Search Results

The Single Use Electrosurgical Knife has been designed to be used with flexible endoscopes to cut tissue using highfrequency current within the digestive tract.

The device is an endoscopic electrosurgical knife for Endoscopic Submucosal Dissection (ESD). The Single Use Electrosurgical Knife is used with flexible endoscopes to cut tissue using high-frequency current within the digestive tract.

It is recommended to use an ERBE VIO-200s electrosurgical unit to supply power to the device.

The provided text focuses on the 510(k) summary for the "Multi-Functional Electrosurgical Knife" and details why it is considered substantially equivalent to existing predicate devices. It does not describe a study that involves acceptance criteria for device performance based on AI/human reader comparison or ground truth established by experts in a diagnostic context. Instead, the performance data section outlines bench and electrical testing to ensure the device performs similarly to predicate devices and meets safety standards for an electrosurgical knife.

Therefore, many of the requested details, such as those related to AI effectiveness, human reader improvement, and expert-adjudicated ground truth, are not applicable to this submission as it doesn't describe such a study.

However, I can extract information related to the performance data and the general approach to demonstrating substantial equivalence for this medical device.

Here's a summary of the information available based on the provided text, addressing the points where information is present or clearly not applicable:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of quantitative acceptance criteria with reported numerical performance values in the format requested (e.g., sensitivity, specificity, AUC). Instead, it lists performance tests conducted to demonstrate equivalence to predicate devices and conformance to standards. The "acceptance criteria" are implicitly that the proposed device performs "without significant difference" compared to predicate devices and meets established safety standards.

2. Sample size used for the test set and the data provenance:

• The document does not specify exact sample sizes for each bench test conducted.
• Data provenance is not explicitly mentioned in terms of country of origin, but the testing was conducted to support a submission to the U.S. FDA. The type of study is bench testing and conformance testing against standards, rather than a clinical trial or study on patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• This question is not applicable. The device is an electrosurgical knife, and its performance evaluation involves physical and electrical bench testing against established engineering and safety standards, and comparison to predicate devices, not interpretation of diagnostic images or data by human experts for ground truth establishment.

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

• This question is not applicable. As in point 3, the evaluation of an electrosurgical knife's performance is based on measurable physical and electrical properties, not on subjective expert consensus or adjudication of diagnostic cases.

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:

• This question is not applicable. The device is an electrosurgical knife, not an AI-powered diagnostic tool. Therefore, no MRMC study involving human readers or AI assistance was performed.

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

• This question is not applicable. The device is a surgical instrument, not an algorithm.

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

• The "ground truth" for this device's performance evaluation is based on established engineering and safety standards (e.g., IEC 60601 series) and the performance characteristics of legally marketed predicate devices. For biocompatibility, it's based on ISO 10993 standards. For tissue cutting and thermal damage, it's based on measurable physical effects demonstrated during bench testing.

8. The sample size for the training set:

• This question is not applicable. The device is a physical electrosurgical knife; it does not involve machine learning or a "training set" of data in the conventional sense.

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

• This question is not applicable for the same reason as point 8.

Ask a specific question about this device

Single use injection needle is to be used in conjunction with an endoscopic injections, such as for the treatment of esophageal and gastric varies and for submucosal dye marking in the GI tract.

The Single Use Injection Needles are sterile, single-use devices. The Single Use Injection Needles can is expected to be used in conjunction with an endoscope to perform endoscopic injections, such as for the treatment of esophageal and gastric varies and for submucosal dye marking in the GI tract. The Single Use Injection Needle is designed to pass through the endoscope's forceps to mark the lesions of the digestive tract and use it for injection. Compatibility with endoscopes, working lengths are 1800mm, 2000mm, 2300mm, and the minimum working clamp channel is φ 2.8 mm.

The provided document is a 510(k) Summary for a Single Use Injection Needle, which is a medical device, not an AI/ML software. Therefore, the questions related to AI/ML software performance criteria, such as "effect size of how much human readers improve with AI vs without AI assistance," "standalone (i.e. algorithm only without human-in-the loop performance)," "training set," and "ground truth for the training set" are not applicable to this submission.

The document describes the non-clinical performance testing conducted to demonstrate the essential performance of the proposed device and confirm it works as intended and is substantially equivalent to a predicate device.

Here's the information extracted from the document regarding the acceptance criteria and study proving the device meets them:

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

The document does not explicitly present a table of "acceptance criteria" side-by-side with "reported device performance" in the format typically seen for AI/ML models (e.g., sensitivity, specificity thresholds). Instead, it lists the types of performance tests conducted and concludes that the results demonstrated substantial equivalence. The predicate device's characteristics serve as the de-facto acceptance criteria for equivalence.

