Search Results

The EndoFix™Tissue Fixation System is an endoscopic tissue approximation system intended for anchoring the gallbladder to the stomach or duodenum to aid placement of a luminal apposing metal stent (LAMS) for EUS-guided gallbladder drainage.

The EndoFix™ Tissue Fixation System (TFS) is an endoscopic (through the scope) tissue approximation device consisting of two main components:

1. EndoFix Tissue Fixation Device – Enables the approximation of soft tissue in the gastrointestinal (GI) tract using a suture-based implant delivered through an 18 gauge echogenic needle.
2. Secure Suture Locking Device – Secures the implant assembly with an implant grade suture lock and cuts the suture once approximation is complete.

The EndoFix TFS is designed to place an implant for endoscopic tissue approximation to anchor the gallbladder to the stomach or duodenum to aid placement of a luminal metal apposing stent (LAMS). During use, the EndoFix Tissue Fixation Device is advanced through a ≥3.2 mm working channel of a commercially available echoendoscope (EUS). Under ultrasound guidance, the EndoFix TFS needle is advanced through the target tissues and the implant subassembly is deployed to approximate the luminal tissues (either transgastric or transduodenal based on clinical requirements). With applied suture tension, a Suture Lock is deployed to secure the tissues using the Secure Suture Locking Device. The implant subassembly and Suture Lock are considered permanent implants.

Each of the respective delivery systems used to deliver the implant assembly/Suture Lock are short term contact devices.

This FDA 510(k) clearance letter for the EndoFix™ Tissue Fixation System does not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and a study proving those criteria are met. This document primarily focuses on establishing substantial equivalence to predicate devices for regulatory clearance.

Specifically, it does not include:

• A table of acceptance criteria with reported device performance metrics (e.g., success rates, tensile strength, specific measurements).
• Details about a "test set" for a performance study (sample size, data provenance, ground truth establishment, expert qualifications, or adjudication methods).
• Information on a multi-reader multi-case (MRMC) comparative effectiveness study or any effect size for human reader improvement.
• Distinction between standalone algorithm performance and human-in-the-loop performance, as this is a medical device, not an AI/software-only device in the context of typical AI performance criteria.
• Training set sample size or how its ground truth was established.

However, based on the provided text, I can infer and extract some relevant information regarding performance testing.

Inferable Acceptance Criteria and Reported Device Performance

The document lists categories of performance testing that were conducted with "acceptable results." While specific numerical acceptance criteria and reported performance values are not given, the implication is that the device met internal, pre-defined criteria for these aspects.

A table of acceptance criteria and reported performance cannot be fully constructed from the provided text because specific numerical values for criteria and performance are absent. However, based on the categories mentioned under "Performance Data," we can infer the types of criteria and the general statement of performance:

Study Details (as far as extractable):

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

   • The document mentions "bench testing" and a "preclinical animal study." For bench testing, sample sizes are not specified.
   • For the animal study, the model used was a "porcine model," indicating an animal test subject. The number of animals or specific cases within that study is not provided.
   • Data provenance: Porcine model (animal study), laboratory/bench for other tests. Retrospective/prospective is not specified, but animal studies are typically prospective experimental designs.

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

   • The document does not specify the number or qualifications of experts for establishing ground truth, as this device's performance assessment relies on physical and functional tests, and an animal study, rather than expert interpretation of medical images or data.

3. Adjudication method for the test set:

   • Not applicable/Not specified. The performance testing described (bench, animal study) does not involve adjudication processes typically used in clinical imaging or diagnostic studies.

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 medical device, not an AI-assisted diagnostic tool subject to MRMC studies. The clearance is for the physical device itself.

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

   • Not applicable. This is a physical medical device, not an algorithm, so "standalone" performance in the context of AI software is not relevant here.

6. The type of ground truth used:

   • For bench testing: Engineering specifications, physical measurements, functional demonstrations.
   • For the animal study: Observation of safety and performance (e.g., successful tissue approximation, LAMS deployment, absence of adverse events) within the porcine model. This could be considered "outcomes data" in an experimental animal model context.

