Search Results

For maintaining open the airway, after dilation of the stenosis or resection of the obstruction, in particular in case of:

• Tracheobronchial tumors
• Tracheal stenoses with scarring
• Stenoses following surgical anastomosis, resection or pulmonary transplantation.

The TRACHEOBRONXANE™ DUMON® stents are flexible tracheobronchial tubes made of medical grade silicone, designed to improve patient respiration capacity while acting as trachea or bronchi support. These medical devices are designed to conform to individual anatomies.

Each stent has a specific treatment, to improve the evacuation of mucus in order to limit the risk of obstruction.

A large range of shape, thickness and sizes is available depending on the pathology to be treated, patient intrinsic factor and location of the implantation. Indeed, the TRACHEOBRONXANE™ DUMON® range consists of various models which vary from each other in the following characteristics:

• The stents type: TD, TF, BD, Y, ST corresponding to various profiles made of silicone with different hardness;
• . The dimensions: each profile consists of different sizes in diameter and length;
• The radiopacity: stents can be provided radiopaque or not radiopaque; barium sulfate . is added during the manufacturing process in order to make the stent radiopaque which allows obtaining a better visibility by X-rays radiography.

The TRACHEOBRONXANE™ DUMON® stents have been designed with studs in order to facilitate their anchorage in the trachea or bronchi (on cartilage rings). The number of stud rows is depending on the stent profile and stent final destination (bronchi or trachea).

The TRACHEOBRONXANE™ DUMON® stent holds the respiratory tract open by exerting a radial force.

The Tracheobronxane™ Dumon® device is a medical-grade silicone tracheobronchial tube intended to maintain an open airway after dilation or resection, particularly in cases of tumors, scarring, or post-surgical/transplantation stenoses.

The provided document does not contain a typical acceptance criteria table with reported device performance for an AI/algorithm-based device. Instead, it describes performance data related to the physical and biological characteristics of a medical device (a stent). The assessment is for demonstrating substantial equivalence to a predicate device, not for an AI's diagnostic or predictive capabilities.

However, based on the information provided, we can infer the acceptance criteria and the studies performed to demonstrate equivalence.

Here's an interpretation based on the provided text, framed as acceptance criteria for the device itself (the stent), rather than for an AI:

1. Table of Acceptance Criteria and Reported Device Performance:

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

The document describes benchmarking performance tests and biocompatibility testing. However, it does not specify "test sets" in the context of an algorithm or AI.

• Biocompatibility Testing: The "samples" would be the device materials (medical-grade silicone, barium sulfate) and the final stents themselves. The exact number of samples for each test (cytotoxicity, sensitization, etc.) is not specified, but standard ISO 10993 testing involves a defined number of replicates/samples. The provenance is internal to the manufacturer (Novatech SA) and involves standard lab testing, not patient data in the sense of retrospective or prospective clinical studies.
• Benchmark Performance Tests (Fatigue, Weighing, Compression): The "samples" are the stents themselves. The number of stents used for these tests (brand new, fatigue-stressed, water-bath treated) is not specified. The provenance is internal laboratory testing by the manufacturer.

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

Not applicable. This device is a physical medical implant (stent), not a diagnostic or AI device that relies on expert interpretation for ground truth establishment. The ground truth for its performance is derived from standardized laboratory tests (biocompatibility, mechanical tests).

4. Adjudication Method for the Test Set:

Not applicable. There is no "test set" in the context of expert review or adjudication as would be relevant for an AI/algorithm. Performance is assessed against pre-defined, standardized test methods and criteria.

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

No. This is not an AI-assisted device, so MRMC studies for human readers with and without AI assistance are not relevant or performed.

6. 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.

7. The Type of Ground Truth Used:

• Biocompatibility: Ground truth is established by adherence to ISO 10993-1 standards and the absence of adverse biological reactions in standardized in-vitro and in-vivo tests, as well as a "long history of safe clinical use" for similar materials.
• Mechanical Performance: Ground truth is established by engineering specifications for stent integrity, radial force, and material absorption/disposal, measured through specific mechanical tests (fatigue, weighing, compression).
• Shelf-Life/Sterilization: Ground truth is established by stability testing and validated sterilization methods demonstrating sterility assurance levels.

8. The Sample Size for the Training Set:

Not applicable. This is a physical medical device, not an AI/algorithm that requires a training set.

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

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

Ask a specific question about this device

The Ultraflex™ Tracheobronchial Stent System is intended for use in the treatment of tracheobronchial strictures produced by malignant neoplasms.

The Ultraflex Tracheobronchial Stent System is a permanently implanted expandable metal stent designed to serve as an intralumenal support to keep open the inner lumen of the tracheobronchial tree. They consist of a flexible delivery catheter preloaded with an expandable metallic stent.

