Search Results

The Entuit PEG is intended for percutaneous endoscopic gastrostomy placement to provide enteral nutrition and/or medication to patients requiring nutritional support, and gastric decompression. This device is indicated for adult use only.

The Entuit PEGJ is intended for percutaneous endoscopic placement to provide enteral nutrition and/or medication to patients requiring nutritional support, and gastric decompression. This device is indicated for adult use only.

The Entuit PEG (subject device) includes a silicone enteral feeding tube (PEG tube) available in 24 Fr or 20 Fr, with site preparation components, introduction components, adapters, and connectors. The device is supplied sterile and is intended for single use in adults. Entuit PEGJ (subject device) includes a polyurethane enteral feeding tube (PEGJ tube) that is available in 12 Fr or 9 Fr. The Entuit PEGJ tube is for direct access to the jejunum. The 12 Fr PEGJ tube is designed to be inserted through the 24 Fr PEG tube and the 9 Fr PEGJ tube is designed to be inserted through the 20 Fr PEG tube such that the distal end extends into the jejunum and the proximal end extends out of the existing PEG tube.

There are several feeding adapters for use with the PEG and PEGJ tubes. The PEG kit has one feeding adapter that is ENFit compatible and two feeding adapters that are compatible with Christmas tree/slip tip giving sets and syringes (Non-ENFit). The PEGJ tubes are also available with either ENFit compatible or Christmas tree compatible feeding adapters (Non-ENFit).

The Entuit PEG is provided as a kit to facilitate either push or pull techniques of placement. In addition, the Entuit PEG kits are available in standard, safety, and international versions. The Entuit PEGJ is sold as a separate kit and available in standard versions.

I'm sorry, but this document contains a letter from the FDA regarding a 510(k) premarket notification for a medical device. It discusses the device's intended use, comparison to a predicate device, and a summary of non-clinical testing.

However, the document does not contain any information about acceptance criteria, device performance results, sample sizes for test or training sets, data provenance, the number or qualifications of experts, adjudication methods, MRMC studies, standalone algorithm performance, or ground truth establishment.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets the acceptance criteria, as the necessary information is not present in the provided text.

Ask a specific question about this device

This device is intended to provide short-term enteral access for delivery of nutrition and/or medications to small bowel. This device is indicated for adult use only.

The subject device is packaged with: a nasal feeding tube, a nasal transfer tube, a wire guide, and two feeding adapters. The single lumen nasal feeding tube is composed of radiopaque polyvinyl chloride with ink markings that are endoscopically visible and assist with tube placement. The nasal feeding tube is available in two diameters, 8 Fr and 10 Fr. with a length of 240 cm and 10 feeding ports. The nasal transfer tube has a diameter of 14 Fr, is composed of clear PVC and is 20 inches in length. The wire guide is stainless steel coated with polytetrafluoroethylene (PTFE) and is 250 cm in length. Two feeding adapters are provided; one as a friction fit version and one ENFit compatible.

This document is a 510(k) Premarket Notification from the FDA for the Entuit Nasal Jejunal Feeding Tube. It focuses on establishing substantial equivalence to a predicate device, primarily due to the addition of an ENFit connector. The document does not provide information about clinical studies with acceptance criteria for device performance in the context of diagnostic accuracy, AI assistance, or human reader performance.

Therefore, I cannot populate the requested tables and information segments because they are related to clinical performance studies, often seen with AI/ML-based devices or diagnostic tools, which are not applicable to the information provided in this 510(k) summary for a medical device like a feeding tube.

The "Performance Data" section explicitly states: "Performance testing consisting of non-clinical bench testing demonstrates the subject device meets the performance requirements to fulfill the intended use." and "The following non-clinical testing was conducted to demonstrate the performance of the subject device and confirms that the subject device performs as intended: ENFit Connector Testing per ISO 80369-3: 2016 and Design Verification of Feeding Adapters."

This indicates that the evaluation was based on bench testing for physical and mechanical properties, not clinical trials impacting accuracy or human performance.

Ask a specific question about this device

The COOK Hemospray device is intended for hemostasis of non-variceal bleeds in the GI (gastrointestinal) tract. It is for prescription use only.

Hemospray is an inert, bentonite powder developed for endoscopic hemostasis. The powder is delivered by use of a carbon dioxide powered delivery system and through a catheter inserted through the working channel of an endoscope which provides access to the bleed. Each device contains approximately 20g of powder.

