Search Results

The ANTHEM® Fracture System is indicated for fixation of fractures, osteotomies, arthrodesis and reconstruction of bones for the appropriate size of the device to be used in adult patients, including the clavicle, scapula, humerus, radius, ulna, small bones (metacarpals, metatarsals, phalanges), wrist, pelvis, femur, tibia, fibula, ankle, and foot. The clavicle hook plate may be used for dislocations of the acromioclavicular joint. Distal femur, distal humerus, proximal ulna, and proximal radius plates are indicated for diaphyseal, metaphyseal, epiphyseal, supracondylar, intra-articular, extra-articular, condylar, periprosthetic, and comminuted fractures, and for non-unions and malunions. Mini fragment plates are also indicated for fixation of fractures of the acetabulum, patella, and bone fragments, replantation, malunions and nonunion, and for non-load bearing stabilization and reduction of long bone fragments. Metaphyseal plates are indicated for non-load bearing stabilization and reduction of long bone fragments, and for fixation of bones including the radius and ulna.

In addition to adult patients, small fragment, mini fragment, proximal tibia, clavicle, metaphyseal, distal humerus, proximal ulna, proximal radius, and distal fibula plates are indicated for use in infant, child, and adolescent pediatric subgroups and small stature adults. Distal femur plates are indicated for use in the diaphyseal and metaphyseal areas of long bones in adolescent pediatric patients. Distal radius, distal tibia, metaphyseal, and mini fragment plates are indicated for use in adolescents (12-21 years of age). Plating can be used in patients with osteopenic bone.

The ANTHEM® Fracture System is a family of plates, screws, and washers designed to be used for internal bone fixation. The implants are available in various sizes and shapes, and may be contoured or straight, with various lengths to accommodate patient anatomy. The subject ANTHEM® plates are manufactured from titanium alloy per ASTM F136 or stainless steel as specified in ASTM F138 and F139. Plates are also available additively manufactured from titanium alloy powder per ASTM F3001.

I am sorry, but based on the provided FDA clearance letter for the ANTHEM® Fracture System, I cannot extract the information you requested regarding acceptance criteria and the study that proves the device meets those criteria, specifically concerning human-in-the-loop performance, ground truth establishment, or training set details.

This document is a 510(k) clearance letter for a physical medical device (bone fixation system) and focuses on demonstrating substantial equivalence to predicate devices, primarily through engineering analysis and mechanical testing of the physical components. It does not appear to involve any AI/software component that would require the kind of performance study details you are asking for (e.g., sample size for test/training sets, expert adjudication, MRMC studies, standalone algorithm performance, or different types of ground truth like pathology or outcomes data).

Therefore, I cannot populate the table or answer the specific questions about AI/software performance studies. The "Performance Data" section solely refers to mechanical testing according to ASTM F382 and biocompatibility, which are standard for physical implants.

Ask a specific question about this device

ExcelsiusXR™, when used in conjunction with ExcelsiusHub™ and/or ExcelsiusGPS®, is intended for use as an aid for precisely locating anatomical structures to be used by surgeons for navigating and/or guiding compatible surgical instruments in open or percutaneous procedures provided that the required fiducial markers and rigid patient anatomy can be identified on CT scans or fluoroscopy. This system is indicated for the placement of spinal and orthopedic (Sacroiliac, Ulna, and Tibia) bone screws, and interbody fusion devices.

The ExcelsiusXR™ Headset displays 2D stereotactic images and 3D virtual anatomy images, and displays the virtual instrument location in relation to the virtual anatomy to assist in percutaneous visualization and trajectory planning. This headset should not be relied upon solely for absolute positional information and should always be used in conjunction with the primary stereotactic display.

ExcelsiusXR™ is a head-mounted navigation device, or headset, that is used in conjunction with ExcelsiusHub, and ExcelsiusGPS if robotic guidance is desired, as an aid for precisely locating anatomical structures in open or percutaneous procedures, and for precisely positioning compatible surgical instruments or implants (screws and interbody devices) during surgery. ExcelsiusXR™ includes hardware and software that enables real-time surgical visualization using radiological patient images (preoperative CT, intraoperative CT, and fluoroscopy), provides tracking and planning capabilities for a series of compatible instruments, and contains hand tracking cameras for manipulation of the head-mounted display by the user. The Headset displays 2D stereotactic images and provides a 3D visual, or virtual image, of the patient anatomy in the lower region. The 2D data and 3D model, along with tracking information, are projected to the surgeon's retina from the transparent near-eye-display Headset, allowing the surgeon to look at the patient and the navigation data at the same time.

The provided FDA 510(k) Clearance Letter for ExcelsiusXR™ describes performance testing in a general manner but does not contain the specific details required to fully address all parts of your request for acceptance criteria and the study that proves the device meets them.

Here's a breakdown of what can be extracted and what information is missing based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a specific table with numerical acceptance criteria and corresponding performance metrics. It generally states that "Verification and validation testing were conducted on ExcelsiusXR™ to confirm that the device meets performance requirements under the indications for use and to ensure safety and efficacy of the system."