Here's a summary of the non-clinical performance tests and the conclusion of equivalence:

Ask a specific question about this device

The Rescue™ Pulmonary Grasping Forceps are intended to retrieve foreign body and/or excised tissue endoscopically within the upper airways and tracheobronchial tree.

The Rescue™ Pulmonary Grasping Forceps is sterile, single-use devices. The Rescue™ Pulmonary Grasping Forceps can retrieve foreign body and/or excised tissue endoscopically within the upper airways and tracheobronchial tree.

The Rescue™ Pulmonary Grasping Forceps is composed of thumb ring, spool and sliding handle at proximal end and the middle section of the Rescue™ Pulmonary Grasping Forceps is flexible shaft with a working length of 120 cm that connects with the distal end jaw assembly with an inner jaw opening of 4.5 mm. The Rescue™ Pulmonary Grasping Forceps is designed to pass through a 2.0 mm or greater working channel of a bronchoscope.

To operate the device, the user slides the spool back and forth over the handle body to open and close the iaws. The spool simultaneously actuates the pull wire which runs the length of the device and terminates with a connection to the jaws. Using Rescue™ Pulmonary Grasping Forceps the users can grasp excised tissue or foreign body by opening and then closing the jaws. The users can then retrieve the excised tissue or foreign body by pulling the Rescue™ Pulmonary Grasping Forceps with bronchoscope out of patient.

The provided text is a 510(k) Pre-market Notification for a medical device called "Rescue™ Pulmonary Grasping Forceps." This document details the device's characteristics, intended use, and performance data to establish substantial equivalence to a predicate device.

However, the document does not contain the information requested regarding acceptance criteria and study details for an AI-enabled medical device. The "Rescue™ Pulmonary Grasping Forceps" is a physical medical instrument, and the performance data described relates to its physical and material properties, not an AI algorithm.

Therefore, I cannot provide the requested information. The document does not describe:

• Acceptance criteria for an AI algorithm.
• Device performance in terms of AI metrics (e.g., sensitivity, specificity).
• Sample sizes for test sets in an AI study.
• Data provenance for AI training or testing.
• Number or qualifications of experts for AI ground truth.
• Adjudication methods for AI test sets.
• MRMC comparative effectiveness study for AI.
• Standalone performance for an AI algorithm.
• Type of ground truth for an AI algorithm.
• Sample size or ground truth establishment for an AI training set.

Ask a specific question about this device

The device is intended for endoscopic removal of biliary stones. The device is supplied sterile and intended for single use only.

The Stone Retrieval Balloon Catheter is comprised of a latex balloon mounted at the distal end of a Pebax catheter with three internal lumens. For some specifications, the balloon can be inflated to 8.5mm, 12mm, 15mm and 18mm only. But for some specifications, the balloon can be inflated to three sizes, 8.5mm, 12mm diameters, or 12mm, 15mm and 18mm. Radiopaque bands placed at the distal and proximal ends of the balloon provide fluoroscopic visualization of the balloon location. The catheter length is 2000mm with an outer diameter of 2.3mm. The three lumens correspond to a balloon inflation port, a wire guide port and an injection port. A stopcock is included at the proximal end of the balloon inflation port to control air movement into or out of the balloon. For rapid exchange models, there is a small hole on the catheter which is about 200mm far away from the distal end. It is used to insert the guide wire rapidly. EO sterilization and use for single use only.

This looks like a 510(k) summary for a medical device called a "Stone Retrieval Balloon Catheter." It describes the device, its intended use, and compares it to a predicate device to establish substantial equivalence.

However, the document does not contain the information you requested about acceptance criteria and a study proving the device meets those criteria, specifically:

• A table of acceptance criteria and reported device performance.
• Sample size and data provenance for a test set.
• Number and qualifications of experts for ground truth.
• Adjudication method.
• MRMC comparative effectiveness study results.
• Standalone algorithm performance.
• Type of ground truth used.
• Sample size and ground truth establishment for a training set.

The document explicitly states: "No clinical study is included in this submission." This means there isn't a study proving the device's clinical performance against acceptance criteria in the way you've described for AI/diagnostic devices.