The stent is an open-ended cylindrical mesh constructed from a single strand of nitinol wire. The wire is configured into a series of circumferential interwoven loops, with the number of loops being dependent on the diameter of the stent. The stent is elongated and compressed onto a plastic delivery catheter. The stent is held onto the delivery catheter by a crocheted nylon suture wrapped around the stent. The delivery catheter has a flush taper tip at the distal end, and a round hub handle at the proximal end.

The partially covered stent has a single layer of silicone that covers the midsection of the stent. Partially covered stents are available with a distal release system only. The distal release system begins stent deployment from the lower (distal) end of the delivery catheter. The uncovered stents are available with a distal or proximal release system.

The radiopaque (RO) markers on the delivery system and stent facilitate fluoroscopic placement.

The uncovered stent has one pair of RO markers indicated the approximate locations of the margins of the deployed stent. The partially covered stent has four (4) RO markers. The outer two (2) RO markers indicate the estimated final position of the ends of the deployed stent. The inner two (2) RO markers indicate the estimated final position of the margins of the deployed stent cover.

The delivery system accepts a 0.035 in (0.89 mm) or 0.038 in (0.97 mm) guidewire. The delivery system is passed over the guidewire into the tracheobronchial lumen. The stent is positioned appropriately using the RO markers for guidance under fluoroscopy and by bronchoscopic visualization of the stent.

The provided text does not describe acceptance criteria for a device performance study in the context of diagnostic accuracy, which is typically represented by metrics like sensitivity, specificity, or AUC. Instead, it describes acceptance criteria and testing for the safety of a medical device within a Magnetic Resonance (MR) environment.

Here's an analysis of the provided information based on your request, focusing on what is available:

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

The document does not explicitly state numerical acceptance criteria for each test in a table format, nor does it provide detailed quantitative results for the device performance beyond stating compliance. However, it implicitly states that the acceptance criteria are compliance with the FDA Guidance Testing and Labeling Medical Devices for Safety in the Magnetic Resonance (MR) Environment issued on May 20, 2021.

List of Tests Performed (as part of demonstrating compliance):

• Magnetically Induced Displacement Force: Tested per ASTM F2052, Standard Test Method for Measurement of Magnetically Induced Displacement Force on Medical Devices in the Magnetic Resonance Environment.
• Magnetically Induced Torque: Tested per ASTM F2213, Standard Test Method for Measurement of Magnetically Induced Torque on Medical Devices in the Magnetic Resonance Environment.
• Heating by Radio Frequency (RF) Fields: Tested per ASTM F2182, Standard Test Method for Measurement of Radio Frequency Induced Heating Near Passive Implants During Magnetic Resonance Imaging.
• Image Artifact: Tested per ASTM F2119, Standard Test Method for Evaluation of MR Image Artifacts from Passive Implants.

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

This information is not provided in the document. The tests described are "bench performance testing," implying laboratory-based evaluations of the device itself, not a study involving patient data or human subjects. Therefore, concepts like sample size for a "test set" in the context of diagnostic accuracy or data provenance (country, retrospective/prospective) are not applicable 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)

This information is not provided and is not applicable. The study described is bench testing for MR safety, not a study evaluating diagnostic performance 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 provided and is not applicable, as it's a bench test, not a study with human adjudication of results.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done. The study described is bench testing for MR safety. AI assistance is not relevant to this type of testing.

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

A standalone performance study in the context of an algorithm's diagnostic accuracy was not done. The performance testing was for the physical device's safety in an MR environment.

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

The concept of "ground truth" (expert consensus, pathology, outcomes data) as it pertains to diagnostic accuracy studies is not applicable here. The ground truth for the safety testing is established by adherence to the specified ASTM standards and the FDA Guidance for MR safety, which define acceptable parameters for magnetic displacement, torque, heating, and artifact generation.

8. The sample size for the training set

This information is not provided and is not applicable. This is not an AI/algorithm-based device requiring a training set.

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

This information is not provided and is not applicable, as there is no training set mentioned or implied for this device.

Ask a specific question about this device

The VisionAir Patient-Specific Airway Stent is indicated for the treatment of adults ≥22 years of age with symptomatic stenosis of the airway. The silicone stent is intended for implantation into the airway by a physician using the recommended deployment system or an equivalent rigid bronchoscope and stent placement system that accepts the maximum stent diameter being placed. The stent is intended to be in the patient up to 12 months after initial placement.

The subject device, VisionAir Patient-Specific Airway Stent is comprised of a cloudbased software suite and the patient-specific airway stent. These two function together as a system to treat symptomatic stenosis of the airway per the indications for use. The implantable patient-specific airway stent is designed by a physician using a CT scan as a guide in the cloud-based software suite. The airway is segmented from the CT scan and used by the physician in designing a patient-specific stent. When design is complete, the stent is manufactured via silicone injection into a 3D-printed mold and delivered to the treating physician nonsterile, to be sterilized before use.