It mentions the types of tests performed:

• Non-clinical system, software, and instrument verification and validation – demonstrated compliance with user needs and corresponding design inputs
• Surgical simulations conducted on phantom models
• Qualitative and quantitative validation to confirm intended use and accuracy
• Optical bench testing to evaluate the image quality characteristics of the head mounted display
• Electrical Safety and Electromagnetic Compatibility (compliance with standards)
• Software Verification and Validation Testing (compliance with FDA guidance)

Without specific numeric thresholds or results, a detailed table cannot be created. However, generally, for a navigation system like this, key performance metrics and their associated acceptance criteria would typically include:

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

• Sample Size: The document does not specify the sample size used for any of the performance tests (e.g., number of phantom models, number of tests, number of unique cases).
• Data Provenance: The document does not specify the country of origin of the data or whether the data was retrospective or prospective. Phantom studies are typically prospective tests under controlled lab conditions.

3. Number of Experts and Qualifications for Ground Truth

• The document does not mention the number of experts used to establish ground truth or their specific qualifications (e.g., "Radiologist with 10 years of experience").
• Given that "surgical simulations conducted on phantom models" were performed, the "ground truth" would likely be established by the physical measurements taken from the phantom and the known ideal trajectory/placement, often assessed by engineers and potentially verified by clinically experienced personnel.

4. Adjudication Method for the Test Set

• The document does not mention any specific adjudication method (e.g., 2+1, 3+1) for establishing ground truth or evaluating performance. This is generally more relevant for studies involving human interpretation of medical images. For phantom studies, ground truth is typically precisely measured rather than adjudicated in the same way.

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

• The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study.
• There is no information provided on the effect size of how much human readers improve with AI vs. without AI assistance. This type of study would typically be done if the device were primarily an AI-driven diagnostic or interpretative tool, which this navigation system is not. Its primary function is to aid surgical guidance.

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

• The document describes the device as "an aid for precisely locating anatomical structures to be used by surgeons for navigating and/or guiding compatible surgical instruments." It also states "This headset should not be relied upon solely for absolute positional information and should always be used in conjunction with the primary stereotactic display."
• This strongly indicates that the device is intended for human-in-the-loop use, assisting the surgeon.
• While there are "software verification and validation testing" and "surgical simulations on phantom models," these would assess the algorithm's performance within the system context, but the document does not present a standalone, algorithm-only performance metric separate from its intended use as a surgeon's aid. The emphasis is on the system's performance when used by surgeons.

7. Type of Ground Truth Used

• Based on "surgical simulations conducted on phantom models" and "qualitative and quantitative validation," the ground truth was likely established through physical measurements and known anatomical references on the phantom models. This is a form of objective, fabricated ground truth suitable for evaluating a navigation system's precision and accuracy in a controlled environment. It is not expert consensus, pathology, or outcomes data in the traditional sense, though expert surgical opinion would guide the design and interpretation of phantom studies.

8. The Sample Size for the Training Set

• The document does not provide any information regarding the training set size. The FDA 510(k) summary focuses on the "performance testing" (verification and validation), which relates to the test set that demonstrates the device's capabilities post-development. Information about model training (if applicable for any AI components involved in image processing or tracking) is typically not included in such summaries unless it's a primary AI/ML device where the training data directly impacts the cleared function.

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

• Since no information about a training set is provided, there is no information on how its ground truth was established.

In summary, the 510(k) summary provides a high-level overview of the types of performance tests conducted (phantom models, software V&V, electrical safety), but it lacks the detailed quantitative data, sample sizes, and specific methodologies for ground truth establishment that would be found in a full study report. This level of detail is typically contained in the more comprehensive "Basis for Substantial Equivalence" documentation submitted to the FDA, which is not fully replicated in the public 510(k) summary letter.

Ask a specific question about this device

The ONVOY Acetabular System is intended for use in reconstruction of the articulating surface of the acetabular portion of the hip that is severely disabled and/or very painful resulting from:

1. Non-inflammatory degenerative joint disease including osteoarthritis, traumatic arthritis, and avascular necrosis.
2. Rheumatoid arthritis.
3. Correction of functional deformity.
4. Treatment of non-union, femoral neck fracture, and trochanteric fractures of the proximal femur with head involvement, unmanageable using other techniques.
5. Revision of previously failed total hip arthroplasty.
6. Dislocation risks.

The ONVOY Acetabular System is used in conjunction with Globus/StelKast Hip Systems. The acetabular components of this hip system are intended for cementless fixation.

The ONVOY™ additional implants consist of acetabular shells, liners, and dual mobility liners and bearings that are used as part of a complete total hip system in conjunction with a femoral head and femoral stem in total hip arthroplasty. New femoral head sizes are also being introduced. Implants are available in various configurations and sizes to fit a wide variety of patient anatomy. Shells are available in a cluster-hole design, liners are available in hooded, non-hooded, and lateralized designs used in conjunction with ONVOY shells. Dual mobility polyethylene bearings are used with dual mobility liners.