This document is a 510(k) Premarket Notification for a medical device called the Hemospray Endoscopic Hemostat. The submission primarily addresses a minor design change to an existing predicate device to correct a failure mode related to the activation knob. Because the changes are focused on a revised manufacturing process and an improved safety feature (the activation knob's tensile strength) rather than a change in the therapeutic mechanism or intended use, many of the typical acceptance criteria for AI/ML-based devices, such as those related to diagnostic performance or multi-reader studies, are not applicable here.

Therefore, I cannot populate the table and sections as requested for an AI/ML device's acceptance criteria and study proving performance. This document concerns a physical medical device and primarily focuses on mechanical performance and safety, not on the performance of a software algorithm.

However, I can extract information related to the device's functional acceptance criteria as demonstrated through bench testing for the design modification.

Here's how I can interpret and present the available information in the context of your request, focusing on the specific modification made to the physical device:

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

Note: The acceptance criteria and performance data provided relate to the mechanical integrity of the modified activation knob, not to an AI/ML algorithm's diagnostic or therapeutic performance.

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

• Sample Size: Not explicitly stated as a number of units, but "All tested samples" implies a complete test of the sample set prepared.
• Data Provenance: The testing was "bench testing" conducted by the manufacturer, Wilson-Cook Medical, Inc., located in Winston-Salem, North Carolina. This is prospective testing performed for the purpose of this 510(k) submission.

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

• Not applicable. This study is not evaluating a diagnostic or AI/ML device requiring clinical expert ground truth for image interpretation or diagnosis. It focuses on the mechanical performance of a device component. The "ground truth" for the new design specification was established based on a human factors study evaluating the maximum force a user could apply.

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

• Not applicable. No adjudication method is described, as the evaluation is based on objective physical measurements (tensile strength) against a defined design specification, rather than subjective interpretations.

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. This study is not an MRMC study and does not involve AI assistance. It evaluates a mechanical design change to a physical hemostatic device.

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

• Not applicable. This study does not involve an algorithm.

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

• The "ground truth" for the new tensile strength design specification was established based on a human factors study that evaluated the maximum force a user could apply to the red activation knob during use. The success of the device was then determined by objective mechanical testing to confirm that the component met this established design specification.

8. The sample size for the training set

• Not applicable. This is not an AI/ML device; therefore, there is no "training set." The human factors study provided data to establish the design specification.

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

• Not applicable. As above, no training set for an AI/ML algorithm. The design specification (which could be considered a form of "ground truth" for the mechanical test) was established through a "human factors study that evaluated the maximum force a user could apply to the red activation knob during use."

Ask a specific question about this device

This device is used for endoscopic removal of stones in the biliary system and for contrast injection.

The subject device is composed of a latex balloon mounted at the distal end of a nylon triple lumen catheter. The balloon can be inflated to four sizes: 8.5 mm, 10 mm, and 15 mm diameters. Radiopaque bands are placed on the catheter to provide fluoroscopic visualization of the catheter and balloon location. The nylon catheter length is 200 cm with a diameter of 6.6 Fr. There is an injection port on the catheter either above the balloon or below the balloon depending on the device model. The catheter also has black ink markings for direct visualization.

This document describes the regulatory clearance (K200247) of the "Fusion Quattro Extraction Balloon" by Wilson-Cook Medical, Inc. It does NOT contain information about acceptance criteria or a study proving the device meets said criteria in the way typically expected for an AI/ML medical device.

The device described is a physical medical device (a balloon catheter for stone extraction), not an AI/ML algorithm. Therefore, many of the requested categories like sample size for test/training sets, data provenance, expert adjudication, MRMC studies, and standalone algorithm performance are not applicable.

Here's a breakdown based on the provided text, highlighting what is (and isn't) present:

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

The document mentions "performance requirements" but does not detail specific quantitative acceptance criteria or their corresponding reported values in a table. It generally states that the device "met the performance requirements" and "will function as intended."

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

Not applicable. This is a physical device undergoing bench testing, not a clinical study with a patient test set or data provenance in the typical sense for AI/ML. The "testing" refers to non-clinical bench testing.

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):

Not applicable. "Ground truth" in the context of expert consensus or pathology is not relevant for bench testing of a physical device.

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

Not applicable. No expert adjudication process is described for this type of device testing.

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. This is a physical device, not an AI system.

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

Not applicable. This is a physical device, not an algorithm.