7. The sample size for the training set:

   • Not applicable. This is a physical medical device. There is no "training set" in the context of machine learning algorithms. Its design would be informed by engineering principles and possibly prior animal/cadaver studies, but not a formal 'training set'.

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

   • Not applicable, as there is no training set mentioned for this type of device.

Ask a specific question about this device

The ARCHIMEDES biodegradable pancreatic stent is intended to drain pancreatic ducts in patients indicated for pancreatic duct stenting.

The ARCHIMEDES Biodegradable Pancreatic Stent is intended to be delivered through the working channel of a therapeutic endoscope using a guidewire with a maximum outer diameter of 0.035 inches and a pushing catheter of between 5 to 10 French.

The ARCHIMEDES™ Biodegradable Pancreatic Stent is a single use, sterile, biodegradable stent implant intended for use in the pancreatic duct. The device is intended to be delivered endoscopically through the working channel of a duodenoscope.

The ARCHIMEDES™ has a fluted cross-sectional profile and provides three drainage channels, two of which spiral in a double helical pattern down the length of the stent and one of which is the hollow inner lumen of the device tube. This unique design permits fluids to flow both around and through the stent. It has a curved form design to fit the natural curvature of the pancreatic duct, and contains flap and split-end features to minimize spontaneous migration of the stent while in situ. The tips of the stent are tapered to facilitate atraumatic insertion through the papilla. The stent is visible under fluoroscopy. The 8F and 10F stent design contains flaps on each end. The 6F stent design has a flap on one end and a split-end feature on the other end.

The stent is offered in outer diameters of 2.0mm (6F), 2.6mm (8F), or 3.4mm (10F), and in various lengths to accommodate variations in pancreatic anatomy across individuals (40, 60, 80, 100, 125, 150, 175, 200, and 225 mm). The ARCHIMEDES™ is designed to be an alternative to plastic stents that maintains the same clinical purpose. In particular, it is used in a manner similar to current FDA-cleared plastic pancreatic stents. The primary difference is that the ARCHIMEDES™ biodegrades in-situ rather than requiring an additional procedure for removal needed of plastic stents.

The Minimal Strength Retention (MSR) time for the material - i.e., the minimum amount of time for which the device retains at least 10% of an initial strength parameter and remains intact with no breaks is 12 days. Full-degradation or no stent presence is reached within

The provided FDA 510(k) clearance letter and summary for the ARCHIMEDES™ Biodegradable Pancreatic Stent do not contain the specific acceptance criteria and detailed performance results for the device. While it states that "All tests met required acceptance criteria," the actual criteria and reported numerical performance are not explicitly listed.

Furthermore, the document alludes to "eight clinical studies" but provides no details whatsoever about their methodology, sample sizes, data provenance, expert qualifications, adjudication methods, or specific outcomes. It's a high-level statement without any actionable data.

Therefore, many of your requested fields cannot be filled from the provided text.

Here's a breakdown of what can be extracted and what cannot, based on the input:

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

Ask a specific question about this device

The Advanix™ Pancreatic Stent and NaviFlex™ Rapid Exchange (RX) Pancreatic Delivery System and Pushers are intended for delivery of the stent to the pancreatic duct (PD):
• Used to drain pancreatic ducts

The Advanix™ Pancreatic Stent and NaviFlex™ RX Pancreatic Delivery System and Pushers is a plastic pancreatic stent designed for the delivery of the stent to the pancreatic duct and used to drain pancreatic ducts.

The pancreatic stents are provided in straight or single pigtail shape. The straight shape stents have trailing barbs and/or leading barbs depending on application, in rounded or tapered leading end tip to facilitate access through papilla, and a rounded trailing end or about the push catheter portion of the delivery system or stent pusher. The single pigtail stent may or may not have leading end barbs depending on application. Some stents have lateral drainage holes in the pigtails, a tapered or rounded leading end tip, and a rounded trailing end. All stents have either an endoscopic or fluoroscopic marker, or both on the trailing or leading end of the stent to assist with depth of placement in the pancreatic duct. The location and presence of an endoscopic or fluoroscopic marker is dependent on the length and diameter size of the stent. Some codes have side port holes in the body of the stent.