The implantable patient-specific airway stent includes the following general features:

• Deployed through a compatible rigid bronchoscope system
• Made of biocompatible, implant-grade silicone
• Steam sterilizable by the end user
• Anti-migration branched design
• Anti-migration studs on anterior surface of main branch
• Single-use

The cloud-based software suite has the following general features:

• Upload of CT scans
• Segmentation of the airway
• Design of a patient specific stent from segmented airway
• Order management of designed stents

The provided text is a 510(k) Summary for the VisionAir Patient-Specific Airway Stent, which focuses on demonstrating substantial equivalence to a predicate device. It primarily discusses the device description, indications for use, technological characteristics, and a list of nonclinical performance and functional tests conducted.

However, the document does not contain the detailed information required to fulfill the request regarding acceptance criteria and the study that proves the device meets those criteria. Specifically, it lacks:

1. A table of acceptance criteria and reported device performance: While it lists types of tests, it does not provide specific quantitative acceptance criteria or the actual results from these tests.
2. Sample size used for the test set and data provenance: No information is given about the sample size for any clinical or performance test, nor the origin or nature of the data (retrospective/prospective, country).
3. Number of experts used to establish ground truth and qualifications: This information is completely absent.
4. Adjudication method for the test set: Not mentioned.
5. Multi-Reader Multi-Case (MRMC) comparative effectiveness study details: No MRMC study is described; the testing mentioned is primarily non-clinical or related to software validation/verification, not human-AI comparative effectiveness.
6. Standalone (algorithm-only) performance: While "Software Verification and Validation Testing" and "Airway Segmentation Process Testing" are mentioned, no specific standalone performance metrics (e.g., accuracy, precision for segmentation) or acceptance criteria are provided.
7. Type of ground truth used: The document mentions "Airway Segmentation Process Testing" and refers to a predicate device (Mimics) for "performance reference specification" for dimensional testing of airway segmentation. This implies that the ground truth for segmentation would likely be derived from expert-reviewed segmentations or potentially from known anatomical measurements, but the method is not explicitly detailed.
8. Sample size for the training set: There is no mention of a "training set" or any machine learning model that would require one. The software aspect described is for physician-guided design and semi-automated segmentation, not explicitly an AI/ML model that undergoes a training phase in the typical sense for medical image analysis.
9. How the ground truth for the training set was established: Not applicable, as no training set is described.

The document states: "Reference devices, Mimics (K073468) and Osirix MD (K101342) were used for reference software performance specifications." and "Dimensional Testing of Airway Segmentation (reference device Mimics K073468 used for performance reference specification)". These statements hint at software validation, especially for the segmentation component, but do not provide the detailed study design, acceptance criteria, or results.

In summary, the provided text does not contain the necessary information to answer the request in detail, as it focuses on demonstrating substantial equivalence through non-clinical performance and functional testing rather than a clinical study with acceptance criteria for device performance based on human reader interaction or AI model performance.

Ask a specific question about this device

The Through the Scope Tracheal Stent System is in the treatment of tracheobronchial strictures caused by malignant neoplasms.

The Through the Scope Tracheal Stent System consists of a flexible delivery system preloaded with a self-expanding implantable metallic stent. The stent is made of Nitinol wire weaved in a tubular mesh shape. This structure may make the stent more flexible, compliant and self-expanding. The stent is fully covered with silicone membrane and a polymer coating. The Parylene N is added on the surface of silicone membrane to restrict tumor in-growth through the wire mesh. A retrieval loop made of PE&PP is threaded through the proximal and distal ends of the stent and is intended to aid in removal during the stent placement procedure. The stent has different dimension with the diameters of 10mm, 12mm, 16mm, 18mm, with the lengths of 20mm, 30mm, 40mm, 50mm, 60mm, 80mm.

The stent is deployed through the endoscopy working channel and under direct vision of endoscopy. The delivery system allows for desheathing to deploy and reposition the stent during the placement procedure. The delivery system consists of two coaxial sheaths and one inner core. The outer sheath serves to constrain the stent until being retracted during the stent deployment. The middle sheath serves to support the delivery system. The round tip acts as a guide when the delivery system enters the body. The front handle is used for deploying the stent. The seal ring, locking ring, and safe lock work to lock the device and prevent the stent from being exposed. The decoration nut connects with the back handle.

The device is supplied sterile, intended for single use only, and is available for prescription use only. Use of this device is restricted to a trained healthcare professional.

The provided text does not describe a study that uses AI or machine learning. It pertains to a medical device (Tracheal Stent System) and its premarket notification (510(k)) to the FDA. The tests conducted are non-clinical performance tests of the physical device, its materials, and its delivery system, ensuring its safety and effectiveness.

Therefore, many of the requested points related to AI/ML model evaluation (such as sample size for test/training sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, and ground truth establishment for training data) are not applicable to this document.

However, I can still extract the acceptance criteria and performance related to the physical device based on the information provided.

Device: Through the Scope Tracheal Stent System
Product Code: JCT
Regulation Name: Tracheal Prosthesis

Since the document does not contain information about an AI/ML model's performance, I will interpret the request in the context of the physical medical device's performance given the available information.