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

Not applicable. The "truth" for bench testing of this device would be established by engineering specifications and measurement standards, not expert consensus, pathology, or outcomes data.

8. The sample size for the training set:

Not applicable. This is a physical device, not an AI algorithm requiring a training set.

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

Not applicable. This is a physical device, not an AI algorithm.

Summary of available information as it pertains to the request, re-framed for a physical device:

The document describes a 510(k) premarket notification for a medical device called the "Fusion Quattro Extraction Balloon." The clearance is based on substantial equivalence to a predicate device (Fusion Quattro Extraction Balloon XL K063677). The modification involved a change in balloon inflation diameters (8.5 mm, 10 mm, 12 mm, and 15 mm).

Performance Data and Testing:

• Type of Study: Non-clinical bench testing.
• Purpose: To demonstrate the subject device met performance requirements and functions as intended, and does not raise new questions of safety or effectiveness compared to the predicate.
• Tests Conducted:
  • Design Verification Testing
  • Dimensional Verification
  • Functional Testing
  • Fluoroscopic Visibility

The core statement is: "Performance testing consisting of non-clinical bench testing demonstrates the subject device met the performance requirements to fulfill the intended use." However, the document does not provide the specific quantitative "acceptance criteria" or the "reported device performance" values for each test. It simply states that they were met.

Ask a specific question about this device

The TeslaTome Bipolar Sphincterotome is intended for cannulation of the ductal system and sphincterotomy. If preloaded, also aids in bridging difficult strictures during ERCP (endoscopic retrograde cholangiopancreatography). Also indicated for sphincterotome-aided, wire-guided selective cannulation of the biliary ducts.

The Tesla Bipolar Active Cord is used to connect the TeslaTome to compatible electrosurgical generators.

The TeslaTome Bipolar Sphincterotome is an endoscopic electrosurgical accessory composed of a single stainless steel drive wire within a triple-lumen polymer catheter. The proximal end of the catheter/wire assembly terminates in a handle, held by the physician or assistant during ERCP procedures and fulfills three (3) functions: connection to an electrosurgical generator, injection of diluted contrast, introduction of an endoscopic wire guide and manipulation of the cutting wire. The distal end contains a stainless steel cutting wire and ink and band markings. Half of the cutting wire is insulated with a non-conductive polymer coating. The device allows for short-wire, distal wire guide exchange through the separation of a weakened wall in the wire guide lumen that separates with manual control. The device is also compatible with traditional long wire guides. The TeslaTome Bipolar Sphincterotome is available in eight model numbers reflecting cutting wire length of 20 or 25 mm, and a .035" Acrobat II wire guide in either 260 cm or 450 cm length, and an optional rotatable handle.

The Tesla Bipolar Active Cord (TESLA-ACU-B) is used to facilitate connection to an Electrosurgical generator (ESU). It uses a magnetic connection at the sphincterotome alignment but facilitates connection with ERBE generators on the distal end with conventional ESU-compatible plugs. The Active cord is non-sterile and reusable.

The provided text describes a 510(k) premarket notification for the TeslaTome Bipolar Sphincterotome and Tesla Bipolar Active Cord. However, it does not contain information about acceptance criteria or a study proving the device meets specific performance criteria in a way that would require a table of acceptance criteria and reported device performance.

The document focuses on demonstrating substantial equivalence to predicate devices rather than proving specific numerical performance metrics against predefined acceptance criteria for the new device itself. The "Discussion of Performance Tests and Test Results" section outlines various tests conducted, but these are verification tests to ensure design inputs are met and the device performs as intended, not a comparative study with quantitative performance metrics and acceptance thresholds.

Given the information provided, it's not possible to populate a table of acceptance criteria and reported device performance, nor can I answer questions 2 through 9, as they pertain to clinical study design and ground truth establishment, which are not detailed in this 510(k) summary.

Therefore, I must state that the requested information (a table of acceptance criteria and reported device performance, sample size, data provenance, expert details, adjudication method, MRMC study, standalone performance, type of ground truth, training set size, and ground truth establishment for the training set) is not present in the provided text.

The document primarily focuses on:

• Device Description: What the device is and how it functions.
• Intended Use: The medical purpose of the device.
• Substantial Equivalence Argument: Comparing the new device to previously cleared predicate devices, highlighting similarities in design, materials, and intended use, and explaining any minor differences.
• Performance Tests: A list of conducted tests (e.g., mechanical, electrical, biocompatibility, simulated use, cleaning validation) to ensure the device meets its design specifications and is safe, but without presenting quantitative acceptance criteria or detailed results of these tests that would fit into the requested table format. These tests are internal verification activities rather than external clinical performance studies with defined acceptance metrics for a specific clinical task.

