(267 days)
The MyShoulder Planner software is a medical device intended for use by surgeons as a preoperative planning tool for total shoulder replacement surgery in skeletally mature individuals. The MyShoulder Planner software is specifically designed to support the planning of the humeral and glenoid components in a total shoulder replacement using Medacta Shoulder System prosthesis. The MyShoulder Planner software should not be used for diagnostic purposes. The MyShoulder Planner software processes CT scan images in DICOM format to allow surgeons to visualize, measure, and reconstruct anatomic data. These features enable surgeons to make decisions on implant size and positioning, including the ability to annotate anatomical structures. The MyShoulder Planner software leads to the generation of patient-specific planning reports, which summarize the preliminary decisions regarding implant size and positioning. The MyShoulder Planner software allows the surgeons to request the MyShoulder patient matched guides according to the pre-surgical plan.
The MyShoulder Planner is a software designed to create patient-specific preoperative plans based on CT scans. It is used to visualize the effect of different devices and positioning options on the patient's shoulder joint biomechanics. It allows the surgeon to preoperatively plan the humeral and glenoid components in total shoulder replacement after the segmentation of a 3D model of the patient's anatomy that can be performed automatically by the software, which uses machine learning algorithms, or manually by a designated Medacta engineer.
The MyShoulder Planner (5.3SSWPL) is a pre-operative planning tool for total shoulder replacement surgery. Its acceptance criteria and performance are based on non-clinical studies, specifically software verification and validation, including segmentation validation. No clinical studies were conducted for this device.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document does not explicitly present a table of acceptance criteria with numerical targets and reported performance. Instead, it generally states that "Automatic segmentation and landmark acquisition performance was adequately verified in comparison to manual segmentation." This implies the acceptance criterion was "adequate verification" or "demonstration of equivalence" between automatic and manual methods, though exact metrics (e.g., Dice similarity coefficient, mean absolute distance) are not provided in this summary document.
| Acceptance Criterion (Implicit) | Reported Device Performance (Implicit) |
|---|---|
| Automatic segmentation and landmark acquisition is adequate | Adequately verified in comparison to manual segmentation |
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify the exact sample size used for the test set. It mentions "segmentation validation" and "automatic segmentation and landmark acquisition performance was adequately verified in comparison to manual segmentation."
- Data Provenance: The document does not explicitly state the country of origin of the data. It also does not specify whether the data was retrospective or prospective.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document does not provide details on the number of experts used or their specific qualifications (e.g., number of years of experience, specific certifications) for establishing the ground truth. It only refers to "manual segmentation" as the comparison point, implying that expert-driven manual segmentation was used as the ground truth.
4. Adjudication Method for the Test Set
The document does not specify any adjudication method (e.g., 2+1, 3+1) used for the test set. The comparison is stated as "automatic segmentation and landmark acquisition performance... in comparison to manual segmentation," suggesting a direct comparison to a manually derived ground truth without mentioning an adjudication process for that manual ground truth.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance
No, an MRMC comparative effectiveness study was not done. The document explicitly states: "No clinical studies were conducted." The device is cleared as a pre-operative planning tool with its functionality focused on automated segmentation and landmark acquisition, not on human reader performance improvement.
6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, a standalone performance evaluation was done. The document states: "Automatic segmentation and landmark acquisition performance was adequately verified in comparison to manual segmentation." This indicates that the algorithm's performance (standalone segmentation and landmark acquisition) was evaluated against a manually established ground truth.
7. The Type of Ground Truth Used
The type of ground truth used was expert consensus/manual segmentation. The performance was verified "in comparison to manual segmentation," implying that human experts performed manual segmentations, which served as the reference standard.
8. The Sample Size for the Training Set
The document does not specify the sample size used for the training set for the machine learning algorithms.
9. How the Ground Truth for the Training Set Was Established
The document does not explicitly detail how the ground truth for the training set was established. However, given that "manual segmentation" was used as the comparison for verification, it is highly probable that the training data's ground truth was also established through manual segmentation by experts, consistent with standard practices for training machine learning models for medical image analysis.
§ 888.3660 Shoulder joint metal/polymer semi-constrained cemented prosthesis.
(a)
Identification. A shoulder joint metal/polymer semi-constrained cemented prosthesis is a device intended to be implanted to replace a shoulder joint. The device limits translation and rotation in one or more planes via the geometry of its articulating surfaces. It has no linkage across-the-joint. This generic type of device includes prostheses that have a humeral resurfacing component made of alloys, such as cobalt-chromium-molybdenum, and a glenoid resurfacing component made of ultra-high molecular weight polyethylene, and is limited to those prostheses intended for use with bone cement (§ 888.3027).(b)
Classification. Class II. The special controls for this device are:(1) FDA's:
(i) “Use of International Standard ISO 10993 ‘Biological Evaluation of Medical Devices—Part I: Evaluation and Testing,’ ”
(ii) “510(k) Sterility Review Guidance of 2/12/90 (K90-1),”
(iii) “Guidance Document for Testing Orthopedic Implants with Modified Metallic Surfaces Apposing Bone or Bone Cement,”
(iv) “Guidance Document for the Preparation of Premarket Notification (510(k)) Application for Orthopedic Devices,” and
(v) “Guidance Document for Testing Non-articulating, ‘Mechanically Locked’ Modular Implant Components,”
(2) International Organization for Standardization's (ISO):
(i) ISO 5832-3:1996 “Implants for Surgery—Metallic Materials—Part 3: Wrought Titanium 6-aluminum 4-vandium Alloy,”
(ii) ISO 5832-4:1996 “Implants for Surgery—Metallic Materials—Part 4: Cobalt-chromium-molybdenum casting alloy,”
(iii) ISO 5832-12:1996 “Implants for Surgery—Metallic Materials—Part 12: Wrought Cobalt-chromium-molybdenum alloy,”
(iv) ISO 5833:1992 “Implants for Surgery—Acrylic Resin Cements,”
(v) ISO 5834-2:1998 “Implants for Surgery—Ultra-high Molecular Weight Polyethylene—Part 2: Moulded Forms,”
(vi) ISO 6018:1987 “Orthopaedic Implants—General Requirements for Marking, Packaging, and Labeling,” and
(vii) ISO 9001:1994 “Quality Systems—Model for Quality Assurance in Design/Development, Production, Installation, and Servicing,” and
(3) American Society for Testing and Materials':
(i) F 75-92 “Specification for Cast Cobalt-28 Chromium-6 Molybdenum Alloy for Surgical Implant Material,”
(ii) F 648-98 “Specification for Ultra-High-Molecular-Weight Polyethylene Powder and Fabricated Form for Surgical Implants,”
(iii) F 799-96 “Specification for Cobalt-28 Chromium-6 Molybdenum Alloy Forgings for Surgical Implants,”
(iv) F 1044-95 “Test Method for Shear Testing of Porous Metal Coatings,”
(v) F 1108-97 “Specification for Titanium-6 Aluminum-4 Vanadium Alloy Castings for Surgical Implants,”
(vi) F 1147-95 “Test Method for Tension Testing of Porous Metal,”
(vii) F 1378-97 “Standard Specification for Shoulder Prosthesis,” and
(viii) F 1537-94 “Specification for Wrought Cobalt-28 Chromium-6 Molybdenum Alloy for Surgical Implants.”