I regret to inform you that the provided text is a U.S. FDA 510(k) clearance letter and summary for a medical device (Advanix™ Pancreatic Stent and NaviFlex™ Rapid Exchange (RX) Pancreatic Delivery System and Pushers).

This type of document primarily focuses on demonstrating substantial equivalence to a predicate device based on non-clinical performance bench testing and biocompatibility.

Crucially, this document does not contain information about clinical studies with human patients, nor does it establish device performance against specific acceptance criteria in a clinical setting.

Therefore, I cannot extract the information you requested regarding:

1. A table of acceptance criteria and the reported device performance: These are not defined in the context of clinical outcomes within this document. The "performance" mentioned refers to bench testing.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): No clinical test set is described.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable as there is no clinical test set with ground truth established by experts.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.
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 device is a physical medical device (a stent and delivery system), not an AI/software device. Therefore, MRMC studies and AI assistance are not relevant.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable, as it's not an algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable for the clinical performance criteria you are asking about. The "ground truth" for the bench tests would be the established engineering specifications and standards.
8. The sample size for the training set: Not applicable, as there is no training set for a clinical algorithm.
9. How the ground truth for the training set was established: Not applicable.

The "Non-Clinical and/or Clinical Tests Summary & Conclusions" section explicitly states that the submission includes Performance Bench Testing and Biocompatibility Testing. These are standard tests for physical devices to ensure their safety and physical functionality, not their clinical effectiveness in terms of patient outcomes or diagnostic accuracy.

In summary, the provided document is not a study report that demonstrates clinical performance against acceptance criteria for patient outcomes or diagnostic accuracy.

Ask a specific question about this device

The EGIS Biliary Double Bare Stent is indicated for the palliation of malignant strictures in the biliary tree.

EGIS Biliary Double Bare Stent has straight and round cylinder form made of nitinol wire. The double bare type is composed of two structures, an inner stent and an outer stent, and has a double-layer form. Each stent has the same structure as the single bare type of the product. A double layer is formed by overlapping a separately manufactured inner stent and an outer stent, and both ends are physically fixed using medical sutures. No additional bonding material in this process. This manufacturing method also allows the product to have more conformability and a smaller cell size.

The provided FDA 510(k) clearance letter for the EGIS Biliary Double Bare Stent does not contain any information about a study involving acceptance criteria for device performance with respect to AI or human reader assistance.

The document primarily focuses on demonstrating the substantial equivalence of the EGIS Biliary Double Bare Stent to a predicate device (EGIS Biliary Single Bare Stent) through non-clinical bench testing and biocompatibility evaluation. The letter explicitly states: "Clinical testing was not required for this submission." This means no human-in-the-loop or standalone AI performance studies were conducted or reported in this clearance.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets those criteria based on the provided input. The information requested regarding AI performance, human reader studies, ground truth establishment, expert adjudication, and training/test set details is entirely absent from this 510(k) clearance letter, as it's not relevant to the type of device (a biliary stent) or the regulatory pathway chosen (510(k) based on substantial equivalence through non-clinical data).

If you have a document pertaining to an AI device or a study involving human reader performance, please provide that document, and I would be happy to analyze it according to your requested criteria.

Ask a specific question about this device

The Single Use Retrieval Basket V FG-V421PR/FG-V422PR/FG-V431P/FG-V432P are intended to be used to retrieve stones from the biliary tract in combination with an endoscope.

The Single Use Retrieval Basket V Series is comprised of four (4), sterile, single-use, retrieval baskets designed to retrieve stones from the biliary tract. The retrieval baskets, manufactured from stainless steel, are provided as an 8-wire or 4-wire type.

Each device has two sections: the handle and the insertion. The grip of the handle is used to control and operate the retrieval basket. The insertion, consisting of the sheath and the retrieval basket, is introduced into the biliary tract through an endoscope.

