Search Results

The MyHip Planner software is intended for image processing and preoperative planning of acetabular cup and femoral stem positioning for Total Hip Arthroplasty (THA). The user is assisted in producing a preoperative plan, making decisions based on the leg offsets, the patient's potential impingement and, optionally, the spino-pelvic interaction. Through the software, the user can request 3D Printed Patient Specific Bone Models not intended for dragnostic use, but only intended for a physical representation of the 3D anatomical models visualized in the software. The 3D Printed Patient Specific Bone Models are provided non-sterile.

The MyHip Planner is a software whose output is a patient-specific preoperative plan based on CT scans and aimed at evaluating the effects of different device choices and positioning options on the patient's hip joint biomechanics in terms of leg length and offset. It is intended to be used in Primary Hip Arthroplasty and it is compatible with Windows and Mac OS operating system. The subject Advanced version of the MyHip Planner additionally allows to evaluate patient's spinopelvic deformities and pelvic tilt starting from preoperative X-ray images, to help the surgeon to understand the implications of spinopelvic mobility on THA stability and optimize implant components orientation. Through the software, the user can request non-sterile 3D Printed Patient Specific Bone Models intended to be used as an additional visual reference of the patients' specific anatomy.

The Medacta International S.A. Advanced MyHip Planner (K221725) is a software intended for image processing and preoperative planning of acetabular cup and femoral stem positioning for Total Hip Arthroplasty (THA). The software assists users in producing a preoperative plan, making decisions based on leg offsets, potential impingement, and optionally, spino-pelvic interaction. It also allows users to request 3D Printed Patient Specific Bone Models (non-sterile, not for diagnostic use, but for physical representation of 3D anatomical models).

Here's an analysis of the acceptance criteria and study data provided:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly present a table of acceptance criteria for specific performance metrics (e.g., accuracy, precision) of the Advanced MyHip Planner software. However, it states that "Software verification and validation including segmentation validation" was conducted, and "[n]o statistical divergence between the algorithm and the manual segmentation has been revealed by an analysis of the automatic segmentation and landmark picking performance on a two-sided students t-distribution."

Based on this, an inferred table might look like this, with the understanding that specific numerical acceptance criteria (e.g., within X mm or degrees of ground truth) are not explicitly detailed:

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

The document does not explicitly state the sample size used for the test set. It mentions "an analysis of the automatic segmentation and landmark picking performance," but the number of cases or images included in this analysis is not provided.

The data provenance (e.g., country of origin, retrospective or prospective) for the test set is also not specified.

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

The document refers to "manual segmentation" as a comparison point for the algorithm's performance. However, it does not specify the number of experts who performed this manual segmentation or landmark picking, nor does it explicitly detail their qualifications (e.g., radiologist with X years of experience, orthopedic surgeon).

4. Adjudication Method for the Test Set

The document refers to a "two-sided students t-distribution" analysis to compare algorithm performance with manual segmentation. This implies a statistical comparison rather than a formal adjudication process involving multiple human readers to resolve discrepancies. Therefore, an explicit adjudication method like 2+1 or 3+1 is not mentioned. The "manual segmentation" serves as the reference, suggesting a single ground truth from a human expert or a pre-established "gold standard" of manual interaction.

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

The document explicitly states: "No clinical studies were conducted." Therefore, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study to evaluate human reader improvement with AI assistance was not performed.

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

The performance data section mentions "Software verification and validation including segmentation validation" and "an analysis of the automatic segmentation and landmark picking performance." This indicates that standalone performance evaluation (algorithm only) of the segmentation and landmark picking functionalities was performed. The comparison was against "manual segmentation" which serves as the independent reference for the algorithm's output.

7. The Type of Ground Truth Used

The ground truth for the verification and validation activities, specifically for segmentation and landmark picking, appears to be expert consensus through "manual segmentation" and "manual landmark picking." The document uses these manual methods as the reference against which the algorithm's performance was compared. There is no mention of pathology or outcomes data being used for ground truth for these specific performance evaluations.

8. The Sample Size for the Training Set

The document does not specify the sample size used for the training set for the Advanced MyHip Planner software.

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

The document does not describe how the ground truth for the training set was established. While it mentions comparison to manual segmentation for validation, it does not elaborate on the process or sources of ground truth used during the development and training phases of the algorithm.