Acceptance Criteria and Reported Device Performance

The document states that "The results of all the performance testing demonstrated that the proposed device met the acceptance criteria and support substantial equivalence to the predicate device Tracheal Stent System (OTW) cleared under K202204."

While the specific numerical acceptance criteria are not detailed in the provided text (e.g., what percentage drop in expansion force is acceptable), the document lists the types of tests conducted and affirms that the device met these criteria, thus demonstrating substantial equivalence.

Here's a table based on the information provided:

Non-Applicable Information (for AI/ML studies)

As this document describes a traditional medical device (a tracheal stent), the following points are not applicable and no information is provided for them:

2. Sample size used for the test set and the data provenance: Not an AI/ML study. Performance tests are typically done on a defined number of physical samples, but this is not a data test set in the AI sense.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not an AI/ML study involving human reader ground truth.
4. Adjudication method for the test set: Not an AI/ML study.
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 an AI/ML study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not an AI/ML study.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not an AI/ML study. Measurements and physical properties constitute the "ground truth" for this device.
8. The sample size for the training set: Not an AI/ML study. There is no "training set."
9. How the ground truth for the training set was established: Not an AI/ML study.

In summary, the provided document describes the non-clinical performance testing of a physical medical device (a tracheal stent) to demonstrate its substantial equivalence to a predicate device, rather than the evaluation of an AI/ML-driven medical device.

Ask a specific question about this device

The Tracheal Stent System (Y -Shaped) is indicated for use in the treatment of tracheobronchial strictures caused by malignant neoplasms.

The Tracheal Stent System (Y-Shaped) consists of a flexible delivery system preloaded with a self-expanding implantable metallic stent. The stent is made of Nitinol wire by weaving in a Y shaped. This structure design can make the stent more flexible, compliant and self-expanding. The stent is integrated Y-shaped stent, which include 1 main stent, 2 branch stents, the integrated Y-shaped stent can replace three straight shape stents, and the overall design of Y-shaped stent can also be used for the expansion of the carina if there are strictures at the carina. The stent is woven from Nitinol wire. The branch stent is formed with a flange at either end. The stent is partially covered with silicone to restrict tumor in-growth through the wire mesh. To aid in visibility under fluoroscopy there are radiopaque markers at the stent. There are 3 retrieval loops at the end of stent which can be used to reposition the stent during the initial placement procedure if desired. The device is supplied sterile, intended for single use only and is available for prescription use only. Use of this device is restricted to a trained healthcare professional.

This document describes the Tracheal Stent System (Y-Shaped) and its substantial equivalence to a predicate device. However, the provided text does not describe acceptance criteria for a study proving device performance in the context of AI/ML or diagnostic accuracy, nor does it detail a study involving human readers or ground truth derived from expert consensus, pathology, or outcomes data related to an AI/ML component.

Instead, the document focuses on the substantial equivalence of a physical medical device (a tracheal stent system) to a predicate device, as required for a 510(k) premarket notification. The "performance data" sections list various engineering and biocompatibility tests conducted on the stent and its delivery system, ensuring its safety and functionality, not its diagnostic or interpretative accuracy in an AI context.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and reported device performance related to diagnostic accuracy.
• Sample size used for the test set or data provenance in an AI/ML context.
• Number of experts or their qualifications for establishing ground truth in an AI/ML context.
• Adjudication method for a test set in an AI/ML context.
• Multi-reader multi-case (MRMC) comparative effectiveness study or effect size of AI assistance.
• Standalone (algorithm only) performance.
• Type of ground truth (expert consensus, pathology, outcomes data) in an AI/ML context.
• Sample size for the training set for an AI/ML model.
• How ground truth for the training set was established for an AI/ML model.

The document states:

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

This indicates that the evaluation primarily relies on bench testing, biocompatibility testing, and comparison of technological characteristics to already approved devices, rather than a clinical trial or a study assessing human or AI diagnostic performance.

Summary of what the document does provide regarding device acceptance and performance (not AI/ML related):

The device is a Tracheal Stent System (Y-Shaped) indicated for treating tracheobronchial strictures caused by malignant neoplasms.

1. Table of Acceptance Criteria and Reported Device Performance:

The document states: "The results of all the performance testing demonstrated that the proposed device met the predetermined acceptance criteria and is substantial equivalence to the predicate device TRACHEOBRONXANE™ DUMON Tracheo-bronchial Silicone Stent and reference device AERO™ Tracheobronchial Stent Technology System."

While specific numerical acceptance criteria for each test (e.g., "Deployment Force shall be X to Y N") are not listed in this summary, the document broadly indicates that the device met these criteria. The "Performance Data" section lists the types of tests conducted:

2. Sample size used for the test set and the data provenance: Not applicable. These tests are primarily bench/lab tests, not studies on patient data in the context of diagnostic accuracy.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth in this context refers to the defined specifications and physical properties of the device, assessed through engineering and biocompatibility standards, not expert interpretation of medical images or conditions.

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: Not applicable.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.

