Search Results

The Single-use Bronchoscopes have been designed to be used with the Electronic Endoscope Imaging Processor, 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 single-use device designed for use in adults.

The Single-use Bronchoscope is a sterile single used flexible bronchoscope. The Electronic Endoscope Imaging Processor is a reusable monitor.

The light emitted by the LED cold light source at the distal tip of the Single-use 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 of the Electronic Endoscope Imaging Processor via the encoding circuit. The Electronic Endoscope Imaging Processor receives video signals from the endoscope, processes the video signals, and outputs the processed video signal to the monitor. The Electronic Endoscope Imaging Processor also controls the brightness of the LEDs on the endoscope.

The optical components and their arrangement at the distal tip for all models of the Single-use Bronchoscope are identical.

The Single-use Bronchoscope is single-use medical devices that are sterilized with ethylene oxide and intended for use in adults. This product is accompanied by an electronic endoscopic image processor, which supports the use of medical monitors. The electronic bronchoscope system is used for endoscopic diagnosis or treatment, and the processor collects, processes, stores, and transmits images of the human body cavity to the monitor.

This FDA 510(k) summary describes the Bronchoscope System (Single-use Bronchoscope: SP-Y-ZQGJ2.8, SP-Y-ZQGJ3.8, SP-Y-ZQGJ4.2, SP-Y-ZQGJ4.8, SP-Y-ZQGJ5.2, SP-Y-ZQGJ5.8; Electronic Endoscope Imaging Processor: SP-TXCLQ12.1). The submission indicates that no clinical studies were performed to demonstrate substantial equivalence. Instead, a series of non-clinical (bench) tests were conducted to verify that the proposed device met all design specifications and was substantially equivalent to the predicate devices (K231107 and K191828).

Therefore, I will provide the acceptance criteria and performance as reported for the non-clinical tests.

1. Table of Acceptance Criteria and Reported Device Performance

Since this submission relies on non-clinical testing for substantial equivalence, the "acceptance criteria" are typically compliance with recognized standards or meeting specific performance benchmarks defined in the device's design specifications. The "reported device performance" refers to the results of these tests confirming that the device meets those standards/specifications.

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: The document does not specify the exact sample sizes for each non-clinical test performed. However, these tests are typically performed on a statistically representative number of manufactured units according to the applicable standard requirements (e.g., a certain number of devices for electrical safety, biocompatibility batches, etc.).
• Data Provenance: The tests are non-clinical, meaning they were conducted in a laboratory or simulated environment, not on human subjects. The manufacturer is Shenzhen Sanping Image Technology Co., Ltd. located in Shenzhen, Guangdong, China. The data would therefore originate from testing facilities associated with the manufacturer or their designated testing laboratories. The data is prospective in the sense that it was generated specifically to support this 510(k) submission.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

Not applicable. Since no clinical studies were performed, there was no test set requiring expert ground truth establishment for diagnostic or clinical performance. The non-clinical tests relied on validated reference methods and calibrated equipment to assess various physical and performance characteristics against established international standards.

4. Adjudication Method for the Test Set

Not applicable, as no clinical test set requiring expert adjudication was used.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The submission explicitly states: "No clinical test data was used to support the decision of substantial equivalence." Therefore, there is no reported effect size regarding human reader improvement with or without AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

This device is not an AI/algorithm-only device. It is a Bronchoscope System, which functions as a direct visualization tool for medical professionals. Therefore, a standalone algorithm performance study is not applicable.

7. The Type of Ground Truth Used

For the non-clinical performance tests, the "ground truth" implicitly refers to the specifications defined by the international consensus standards (e.g., IEC, ISO) and the device's own design specifications. The tests verify that the device's physical, electrical, mechanical, and imaging properties meet these predefined engineering and safety benchmarks.

8. The Sample Size for the Training Set

Not applicable. This device is not an AI/machine learning device that requires a training set.

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

Not applicable, as there is no training set for this device.

Ask a specific question about this device

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

The Single-use Bronchoscope have been designed to be used with the Image Processor, 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 is a single-use device designed for use in adults.

The Bronchoscope System consists of Single-use Bronchoscope (six models shown in below) to be introduced within the airways or tracheobronchial tree and Image Processor (model: VLM-02) for clinical image processing. The Flexible Bronchoscope is inserted through the airways and tracheobronchial tree during Bronchoscopy. The Image Processor provides power and processes the images for medical electronic endoscope.