Ask a specific question about this device

MyKnee® R Pin Positioners are intended for use as anatomical pin positioners specific for a single patient anatomy in case of revision total knee replacement. They are designed based on CT images of a patient's knee and the primary TKA implant in situ to assist in positioning the total knee replacement components intraoperatively and in guiding the marking of bone prior to cutting. MyKnee® R Pin Positioners are intended for single use only. Resections are performed through the standard or revision cutting guides. These are positioned on the holes drilled through the MyKnee® R Pin Positioner blocks after removal of the primary total knee implant components and according to the surgeon's preoperative planning. MyKnee® R Pin Positioners are intended for use with GMK® Primary, GMK® SpheriKA, GMK® Revision, GMK® Hinge and their cleared indications for use.

MyKnee R Pin Positioners are a line extension to the currently marketed MyKnee Cutting Blocks (K093806) and MyKnee PPS-Pin Positioners (K170106). The MyKnee R blocks are single use, patient-specific pin positioner blocks designed based on CT images of a patient's knee and the primary TKA implant in situ. They are intended to position the pins for placement of the standard instruments according to the surgeon's preoperative surgical planning. The MyKnee R Pin Positioners are manufactured from medical grade nylon for sintering which is identical to the predicate devices. They are available in left and right configuration with sizes 1-6 for the both the femurs and the tibia and, as the predicate devices, they can be provided in both non-sterile version.

The provided FDA 510(k) summary for Medacta International S.A.'s MyKnee R Pin Positioners does not describe the specific acceptance criteria and detailed study that proves the device meets those criteria in the way typically expected for an AI/CADe device.

The MyKnee R Pin Positioners are patient-specific surgical guides, not an AI or CADe device in the sense of image analysis or diagnostic assistance. The performance data section explicitly states "No clinical studies were conducted," and the non-clinical studies primarily focus on software validation and cadaver testing validating the intended use, functional characteristics, and features of the physical guides themselves.

Therefore, many of the requested items related to AI/CADe performance (e.g., AUC, sensitivity/specificity, MRMC studies, ground truth establishment for training and test sets, number of experts, adjudication methods) are not applicable to this submission.

However, based on the information provided, we can infer and present what is available, noting the limitations of this document regarding the specific questions.

Here's an attempt to address the request based on the provided document:

Device: MyKnee R Pin Positioners

Device Type: Patient-specific anatomical pin positioners (surgical guides) for revision total knee replacement. This is NOT an AI/CADe device for image analysis or diagnosis.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of quantitative acceptance criteria and corresponding reported device performance values in the context of accuracy metrics (e.g., for an AI algorithm's diagnostic performance). Instead, the "performance data" section focuses on validation activities for the physical device's functionality and intended use.

Note: The document states that "testing activities were conducted to written protocols" and that the "slight differences between the subject and predicate devices do not raise new questions of safety and effectiveness." This implies that the acceptance criteria for these functional aspects were met, but the specific numerical targets or results are not detailed in this public summary.

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

• Test Set Sample Size: Not explicitly stated. The "Cadaver testing" refers to testing the physical device's function. The number of cadavers or specific test cases is not provided.
• Data Provenance: The document does not specify the country of origin for any data related to the cadaver testing. It is implied that the software processes CT images, but the origin of these CT images (e.g., patient demographics, retrospective/prospective collection) is not detailed as this is not an image analysis AI device.

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

• Not Applicable in the AI/CADe sense. This submission is for a physical surgical guide. Ground truth for the geometric accuracy or fit of the guides would likely be established through engineering measurements and potentially surgeon feedback during cadaver trials, rather than expert consensus on image interpretation. The document does not specify the number or qualifications of any experts involved in the cadaver testing or validation of the guide's fit.

4. Adjudication Method for the Test Set

• Not Applicable. As there's no clinical imaging data interpretation or diagnostic task, there is no need for an adjudication method for establishing ground truth from image readers.

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

• No MRMC study was done. The document explicitly states "No clinical studies were conducted." The device is a surgical guide, not an AI assistance for human readers in diagnostic tasks.

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

• No standalone algorithm performance study (in the AI sense) was done. The "software validation" performed is likely related to the accuracy of the software in converting CT images into the physical design of the pin positioners and ensuring the correct output for manufacturing, not for diagnostic performance.

7. Type of Ground Truth Used

• For the cadaver testing, the ground truth would inherently be physical measurements and functional assessment of the pin positioners in situ, confirming that they achieve their intended purpose of guiding pin placement accurately according to preoperative plans. No diagnostic "ground truth" (e.g., pathology, outcomes data, or expert consensus on image findings) is mentioned or relevant to the device's function.

8. Sample Size for the Training Set

• Not Applicable. This is not an AI/ML model that requires a training set for learning. The device's design is based on established principles of patient-specific instrumentation derived from CT images, not on training a machine learning model.

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

• Not Applicable. Since there is no training set for an AI/ML model, this question is not relevant. The "ground truth" for the device's development lies in anatomical principles, engineering specifications, and the accuracy of the CT data used for individual patient planning.