7. The type of ground truth used:
The "ground truth" for the performance evaluation of this physical medical device is based on engineering specifications and established international standards (e.g., ISO, ASTM standards for biocompatibility, sterility, MR compatibility, and mechanical properties). The device's performance is measured against these predetermined specifications.

8. The sample size for the training set: Not applicable (no AI/ML training involved).

9. How the ground truth for the training set was established: Not applicable (no AI/ML training involved).

Ask a specific question about this device

The Tracheal Stent System (OTW) is indicated for use in the treatment of tracheobronchial strictures caused by malignant neoplasms.

The Tracheal Stent System (OTW) consists of a flexible delivery system preloaded with a self-expanding implantable metallic stent. The stent is made of Nitinol wire weaved in a tubular mesh shape. This structure may make the stent more flexible, compliant and self-expanding. The stent is partially or fully covered with silicone membrane and a polymer coating to restrict tumor in-growth through the wire mesh. A retrieval loop made of PE&PP is threaded through the proximal and distal ends of the stent and is intended to aid in removal during the stent placement procedure. To aid in visibility under fluoroscopy, there are Tantalum radiopaque markers at the body of the stent. The stent has flanges at the ends to aid in minimizing migration after

The provided text outlines the acceptance criteria and a study that demonstrates the Micro-Tech (Nanjing) Co., Ltd. Tracheal Stent System (OTW) meets these criteria for substantial equivalence to a predicate device. However, this is not a study that proves the device meets an acceptance criterion, but rather that it meets the acceptance criteria set by the predicate device.

Here's the information extracted from the document:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not present a formal table of explicit acceptance criteria with numerical targets alongside performance results for each criterion. Instead, it states that "The results of all the performance testing demonstrated that the proposed device met the acceptance criteria and support substantial equivalence to the predicate device AERO™ Tracheobronchial Stent Technology System." The "acceptance criteria" are implied by the successful completion of the listed tests in accordance with relevant standards and guidelines, demonstrating functional equivalence to the predicate.

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

The document does not explicitly state sample sizes for the various bench tests, nor does it specify the data provenance (e.g., country of origin, retrospective/prospective). These details are typically found in the full test reports, which are not included in this summary.

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

Not applicable. This submission is for a device, not an AI/software product that relies on expert interpretation for ground truth. The "ground truth" for the performance tests would be established by the defined parameters and methodologies of the referenced international standards and FDA guidance documents.

4. Adjudication Method for the Test Set

Not applicable. This is not a study involving human reader performance.

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 medical device submission, not an AI/software submission. No MRMC study was conducted or mentioned.

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

Not applicable. This is a medical device submission, not an AI/software submission. No standalone algorithm performance was assessed.

7. The Type of Ground Truth Used

For the various performance tests (biocompatibility, mechanical performance, sterility, shelf-life, MR compatibility), the "ground truth" is defined by the acceptance limits and methodologies specified in the cited international standards (e.g., ISO 10993-1, ASTM F1980-16, ISO 11607, ISO 11135, ASTM F2052, etc.) and FDA guidance documents. These standards provide objective, measurable criteria for evaluating device properties.

8. The Sample Size for the Training Set

Not applicable. This is a medical device submission, not an AI/software submission. There is no mention of a "training set."

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

Not applicable. As above, there is no training set for an AI algorithm.

Ask a specific question about this device

The HANAROSTENT® TracheaBronchium (CCC) is indicated for use in the treatment of tracheobronchial strictures caused by malignant neoplasms.

The HANAROSTENT® Trachea/Bronchium (CCC) is a self-expanding tubular prosthesis designed to maintain patency of tracheal or/and bronchial obstructions caused by malignant tumors. It consists of a self-expandable metal stent and a delivery device. The self-expandable metal stent is made of nickel titaniumalloy (nitinol) wire that is fully covered with a silicone membrane and has one repositioning lasso at one end of the stent. The delivery device is made of polymeric materials. The stent is loaded into the distal part of the delivery device and expanded in the body by pulling the outer sheath of the delivery device. The stent and delivery device are provided sterile and are intended for single use only.

The provided text describes a medical device, the HANAROSTENT® Trachea/Bronchium (CCC), and its 510(k) submission to the FDA. This document focuses on establishing substantial equivalence to predicate devices based on intended use, technological characteristics, biocompatibility, and bench testing.

The document does not contain information about acceptance criteria, the specific study that proves the device meets acceptance criteria, sample sizes for test or training sets, data provenance, number or qualifications of experts, adjudication methods, MRMC studies, or standalone algorithm performance.

Instead, the document details physical and functional attributes of the device and compares them to predicate devices to demonstrate substantial equivalence. It confirms that the device meets certain performance benchmarks through bench testing and biocompatibility standards.

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance based on studies, nor can I provide details about sample sizes, expert involvement, or algorithm-specific metrics as this information is not present in the provided text.

