Search Results

The Single-use Bronchoscopes have been designed to be used with the Monitor for Single-Use Endoscopy, endotherapy accessories and other ancillary equipment for endoscopy within the airways and tracheobronchial tree. The Bronchoscope System is for use in a hospital environment.

The Single-use Bronchoscope is a disposable device designed for use in adults.

The Bronchoscope System consists of Single-use Bronchoscope (Model: BC12-1, BC12-2, BC20-1, BC20-2, BC22-1, BC22-2, BC22-3, BC28-1, BC28-2, BC28-3) to be introduced within the airways or tracheobronchial tree and Monitor for Single-Use Endoscopy (Model: P1-A, P1-C, P1-C, P1-D, P1-E, P2-A, P2-B, P2-C, P2-D, P2-E) for clinical image processing. The Single-use Bronchoscope is inserted through the airways and tracheobronchial tree during Bronchoscopy. The Monitor provides power and processes the images for medical electronic endoscope.

The Single-use Bronchoscope is a sterile single use flexible bronchoscope. The Monitor for Single-Use Endoscopy is a reusable monitor.

The light emitted by the LED cold light source at the distal tip of the disposable video Bronchoscope is irradiated into the body cavity, and the light reflected from the cavity enters the optical system and is captured by the CMOS image sensor. The CMOS acquisition image is controlled by the CMOS drive circuit, and the RGB video signal is output to the Monitor for Single-Use Endoscopy via the VI circuit. The Monitor receives video signals from the endoscope, processes the video signals and outputs the processed video signal. The Monitor also controls the brightness of the LEDs on the endoscope.

The provided document is a 510(k) Premarket Notification and primarily focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed study report for a novel AI/ML-driven medical device. Therefore, it does not contain the specific information required to answer many of the questions about acceptance criteria, detailed study design, ground truth establishment, or human-in-the-loop performance.

This document describes a "Bronchoscope System," which includes a "Single-use Bronchoscope" and a "Monitor for Single-Use Endoscopy." The core technology described involves an optical system with a CMOS sensor to capture images for display, which is a common technology for endoscopes, not necessarily an AI/ML device in the sense of image analysis/decision support.

Here's an attempt to answer the questions based only on the provided text, highlighting what is not available:

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

The document does not present a formal table of acceptance criteria with reported quantitative performance metrics in the format usually seen for AI/ML device studies (e.g., sensitivity, specificity, AUC). Instead, it relies on demonstrating equivalence through various non-clinical tests compared to a predicate device.

The "Summary of Testing" section lists the types of tests performed. The acceptance criteria are implicitly that the device performs "as well as" the predicate or meets established ISO standards.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document states: "Based on the similarities of the device specifications, intended use, indications for use between the Bronchoscope System and its predicate device, no clinical studies were needed to support this 510(k) Premarket Notification."

This means there was no clinical test set in the traditional sense for evaluating something like diagnostic accuracy of an AI/ML model. The evaluation was done through non-clinical bench testing, electrical safety, biocompatibility, and software V&V. Therefore, information on sample size, data provenance (country, retrospective/prospective) for a clinical test set is not applicable to this submission.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

Since no clinical studies were performed, no expert ground truth establishment for a clinical test set was required or conducted.

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

Not applicable as no clinical test set using expert adjudication was conducted.

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

Not applicable, as this is not an AI-assisted diagnostic device submission requiring MRMC studies. The device is a bronchoscope system for visualization.

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

This refers to an AI algorithm's performance. The Bronchoscope System is a hardware device for direct visualization, not an AI algorithm. Therefore, "standalone performance" in the AI sense is not applicable.

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

For the non-clinical tests, the "ground truth" was established by engineering specifications, validated test methods (e.g., ISO standards), and comparisons against the predicate device's established performance parameters. For example:

• Electrical Safety/EMC: Compliance to IEC standards.
• Optical Performance: Measurement against ISO 8600 series specifications.
• Biocompatibility: Results of standard biological tests (e.g., cytotoxicity, sensitization) against established safe thresholds.

8. The sample size for the training set

The document does not mention a "training set" because it is not an AI/ML device that requires machine learning training.

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

Not applicable, as no training set for an AI/ML model was used.

Ask a specific question about this device