Search Results
Found 1 results
510(k) Data Aggregation
(204 days)
Ortho AI is an image-processing software indicated to assist in making measurements for a total hip arthroplasty, total knee arthroplasty, and lumbar spine fusion surgery.
It is intended to assist in the measurement of x-ray images by measuring lengths, angles and position of implants relative to the bone structures of interest provided, that the points of interest can be identified from radiology images.
The device allows for overlaying of digital annotations on radiological images and includes tools for performing measurements using the images and digital annotations. The software is not for primary image interpretation. The software is not for use on mobile phones.
Intended patient population: Adult patients >=22 years old, with appropriate imaging, undergoing primary hip replacement, primary knee replacement, and lumbar spine surgery.
Intended user population: orthopaedic surgeons who perform hip and knee replacement, and orthopaedic/neurosurgeons who perform lumbar spine surgery.
Ortho AI is a software as a medical device (SaMD) system that provides preoperative planning data for hip replacement surgery, knee replacement surgery, and lumbar spinal fusion surgery using AI/ML models that are semi-automated and interpretable. The software guides the user through a predetermined workflow that begins with the use of preoperative radiographic images as input to the software. As part of this initial preoperative workflow, the software places digital annotations on these preoperative images, which can be modified by the user (semi-automated). The software additionally includes functionality to store user, patient, and case information.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Module | Acceptance Criteria (Dice Coefficient) | Reported Performance (Dice Coefficient) | Other Performance Metrics Reported |
|---|---|---|---|
| Overall | Minimum 0.85 for all algorithms and connected domains | All connected domains above 0.85 | See specific model performance |
| Hip Model | Minimum 0.85 for all connected domains | All connected domains above 0.85 | LLD: within +/- 1.96mm of human measurement |
| Offset (global): within +/- 0.88mm of human measurement | |||
| SFP angle: within +/- 1.05mm of human measurement | |||
| Hip-Spine Model | Minimum 0.85 for all connected domains | All connected domains above 0.85 | SS, SPT, APPt, PI, LL, PI-LL: all within 2 degrees of human measurement (no statistical difference) |
| Knee Model | Minimum 0.85 for all connected domains | All connected domains above 0.85 | LDFA, mPTA, aHKA, aJLOA: all within 2 degrees of human measurement (no statistical difference) |
2. Sample Size for the Test Set and Data Provenance
- Sample Size for Test Set: The acceptance criteria section states, "A test sample size of ≥ 150 samples". While the exact number of test images for each model's independent test set isn't explicitly detailed within the provided text, the document implies that this minimum was met or exceeded for the performance testing.
- Data Provenance: The text 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 Ground Truth for the Test Set and Qualifications
- Number of Experts: 3
- Qualifications of Experts: All 3 were fellowship-trained, ABOS board-certified orthopaedic surgeons, each with greater than 10 years of experience.
4. Adjudication Method for the Test Set
- Adjudication Method: 2+1 truthing process. Two blinded orthopaedic surgeons independently reviewed each segmented image in the testing set and applied modifications. A final senior-level surgeon adjudicator then reviewed these modifications and made further adjustments if necessary.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The provided text does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to evaluate how much human readers improve with AI vs. without AI assistance. The study focuses on the standalone performance of the algorithm against human measurements and ground truth.
6. Standalone Performance
- Yes, standalone performance was evaluated. The section "Standalone algorithm testing" directly addresses this, providing specific measurement accuracies for the Hip, Hip-Spine, and Knee models (e.g., LLD, Offset, angles) and reporting Dice coefficients. The statement "no statistical difference between human vs. machine learning measurements" for Hip-spine and Knee models further confirms this.
7. Type of Ground Truth Used
- Expert Consensus / Human Measurement: The ground truth for the test set was established through a "2+1 truthing process" by three qualified orthopaedic surgeons, which constitutes expert consensus. The device's performance is reported against "human measurement" for various parameters (e.g., LLD measurements within +/- 1.96mm of human measurement).
8. Sample Size for the Training Set
- Hip Model: 1,367 images from 1,367 patients
- Hip-Spine Model: 4,836 images from 4,836 patients
- Knee Model: 4,536 images from 4,536 patients
9. How the Ground Truth for the Training Set Was Established
- The text describes the "Truthing process" for the test set. While the methodology for the training set's ground truth is not explicitly detailed in the provided snippet, it is a standard practice that such large training datasets would also have their ground truth established by experts, likely following a similar or more extensive version of the described truthing process. However, the document only explicitly explains the ground truthing for the test set.
Ask a specific question about this device
Page 1 of 1