The information that can be extracted relevant to performance and testing is as follows:

1. Table of Acceptance Criteria and Reported Device Performance:

Since explicit "acceptance criteria" for clinical performance are not stated in the document, and no clinical study results are provided, a table like the one requested cannot be fully generated. The document only lists types of bench tests performed.

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

• The document states: "No clinical performance data is submitted in this 510(k)." and "No animal performance data is submitted in this 510(k)." Therefore, there is no test set of patient data described.
• The only tests mentioned are bench tests and biocompatibility tests, typically performed on a certain number of device units or material samples. The specific sample sizes for these bench and biocompatibility tests are not provided in this document.
• Data provenance is not applicable for a clinical or animal test set, as none were submitted.

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

• Not applicable, as no clinical test set with ground truth established by experts is mentioned.

4. Adjudication method for the test set:

• Not applicable, as no clinical test set requiring adjudication is mentioned.

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 medical device (stent), not an AI algorithm for diagnostic imaging, and therefore an MRMC study is not relevant to its type of premarket submission.

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

• Not applicable. This is a physical medical device (stent), not an algorithm.

7. The type of ground truth used:

• For the biocompatibility and bench tests, the "ground truth" would be established by industry standards (e.g., ISO, USP) and pre-defined specifications for material properties, mechanical performance, and biological response. These are not "expert consensus, pathology, or outcomes data" in the context of clinical evaluation.

8. The sample size for the training set:

• Not applicable. As this is a physical medical device and not an AI algorithm, there is no "training set" in the context of machine learning.

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

• Not applicable, as there is no training set for an AI algorithm.

Ask a specific question about this device

The Patient-Specific Airway Stent is indicated for the treatment of adults ≥22 years of age with symptomatic stenosis of the airway. The silicone stent is intended for implantation into the airway by a physician using the recommended deployment system or an equivalent rigid bronchoscope and stent placement system that accepts the maximum stent diameter being placed. The stent is intended to be in the patient up to 12 months after initial placement.

The Patient-Specific Airway Stent is comprised of Web Software and the Patient-Specific Silicone Y-Stent. These two function together as a system to treat symptomatic stenosis of the airway. The Patient-Specific Silicone Stent is designed by a physician using a CT scan as a guide in the Web Software. The Web Software gives the user (physician) the ability to upload a scan, view the airway, and design a stent. The stent, after physician approval, is manufactured via silicone injection into a 3D-printed mold and delivered to the treating physician's medical center nonsterile.

This document (K182743) is a 510(k) Premarket Notification for a Patient-Specific Airway Stent. It primarily focuses on demonstrating substantial equivalence to a predicate device (ENDOXANE, K971509) and the safety/effectiveness of the device.

Based on the provided text, the device in question is a Patient-Specific Airway Stent System, which includes Web Software and the Patient-Specific Silicone Y-Stent. The software allows physicians to design the stent based on a CT scan, and then the stent is manufactured via silicone injection into a 3D-printed mold.

The acceptance criteria and study that proves the device meets them are mostly related to non-clinical performance testing and software verification/validation, rather than a full clinical study with human patients evaluating the AI's diagnostic performance. Therefore, many of the typical acceptance criteria and study elements for an AI-powered diagnostic device are not explicitly detailed in this 510(k) summary.

Here's an attempt to extract the relevant information based on your request, acknowledging the limitations of the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't provide a direct table of acceptance criteria with specific numerical performance metrics for the software's ability to accurately design the stent or for the final stent's intended clinical outcome in terms of patient-specific fit. Instead, it describes various tests performed to ensure the device functions as intended and is substantially equivalent to the predicate.

The closest to "acceptance criteria" are the objectives of the non-clinical performance tests, and "reported device performance" is described qualitatively as "supports the claim" or "confirms."

Please note: The "device performance" here refers to the engineering and functional performance of the stent and software, not clinical outcome metrics (e.g., patient improvement rates).

Note on Quantitative Acceptance Criteria: The document explicitly mentions some differences, such as the subject device having lower flat-plate compression strength than the predicate device. However, it states that "Any risks related to these technological differences have been mitigated to an acceptable level," implying that these differences did not prevent meeting overall safety/effectiveness. For the AI component (segmentation and design), specific quantitative acceptance criteria (e.g., Dice score for segmentation accuracy, deviation from ideal stent dimensions) are not provided in this summary document.

2. Sample Size for Test Set and Data Provenance

• The document does not specify a sample size for the "test set" in the context of typical AI performance evaluation (e.g., number of CT scans used to validate segmentation or design accuracy).
• The closest mentions are "Dimensional Testing of Airway Segmentation" and "Airway Segmentation Process Validation." It's implied that some CT scan data was used for these, but neither the sample size nor the provenance (country, retrospective/prospective) of this data is mentioned.