The subject devices are intended to be used with Olympus endoscopes featuring a working length of less than 1400 mm (model: TJF) and a channel inner diameter of Ø 4.2 mm. The Olympus Lithotriptor (model BML-110A-1 or BML-610A) may be used in case of an emergency.

Legally marketed Olympus guidewires (outer diameter Ø 0.89 mm) may be used with the Single Use Retrieval Basket V FG-V431P and FG-V432P models.

This document, a 510(k) Premarket Notification for the Olympus Single Use Retrieval Basket V (K243807), details the device's substantial equivalence to a predicate device. However, it does not contain the specific information required to address your request regarding acceptance criteria and a study proving the device meets those criteria, particularly in the context of an AI/human comparative effectiveness study.

The provided text focuses on the device's mechanical, material, and operational equivalence to a previously cleared device. It outlines:

• Device Description: Single-use retrieval baskets for stones in the biliary tract.
• Performance Data: Biocompatibility testing (ISO 10993-1), sterilization validation (ISO 11135), packaging validation (ISO 11607-1, ASTM F1980-21), and mechanical testing (Insertion/Withdrawal, Open/Close Basket, Dimensional verification, Grasping Basket Effective Test, Attachment/Detachment of Hook, Injecting Fluid, Strength of Junction).
• Conclusion: The device is substantially equivalent to the predicate based on these non-clinical tests.

Crucially, the document explicitly states:

• "Animal study data and clinical study data were not required to demonstrate substantial equivalence."

This indicates that a study involving human subjects or AI-assisted performance, which would typically contain the data you're requesting, was not part of this 510(k) submission. The acceptance criteria described are for the physical and material properties of the basket, not for diagnostic performance or human-AI interaction.

Therefore, I cannot provide the requested information from this document. The device in question is a medical instrument (a retrieval basket), not an AI/software as a medical device (SaMD) that would have diagnostic performance metrics, ground truth establishment, or multi-reader studies.

Ask a specific question about this device

This device is indicated for use in adult and adolescent populations to endoscopically dilate strictures of the gastrointestinal tract. It is also indicated in adults for endoscopic dilatation of Sphincter of Oddi with or without prior sphincterotomy.

According to the structure of the device, it can be divided into three types, RX type, OTW type and OTW with Stainless Wire-guided type. The Rx proposed device mainly consists of tip, balloon, marker band, shaft, sleeve, stress diffusion tube and hub. The OTW proposed device mainly consists of tip, balloon, marker band, shaft, stress diffusion tube and hub. The structure of the OTW with Stainless Wire-guided model same with the structure of OTW model. The difference between OTW with Stainless Wire-guided type catheter and OTW type catheter is that OTW with Stainless Wire-guided type catheter is preloaded with a guide wire and a guide wire locking component. The difference between the RX type catheter and the OTW series catheter is that the guidewire exit position is different. The guide wire of OTW series catheter passed through the guide wire lumen of the catheter. The guidewire of the Rx type catheter will pass through the guidewire exchange port on the shaft.

Single-use Balloon Dilatation Catheter is divided into different specifications. Shafts are available in two different diameters. The effective length of the catheter is 180cm and 240cm. Balloon diameters are available in six different diameters 6-7-8mm, 8-9-10 mm, 12-13.5-15 mm, 15-16.5-18 mm, 18-19-20 mm, and the balloon lengths are available in 30 mm,55 mm and 80 mm three different length.

The provided FDA 510(k) summary for the "Single-use Balloon Dilatation Catheter" (K241888) details a non-clinical study to demonstrate substantial equivalence to predicate devices, rather than an AI/ML software performance study. Therefore, most of the requested information regarding AI/ML device acceptance criteria, human reader studies, and ground truth establishment for AI/ML models is not applicable to this document.

The document describes performance testing for a physical medical device. Here's a breakdown of the applicable information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document states: "All the test results demonstrate proposed device meet the requirements of its pre-defined acceptance criteria and intended uses." However, it does not provide a specific table detailing the exact quantitative acceptance criteria for each test and the corresponding measured performance values. It lists the types of tests performed.