ONVOY™ acetabular shells are additively manufactured from titanium alloy powder per ASTM F3001. Acetabular liners and dual mobility bearings are manufactured from highly crosslinked ultra-high molecular weight polyethylene (UHMWPE) with Vitamin E. Dual mobility liners are manufactured from Cobalt Chrome (CoCr) alloy and femoral heads are manufactured from alumina matrix composite ceramic.

This document is an FDA 510(k) clearance letter for a medical device called the "ONVOY™ Acetabular System." It details the device's purpose, indications for use, and the basis for its substantial equivalence to other legally marketed devices.

However, it does not contain information about acceptance criteria and a study proving a device meets those criteria for an AI/Software as a Medical Device (SaMD).

This clearance is for an orthopedic implant (hip prosthesis components: acetabular shells, liners, dual mobility implants, and femoral heads), not a software device or an AI application. Therefore, the questions related to MRMC studies, ground truth establishment, training sets, and expert adjudication are not applicable to the content provided in this FDA 510(k) letter.

The "Performance Data" section solely refers to mechanical and material testing standards relevant to orthopedic implants (fatigue, wear, range of motion, material composition, etc.) and states that "Performance data demonstrate substantial equivalence to the predicate devices." It does not describe any clinical study involving human readers or AI performance metrics.

In summary, based on the provided text, I cannot describe acceptance criteria and a study that proves a device meets those criteria, as the document pertains to an orthopedic implant and not an AI/SaMD.

Ask a specific question about this device

Pulse Navigation is intended as an intraoperative image-guided localization system in either open or minimally invasive spinal surgical procedures. Instruments and implants tracked by a passive marker sensor system are virtually displayed on a patient's 3D radiographic image data. The system enables computer-assisted navigation for spinal surgical procedures in which the use of stereotactic surgery may be appropriate and where a reference to a rigid anatomical structure can be identified relative to the acquired image of the anatomy.

This may include the following spinal implant procedures:

• Pedicle Screw Placement (cervical, thoracic, lumbar)
• Iliosacral screw placement

The subject device, Pulse ICT Adapter is introducing compatibility based on the design of existing fria patient reference hardware, the Spinous Process Clamp (Pulse System K210574) and Globus Medical 1CT Fixture (ExcelsiusGPS K171651 and K 191100). The subject device, Pulse ICT Adapter was designed to offer surgeons more flexibility during the registration process of Pulse Navigation by providing an additional patient reference hardware design option by attaching Globus Medical Intra-Op CT Fixture to the following: existing Articulating Arm and Bedrail Clamp. Despite the changes introduced to predicate Spinous Process Clamp (K210574), the subject device is substantially equivalent to the predicate as demonstration and validation testing performed using well established and previously cleared test methods.

The Pulse System is a medical device consisting of Pulse LessRay, and Pulse Navigation. The Pulse System hardware includes a control unit, as well as accompanying accessory components.

The Pulse NVM5 is a medical device that is intraoperative neurological monitoring and status assessment during spinal surgery. The device provides information directly to the surgeon, to help assess a patient's neurological status. The Pulse NVMS provides this information by electrically stimulating nerves via electrodes located on surgical accessories and monitoring electromyography (EMG), motor evoked potential (MEP) or somatosensory evoked potential (SSEP) responses of the muscle groups innervated by the nerves. Moreover, a Twitch Test ("Train of Four") function is utility of the nerve to respond, or contract, following four stimulation pulses to determine the presence of neuromuscular block.

Additionally, the Pulse NVM5 System includes a software function that measures spinal parameters and acquires the location of spinal implants (screws, hooks) to assist the surgeon in bendini). Lastry, the Pulse NVMS provides Remote Access in two pathways, Local Wireless Control and Remote Monitoring.

Pulse LessRay is a software application which can be interfaced to a fluoroscope with a video cable. The images produced by the fluoroscope are transmitted to a frame grabber in the computer running LessRay where the images are enhanced and then displayed. When used in connection with the low dose and/or pulse setting on the fluoroscope, the user can improve the quality (clarity, contrast, noise level, and usability) of a noisy (low-quality) image. Using this system, much of the graininess of low radiation dose images can be eliminated. This allows for greater utility of low dose imaging. LessRay provides the additional feature of being able to interface LessRay with a tracking system in order to aid the C-arm technician in positioning the fluoroscope between the various views of the patient necessary for the intervention. LessRay with Tracking ensures that the fluoroscope is centered over the correct anatomy prior to taking any additional x-ray images.

Pulse Navigation is a stereotactic surgical as an aid for precisely locating anatomical structures in either open or percutaneous procedures. It is intended for intraoperative image-guided localization which allows for surgical instruments to be tracked in three-dimensional space. The device provides real-time information directly to the surgeon to evaluate the instrument depth and trajectory for computer-assisted navigation during spine surgery. Instruments are tracked in threedimensional space with an Infrared (IR) Camera, being virtually displayed and superimposed on registered radiographic images. Radiographic images are in the form of 3D intraoperative scan (CT or Cone Beam CT).

