKA) alignment angle versus the surgically planned HKA alignment angle.

Note: The document states "satisfactory performance" but does not provide specific numerical thresholds or a statistical comparison for the HKA alignment angle, which would typically be included in detailed acceptance criteria. It also mentions "substantial equivalence in cut accuracy with regards to femoral and tibial frontal and sagittal angles, as well as femoral rotation and resection depth" based on full system validation tests, but no specific acceptance criteria for these were detailed.

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 explicitly state the sample size for the clinical study (test set) or the data provenance (country of origin, retrospective/prospective). It only refers to it as a "Non-Significant Risk Clinical Study."

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)

The document does not provide details on the number of experts or their qualifications for establishing the ground truth in the clinical study.

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

The document does not describe any adjudication method used for the clinical study's 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

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study or any assessment of human reader improvement with AI assistance. The device is an orthopedic instrument system that assists in surgical planning and guiding, not a diagnostic AI tool that human readers would interpret.

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

The document describes "Software System Tests" which were performed to "ensure that no hazardous anomalies were present in the system software components" and "consisted of testing software features and functionalities in correspondence to software design requirements." This implies a standalone evaluation of the software's functional performance, but not in terms of diagnostic accuracy or clinical outcomes in isolation. The "Full System Validation Tests" using cadaver specimens and bone models involved "multiple surgeons," indicating a human-in-the-loop component for these tests, rather than purely standalone algorithm performance on clinical metrics.

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

For the clinical study, the ground truth was implied by surgically planned HKA alignment angle against which the "resulting frontal Hip-Knee-Ankle (HKA) alignment angle" was compared. This implies the surgical plan served as the reference for evaluating positioning accuracy. For the "Full System Validation Tests," the ground truth for "cut accuracy" (femoral/tibial angles, rotation, resection depth) would typically be established by precise measurements from the bone models or cadaver specimens, likely compared against the planned surgical cuts.

8. The sample size for the training set

The document does not specify a sample size for the training set for the software or any AI/ML components. It mentions that the software "sequentially construct[s] 3-D surface models of each patient's knee joint bony structures and articular surfaces from the patient's X-Ray images," but it doesn't detail how this software was trained or validated in terms of data volume.

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

The document does not provide information on how the ground truth for any potential training set was established.

Ask a specific question about this device