Ask a specific question about this device

The NextAR™ TKA Platform is intended to be used to support the surgeon during total knee replacement procedures by providing information on bone resections, ligaments behavior, instrument and implant positioning.

The NextAR™ TKA Platform is intended to be used in combination with NextARTM stereotaxic instruments, the MyKnee® NextAR™ cutting guides, and general surgical instruments to implant the GMK Sphere Total knee system and perform ligament balancing. As an optional display, the smart glasses can be used auxiliary to the NextAR Platform to view the same 2D stereotaxic information as presented by the NextAR Platform.

The smart glasses should not be relied upon solely and should always be used in conjunction with the primary computer display.

The MyKnee® NextAR cutting guides include a camera/target holder and a PSI MyKnee® cutting guide both for tibia and femur. The MyKnee® cutting guides must be used as anatomical cutting blocks specific for a single patient anatomy, to assist in the positioning of total knee replacement components intraoperatively and in guiding the marking of bone before cutting. MyKnee® NextAR TKA cutting guides are for single use only.

The NextAR™ stereotaxic instruments are intended to be used to surgeon during specific orthopedic surgical procedures by providing information on bone resections, ligaments behavior, instrument and implant positioning. The NextAR™ stereotaxic instruments, when registered with the myKnee NextAR TKA cutting guides, provide reference to a patient's rigid anatomical structures, such as the femur and tibia, that can be identified relative to pre-operative CT based planning.

The NextAR™ TKA Platform is a CT based computer-assisted surgical navigation platform used in total knee replacement surgery and includes the following components:

• navigation software which displays information to the surgeon in real-time;
• Augmented Reality glasses;
• optical tracking system;
• PC based hardware platform;
• MyKnee NextAR Cutting Blocks; and
• reusable surgical instruments for total knee replacement procedures.

The system operates on the common principle of stereotaxic technology in which passive markers are mounted on the bones and an infrared camera is used to monitor the spatial location of the markers to avoid intraoperative registration of bony landmarks. Tracking sensors attached to the bones enable the surgeon to view the position and orientation of bones and instrumentation relative to preoperative data in real-time while performing the surgical procedure. The tracking sensors are provided sterile.

The NextAR™ TKA Platform aids the surgeon in executing the surgical plan by visualizing all the information in real time in a screen monitor. The placement of the implants is performed by cutting the bones using MyKnee® NextAR™ Cutting Blocks while reusable surgical instrumentation (provided non-sterile) guided by the tracking sensors can be used for recut. Although the position of the implants can be validated to assess the correct execution of the planning, the surgeon can change the surgical plan intraoperatively by analyzing the 3D models of the patient, the CT scan, and the 3D geometry of the implants.

The MyKnee® NextAR™ Cutting Blocks, manufactured from medical grade nylon, are single use patient-specific blocks which are designed from patient MRI or CT images. The blocks are designed to be used in standard medial or lateral parapatellar surgical approaches with each set comprised of a femoral block, a tibial block, and two bone models of the patient's femur and tibia (optional). The femoral cutting blocks are provided in right and left configurations in sizes 1 to 7 and 1+ to 6+ and the tibial cutting blocks are provided in right and left configurations in sizes 1 to 6. The blocks are provided sterile via gamma irradiation or non-sterile.

The FDA 510(k) summary for the NextAR™ TKA Platform (K193559) provides details on the device's acceptance criteria and the studies conducted to prove its performance.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics in a single, consolidated format. However, it mentions various types of testing and states that "Testing was conducted according to written protocols with acceptance criteria that were based on standards." The "Discussion" section also states, "Minor differences in the optical tracking systems and use of patient specific instrumentation are addressed by performance testing." This implies that the performance testing confirmed the device met established criteria for those specific aspects.

Based on the information provided, we can infer some of the areas where acceptance criteria would have been applied:

2. Sample Size for Test Set and Data Provenance

The document explicitly mentions a "cadaver study" as part of the performance data.

• Sample Size for the Test Set: Not explicitly stated in the provided text.
• Data Provenance: The cadaver study would involve human remains, but the exact country of origin or whether it was retrospective/prospective in the context of data collection for this specific study is not detailed. However, cadaver studies are inherently prospective for the purpose of testing the device.

3. Number of Experts and Qualifications for Ground Truth

The document does not explicitly mention the number of experts, their qualifications, or their role in establishing ground truth specifically for the reported studies (e.g., cadaver study). For a device like this, ground truth would likely be established through precise anatomical measurements or post-hoc imaging.