The reason for the submission is to introduce a new intra-operative CT (ICT) adapter for use with the ExcelsiusGPS ICT Registation Fixture for the Pulse Navigation application.

The provided documentation (K243814) describes the NuVasive Pulse System (specifically, the Pulse ICT Adapter), a stereotaxic instrument for image-guided spinal surgery. The submission focuses on introducing a new intra-operative CT (ICT) adapter for use with the ExcelsiusGPS ICT Registration Fixture for the Pulse Navigation application.

The document does not provide a comprehensive study proving the device meets specific acceptance criteria in the format requested (e.g., performance metrics like sensitivity, specificity, or accuracy compared to a ground truth established by experts). Instead, it focuses on demonstrating substantial equivalence to predicate devices through verification testing.

However, based on the information provided, we can infer some aspects related to acceptance criteria and the testing performed.

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

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

The document does not present a table of specific quantitative acceptance criteria or detailed performance results in the usual sense (e.g., sensitivity, specificity, accuracy for a diagnostic AI). Rather, it states that "the subject Pulse System meets product and software for the system and satisfies the same acceptance criteria as the predicate device."

The performance testing mentioned is primarily focused on verification and validation to ensure compliance with design specifications and user needs, particularly regarding tracking accuracy and usability.

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 a "sample size" for a test set in terms of patient data or images (as would be common for AI/ML diagnostic devices). The testing described is non-clinical verification and validation. This would typically involve physical testing on phantoms or test setups rather than patient data.

• Sample Size: Not specified in terms of patient cases. The testing would be on a sufficient number of test samples/setups to prove the specific engineering requirements and standards.
• Data Provenance: Not applicable as it's non-clinical testing. The tests are performed in a laboratory/engineering environment.
• Retrospective/Prospective: Not applicable.

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 document describes a surgical navigation system, not a diagnostic AI that interprets images. Therefore, the concept of "experts establishing ground truth for a test set" in the radiological interpretation sense does not apply directly.

The "ground truth" for a surgical navigation system's accuracy would be established through precise metrological measurements using phantoms or physical setups, not expert human agreement on medical images.

For usability testing (IEC 62366), "users" (e.g., simulated surgeons or clinical personnel) would interact with the device, and their feedback/performance would be assessed, but this is different from establishing a diagnostic ground truth.

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

Not applicable, as this is not a study requiring expert adjudication of medical images.

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 such MRMC study is described in this document. The device is a surgical navigation system, not an AI for image interpretation or a tool to assist human readers in diagnosis.

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

This also doesn't directly apply. The "algorithm" (Pulse Navigation) is inherently human-in-the-loop: it assists the surgeon. The "standalone" performance would be its tracking accuracy and computational correctness, which are assessed through the non-clinical verification as per ASTM F2554-10. The document states this testing was done to ensure the system meets its specifications.

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

For the aspects of the device discussed (tracking accuracy, usability), the "ground truth" would be established by:

• Metrological standards: For tracking accuracy (e.g., using precise measurement tools and phantoms as per ASTM F2554-10). The true position would be known and deviations measured.
• Engineering specifications and user requirements: For general system functionality and safety.
• Usability engineering principles: For usability testing, where adherence to principles defined in standards like IEC 62366 is verified.

8. The sample size for the training set

This document does not describe an AI/ML device that undergoes a "training phase" on a dataset in the sense of deep learning or machine learning. The device is a hardware/software system that uses pre-defined algorithms for navigation and tracking. Therefore, there is no "training set" in the context of data-driven model learning.

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

Not applicable as there is no "training set" in the AI/ML sense. The system's algorithms are developed based on established engineering principles and physics.

Ask a specific question about this device

ExcelsiusGPS® is intended for use as an aid for precisely locating anatomical structures and for the spatial positioning and orientation of an instrument holder or guide to be used by surgeons for navigating and/or guiding compatible surgical instruments in open or percutaneous provided that the required fiducial markers and rigid patient anatomy can be identified on CT scans or fluoroscopy. The system is indicated for the placement of spinal and orthopedic bone screws.

ExcelsiusHub™ is intended for use as an aid for precisely locating anatomical structures to be used by surgeons for navigating compatible surgical instruments in open or percutaneous procedures provided that the required fiducial markers and rigid patient anatomy can be identified on CT scans or fluoroscopy. The system is indicated for the placement of spinal and orthopedic bone screws.

Subject ExcelsiusGPS® instruments consist of array sleeve adapters and surgical instruments, including drivers, drills, taps, and probes, that may be used manually or navigated with the use of ExcelsiusGPS® or ExcelsiusHub™. The surgical instruments are used to prepare the implant site or implant the device. Instruments are non-sterile and reusable.

The provided document is a 510(k) premarket notification for the ExcelsiusGPS® Instruments, specifically for additional instruments to be used with the existing ExcelsiusGPS® or ExcelsiusHub™ systems for navigating and/or guiding compatible surgical instruments for the placement of spinal and orthopedic bone screws.