Ask a specific question about this device

This device is used for endoscopic injection into gastrointestinal mucosa. The intended population is adult use only.

The Gastrointestinal Injection Needles (subject devices) are sterile, single use devices that consist of a needle on an inner catheter fitted inside an outer catheter sheath featuring a luer slip/adjustment wheel handle with either a plastic or metal hub used as an injection port at the proximal end of the device. The devices are compatible with endoscopes with a minimum accessory channel of 2.0 mm or 2.8 mm. The Gastrointestinal Injection Needles have catheters which ranges in length from 195 to 315 cm, outer diameters of 5.4 FR and 6.9 FR, and needle gauges of 21, 23 and 25. Some configurations of the Gastrointestinal Injection Needles include ink marks at the distal end of the device to aid endoscopic visualization.

The provided text describes the regulatory clearance for "Gastrointestinal Injection Needles (VIN, LDVI, DVI and MHI)" and primarily focuses on demonstrating substantial equivalence to a predicate device through non-clinical bench testing. It does not contain information about an AI/ML device or its acceptance criteria and a study proving it.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance.
2. Sample size used for the test set and data provenance.
3. Number of experts used to establish ground truth and their qualifications.
4. Adjudication method for the test set.
5. MRMC comparative effectiveness study or its effect size.
6. Standalone performance study.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

The document states that "non-clinical bench testing demonstrates that the Gastrointestinal Injection Needles meet the performance requirements to fulfill the intended use of the device" and lists the following tests:

• Functional Testing
• Tensile Strength Testing
• Needle Verification and Validation Testing
• Shelf Life Testing
• Packaging Validation
• Biocompatibility testing (in accordance with ISO 10993-1)

However, it does not provide specific acceptance criteria or detailed results from these tests. It only concludes that the testing "confirmed that the subject device performs as intended" and that modifications "do not raise any new questions of safety or effectiveness."

Ask a specific question about this device

Used for collection of cells in the biliary system.

The subject devices, the Fusion Cytology Brush and CytoMax II Double Lumen Cytology Brush, consist of a nylon brush on a stainless-steel drive wire with a stainless-steel tip, a double lumen catheter with ink markings, radiopaque markers, wire guide access via a wire guide hub or and IDE port, a detachable extension line with a luer lock for optional flushing of the wire guide hub and a pin-vise handle.

The Fusion Cytology Brush and CytoMax II Double Lumen Cytology Brushes are used by passing the device through an endoscope over a prepositioned wire guide to a target location. The cytology brush is located at the distal end (patient contacting) of the device with the pin vise handle located at the proximal end (non-patient contacting). The handle is actuated by pushing the pin vise handle forward to extend the cytology brush and then pulling backward to retract the brush.

The provided text is a 510(k) summary for the Fusion Cytology Brush and CytoMax II Double Lumen Cytology Brush. This document focuses on demonstrating substantial equivalence to previously cleared predicate devices after a design modification. It does not describe an AI medical device, nor does it contain information about acceptance criteria for an AI model, a study proving an AI device meets acceptance criteria, sample sizes for test or training sets for AI, expert involvement for AI ground truth, or MRMC studies.

Therefore, I cannot fulfill your request for information about acceptance criteria and studies related to an AI device based on this input.

The document discusses non-clinical bench testing to ensure the modified devices meet performance requirements and function as intended, specifically:

• Tensile Strength Testing: Assesses the strength of the device.
• Tensile Strength of Handle: Evaluates the handle's ability to withstand pulling forces.

These tests are to ensure the physical integrity and functionality of the cytology brushes themselves, not the performance of an AI algorithm.

Ask a specific question about this device

The AcuSnare Polypectomy Snare - Duckbill (ASDB) device is used endoscopically in the removal and cauterization of sessile polyps and pedunculated polyps from within the gastrointestinal tract.

