(155 days)
The Gentuity® HF-OCT Imaging System with Vis-Rx® Micro-Imaging Catheter is intended for intravascular imaging and is indicated for use in coronary arteries in patients who are candidates for transluminal interventional procedures. The Vis-Rx Micro-Imaging Catheter is intended for use in vessels 1.3 to 6.0 mm in diameter. The Vis-Rx Micro-Imaging Catheter is not intended for use in a target vessel that has undergone a previous bypass procedure.
The Gentuity® HF-OCT Imaging System with Vis-Rx® Micro-Imaging Catheter (herein the "Gentuity Imaging System") provides images of the coronary arteries in patients who are candidates for transluminal interventional procedures. The system utilizes fiber-optic technology to deliver near-infrared light and receive light reflected from coronary tissue to produce high resolution, real-time images. The Gentuity Imaging System consists of the Gentuity Imaging Console, Vis-Rx Micro-Imaging Catheter, and Optional Gentuity Review Station.
Here's an analysis of the acceptance criteria and study details based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text only discusses the device performance for the AI feature designed to identify "B-Mode with Stent & Guide Catheter." It specifies performance targets and the achieved performance within a table. Note that the other new software features (Stent Expansion View Mode, Longitudinal Zoom & Zoom Indicator, Training Mode, Image Display Speed Optimization, and Angle measurement tool) are verified and validated but their specific performance metrics are not explicitly detailed as acceptance criteria in the same way as the AI feature.
| Feature / Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| AI to identify B-Mode with Stent & Guide Catheter | ||
| Accuracy | ≥ 90% per vessel for detection of Stent and Guide Catheter | 100% per vessel for Stent and 100% for Guide Catheter |
| Sensitivity | ≥ 90% per frame for detection of Stent and Guide Catheter | 98.7% per frame for Stent and 99.8% for Guide Catheter |
| Specificity | ≥ 90% per frame for detection of Stent and Guide Catheter | 99.9% per frame for Stent and 99.9% for Guide Catheter |
| Accuracy (Image Annotation - Overall) | ≥ 90% for image annotation overall | 99.6% |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: The text indicates that the test set included 25 patients. The "Patient population included the following" table shows age, sex, and BMI distribution for 25 patients in the test set.
- Data Provenance: The HF-OCT images used for the AI training and test data sets included "clinical data acquired with the Gentuity HF-OCT Imaging System and Vis-Rx catheters." The study population consisted of participants "already scheduled for a visit to the catheterization laboratory and were candidates for transluminal interventional procedures." This strongly suggests the data is retrospective clinical data from an unspecified country, likely where the Gentuity system is used.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document does not explicitly state the number of experts used or their specific qualifications (e.g., "radiologist with 10 years of experience") for establishing the ground truth on the test set.
4. Adjudication Method for the Test Set
The document does not describe the adjudication method used for the test set. It mentions "ground truth for the test data was established by expert consensus," but no details on the consensus process (e.g., 2+1, 3+1) are provided.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly described. The study focused on the performance of the AI algorithm in isolation (standalone). There is no mention of comparing human readers with and without AI assistance or any effect size for human improvement.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, a standalone performance study was done for the AI feature. The acceptance criteria and reported performance metrics (Accuracy, Sensitivity, Specificity for B-Mode with Stent & Guide Catheter detection, and overall image annotation accuracy) are for the algorithm's performance without direct human intervention in the interpretation phase for these specific AI tasks.
7. The Type of Ground Truth Used
The ground truth for the test set was established by expert consensus. The text states: "The ground truth for the test data was established by expert consensus."
8. The Sample Size for the Training Set
The training set included 20 patients. The "Patient population included the following" table shows age, sex, and BMI distribution for 20 patients in the training set.
9. How the Ground Truth for the Training Set Was Established
The document states, "The ground truth for the training data was established by expert consensus." No further details on the specific experts or the consensus method are provided.
§ 870.1200 Diagnostic intravascular catheter.
(a)
Identification. An intravascular diagnostic catheter is a device used to record intracardiac pressures, to sample blood, and to introduce substances into the heart and vessels. Included in this generic device are right-heart catheters, left-heart catheters, and angiographic catheters, among others.(b)
Classification. Class II (performance standards).