K Number
K173329
Manufacturer
Date Cleared
2017-11-15

(23 days)

Product Code
Regulation Number
892.2050
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

JointVue's ¡Fit Surgical Planner is a software device intended to assist medical professionals in preoperative planning of orthopedic surgery. The device allows for overlaying templates of prostheses on 3D bone models generated from radiological images. The software includes tools for performing measurements on the images and for positioning the prosthetic template. Clinical judgment and experience are required to properly use the software.

Device Description

JointVue's ¡Fit Surgical Planner is an orthopedic preoperative planning software. It allows for overlaying templates of prostheses on patient 3D bone models generated from radiological images using JointVue's 3D echo software (K172513) for overlaying templates of prostheses for surgical preplanning of joint replacement surgery. jFit Surgical Planner is intended to run on a PC and requires the Microsoft Windows™ operating system, version 7, windows 8 or windows 10 (32-bit/64-bit). A PDF Reader such as Adobe Acrobat or Foxit is recommended in order to access the instructions for use. ¡Fit Surgical Planner software requires the following minimum requirements for computer hardware listed in the following table: Processor Intel Core i5-5300 @ 2.3 GHz or higher, Memory 8 GB RAM or more, Graphics Intel HD Graphics 5500 or higher, Resolution Minimum 1920*1080, HD Space 1 GB or more. The major functions and features of jFit Surgical Planner include: 1. Patient Case Loading, 2. Loading X-Ray Images, 3. Editing and Verifying Femur Landmarks, 4. Editing and Verifying Tibia Landmarks, 5. Conducting Femur Planning, 6. Conducting Tibia Planning, 7. Validating Surgical Planning, 8. Generation of a Surgical Planning Summary Report. iFit Surgical Planner is for installation on a secure computer workstation to protect patient data. Typical environment of use is an office environment. jFit Surgical Planner utilizes 3D bone models for preoperative planning of joint replacement surgery. Surgical preplanning starts by importing patient 3D bone models along with anterior-posterior and lateral X-Ray images, if available. ¡Fit Surgical Planner calculates relevant surgical landmarks which can then be verified and edited. ¡Fit Surgical Planner will suggest an initial implant selection and placement based on anatomical landmarks selected and verified by the clinician is responsible to adjust the implant selection and placement parameters to validate patient-specific surgical plan. Upon completion of surgical planning, a summary report is generated that must be signed by a physician to approve the surgical plan.

AI/ML Overview

Here's a summary of the acceptance criteria and study information for the jFit Surgical Planner, based on the provided text:

Acceptance Criteria and Device Performance

The provided document describes the equivalence of the subject device (jFit Surgical Planner) to the predicate device (TraumaCAD 2.0) based on their ability to identify the same size implants.

Acceptance CriteriaReported Device Performance (jFit Surgical Planner)
Identify same size implants as predicate100% agreement with predicate
Precision and accuracy equivalent to predicateEquivalent demonstrated by benchtop testing

Study Details

2. Sample Size and Data Provenance for Test Set

  • Sample Size: 39 simulated cases.
  • Data Provenance: The cases were "simulated," implying they were not from real patients but rather constructed scenarios for testing. The country of origin is not specified. The study was retrospective in nature as it involved pre-defined simulated cases.

3. Number of Experts and Qualifications for Ground Truth

The document does not explicitly state the number of experts or their specific qualifications (e.g., radiologist with 10 years of experience) used to establish the ground truth for the test set in the benchtop study. However, the study involved "two independent users" who performed the implant sizing tasks for both devices. While these "users" are implicitly qualified to perform surgical planning, their specific expert credentials for establishing ground truth are not detailed.

4. Adjudication Method for Test Set

The adjudication method for the test set is implied to be a direct comparison of the output from two independent users operating both the subject and predicate devices. No formal "adjudication method" in the sense of resolving discrepancies among multiple experts (like 2+1 or 3+1) is mentioned, as the focus was on the agreement between the devices' outputs by individual users. The case IDs were blinded for both operators, suggesting an attempt to reduce bias.

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

No multi-reader multi-case (MRMC) comparative effectiveness study was explicitly mentioned or conducted as described in the provided text. The study focused on side-by-side performance of the two devices by two independent users, rather than a comparative effectiveness study involving human readers with and without AI assistance to measure improvement effect size.

6. Standalone (Algorithm Only) Performance

The benchtop testing implicitly demonstrates standalone performance of the algorithm within the software, as it evaluated the device's output (implant sizing) based on simulated cases. The "two independent users" were operating the software to achieve these results. The device itself is a "software device."

7. Type of Ground Truth Used

The ground truth for the benchtop testing was established by the "predicate device" (TraumaCAD 2.0) as the reference, which the subject device was compared against. The study aimed to demonstrate that the subject device identified "the same size implants" as the predicate. This implies the ground truth was essentially the output of a previously cleared device, rather than pathology, expert consensus on imaging, or outcomes data.

8. Sample Size for the Training Set

The document does not specify a separate "training set" or its sample size. The description focuses on validation testing and equivalence to a predicate device. If the device uses machine learning, the training data used to develop the underlying models is not disclosed in this regulatory submission.

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

As no training set is mentioned, the method for establishing its ground truth is also not provided.

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).