There is no mention of an AI/ML component in this document. The device is a set of surgical instruments (array sleeve adapters, drivers, drills, taps, probes) that can be used manually or navigated with the existing ExcelsiusGPS® or ExcelsiusHub™ systems. Therefore, the questions related to AI/ML device performance, such as acceptance criteria for AI algorithms, test set sample sizes, expert ground truth, MRMC studies, or standalone algorithm performance, are not applicable to this submission.

The "Performance Testing" section describes verification tests including "instrument integration and comparison to the predicate devices" to confirm the instruments meet performance requirements. However, specific acceptance criteria and the results of these tests are not detailed in this summary. Biocompatibility was also confirmed by using materials consistent with predicate devices.

Therefore, I cannot provide the requested information regarding AI/ML acceptance criteria and study details because the document does not indicate that the ExcelsiusGPS® Instruments or its associated systems utilize AI/ML technology subject to such evaluation.

Ask a specific question about this device

The ACTIFY™ Unicondylar Knee System is indicated for unicompartmental knee replacement due to the following conditions:

1. Moderately disabling joint disease of the knee resulting from painful osteo- and/or post-traumatic arthritis, or avascular necrosis.
2. Revision of previous unsuccessful unicompartmental knee replacement or other procedure.
3. Alternative to tibial osteotomy in patients with unicompartmental osteoarthritis.
4. Previous tibial condyle or plateau fractures with loss of anatomy or function.
5. Varus or valgus deformities.
   These devices are indicated for cemented use only.

The ACTIFY™ Unicondylar Knee System implants consist of femoral and tibial implants that are used as part of a unicompartmental knee system for partial knee arthroplasty. Implants are available in various configurations and sizes to fit a wide variety of patient anatomy. ACTIFY Unicondylar femoral implants are manufactured from cobalt chrome alloy, tibial inserts are manufactured from ultra high molecular weight polyethylene (UHMWPE) with and without Vitamin E, and tibia trays are manufactured from titanium alloy.

I am sorry, but the provided text is a 510(k) premarket notification for a medical device (ACTIFY™ Unicondylar Knee System) and does not contain information about acceptance criteria, device performance, sample size, ground truth establishment, or expert qualifications for a study proving the device meets acceptance criteria.

The document discusses:

• The FDA's decision of substantial equivalence to predicate devices.
• The indications for use of the device.
• The materials and components of the device.
• A list of performance tests conducted (fatigue, wear, interlocking strength, etc.) according to various ASTM and ISO standards.
• A general statement that "Performance data demonstrate substantial equivalence to the predicate devices."

It does not provide:

1. A table of acceptance criteria and reported device performance.
2. Sample sizes or data provenance for any clinical or large-scale performance study.
3. Information on experts, adjudication methods, or ground truth for a test set.
4. Details on MRMC studies or AI assistance.
5. Information about standalone algorithm performance.
6. Sample sizes or ground truth establishment for a training set.

Therefore, I cannot fulfill your request based on the provided text.

Ask a specific question about this device

The COSINE™ Spacer is an interbody fusion device intended for use at one or more levels of the thoracic spine (T1-T12), thoracolumbar junction (T12-L1), or lumbosacral spine (L1-S1) as an adjunct to fusion in patients with the following indications: degenerative disc disease (DDD), disc herniation (with myelopathy and/or radiculopathy), spondylolisthesis, deformity (degenerative scoliosis or kyphosis), spinal stenosis, and failed previous fusion (pseudarthrosis). DDD is defined as discogenic back pain with degeneration of the disc confirmed by history and radiographic studies. These patients should be skeletally mature and have had at least six (6) months of non-operative treatment.

The COSINE™ Spacer is to be filled with autograft and/or allogenic bone graft comprised of cancellous and/or corticocancellous bone or a bone void filler as cleared by the FDA for use in intervertebral body fusion to facilitate fusion.

This device is intended to be used with supplemental fixation systems that have been cleared for use in the thoracolumbosacral spine (e.g., posterior pedicle screw and rod systems, anterior plate systems, and anterior screw and rod systems). Hyperlordotic interbody devices (≥20° lordosis) must be used with at least anterior supplemental fixation.

COSINE™ Spacers are expandable lateral lumbar interbody fusion devices used to provide structural stability in skeletally mature individuals following discectomy. The devices are available in various heights and geometric options to fit the anatomical needs of a wide variety of patients.

COSINE™ Spacers are manufactured from titanium alloy per ASTM F136 or ASTM F1295. The endplates are additively manufactured from titanium powder, as specified in ASTM F3001, and an internal component is manufactured from radiolucent PEEK polymer.

This document pertains to the 510(k) premarket notification for the COSINE™ Spacer, an intervertebral body fusion device. Regulatory information for the device is provided in the document. However, the provided text does not contain any information regarding acceptance criteria or a study that proves the device meets those criteria.

