AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Identity Imprint CR KRS

The Identity Imprint CR Knee Replacement System is intended for use as a total knee replacement in patients with knee joint pain and disability whose conditions cannot be solely addressed by the use of a prosthetic device that treats only one or two of the three knee compartments, such as unicondylar, patellofemoral or bicompartmental prosthesis.

The Indications for Use include:

· Painful joint disease due to osteoarthritis, traumatoid arthritis or osteonecrosis of the knee.

  • Post traumatic loss of joint function
    · Moderate varus, valgus, or flexion deformity in which the ligamentous structures can be returned to adequate function and stability.

· Failed osteotomies, hemiarthroplasties, and unicondylar, patellofemoral or bicompartmental implants

· Revision procedures provided that anatomic landmarks necessary for alignment and positioning of the implant are identifiable on patient imaging scans.

This implant is intended for cemented use only.

Identity Imprint PS KRS

The Identity Imprint PS Knee Replacement System is intended for use as a total knee replacement in patients with knee joint pain and disability whose conditions cannot be solely addressed by the use of a prosthetic device that treats only one or two of the three knee compartments, such as unicondylar, patellofemoral or bicompartmental prosthesis.

The Indications for Use include:

· Painful joint disease due to osteoarthritis, traumatoid arthritis, polyarthritis, polyarthritis or osteonecrosis of the knee.

· Post traumatic loss of joint function

  • · Moderate varus, valgus or flexion deformity
    · Failed osteotomies, hemiarthroplasties, and unicondylar, patellofemoral or bicompartental implants

· Revision procedures provided that the anatomic landmarks necessary for alignment and positioning of the implant are identifiable on patient imaging scans.

This implant is intended for cemented use only.

Device Description

The subject device, Identity Imprint Knee Replacement System, is a knee replacement system including standardized implant sizes combined with standard and patient-specific ancillary surgical instrumentation. As with all Conformis Knee Replacement Systems (KRS), the Identity Imprint Knee Replacement System is semi-constrained knee implants which consist of a femoral, tibial, and/or patellar components. The products are intended for treatment of severe pain and/or disability of the knee damaged by osteoarthritis or trauma.

Using patient imaging (either CT or MR scans), a standard implant is selected that best meets the geometric and anatomic requirements of the specific patient. The femoral components of the subject devices are manufactured from cobalt chromium molybdenum (CoCrMo) alloy. The tibial component includes a metal tray manufactured from titanium alloy and polyethylene inserts. The patellar components are manufactured from UHMWPE.

For user convenience, single-use, standard and patient-specific ancillary orthopedic manual surgical instruments designed for use with the selected Identity Imprint implants are provided to assist in the positioning of the total knee replacement components intraoperatively and in guiding the cutting of bone. In addition, reusable orthopedic manual surgical instruments are provided separately.

AI/ML Overview

The provided document is a 510(k) Premarket Notification from the FDA for a medical device: the Identity Imprint Knee Replacement System. This type of document is a submission for regulatory clearance, not a clinical study report. Therefore, it does not contain the detailed acceptance criteria for an AI/software device, nor does it describe a study that explicitly proves the device meets such criteria in the way an AI/ML device would be evaluated (e.g., involving AI performance metrics like sensitivity, specificity, or AUC).

The document states that the "focus of this submission is on additional manufacturing software enhancements aimed at adding an option to enhanced automated processes in lieu of the previously cleared manual and automated processes in order to improve manufacturing efficiencies." It further mentions "Software Verification and Validation" as a confirmatory test. This suggests the software in question is primarily for manufacturing process enhancement, not for diagnostic or therapeutic AI assistance to clinicians.

Therefore, many of the requested details about acceptance criteria and study design for an AI/ML-based device cannot be extracted from this document, as it doesn't describe such a device or study.

Here's what can be inferred or directly stated from the document, acknowledging the limitations regarding AI/ML-specific evaluations:


Based on the provided document, the Identity Imprint Knee Replacement System is primarily a hardware device with associated manufacturing software enhancements, not an AI/ML diagnostic or therapeutic device. As such, the document does not describe the types of acceptance criteria or performance studies typically associated with AI/ML products (e.g., sensitivity, specificity, MRMC studies).

The document focuses on demonstrating substantial equivalence to a previously cleared predicate device, largely through manufacturing process updates and software enhancements related to those processes.

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

  • Acceptance Criteria: Not explicitly stated in terms of performance metrics like sensitivity, specificity, or F1-score as would be seen for an AI/ML diagnostic device. The acceptance criterion is "substantial equivalence" to the predicate device, K221059, demonstrated through "Software Verification and Validation."
  • Reported Device Performance: The document states: "The software verification and validation data provided in this submission supports that the subject device is safe, effective, and performs as well as or better than the predicate device. No new issues of safety or efficacy were raised." No specific metrics are provided.

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

  • Sample Size: Not specified. The "Software Verification and Validation" would typically involve testing of the software itself, potentially using simulated or real manufacturing data, but the sample size of such data is not detailed.
  • Data Provenance: Not specified. Given it's a manufacturing software enhancement, the data would likely be related to manufacturing inputs, outputs, and quality control, potentially from the manufacturer's own internal processes. The document doesn't indicate if it's retrospective or prospective data from a clinical context.

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

  • Not applicable as described. This document pertains to regulatory clearance of a physical medical device and its manufacturing software, not to an AI diagnostic tool requiring expert ground truth for clinical image analysis. "Ground truth" for manufacturing software validation would likely relate to the correctness of the enhanced automated processes, validated against established engineering or quality control standards, rather than expert clinical consensus.

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

  • Not applicable. Adjudication methods like 2+1 are typically used in clinical studies for AI diagnostic devices where there's a need to reconcile divergent expert opinions on medical images. This document describes software verification and validation for a manufacturing process.

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. An MRMC study is not mentioned or implied. This type of study is specifically designed to assess the impact of an AI system on human diagnosticians' performance.

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

  • Not directly applicable in the context of an AI diagnostic algorithm. "Software Verification and Validation" was performed, which assesses the software's functionality and performance independently, but this is for manufacturing processes, not for a clinical diagnostic algorithm.

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

  • Not explicitly stated. For "Software Verification and Validation" in a manufacturing context, ground truth would likely be defined by engineering specifications, validated process outputs, and quality control measurements rather than clinical ground truth types like pathology or outcomes data.

8. The sample size for the training set

  • Not applicable. This document describes the clearance of a device with manufacturing software enhancements. It does not mention machine learning model training.

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

  • Not applicable. See point 8.

§ 888.3560 Knee joint patellofemorotibial polymer/metal/polymer semi-constrained cemented prosthesis.

(a)
Identification. A knee joint patellofemorotibial polymer/metal/polymer semi-constrained cemented prosthesis is a device intended to be implanted to replace a knee 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 femoral component made of alloys, such as cobalt-chromium-molybdenum, and a tibial component or components and a retropatellar resurfacing component made of ultra-high molecular weight polyethylene. This generic type of device is limited to those prostheses intended for use with bone cement (§ 888.3027).(b)
Classification. Class II.