The "Non-Clinical Performance Testing" section lists various standards (e.g., ISO, ASTM, USP) that the device complies with, but it does not provide specific acceptance criteria (e.g., "sensitivity > 90%") or the results of meeting those criteria in the context of an AI-driven or diagnostic device study. The non-clinical tests are primarily focused on material properties, biocompatibility, sterilization, and packaging integrity, which are standard for this type of medical device.

Therefore, I cannot fulfill your request for these particular details based on the provided text, as this document pertains to a medical device clearance application that relies on demonstrating substantial equivalence to a predicate device rather than a clinical performance study with AI components.

Ask a specific question about this device

Single Use Rotatable and Repositionable Hemoclip is indicated for clip placement within the Gastrointestinal (GI) tract for the purpose of: 1) Endoscopic marking 2) Hemostasis for: Mucosal/sub-mucosal defects

The proposed device is a sterile, single-use endoscopic clipping device. It is consisted of two main components: the delivery system and the clip. The delivery system is available in three different working length. The clip is deployed from the delivery system during use. The hemoclip jaws can be opened and closed up to five times prior to deployment, aiding in repositioning of the clip at the lesion site.

The provided document is an FDA 510(k) premarket notification for a medical device called the "Single Use Rotatable and Repositionable Hemoclip." This type of submission aims to demonstrate that a new device is "substantially equivalent" (SE) to a legally marketed predicate device, rather than proving its safety and effectiveness through extensive clinical trials as would be required for a Premarket Approval (PMA).

As such, the document does not describe a study that proves the device meets specific acceptance criteria in the manner of a clinical trial for an AI/algorithm-based device. Instead, it focuses on demonstrating equivalence through non-clinical testing and comparison to predicate devices.

Therefore, many of the requested details about acceptance criteria, test set sizes, expert involvement, and ground truth establishment (which are typical for AI/algorithm performance studies) are not applicable to this 510(k) submission.

Here's a breakdown of the information that is available and what is not for this specific product, structured to address your points as much as possible:

Acceptance Criteria and Device Performance (Not applicable in the context of an algorithm or AI performance)

This device is a mechanical medical instrument (hemoclip), not an AI or algorithm-based device. Therefore, the "acceptance criteria" here refer to meeting design specifications and demonstrating performance comparable to predicate devices through bench testing (mechanical and biocompatibility). There are no performance metrics like sensitivity, specificity, or accuracy for an AI.

Table of Acceptance Criteria and Reported Device Performance (as per non-clinical testing for a mechanical device):

Study to Prove Device Meets Acceptance Criteria

The "study" refers to the non-clinical testing described, not a clinical trial or AI performance study.

1. Sample size used for the test set and the data provenance:

   • Sample Size: Not explicitly stated numerically for each non-clinical test (e.g., how many clips were tested for clamping strength). However, the general statement "Performance test was performed on both the proposed device and predicate device" implies a sufficient number of samples were tested to robustly compare performance and draw conclusions of no significant difference.
   • Data Provenance: The tests were conducted internally by Anrei Medical (Hangzhou) Co., Ltd. in the People's Republic of China, as indicated by the sponsor's identification. This is non-clinical laboratory data.
   • Retrospective or Prospective: These are laboratory bench tests conducted prospectively to gather data for the submission.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Not Applicable. This is a mechanical device. Ground truth, in the context of an AI device, refers to expert labeling of medical images or other data. For a mechanical device, "ground truth" is measured physical properties or biological responses to materials (e.g., measuring clamping force, observing cell growth in cytotoxicity tests, or confirming sterility). These are objective measurements against established standards, not expert consensus on interpretations.

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

   • Not Applicable. Adjudication methods are used in studies involving human interpretation or subjective assessments, typically for AI/imaging devices. For mechanical performance and biocompatibility tests, results are derived from objective measurements and laboratory protocols, not human adjudication between different interpretations.

4. 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:

   • No. This is a mechanical device, not an AI or imaging device. Therefore, MRMC studies are not relevant.

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

   • Not Applicable. As a mechanical device, there is no "algorithm only" performance.

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

   • Objective Measurements Against Standards. The "ground truth" for this device's performance is established by objective physical and biological tests according to recognized international and national standards (e.g., ISO, ASTM, USP). For example:
     • Biocompatibility: Established biological reactions (e.g., no cytotoxicity via cell culture tests).
     • Mechanical Properties: Measured physical forces (e.g., tensile strength in Newtons, clamping force).
     • Sterility: Absence of microbial growth, reaching a specific SAL.
     • Shelf Life: Data demonstrating stability of materials/performance over time.