The AcuSnare Polypectomy Snare - Duckbill (ASDB) is a sterile, single use device compatible with the accessory channel of endoscope. This type endoscopic polypectomy device is designed to connect to an electrosurgical unit via an active cord accessory and the drive cable delivers energy through the snare head to cut and/or cauterize tissue as described in the instructions for use. The device consists of a handle, sheath, drive cable and wire loop snare head. The sheath is comprised of polytetrafluoroethylene (PTFE) and is offered in 7 Fr. (2.3 mm) diameter and 240 cm length models. The snare head is available in the shape of a duckbill configuration and offered in a 15 mm or 25 mm width. The stainless-steel drive cable and snare head pass through the sheath and the three ring (polycarbonate) handle allows the user to extend and retract the snare through the distal tip of the sheath.

The provided text describes a 510(k) premarket notification for a medical device called the AcuSnare Polypectomy Snare - Duckbill (ASDB). This is for a device intended for polypectomy (removal of polyps) during endoscopy. The document is a regulatory submission to the FDA, demonstrating substantial equivalence to a predicate device.

Here's an analysis of the acceptance criteria and the study as described in the provided text:

Key Takeaways from the Document:

• This is a Special 510(k) submission, indicating minor modifications to an already cleared device (AcuSnare Polypectomy Snare - K173673).
• The primary change is the addition of a new duckbill shape configuration and associated cannula components.
• The manufacturer claims this change does not alter the method of operation or intended use of the device.
• Performance Data: The document states that a Risk Analysis (DFMECA) was completed, and Design Verification and/or Validation testing was performed to address the impact of modifications. The conclusion is that these tests provide "reasonable assurance that the modifications to the device do not raise any new questions of safety or effectiveness and demonstrate that the AcuSnare Polypectomy Snare - Duckbill (ASDB) meets the performance requirements to fulfill the intended use of the device."

Important Note: The provided text does not contain detailed information about specific acceptance criteria, quantitative performance metrics, or a formal clinical study with a test set, ground truth, or expert review. The focus of this 510(k) is on demonstrating substantial equivalence through design validation and verification of the modifications rather than a de novo extensive performance study.

Given the information, here's an attempt to answer your questions, highlighting where specific details are not provided in the document:

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

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 does not specify a sample size for a clinical "test set" in the context of human patients or a specific dataset.
   • The "testing" mentioned refers to design verification and validation testing. This typically involves laboratory-based tests on device samples, not patient data.
   • Provenance is not applicable as this describes device design testing, not clinical data analysis.
   • The submission is a regulatory filing, not a peer-reviewed research paper detailing a study's methodology.

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)

   • This information is not applicable and not provided. As explained above, the submission describes design verification and validation testing of the device itself, not a study involving human interpretation of data where expert ground truth would be established.

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

   • This information is not applicable and not provided. Adjudication methods are relevant for studies where multiple human readers or algorithms interpret medical images or data against a consensus ground truth. This submission focuses on engineering and design testing.

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

   • No, an MRMC comparative effectiveness study was not done (or at least, not reported in this document).
   • This device is a physical medical instrument (polypectomy snare), not an AI or imaging-based diagnostic tool. Therefore, a study on human reader improvement with AI assistance is entirely irrelevant to this device.

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

   • No, this is not applicable. This is a physical device, not an algorithm.

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

   • For the "design verification and validation testing," the "ground truth" would be established against engineering specifications, industry standards, and the performance characteristics of the predicate device. For instance, a test might verify that the snare loop can open to a specified diameter, or that it can effectively cut a tissue phantom without breaking, matching the performance of the predicate. This is functional and safety performance, not clinical ground truth.

8. The sample size for the training set

   • This information is not applicable and not provided. Training sets are used for machine learning algorithms. This document solely concerns a physical medical device.

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

   • This information is not applicable and not provided.

In summary, the provided document is a regulatory submission for a minor device modification. It details the device, its intended use, and states that design verification and validation testing were conducted to confirm that the modifications do not raise new safety or effectiveness concerns and that the device meets performance requirements equivalent to the predicate. It does not provide details on clinical study methodologies or quantitative performance metrics typically found in clinical trials or AI/diagnostic device studies.

Ask a specific question about this device

The Entuit PEG is intended for percutaneous endoscopic gastrostomy placement to provide enteral nutrition and/or medication to patients requiring nutritional support, and gastric decompression. This device is indicated for adult use only.

The Entuit PEGJ is intended for percutaneous endoscopic placement to provide enteral nutrition and/or medication to patients requiring nutritional support, and gastric decompression. This device is indicated for adult use only.