The Single-use Bronchoscope is a sterile single used flexible bronchoscope. The Image Processor is a reusable monitor.

The light emitted by the LED cold light source at the distal tip of the Single-use 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 Image Processor via the VI circuit. The Image Processor receives video signals from the endoscope, processes the video signals, and outputs the processed video signal to the monitor. The Image Processor also controls the brightness of the LEDs on the endoscope.

The optical components and their arrangement at the distal tip for all models of the Singleuse Bronchoscope are identical.

Single-use Bronchoscope has the following physical and performance characteristics:

• Maneuverable tip controlled by the user
• Flexible insertion cord
• Camera and LED light source at the distal tip
• Sterilized by Ethylene Oxide
• For single use

Image Processor has the following physical and performance characteristics:

• Display the image from the Single-use Bronchoscope on the screen ●
• Can record screenshots or video of image from the Single-use Bronchoscope
• Can connect to an external monitor ●
• Reusable device

The provided text is a 510(k) summary for a Bronchoscope System. It details the device description, indications for use, comparison to a predicate device, and performance data. However, it does not contain information about an AI/ML-based device or a study involving human readers and AI assistance.

Therefore, I cannot provide the requested information regarding:

• A table of acceptance criteria and reported device performance for an AI/ML device. The document lists bench performance tests according to ISO 8600 series and other parameters, but these are for a standard bronchoscope system, not an AI component.
• Sample size used for the test set and data provenance.
• Number of experts and their qualifications for establishing ground truth.
• Adjudication method for the test set.
• Multi-reader multi-case (MRMC) comparative effectiveness study or effect size.
• Standalone (algorithm only) performance.
• Type of ground truth used (expert consensus, pathology, outcomes data, etc.) for an AI/ML component.
• Sample size for the training set for an AI/ML component.
• How ground truth for the training set was established for an AI/ML component.

The document explicitly states: "No clinical study is included in this submission" (Section 10), and the performance data primarily relates to bench testing, biocompatibility, sterilization, electrical safety, and software verification/validation for the traditional bronchoscope system.

To answer your request for an AI/ML device, I would need a different document that describes such a device and its associated clinical or performance studies.

Ask a specific question about this device

The flexible bronchoscope have been designed to be used with the video processor, 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 Flexible Bronchoscope is a single-use device designed for use in adults.

The Bronchoscope System consists of Flexible Bronchoscope (twelve models shown in below) to be introduced within the airways or tracheobronchial tree and Video Processor (model: EOS-H-01) for clinical image processing. The Flexible Bronchoscope is inserted through the airways and tracheobronchial tree during Bronchoscopy. The Video Processor provides power and processes the images for medical electronic endoscope.

The Flexible Bronchoscope is a sterile single used flexible bronchoscope. The Video Processor 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 Video Processor via the VI circuit. The Video Processor receives video signals from the endoscope, processes the video signals, and outputs the processed video signal to the attached monitor. The video processor also controls the brightness of the LEDs on the endoscope.

The provided text does not contain information about acceptance criteria and a study proving the device meets those criteria from an AI/ML perspective. The document is a 510(k) summary for a Bronchoscope System, which is a medical device, but it does not describe an AI/ML-driven diagnostic or assistive technology.

The "Performance Data" section details various engineering and biological tests conducted for the Bronchoscope System, such as biocompatibility, sterilization, electrical safety, EMC, software verification, and bench performance testing. These tests ensure the device's physical and functional safety and effectiveness, but they do not involve AI/ML performance metrics like sensitivity, specificity, or AUC against a ground truth.

Specifically, there is no mention of the following in the provided text:

1. A table of acceptance criteria and reported device performance for an AI/ML component.
2. Sample size, data provenance, number of experts, adjudication method, MRMC study, standalone performance, or ground truth type related to an AI/ML model for a test set.
3. Sample size or ground truth establishment for a training set of an AI/ML model.

The document explicitly states under "Clinical Testing": "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 further confirms that no studies involving human interpretation augmented or replaced by AI, or studies evaluating AI performance metrics, were part of this submission.

Therefore, I cannot fulfill your request for information related to AI/ML acceptance criteria and study data from this document.

Ask a specific question about this device