2. Sample sizes used for the test set and data provenance:
The document states "The performance testing conducted on subject device and predicate device are listed below." and mentions "ASTM F3172 Standard Guide for Design Verification Device Size and Sample Size Selection for Endovascular Devices". This suggests that standard device testing sample sizes were used in accordance with this guideline, but the specific sample sizes for each test are not explicitly stated in this summary.
Data provenance: This is a physical device, so "data provenance" would refer to the testing conditions and results. The tests were performed in a lab setting to verify design specifications and compliance with international standards (e.g., ISO, ASTM, USP). The country of origin for the testing is not specified, but the applicant company is Leo Medical Co., Ltd. in China. The data is prospective as it's generated through device testing.

3. Number of experts used to establish the ground truth for the test set and qualifications of those experts:
This question is not applicable as this is a physical device performance study, not a study involving human reader interpretation of images or AI/ML model output requiring "ground truth" established by experts in a clinical context. The "ground truth" for these tests are the physical measurements and compliance with engineering and material standards.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
This is not applicable as it's a physical device performance study. Adjudication methods are typically for clinical consensus on ground truth in image interpretation or diagnosis, not for engineering performance tests.

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 is not applicable. No MRMC study was performed as this is not an AI/ML-assisted diagnostic device. The document explicitly states: "No clinical study is included in this submission."

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
This is not applicable. This is not an algorithm, but a physical medical device.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
For this physical device, the "ground truth" for the non-clinical tests is based on established engineering and material science standards, measurements, and pre-defined acceptance criteria. For example, burst pressure is measured against a standard, biocompatibility is assessed against ISO 10993, and sterility against ISO 11135.

8. The sample size for the training set:
This is not applicable. No training set was used as this is a physical device, not an AI/ML model being "trained."

9. How the ground truth for the training set was established:
This is not applicable. No training set was used.

Ask a specific question about this device

This device is used to dilate strictures in the pancreatobiliary systems and to dilate openings via the transgastric or transduodenal wall. This device is indicated for adult use only.

The Tornus ES is a rotary-operated dilator designed for use in bile duct/pancreatic duct strictures and via transgastric/transduodenal dilation of openings. The Tornus ES is comprised of stainless-steel coils and polymeric materials. The Dilation and Shaft segments are composed of coils materials that are welded together. The Tornus ES is available for prescription use only.

The provided text describes the performance data for the Tornus ES device, specifically focusing on non-clinical testing and biocompatibility assessments. It does not detail a study involving human subjects or AI assistance, which would typically involve acceptance criteria related to accuracy, sensitivity, specificity, or reader performance metrics. Therefore, several points of your request cannot be fulfilled as they are not applicable to the information provided.

Based on the provided text, primarily pages 8 and 9, here's the information regarding the device's acceptance criteria and the study that proves it meets those criteria:

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

The document provides acceptance criteria specifically for biocompatibility testing, and a general "Pass" for non-clinical performance tests.

Table 1: Non-Clinical Testing Performance

Table 2: Biocompatibility Testing Acceptance Criteria and Results

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 refers to "Non clinical laboratory testing" and "in vitro bench tests". This indicates that the testing was performed on units of the device itself and not on patient data. No specific sample sizes for these tests are provided, nor is the country of origin of the data or whether it was retrospective or prospective, as these terms are generally applicable to clinical trials or studies involving patient data, which is not the case here.

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. The testing was non-clinical and benchtop, not requiring human expert interpretation or ground truth establishment in the context of imaging or clinical diagnosis.

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

Not applicable, as this refers to adjudication of ground truth in clinical data, not bench 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 document describes a medical device (a catheter) and its non-clinical performance and biocompatibility. It does not involve AI or human image readers.

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

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

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

For the non-clinical tests, the "ground truth" would be the engineering specifications and performance standards established for the device. For biocompatibility, the ground truth is established by the methods and criteria defined in the ISO 10993 series of standards.

8. The sample size for the training set

Not applicable. This device is not an AI algorithm that requires a training set.

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

Not applicable.

Ask a specific question about this device

This device is used for the endoscopic removal of stones in the biliary system and foreign bodies.