7. The sample size for the training set:

   • Not Applicable. This is a mechanical device, not an AI requiring a "training set."

8. How the ground truth for the training set was established:

   • Not Applicable. There is no training set for this type of device.

Ask a specific question about this device

The Single Use Endoscope Valves Set are used to fit to multiple endoscope working channels/ports to enable an endoscope operator control the function of the working channels/ports and prevent retrograde flow of the fluids, gases, and other materials.

The Air/Water Valve is intended to be used to control the air/water function on an endoscope during a GI endoscopic procedure.

The Suction Valve is intended to be used to control the suction on an endoscope during a GI endoscopic procedure.

The Biopsy Valve is intended to accommodate various sizes of endoscopic accessory instruments while still providing a seal around the instrument channel inlet.

The Single Use Endoscope Valves Set collects three types of valve products into one package unit, and which are used to fit to multiple endoscope working channels/ports to enable an endoscope operator control the function of the working channels/ports and prevent retrograde flow of the fluids, gases, and other materials.

This is single-use device and supplied sterile.

There are three main components included, which are Air/Water Valve, Suction Valve and Biopsy Valve.

The Air/Water Valve is intended to be used to control the air/water function on an endoscope during a GI endoscopic procedure.

The Suction Valve is intended to be used to control the suction on an endoscope during a GI endoscopic procedure.

The Biopsy Valve is intended to accommodate various sizes of endoscopic accessory instruments while still providing a seal around the instrument channel inlet.

There are three models for fitting to varied endoscopes as AMH-EV-01; AMH-EV-02; AMH-EV-03. The main differences between models are physical size of components for varied endoscopes interface, but they share same indication for use, materials and components form.

This document is a 510(k) Premarket Notification from Anrei Medical (Hangzhou) Co., Ltd. for their "Single Use Endoscope Valves Set." It is a submission to the FDA seeking to demonstrate substantial equivalence to previously cleared predicate devices.

Based on the provided document, there is no clinical study or human subject testing described. The document explicitly states: "No clinical study is included in this submission." (Page 6)

Therefore, it is impossible to answer questions related to acceptance criteria proved by a study involving human subjects or AI performance. The document focuses on demonstrating substantial equivalence through non-clinical testing and comparison to predicate devices.

However, I can extract information regarding the non-clinical acceptance criteria and "performance" as it relates to demonstrating substantial equivalence for THIS device.

Acceptance Criteria and Reported Device Performance (Non-Clinical)

Since this submission is a 510(k) for a medical device (endoscope valves), the "acceptance criteria" and "performance" are primarily related to demonstrating substantial equivalence to predicate devices through a series of non-clinical tests, rather than clinical efficacy involving human patients or complex AI algorithm performance.

The document discusses various non-clinical tests conducted to prove the device meets design specifications and is substantially equivalent.

1. Table of Non-Clinical Acceptance Criteria and Reported Device Performance:

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

• Sample Size: The document does not specify exact sample sizes for each non-clinical test. It generally states that "Non clinical tests were conducted to verify..." without providing the number of units tested.
• Data Provenance: The tests were conducted by Anrei Medical (Hangzhou) Co., Ltd. in China. The data is retrospective in the sense that the testing was completed prior to the 510(k) submission.

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

• Not Applicable. This is a non-clinical device performance and substantial equivalence study for a physical device, not an AI or diagnostic imaging study requiring expert radiologists or clinicians to establish ground truth for a test set. The "ground truth" for these tests are the objective measurements against established engineering and biological standards.

4. Adjudication Method for the Test Set:

• Not Applicable. As above, this is not a study requiring human interpretation or multi-reader adjudication. The results are objective measurements from laboratory tests.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

• No. This type of study is typically performed for diagnostic devices (e.g., AI algorithms for image interpretation) to compare human performance with and without AI assistance. This submission is for a physical endoscope accessory, not an AI system.

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

• No. This question is also relevant to AI algorithms. This submission is for a physical medical device.

7. The Type of Ground Truth Used:

• Objective Test Standards and Predicate Device Performance. The "ground truth" for the non-clinical tests is established by recognized international standards (ISO, ASTM, DIN, USP) for biocompatibility, sterility, packaging, and shelf-life, and by direct comparison of the proposed device's functional performance against the performance of the legally marketed predicate devices.

8. The Sample Size for the Training Set:

• Not Applicable. This question applies to machine learning models, not physical medical devices undergoing non-clinical testing for substantial equivalence.

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

• Not Applicable. As above, this pertains to machine learning models.

Ask a specific question about this device