The document states that:

• Mechanical testing (static and dynamic compression and compression-shear, and subsidence) was conducted in accordance with "Guidance for Industry and FDA Staff, Class II Special Controls Guidance Document: Intervertebral Fusion Device," ASTM F2077, and ASTM F2267 to demonstrate substantial equivalence to the predicate devices.
• The subject implants have the same technological characteristics as the predicate devices, including design, intended use, material composition, and range of sizes.
• The subject interbody devices have been found substantially equivalent to the predicate devices with respect to technical characteristics, performance, and intended use.

To answer your request, the following information is missing from the provided text:

1. A table of acceptance criteria and the reported device performance: The document mentions mechanical testing was performed in accordance with standards, but it does not list specific acceptance criteria (e.g., minimum compression strength, subsidence limits) or the actual performance values achieved by the COSINE™ Spacer.
2. Sample size used for the test set and the data provenance: This information is not provided.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This is irrelevant as the "ground truth" for mechanical testing is typically defined by engineering standards, not expert interpretation.
4. Adjudication method for the test set: Not applicable for mechanical testing.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: This is not applicable as the device is a physical implant, not an AI or imaging system requiring human reader interaction.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable.
7. The type of ground truth used: For mechanical testing, the "ground truth" would be the engineering specifications and performance limits defined by the referenced ASTM standards and FDA guidance. Specific quantitative values are not given.
8. The sample size for the training set: Not applicable as this is a physical device, not an AI model requiring a training set.
9. How the ground truth for the training set was established: Not applicable.

In summary, the provided FDA communication confirms the clearance of the COSINE™ Spacer based on its substantial equivalence to predicate devices through mechanical testing. However, it does not detail the specific acceptance criteria, test results, or methodology (beyond mentioning adherence to standards) that would allow for a complete answer to your request.

Ask a specific question about this device

ACTIFY™ Total Knee System and ACTIFY™ 3D Total Knee System are indicated for single use only in skeletally mature individuals undergoing reconstruction of severely disabled and/or very painful joints.

ACTIFY™ Total Knee System and ACTIFY™ 3D Total Knee System are indicated for total knee replacement due to osteoarthritis, osteonecrosis, rheumatoid arthritis, and/or post-traumatic degenerative problems, and revision of failed previous reconstructions where sufficient bone stock and soft tissue integrity are present.

ACTIFY™ Total Knee System is indicated for cemented use only, except for the porous femoral component which is indicated for both cemented and uncemented use.

ACTIFY™ 3D Total Knee System is indicated for cemented and uncemented use.

The ACTIFY™ 3D Total Knee System and ACTIFY™ Total Knee System implants consist of modular femoral, tibial, and patellar implants that are used as part of a complete knee system in total knee arthroplasty. Implants are available in various configurations and sizes to fit a wide variety of patient anatomy. Femoral components and tibial inserts are available in posterior-stabilized (PS) and cruciate-retaining (CR) designs.

Femurs are manufactured from cobalt chromium alloy (CoCr) with a CoCr coating. Tibial inserts and patella implants are manufactured from ultrahigh molecular weight polyethylene (UHMWPE) with and without Vitamin E. ACTIFY™ 3D Total Knee tibia trays and the patella metal base are additively manufactured from titanium alloy powder per ASTM F3001. ACTIFY™ Total Knee tibia trays are manufactured from titanium alloy per ASTM F136.

The provided document describes the K240669 submission for the ACTIFY™ 3D Total Knee System and ACTIFY™ Total Knee System. This submission focuses on orthopedic implants, specifically knee joint prostheses, not AI/ML-driven medical devices. Therefore, the questions related to AI/ML acceptance criteria, study design for AI models, ground truth establishment, sample sizes for training/test sets, expert adjudication methods, and MRMC studies are not applicable to this 510(k) summary.

The performance data section mentions mechanical testing conducted in accordance with several ASTM standards and a guidance document. These tests are standard for evaluating the mechanical integrity and performance of orthopedic implants and ensure their substantial equivalence to predicate devices, particularly regarding issues such as fatigue, shear, and tensile strength. However, specific acceptance criteria values and reported device performance from these mechanical tests are not explicitly detailed in the provided text.

The document states:

• Performance Data: Mechanical testing (tray fatigue, A-P shear, shear, and tensile) was conducted in accordance with the "Knee Joint Patellofemorotibial and Femorotibial Metal/Polymer Porous-Coated Uncemented Prostheses - Class II Special Controls Guidance Document for Industry and FDA Staff," January 16, 2003, ASTM F2083, ASTM F1800, ASTM F1044, ASTM F1147, and ASTM F1672. Performance data demonstrate substantial equivalence to the predicate devices. Bacterial endotoxin testing (BET) was conducted in accordance with ANSI/AAMI ST-72:2011.

This indicates that the device's performance was evaluated against the requirements outlined in these standards and guidance documents, and the results supported a finding of substantial equivalence. Without access to the full submission, the specific numerical acceptance criteria and the device's performance against those criteria cannot be provided.