The proposed device is a sterile, single-use accessory to be used with endoscopic, intended to be used for the removal of stones in the biliary system and foreign bodies. The proposed device includes two types, one type (Hereinafter referred to Type 1) is working through the channel provided by duodenoscopy, cross the duodenal papilla and insert into the bile duct, with the assistance of Imaging field of view formed by X-ray, capture and remove stones out of bile duct. Another one (Hereinafter referred to Type 2) is working through the channel provided by choledochoscope, after the choledochoscope was inserted into the bile duct successfully, inserted the extraction basket into the bile duct by the channel of choledochoscope, capture and remove stones out of bile duct by the direct field view of choledochoscope.

The proposed device is EO sterilized to achieve the Sterility Assurance Level (SAL) of 106 and placed in a sterility maintenance package to ensure a shelf life of 1 year for Type 1 and 3 years for Type 2.

The provided text is a 510(k) summary for a medical device called "Extraction Basket". It describes the device, its intended use, and comparison to a predicate device, along with performance data. However, this document does not describe acceptance criteria and a study that proves the device meets those criteria in the context of diagnostic or AI-driven performance.

The document primarily focuses on demonstrating substantial equivalence to a predicate device for regulatory clearance, which involves:

• Biocompatibility testing: To ensure the materials are safe for use in the human body.
• Performance testing: To confirm the mechanical functionality and intended operation of the physical device.
• Shelf-life and packaging integrity testing: To ensure the device remains sterile and functional over time.
• Sterilization validation: To confirm the sterilization process is effective.

Therefore, the information required to answer your request (acceptance criteria, device performance, sample sizes for test/training sets, ground truth establishment, expert qualifications, adjudication methods, MRMC studies, or standalone algorithm performance) is not present in this document.

The "Performance Data" section lists various types of tests conducted, such as "Dimension Testing," "Connection Force Testing," "Simulated-Use Testing," and "Stone Capture and Durability Testing," but it does not provide specific acceptance criteria or quantitative results of these tests.

The document explicitly states:

• No animal study is included in this submission.
• No clinical study is included in this submission.

The question you've posed is typically relevant for AI/ML-driven diagnostic devices or devices where performance is measured against a clinical outcome or diagnostic accuracy. This document describes a physical medical tool (an extraction basket) for removing stones/foreign bodies, and its clearance is based on demonstrating mechanical and material safety and effectiveness, not diagnostic performance.

Ask a specific question about this device

The WallFlex Biliary PLUS RX Stent System is indicated for use in the palliative treatment of biliary strictures produced by malignant neoplasms and relief of malignant biliary obstruction prior to surgery.

The WallFlex™ Biliary PLUS RX Stent System is an implantable biliary self-explaining metal stent that is pre-loaded onto a Delivery System with a working length of 194cm, which allows delivery of the stent into the Biliary system endoscopically. The self-expanding metal stent consists of Platinum cored Nitinol wires wound together to form a cylinder including flares on both the hilar and duodenal ends. WallFlex™ Biliary PLUS RX Stent is available fully covered with a Permalume™ covering.

I am sorry, but the provided text does not contain the information required to describe the acceptance criteria and the study proving the device meets these criteria. The document is an FDA 510(k) clearance letter for a medical device (WallFlex Biliary PLUS RX Stent System) and its accompanying 510(k) summary.

While it mentions that "Performance testing for the proposed WallFlex™ Biliary PLUS RX Stent System was completed in accordance with the following FDA Guidance documents to support substantial equivalence," it does not provide:

• A table of acceptance criteria and reported device performance.
• Details on sample size, data provenance, number/qualifications of experts, or adjudication methods for any test set (it mentions non-clinical tests, not a clinical trial or AI model validation).
• Information on Multi-Reader Multi-Case (MRMC) comparative effectiveness studies.
• Stand-alone (algorithm only) performance studies.
• Type of ground truth used or how it was established.
• Training set details (sample size or ground truth establishment).

The document is primarily a regulatory communication confirming substantial equivalence to predicate devices based on non-clinical performance data and design comparisons, not a detailed report of a clinical efficacy/effectiveness study or performance validation for an AI/CADe device.