3. Number of Experts and Qualifications for Ground Truth

• The document describes the device as a "Patient-Specific Airway Stent" where creation involves a "physician using a CT scan as a guide in the Web Software" and the stent is manufactured "after physician approval."
• The "Web Software" allows "COS technicians to segment the airway and automatically calculate a centerline."
• "Ground truth" for the AI component (segmentation, centerline calculation, stent design) is not explicitly defined in terms of expert consensus or pathological verification in this summary. Instead, it appears the software's output is reviewed and approved by a single physician for an individual patient.
• Therefore, it's not a panel of experts establishing ground truth for a general test set, but rather an individual physician performing the critical review and approval step for each patient. No specific number of experts used to establish ground truth for a general test set is mentioned, nor are their qualifications.

4. Adjudication Method for the Test Set

• Given that the "ground truth" for the AI's output is implied to be physician review and approval for each specific case, there is no multi-reader adjudication method (like 2+1 or 3+1) described for a general test set. The process involves one physician approving the design.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No MRMC study comparing human readers with and without AI assistance is mentioned or implied. The product is a custom-designed stent system, not a diagnostic AI intended to assist in interpreting medical images. The AI (software) assists in the design and manufacturing process, which is then approved by a physician.

6. Standalone (Algorithm Only) Performance

• No standalone (algorithm only) performance metrics are explicitly provided. The software acts as a design tool that then requires physician approval before manufacturing. The document describes "Software Verification and Validation Testing" and "Dimensional Testing of Airway Segmentation" which implies internal testing of the algorithm, but specific standalone metrics (e.g., segmentation accuracy against ground truth) are not reported in this summary.

7. Type of Ground Truth Used

• For the software's AI components (segmentation, centerline calculation), the implicit "ground truth" during real-world use is the physician's subjective review and approval based on the CT scan.
• For the non-clinical tests (e.g., tear strength, fatigue), the ground truth relates to engineering specifications and established test methods.
• No pathology or outcomes data is mentioned as ground truth for the software's performance, as this is a device design tool, not a diagnostic algorithm.

8. Sample Size for the Training Set

• The document does not specify the sample size for the training set used for any AI component (segmentation, centerline calculation). It only refers to a "proprietary software" used by "COS technicians" to segment the airway and calculate the centerline.

9. How Ground Truth for Training Set Was Established

• The document does not describe how ground truth for any potential AI training set was established.

Ask a specific question about this device

The Merit ENDOTEK AEROmini™ Tracheobronchial Stent System is indicated for use in the treatment of tracheobronchial strictures produced by malignant neoplasms.

The MERIT ENDOTEK AEROmini Tracheobronchial Stent System is comprised of two components: the radiopaque self-expanding nitinol stent and the delivery system. The stent is completely covered with a biocompatible polvurethane membrane. The stent expansion results from the physical properties of the metal and the proprietary geometry. The overall stent geometry is designed to maintain a constant length over the entire range of possible diameters. As a result of this unique design the stent has virtually no foreshortening, thus facilitating the selection of the appropriate stent length. The stent is deployed endoscopically with a dedicated delivery system with or without the aid of fluoroscopic imaging. The delivery system consists of two coaxial sheaths. The exterior sheath serves to constrain the stent until the sheath is retracted during deployment. The stent remains constrained by the delivery system until the trigger is pulled beyond the white deployment threshold mark located between the trigger and hand grip. This feature allows for repositioning of the stent proximally. A radiopaque tip and marker on the inner shaft aid the operator in determining stent position in relation to the deployment threshold mark, where repositioning or en bloc withdrawal is no longer possible. The inner sheath of the delivery system contains a central lumen that will accommodate a 0.035" guide wire. This feature is designed to allow guidance of the delivery system to the intended implant site while minimizing the risk of airway injury from the delivery system tip.

The stent and delivery system are provided sterile using ethylene oxide (EO) process.

This document describes a 510(k) premarket notification for the AEROmini Tracheobronchial Stent System, manufactured by Merit Medical Systems, Inc. The submission aims to demonstrate substantial equivalence to a legally marketed predicate device (K140382) to allow the device to be marketed.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly numerical targets in the provided text. Instead, the document states that the device "met the standards' established acceptance criteria applicable to the substantial equivalence of the device" and "met the predetermined acceptance criteria applicable to the performance of the device" for various tests. The general acceptance criterion is demonstrating that the new AEROmini device, with its new sizes and a new delivery system, performs equivalently to the predicate device and national/international standards without raising new questions of safety or effectiveness.

Below is a table summarizing the types of tests conducted (representing the indirectly stated acceptance criteria categories) and the reported device performance. No specific numerical thresholds or performance metrics are provided in this summary.

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

The document does not specify the sample sizes used for each individual test. It lists a "battery of tests" that were performed based on recognized performance standards and guidance. The provenance of the data (e.g., country of origin) is not mentioned beyond the fact that it was conducted by the manufacturer, Merit Medical Systems, Inc., for a U.S. FDA submission. The nature of these tests (mechanical, biocompatibility, sterilization, etc.) implies laboratory or bench testing rather than human clinical data. Therefore, it is not retrospective or prospective in the clinical trial sense.