The Entuit PEG includes a silicone enteral feeding tube (PEG tube) available in 24 Fr or 20 Fr, with site preparation components, introduction components, adapters. The PEG tube is supplied sterile and is intended for single use in adults. Entuit PEGJ includes a polyurethane enteral feeding tube (PEGJ tube) that is available in 12 Fr or 9 Fr. The Entuit PEGJ tube is available for direct access to the jejunum. The 12 Fr PEGJ tube is designed to be inserted through the 24 Fr PEG tube and the 9 Fr tube is designed to be inserted through the 20 Fr PEG tube such that the distal end extends into the jejunum and the proximal end extends out of the existing PEG tube.

There are several feeding adapters for use with the PEG and PEGJ tubes. The PEG kit has two feeding adapters that are ENF it compatible and two feeding adapters that are compatible with Christmas tree or slip tip giving sets and syringes (Non-ENFit). The PEGJ tubes are available with either ENFit compatible or Christmas tree compatible feeding adapters (Non-ENFit). The Entuit PEG is provided as a kit to facilitate either push or pull techniques of placement. In addition, the Entuit PEG are available in standard, safety, and international versions. The PEGJ tubes are sold as a separate kit.

This document is an FDA 510(k) clearance letter for the Entuit PEG and Entuit PEGJ devices. It is a review of the substantial equivalence of these devices to a previously marketed predicate device. This document describes the device itself and its intended use, along with non-clinical testing conducted to demonstrate performance.

However, this document does NOT contain information about an AI/ML-driven medical device, nor does it detail a study involving human readers or the establishment of ground truth for AI model training or testing.

Therefore, I cannot provide the requested information, which pertains to the acceptance criteria and study proving an AI/ML device meets those criteria. The provided text does not describe an AI medical device or its validation.

Ask a specific question about this device

Used for collection of cells in the biliary system.

The Fusion® Cytology Brush and CytoMax II® Double Lumen Cytology Brush (subject devices) represent modifications made to the Wilson-Cook Double Lumen Biliary Cytology Brush and Fusion® Cytology Brush (predicate devices) cleared to market via 510(k) K171573 by Wilson-Cook Medical, Inc.

The Fusion® Cytology Brush and CytoMax II® Double Lumen Cytology Brushes consist of a nylon brush on a stainless-steel drive wire with a stainless-steel tip, a double lumen catheter with ink markings, radiopaque markers, wire guide access via a wire guide hub or an IDE port, a detachable extension line with a leur lock for optional flushing of the wire guide hub and a pinvise handle.

The Fusion® Cytology Brush and CytoMax II® Double Lumen Cytology Brushes are used by passing the device through an endoscope over a prepositioned wire guide to a target location. The cytology brush is located at the distal end (patient contacting) of the device with the pin vise handle located at the proximal end (non-patient contacting). The handle is actuated by pushing the pin vise handle forward to extend the cytology brush and then pulling backward to retract the brush.

This document is a 510(k) summary for a medical device (Fusion Cytology Brush, CytoMax II Double Lumen Cytology Brush) and primarily focuses on demonstrating substantial equivalence to a predicate device based on modifications and non-clinical bench testing. It does not present a clinical study or performance data related to AI/algorithm performance, which is what your request is specifically asking for regarding acceptance criteria, training/test sets, ground truth establishment, or human reader improvement with AI assistance.

Therefore, I cannot provide the information requested in your prompt based on the provided text, as the document does not contain any details about:

1. Acceptance criteria and reported device performance (in the context of an AI/algorithm). The "performance data" mentioned here refers to mechanical and material properties, not clinical diagnostic accuracy or AI metrics.
2. Sample sizes used for a test set or data provenance for an AI/algorithm.
3. Number of experts and their qualifications for establishing ground truth for an AI/algorithm.
4. Adjudication method for a test set for an AI/algorithm.
5. Multi-reader multi-case (MRMC) comparative effectiveness study information.
6. Standalone (algorithm-only) performance.
7. Type of ground truth used for an AI/algorithm.
8. Sample size for the training set for an AI/algorithm.
9. How ground truth for the training set was established for an AI/algorithm.

The document states: "Performance testing consisting of non-clinical bench testing that demonstrates the subject devices met the performance requirements to fulfill their intended use. This testing provides reasonable assurance that the subject devices will function as intended. The subject devices do not raise new questions of safety or effectiveness as compared to the predicate devices." This highlights that the evaluation was primarily focused on bench testing for mechanical and material properties, not clinical performance metrics typical for AI-powered diagnostics.

Ask a specific question about this device