Ask a specific question about this device

ExcelsiusFlex™ when used in conjunction with ExcelsiusHub™ is intended for use as an aid for precisely locating anatomical structures and for spatial positioning and orientation of a tool holder to be used by surgeons for navigating and/or guiding compatible surgical instruments provided that the required fiducial markers and rigid patient anatomy can be identified on CT scans or directly acquired anatomical structures. The system is indicated to assist the surgeon in planning the position of the implant components and preparing the bony anatomy during orthopedic procedures.

The Total Knee Arthroplasty (TKA) implant systems compatible with ExcelsiusFlex™ are GENflex2® and ACTIFY™ Total Knee System.

The ExcelsiusHub™ is intended for use as an aid for precisely locating anatomical structures to be used by surgeons for navigating compatible surgical instruments in open or percutaneous procedures provided that the required fiducial markers and rigid patient anatomy can be identified on CT scans, fluoroscopy or directly acquired anatomical structures. The system is indicated for the planning of orthopedic devices and placement of spinal and orthopedic bone screws and interbody fusion devices.

The ExcelsiusFlex™ is a robotic positioning system with a computer controlled robotic arm, hardware and software that works in conjunction with ExcelsiusHub™ , to enable real time surgical navigation and robotic guidance using patient tracking arrays and a positioning camera. The system assists the surgeon in implant placement planning and intraoperative tracking of patient anatomy by locating anatomical structures and stereotaxic positioning of surgical instruments relative to patient CT images or directly acquired anatomical structures. The navigation and quidance system determines the registration or mapping between the virtual patient (points on the patient images) and the physical patient (corresponding points on the patient's anatomy), or directly acquired anatomical structures. Once this reqistration is created, the software positions the robotic arm on a planned resection plane.

The ExcelsiusFlex™ is intended for stereotaxic surqery in surgical knee procedures to assist the surgeon in spatial positioning and orientation of a sagittal sawblade, planning the position of the femoral and tibial implants, and for bone preparation during total knee arthroplasty (TKA) procedures. The system constrains the position of the robotic arm to planned resection planes based on the pre-operative or intra-operative plans developed using ExcelsiusFlex™-TKA software on either the ExcelsiusHub™ or a planning laptop.

ExcelsiusFlex™ instruments consist of patient tracking instruments, patient attachment instruments, navigation instruments, end effectors and end effector instruments. Patient attachment instruments provides a point of rigid fixation for the patient tracking instruments. Patient tracking instruments and navigated instruments incorporate unique array patterns with reflective markers, and are used to track patient anatomy and surgical instruments. End effectors attach to the distal end of the robotic arm and provide a rigid connection to the saw blade.

The provided text discusses the ExcelsiusFlex™ medical device and its clearance by the FDA. However, it does not contain specific acceptance criteria or details of a study that directly proves the device meets those criteria, such as a clinical performance study with specific quantitative metrics.

Instead, the document focuses on:

• Regulatory Clearance (510(k) Summary): It states that the device is "substantially equivalent" to predicate devices based on technological characteristics, performance, and intended use.
• Verification and Validation Testing: It lists the types of testing performed (non-clinical, surgical simulations, cadaveric quantitative/qualitative validation, electrical safety, EMC, software V&V) but does not provide the results or specific acceptance criteria met by these tests.
• Safety and Standards Compliance: It mentions compliance with various IEC standards related to electrical safety, EMC, usability, and software lifecycle.

Therefore, many of the requested details cannot be extracted directly from the provided text. Based on the information available, here's what can be provided:

Acceptance Criteria and Device Performance

The document does not explicitly state quantitative acceptance criteria or corresponding reported device performance metrics in a readily extractable table format for clinical efficacy. The discussion of "substantial equivalence" implies that performance is comparable to predicate devices but no specific quantitative thresholds are provided.

Table of Acceptance Criteria and Reported Device Performance:

Study Details (Based on provided text)

Since no full clinical study details with quantitative results are provided, many of these sections will indicate "Not provided in the text."

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

   • Test Set Sample Size: "Surgical simulations conducted on bone models" and "Cadaveric quantitative validation under clinically relevant scenarios" are mentioned. However, the specific number of bone models or cadavers used is not provided.
   • Data Provenance: Not explicitly stated for the testing mentioned, but cadaveric studies typically involve human cadaveric specimens. The origin (e.g., country) is not provided. The mention of "pre-operative images" and "pre-op CT-based patient registration" for the device's operation implies that patient data is processed, but details for actual test sets are scarce. It's unclear if the testing was retrospective or prospective.

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

   • Number of Experts: Not provided.
   • Qualifications of Experts: Not provided.

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

   • Adjudication Method: Not provided.

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:

   • The document describes a robotic positioning system and navigation aid, not an AI interpretation device for human "readers." Therefore, a traditional MRMC study comparing human readers with and without AI assistance is not applicable to this device in the context of the provided text. The device "assists the surgeon" but the nature of this assistance isn't described as AI-based interpretation for a human reader.