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 the document. The "ground truth" for these engineering and materials tests is established by adhering to widely accepted international and national standards (e.g., ISO, ASTM, FDA guidance) and their specified methodologies, rather than expert consensus on individual cases. The manufacturers' internal experts and testing personnel would perform these tests and interpret the results against the standard criteria.

4. Adjudication method for the test set:

This is not applicable as the tests are primarily objective measurements against defined standards, not subjective interpretations requiring adjudication.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, what was the effect size of how much human readers improve with AI vs without AI assistance:

This is not applicable. The device described, the AEROmini Tracheobronchial Stent System, is a physical medical device (a stent and its delivery system), not an AI-powered diagnostic or assistive tool.

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

This is not applicable as the device is a physical stent system, not an algorithm.

7. The type of ground truth used:

The "ground truth" for the performance evaluations is based on adherence to:

• Recognized Performance Standards: e.g., ISO 11135:2014, ASTM D4169-16, ASTM F2052-15, ISO 10993 series.
• FDA Guidance: Specifically, "Guidance for the Content of Premarket Notifications for Esophageal and Tracheal Prostheses, April 28, 1998" and "Required Biocompatibility Training and Toxicology Profiles for Evaluation of Medical Devices, May 1, 1995."
• Internal specifications and risk analysis: "Performance testing was conducted based on the risk analysis."

These documents and standards define acceptable methods, materials properties, and performance limits for such devices.

8. The sample size for the training set:

This is not applicable. The device is a physical medical device and does not involve AI algorithms that require training sets.

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

This is not applicable.

Ask a specific question about this device

The WALLSTENT™ RP Endoprosthesis and WALLSTENT™ Endoprosthesis Tracheobronchial are indicated for use in the treatment of tracheobronchial strictures produced by malignant neoplasms.

The WALLSTENT RP Endoprosthesis Tracheobronchial and WALLSTENT Endoprosthesis Tracheobronchial are comprised of two components: The implantable metallic stent and the UNISTEP Plus delivery system. The stent is composed of biomedical superalloy wire, braided in a tubular mesh configuration. This design configuration results in a stent that is flexible, compliant, and self-expanding. The delivery system consists in part of coaxial tubes. The exterior tube serves to constrain the stent until retracted during delivery. Radiopaque marker bands situated on the interior and exterior tubes aid in imaging during deployment. Small stent sizes (5mm-12mm) may have a radiopaque core to improve radiopacity. The interior tube of the coaxial system contains a central lumen that accommodates a 0.035 in (0.89mm) guidewire.

This document describes the regulatory clearance for the WALLSTENT™ RP Endoprosthesis Tracheobronchial and WALLSTENT™ Endoprosthesis Tracheobronchial. This is a medical device, specifically a self-expanding stent used to treat tracheobronchial strictures caused by malignant neoplasms.

The submission is a 510(k) premarket notification, which means the manufacturer is demonstrating that the device is substantially equivalent to a legally marketed predicate device. Therefore, the "study" described is primarily focused on demonstrating this substantial equivalence, particularly regarding MRI compatibility, rather than a clinical study evaluating the device's efficacy against clinical acceptance criteria in a human population.

Given the nature of the document (a 510(k) summary), many of the requested details about acceptance criteria for device performance, ground truth establishment, expert adjudication, multi-reader multi-case studies, and training set information are not directly applicable or available. The study in question is a non-clinical bench test study for MR compatibility.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present specific quantitative acceptance criteria for clinical performance (e.g., success rates, complication rates) or an AI model's performance. Instead, it focuses on demonstrating substantial equivalence to a predicate device and safety, particularly regarding MR compatibility.

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

The document describes non-clinical bench testing. Therefore, the concept of a "test set" in the context of patient data or clinical images does not apply. The "sample size" would refer to the number of physical devices or components tested in the lab. This specific number is not explicitly stated in the provided text, but the testing was for MR compatibility. The data provenance is from bench testing conducted by Boston Scientific Corporation.

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

Not applicable. The study is non-clinical bench testing for MR compatibility, not a study involving medical images needing expert interpretation.

4. Adjudication Method for the Test Set

Not applicable. This was a non-clinical bench test, not a study involving human interpretation or adjudication of medical data.

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

No. This document describes a 510(k) submission for a physical medical device, not an AI or imaging software. The study performed was non-clinical bench testing for MR compatibility.

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

Not applicable. This is not an AI or algorithm-based device.

7. The Type of Ground Truth Used

For the MR compatibility testing, the "ground truth" would be established by physical measurements and adherence to the FDA guidance document "Establishing Safety and Compatibility of Passive Implants in the Magnetic Resonance (MR) Environment." This involves objective physical testing for parameters such as magnetically induced displacement force, torque, and heating, and assessment of image artifact.

8. The Sample Size for the Training Set

Not applicable. This is not an AI or algorithm-based device, so there is no "training set."

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

Not applicable. There is no training set for this type of device submission.

Ask a specific question about this device