(197 days)
This device is a self-help tool for individuals aged 18 or older with diagnosed depression. It is intended to be used in addition to usual care and not as a replacement for it.
[Input Description text here]
The provided FDA 510(k) Clearance Letter for the HJY VisualNext 3D Endoscopic Vision System focuses on the device's substantial equivalence to a predicate device, as opposed to a detailed standalone or comparative effectiveness study of an AI-powered diagnostic device. Therefore, many of the requested details, particularly those related to AI algorithm performance (e.g., sample size for test/training sets, data provenance, ground truth establishment, MRMC studies, and effect size of human reader improvement with AI assistance), are not present in this document.
However, based on the information available, here's a breakdown of the acceptance criteria and the study that proves the device meets them:
Device Type: The HJY VisualNext 3D Endoscopic Vision System is an endoscopic vision system, not an AI-powered diagnostic device. Its primary function is to provide 3D visualization during surgical procedures, differentiating it from an AI-based system that might perform automated image analysis or diagnosis.
Acceptance Criteria and Reported Device Performance:
The document outlines acceptance criteria implicitly through the performance of various non-clinical tests. The criteria are met if the device "Pass[es]" the respective tests and demonstrates performance metrics comparable to predefined standards or the predicate device.
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Sterility (Device must be sterile as labeled) | Testing completed in accordance with FDA guidance. (Result: Met) |
| Biocompatibility (Safe for contact with neural tissue, bone, dentin, blood) | All acceptance criteria for cytotoxicity, sensitization, irritation/intracutaneous reactivity, acute systemic toxicity, neurotoxicity, and hemocompatibility met. (Result: Favorable biocompatibility profile) |
| Software Validation (Software functions as intended and safely) | Completed in accordance with FDA guidance document "Content of Premarket Submissions for Device Software Functions". (Result: Met requirements) |
| Electromagnetic Compatibility (EMC) & Thermal Safety (Meets safety standards for electrical and thermal properties) | Completed in accordance with IEC60601-1, IEC60601-1-2, IEC60601-2-18. (Result: Met standards) |
| Photobiological Safety (No hazardous light emission) | Completed in accordance with IEC 62471. (Result: Met standards) |
| Bench Testing - Image Quality & Performance (FOV, DOV, DOF, Optical Magnification, Distortion, Image Intensity Uniformity, Signal-to-Noise Ratio, Sensitivity, Resolution (MTF) of aged and non-aged devices comparable to predicate) | Both aged and non-aged subject devices met the predefined acceptance criteria, demonstrating consistent image quality metrics comparable to the predicate device. (Result: Pass) |
| Animal Study Testing - 3D Visualization Performance (Clear and stable 3D visualization of brain and spine tissues, with resolution, color representation, contrast, and noise comparable to predicate, and compatibility with 3D monitor) | The subject device provided clear and stable 3D visualization of brain and spine tissues across all tested conditions. Image quality parameters, including resolution, color representation, contrast, and noise, met the predefined acceptance criteria when compared to the predicate device. Testing also validated compatibility with the Sony LMD-2451MT 3D Monitor. (Result: Pass) |
Study Details (for the Non-Clinical Performance Testing):
Since the device is a vision system and not an AI algorithm, the traditional "test set" and "training set" concepts as applied to AI models do not directly apply in the same way. The non-clinical testing evaluates the physical and functional performance of the device itself.
-
Sample size used for the Test Set and Data Provenance:
- Bench Testing: The sample size is not explicitly stated, but it involved "aged and non-aged subject devices" and direct comparison to the predicate device. The data provenance would be laboratory-generated data from device performance measurements.
- Animal Study Testing: "A porcine animal model" was used. The specific number of animals or trials within the animal study is not provided. The data provenance is described as being from a porcine animal model. This would be prospective data collection, specifically for this study.
-
Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
- This metric is not applicable in the context of this device's testing. The "ground truth" for a vision system's performance is typically established by objective physical measurements (e.g., MTF for resolution, calibrated light meters for illumination) and expert subjective evaluation of visual quality in a controlled setting, rather than a consensus on diagnostic findings. The document does not specify the number or qualifications of any human evaluators involved in the image quality assessment during bench or animal testing, only that the data "met the predefined acceptance criteria."
-
Adjudication Method for the Test Set:
- Not applicable as the testing involves objective performance measurements and comparison against predefined criteria, not diagnostic interpretations requiring adjudication.
-
If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:
- No. An MRMC study is typically performed for diagnostic devices where human readers interpret medical images, often with and without AI assistance, to measure diagnostic accuracy and efficiency. This device is a surgical visualization tool, not a diagnostic imaging device.
-
If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- This is not an AI algorithm, so the concept of "standalone performance" of an algorithm is not applicable. The core function of the device is to provide images for human viewing. The non-clinical tests assess the device's ability to produce high-quality images and function as intended.
-
The Type of Ground Truth Used:
- For Bench Testing: Objective physical measurements (e.g., resolution targets, light sensors, distortion grids) served as the "ground truth" for parameters like FOV, DOF, resolution, etc., along with comparison to the known performance of the predicate device.
- For Animal Study Testing: The "ground truth" for image quality (resolution, illumination, color representation, contrast, noise) was likely based on objective evaluation against predefined standards and comparative assessment by skilled observers (e.g., surgeons, imaging specialists) who could judge the clarity and utility of the visualization in an anatomical context, compared to the predicate device's 2D view. Anatomical structures within the porcine model served as the "true" objects being visualized.
-
The Sample Size for the Training Set:
- Not applicable. This device is a hardware system, not an AI algorithm trained on data. There is no "training set" in the context of machine learning.
-
How the Ground Truth for the Training Set was Established:
- Not applicable, as there is no training set.
§ 882.1480 Neurological endoscope.
(a)
Identification. A neurological endoscope is an instrument with a light source used to view the inside of the ventricles of the brain.(b)
Classification. Class II (performance standards).