Search Results

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 designed for use on a skeletally mature patient population. The targeted population has the same characteristics as the population that is suitable for the implants compatible with the Signature™ ONE System.

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 System pre-operative planning is also compatible with the humeral components of the following shoulder implant systems in accordance with their indications and contraindications: Comprehensive® Total Shoulder System, Comprehensive® Reverse Shoulder System, and Identity™ Shoulder System.

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

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

The Signature ONE Guides and Bone Models are designed and manufactured of polyamide (nylon) using additive manufacturing selective laser sintering (SLS), based on the approved/finalized pre-surgical plan and shipped prior to surgery. The guides and bone models are provided non-sterile and sterilized at the hospital. They are used intra-operatively to assist the surgeon in reproducing the plan on the scapula. The Signature ONE System surgical technique remains close to the conventional shoulder arthroplasty workflow.

The Signature™ ONE System uses a Non-Device Medical Device Data System (MDDS) called the Zimmer Biomet 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 purpose of the submission is that the CT Reconstruction internal software application was updated with an improved AI/ML locked model for automatic segmentation and also retraining the model with new production grade scapula and humerus CT segmentations. The AI/ML model is used in the Segmentation step only within the CT Reconstruction internal software application prior to manual segmentation performed by the Zimmer Biomet operator. The use of AI has not changed since predicate K232425. In addition, the Landmarking step within the internal software application was updated with option to select additional configurable landmarks in the Planning application (used to determine the reference coordinate systems to provide native bone information).

The provided FDA 510(k) clearance letter for the Signature™ ONE System does not contain a detailed study with specific acceptance criteria, reported performance, or comprehensive information about the data used for testing and training. This document focuses on demonstrating substantial equivalence to a predicate device, K232425 Signature™ ONE System.

The information regarding acceptance criteria and the study that proves the device meets them is very limited in this document. The submission states that "Performance tests documented to ensure the performance of the implemented features and verify related design inputs" were conducted, but does not provide details of these tests or their results.

Here's an attempt to extract and infer the requested information based on the provided text, highlighting what is missing:

Acceptance Criteria and Device Performance Study for Signature™ ONE System (AI/ML Segmentation Update)

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Test Set: Not specified. The document mentions the AI/ML model was "retrained with new production grade scapula and humerus CT segmentations" and previous "humerus scans were exploratory quality." This implies a test set was used to establish the "new production grade" status, but the exact size is not provided.
• Data Provenance: Not specified. It only mentions "production grade scapula and humerus CT segmentations." The country of origin and whether the data is retrospective or prospective are not mentioned.

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

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

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified.

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

• Was an MRMC study done? No, the document does not mention an MRMC comparative effectiveness study where human readers improve with AI vs. without AI assistance. The AI/ML model is described as assisting "prior to manual segmentation performed by the Zimmer Biomet operator," implying an assistive role, but no comparative study is detailed.

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

• Was a standalone study done? Not explicitly stated as a standalone "study." The language "used in the Segmentation step only (...) prior to manual segmentation" suggests the AI performs segmentation independently before human review/modification, but its standalone performance metrics are not provided. The overall system is described as having manual segmentation by an operator after the AI step.

7. Type of Ground Truth Used

• Type of Ground Truth: The document refers to "new production grade scapula and humerus CT segmentations." This implies that the ground truth for segmentation was established by expert review and/or manual segmentation deemed as high quality (i.e., "production grade"). It does not specify if this was expert consensus, pathology, or outcomes data.

8. Sample Size for the Training Set

• Sample Size for Training Set: Not specified. The document states the model was "retrained with new production grade scapula and humerus CT segmentations." The size of this new training set is not provided.

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

• How Ground Truth Was Established: The ground truth for the training set was established through "production grade scapula and humerus CT segmentations." This suggests that human experts (likely trained Zimmer Biomet operators or clinicians) performed manual segmentations that were then refined and verified to a high standard, serving as the ground truth for training the AI/ML model.

Ask a specific question about this device