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

   • The device is a "robotic positioning system" and "surgical navigation and robotic guidance" system. It is explicitly stated as "intended for use as an aid for precisely locating anatomical structures and for spatial positioning and orientation of a tool holder to be used by surgeons," and "to assist the surgeon." This strongly implies a human-in-the-loop system. While components might operate autonomously (e.g., the robotic arm positioning itself), the overall performance as described is not a standalone, algorithm-only performance without human-in-the-loop.

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

   • For "surgical simulations conducted on bone models" and "cadaveric quantitative validation," the ground truth would likely be established through highly precise measurement devices (e.g., metrology, optical trackers, CMMs) or anatomical landmarks verified by anatomical experts. However, the specific type of ground truth (e.g., expert consensus for image segmentation, direct physical measurement, etc.) is not explicitly detailed for each test.

7. The sample size for the training set:

   • The document describes verification and validation testing for performance and regulatory clearance. It does not explicitly mention a "training set" in the context of machine learning or AI model development testing. Therefore, relevant sample size for a training set is not provided.

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

   • As no "training set" for an AI model is explicitly mentioned, the method for establishing its ground truth is not provided.

Ask a specific question about this device

The TENSOR® Suture Button System is intended to be used as an adjunct in fracture repair involving metaphyseal and periarticular small bone fragments where screws are not indicated, and as an adjunct in external and intramedullary fixation systems involving plates and rods, with fracture braces and casting.

Specifically, the TENSOR® implants are intended to provide fixation during the healing process for the following indications:

Syndesmotic trauma, such as ankle syndesmosis fixation (syndesmosis disruptions), and as an adjunct in connection with trauma hardware for Weber B and C ankle fractures; fixation of dorsal distal radioulnar ligament (DRUL) disruptions; Acromioclavicular separations due to coracoclavicular ligament disruptions; Tarsometatarsal (TMT) injury, such as fixation of foot soft tissue separations due to a Lisfranc injury (Midfoot Reconstruction); Hallux Valgus reconstruction (correction) by providing for the reduction of 1st metatarsal intermetatarsal angle; and, Carpal Metacarpal (CMC) joint arthroplasty as an adjunct in the healing process.

The TENSOR® Suture Button System consists of metal buttons, a polymer suture, an optional washer, and instruments. The buttons are available in various sizes to accommodate varying patient anatomy and surgical needs. The buttons and washer are manufactured from titanium alloy or stainless steel, and the suture is manufactured from ultra high molecular weight polyethylene (UHMWPE) and polyethylene terephthalate (PET). The implants are sterile packaged with various instruments to aid in insertion.

The provided text is a 510(k) Premarket Notification from the FDA for a medical device called the TENSOR® Suture Button System. It outlines the device's classification, indications for use, and the basis for its substantial equivalence to previously cleared predicate devices.

However, the document does not contain any information about a study proving the device meets acceptance criteria related to AI/Machine Learning performance. The "Performance Data" section specifically mentions "Mechanical testing (static and dynamic tension)" and "Bacterial endotoxin testing (BET)," which are standard tests for evaluating the mechanical properties and biocompatibility of implantable devices. There is no mention of clinical trials, AI/ML algorithm development, or human-in-the-loop performance studies.

Therefore, I cannot fulfill the request to describe the acceptance criteria and the study that proves the device meets those criteria in the context of AI/ML performance, as the provided document does not pertain to an AI/ML device.

To directly answer your questions based only on the provided text, a significant portion of the requested information is absent because the device is a mechanical implant, not an AI/ML-driven diagnostic or assistive system.

Here's what can be extracted and what cannot:

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

• Acceptance Criteria Mentioned (Implicit/Explicit):
  • Mechanical Performance: Static and dynamic tension (implied to meet relevant standards for load-bearing and fatigue).
  • Biocompatibility/Sterility: Bacterial endotoxin testing (BET) in accordance with ANSI/AAMI ST72:2011 (acceptance criteria would be below a certain endotoxin limit).
  • Substantial Equivalence: To predicate devices in terms of design, intended use, material composition, and range of sizes, and that differences "do not raise any different questions of safety or effectiveness."
• Reported Device Performance:
  • "Performance data demonstrates substantial equivalence to the predicate devices." (This is a summary statement, specific numerical results are not provided).

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

• Not applicable/Not provided. The testing mentioned (mechanical, endotoxin) uses material samples, not a "test set" in the sense of patient data for AI.

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

• Not applicable/Not provided. Ground truth, in the context of the requested AI/ML study, is not relevant for this device.

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

• Not applicable/Not 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

• No, not applicable/Not provided. This is a mechanical implant, not an AI-assisted diagnostic tool.

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

• No, not applicable/Not provided.

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

• Not applicable. For mechanical testing, the "ground truth" would be engineering specifications and validated test methods.

8. The sample size for the training set

• Not applicable/Not provided. No AI/ML training set is mentioned.

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

• Not applicable.

In summary: The provided document is a regulatory clearance for a traditional medical implant, not an AI/ML device. Therefore, the requested information pertaining to AI/ML development, testing, and clinical validation is not present.

Ask a specific question about this device