4. Adjudication Method for the Test Set

The document does not detail any adjudication method (e.g., 2+1, 3+1) for the test set. Adjudication methods are typically associated with human interpretation of medical images or data, which is not the primary focus for establishing the technical accuracy of a navigation system in a cadaver study.

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

No mention of an MRMC comparative effectiveness study, or the effect size of human readers improving with AI vs. without AI assistance, is made. This device is a surgical navigation platform, not an AI-assisted diagnostic tool that heavily relies on human reader interpretation of images. The smart glasses are described as an auxiliary display, not an AI-driven interpretive aid for human readers.

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

The performance testing, particularly the "performance testing to evaluate mechanical and optical properties" and elements of the "cadaver study," would inherently involve evaluating the standalone performance of the algorithm and system components. The software validates the navigation software's ability to display information to the surgeon accurately. The cadaver study would assess how accurately the system guides the surgeon, implying that the system's output (measurements, guidance) is evaluated independently of a human's ultimate judgment during the assessment phase of the study, though a human surgeon performs the actions based on the guidance.

7. Type of Ground Truth Used

For the specific performance testing of this surgical navigation platform, especially in the cadaver study, the ground truth would likely be established using precise direct physical measurements (e.g., with highly accurate measurement tools or CMMs) or potentially post-operative imaging with precise measurements of the cadaver bones to verify the accuracy of resections and implant positioning as guided by the system. The "pre-operative CT based planning" is used by the device, and the device ensures "reference to a patient's rigid anatomical structures... that can be identified relative to pre-operative CT based planning." Therefore, the ground truth would be tied back to the anatomical accuracy relative to these plans.

8. Sample Size for the Training Set

The document does not provide information about a specific "training set" sample size. This type of device relies on established biomechanical principles and image processing of CT scans for its planning and navigation, rather than a deep learning model that requires a discrete training set in the conventional sense. The software is validated, but not "trained" in an iterative machine learning fashion on a large dataset of patient outcomes.

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

As no specific training set for a machine learning model is mentioned, the method for establishing its ground truth is not applicable or detailed in this summary. The system's foundational data (e.g., anatomical models, instrument specifications) are established through engineering design, scientific principles, and preclinical testing.

Ask a specific question about this device

MySpine is intended as a thoracic and lumbar posterior pedicle targeting quide for patients requiring spinal fusion between the levels of T1 to L5.

MySpine Screw Placement Guides are intended to be used as anatomical perforating guides specific for a single patient anatomy to assist intraoperatively in the positioning of Pedicle screws in the vertebral body. MySpine is intended for use with M.U.S.T Pedicle Screw System and its cleared indications for use. Use of the quides involves surgical planning software used pre-operatively to plan the surgical placement of the components on the basis of patient radiological images with identifiable placement anatomical landmarks and surqiçal equipment components. These components include patient-specific guides fabricated on the basis of the surgical plan to precisely reference the placement of the implant components intra-operatively per the surgical plan.

MySpine Screw Placement Guides are intended for single use only.

The MySpine Pedicle Screw Placement Guides are patient specific surgical instruments that allow for guided pedicle screw placement of the M.U.S.T pedicle screws (K121115). The M.U.S.T pedicle screws are guided through the patient's anatomically matched MySpine Pedicle Screw Placement Guides in order to provide optimal positioning according to the surgeon's preoperative planning. The MySpine software platform allows the surgeon to complete the preoperative planning in 3D based on the patient's spinal CT scans.

The components of the MySpine Pedicle Screw Placement Guides include a Drill Guide (Polyamide PA 2200), Sleeves for Awls, Probes and Screw Drivers (Polyamide PA 2200). Sleeves for taps and drills (Wrought stainless steel AISI 630. ASTM F 899), and Vertebral Bone Models (Polyamide PA 2200). The MySpine Pedicle Screw Placement Guides are single use, external communicating devices with limited (

The provided document describes the MySpine Pedicle Screw Placement Guides, a patient-specific surgical instrument. It details performance testing and establishes substantial equivalence to a predicate device, but it does not include a typical AI/ML medical device study with acceptance criteria, sample sizes, and expert validation for an algorithm's performance.

Instead, the performance testing focuses on traditional medical device validation, such as biocompatibility, dimensional accuracy, mechanical testing, and process reproducibility. The document mentions "software tools used to manufacture the MySpine Pedicle Screw Placement Guides were validated for their intended use," but this refers to the software used for design and fabrication, not an AI algorithm performing diagnostic or predictive tasks.

Therefore, the requested information elements related to AI/ML device studies cannot be extracted from this 510(k) summary.

However, I can extract information regarding the general performance testing and a design validation cadaver study.

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

Ask a specific question about this device