Ask a specific question about this device

The Single-use Extraction Baskets is intended for the endoscopic removal of stones and stone fragments in the biliary system.

The Single-use Extraction Baskets is a single-use, sterile, disposable device. It is intended for the endoscopic removal of stones and stone fragments in the biliary system. The device consists of basket, sheath, and handle components. The basket component is constructed of stainless steel/nitinol wires. And the basket is connected to the handle of the operating portion through the insertion portion. Activating the handle allows the basket to open or close. This device is not compatible with any mechanical lithotripter.

The provided document is a 510(k) Premarket Notification from the FDA for a medical device called "Single-use Extraction Baskets." This type of document is concerned with demonstrating substantial equivalence to a legally marketed predicate device, primarily through non-clinical performance testing. It is not a document that details the rigorous clinical validation of an AI-powered diagnostic device, which is what your request implies by asking about acceptance criteria, ground truth, training sets, and MRMC studies.

Therefore, most of the information you requested regarding acceptance criteria and a study proving device performance (especially for an AI device) cannot be found in this document because the device in question is a mechanical medical device (extraction baskets), not an AI diagnostic tool, and the review process outlined here focuses on substantial equivalence through non-clinical and mechanical performance testing.

However, I can extract information related to what was used to demonstrate the device's performance for this specific 510(k) submission:

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

The document does not provide a formal table of acceptance criteria with numerical performance metrics for an AI device. Instead, it lists the types of performance tests conducted and states that the "test results demonstrated that the subject device complies with the standard requirements." "Compliance with standard requirements" is the implicit acceptance criterion for these non-clinical tests.

• Dimensions Testing
• Tensile Pull Testing
• Simulated-Use Functionality & Durability Testing
• Stone Capture Testing
• Deflection Testing | Demonstrates basic performance and performs as intended. | Confirmed that the subject device performs as intended. |
  | Comparative Testing | Performance comparable to the predicate device (K203322). | Demonstrated that the subject is as safe and effective as the predicate. |

2. Sample sized used for the test set and the data provenance

• Sample Size for Test Set: Not specified in terms of numbers of devices or specific test runs for each mechanical test. The document states "The following performance data were provided..." without quantifying the test samples.
• Data Provenance: Not explicitly stated, given that these are non-clinical bench tests rather than patient data. These tests would typically be performed in a lab setting by the manufacturer.

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

• This information is not applicable and not provided in this document. Since the device is a mechanical extraction basket, there is no "ground truth" in the diagnostic sense or expert interpretation required for these performance tests. The ground truth for mechanical performance is typically defined by engineering specifications and objective measurements.

4. Adjudication method for the test set

• This information is not applicable and not provided. Adjudication methods (e.g., 2+1, 3+1) are relevant for human expert review processes, typically in clinical studies or for establishing ground truth in diagnostic AI datasets. This document describes non-clinical engineering and performance tests.

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. This type of study is specifically for evaluating the impact of AI on human reader performance, usually in image-based diagnostics. This document is for a mechanical medical device, not an AI diagnostic tool.
• The document explicitly states: "The clinical data is not applicable."

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

• No, this is not applicable. The device is a "Single-use Extraction Basket," a physical tool, not an algorithm. Therefore, there is no "standalone algorithm" performance to report.

7. The type of ground truth used

• For mechanical performance tests: The "ground truth" is established by engineering specifications, physical measurements, and industry standards (e.g., ISO, ASTM). For example, "Dimensions Testing" would verify that the device's dimensions meet pre-defined specifications. "Stone Capture Testing" would evaluate the basket's ability to capture stones under simulated conditions, with the "truth" being whether it successfully performed the action based on defined criteria.
• Not applicable for clinical or diagnostic "ground truth" derived from expert consensus, pathology, or outcomes data, as this is not an AI diagnostic device.

8. The sample size for the training set

• Not applicable. This device is a mechanical one and does not involve AI or machine learning that requires a "training set."

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

• Not applicable. As a mechanical device, there is no AI training set.

Ask a specific question about this device