Search Results

The HANAROSTENT® Esophagus (CCC) and HANAROSTENT® Esophagus (NCN) are intended for maintaining esophageal luminal patency in esophageal strictures caused by intrinsic malignant tumors, and occlusion of concurrent esophageal fistulas.

This self-expanding tubular prosthesis is designed to maintain patency in esophageal strictures caused by intrinsic and/or extrinsic malignant tumors, and occlusion of concurrent esophageal fistulas. It consists of a self-expandable metal stent and an over the wire (OTW) delivery device. The self-expandable metal stent is made of nickel titanium alloy (Nitinol) wire, radiopaque markers made of gold wire, fully or partially covered silicone membrane, and one repositioning lasso at each end of the stent made of polymeric materials. 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 HANAROSTENT® Esophagus (CCC) and the HANAROSTENT® Esophagus (NCN) are intended for single use only.

The provided text is a 510(k) summary for the HANAROSTENT® Esophagus (CCC) and HANAROSTENT® Esophagus (NCN) devices. This document focuses on demonstrating substantial equivalence to a predicate device through bench testing rather than presenting a clinical study with acceptance criteria for device performance.

Therefore, the requested information regarding acceptance criteria, study details, sample sizes, ground truth, and expert involvement for a study proving device performance against acceptance criteria cannot be fully extracted from the provided text. The document explicitly states:

• "No animal performance data is submitted in this 510(k)."
• "No clinical performance data is submitted in this 510(k)."

Instead, the submission relies on bench testing to demonstrate performance and substantial equivalence.

Here's an analysis of what can be extracted or inferred based on the scope of the document:

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

The document does not explicitly present a table of acceptance criteria with corresponding performance values in the way you've requested for a device proving study. It lists various bench tests performed and states:

• "Bench testing was performed to confirm the safety and effectiveness of the proposed subject devices as compared to the predicate devices."
• "Performance testing was performed as per the design control system."
• "The subject and predicate devices have equivalent expansion forces."
• "The subject and predicate devices have equivalent compression forces."
• "The subject delivery device in both 6mm (18Fr) and 8mm (24Fr) diameters have lower deployment forces than the predicate delivery device when deploying the HANAROSTENT® Esophagus (CCC)."
• "The subject delivery device in 6mm (18Fr) diameter has lower deployment force than the predicate delivery device when deploying the HANAROSTENT® Esophagus (NCN). The subject delivery device in 8mm (24Fr) diameter has equivalent deployment force to the predicate delivery device when deploying the HANAROSTENT® Esophagus (NCN)."

From this, we can infer that the acceptance criterion for many of these bench tests was "equivalence to the predicate device" or "lower than the predicate device" (for deployment force, which is a positive outcome). However, specific numerical acceptance thresholds or detailed performance metrics are not provided.

Inferred Table of Performance and Criteria (Based on Bench Testing for Substantial Equivalence):

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

The document does not specify sample sizes used for the bench tests. Since no clinical data was submitted, there is no "test set" in the context of patient data. The bench tests were presumably conducted internally by M.I.Tech Co., Ltd., based in the Republic of Korea. Therefore, the data provenance for these bench tests would be the Republic of Korea. It's not applicable to categorize bench testing as retrospective or prospective.

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 submission relies entirely on bench testing for substantial equivalence, not on a clinical test set requiring expert interpretation or ground truth establishment in a medical context.

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

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

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 not an AI/software device and no MRMC study was conducted.

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

Not applicable. This is a medical device (stent and delivery system), not an algorithm.

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

Not applicable. For the bench tests, the "ground truth" would be the engineering specifications and established standards for material and device performance, against which the physical properties of the stent were tested.

8. The sample size for the training set

Not applicable, as no clinical study (and thus no training set) was conducted or submitted.

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

Not applicable, as there is no training set.

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 HANAROSTENT® Esophagus TTS (CCC) and HANAROSTENT® Esophagus TTS (NCN) are intended for maintaining esophageal luminal patency in esophageal strictures caused by intrinsic malignant tumors, and occlusion of concurrent esophageal fistulas.

This self-expanding tubular prosthesis is designed to maintain esophageal luminal patency in esophageal strictures caused by intrinsic and/or extrinsic malignant tumors, and occlusion of concurrent esophageal fistulas. It consists of a self-expandable metal stent and a through-the scope delivery system. The self-expandable metal stent is made of nickel titanium alloy (Nitinol) wire, radiopaque markers made of gold wire, fully or partially covered silicone membrane, and repositioning lasso made of polyester. 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 delivery system is compatible with a minimum 3.7mm working channel of a therapeutic endoscope. The HANAROSTENT® Esophagus TTS (CCC) and HANAROSTENT® Esophagus TTS (NCN) are intended for single use only.

This document describes the FDA 510(k) premarket notification for the HANAROSTENT Esophagus TTS (CCC) and HANAROSTENT Esophagus TTS (NCN) devices. This is a medical device, specifically an esophageal prosthesis, and the submission focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than providing clinical performance data from studies involving AI or complex data analysis.

Therefore, many of the requested items (e.g., sample size for test/training sets, expert ground truth establishment, MRMC studies, standalone algorithm performance, effect size of human reader improvement with AI) are not applicable to this type of device submission. The information provided is primarily related to bench testing (physical and mechanical properties) to prove equivalence.

Here's a breakdown of the relevant information provided in the document based on your request:

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

The document describes bench testing to demonstrate similarity to the predicate device. It doesn't explicitly state "acceptance criteria" in a numerical table form for each test, but it indicates that the subject devices "have equivalent" or "greater" performance in certain aspects compared to the predicate device. The underlying acceptance criterion for these tests would be "equivalent performance to the predicate device" or "acceptable performance within a given range" determined by the manufacturer and accepted by the FDA for substantial equivalence.

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

• Test set sample size: Not explicitly stated. The "test set" here refers to the samples of the HANAROSTENT device used for bench testing. The testing would have involved a number of manufactured units, but the specific count is not provided.
• Data provenance: The bench testing was performed by the manufacturer, M.I. Tech Co., Ltd., which is based in South Korea. The data is from prospective testing of newly manufactured devices.

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

• Not applicable. This device relies on pre-clinical bench testing (mechanical and material properties) and substantial equivalence to a predicate device. There is no "ground truth" derived from expert interpretation of medical images or clinical outcomes in this submission.

4. Adjudication method for the test set:

• Not applicable. As there are no human interpretations or clinical outcomes requiring adjudication.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

• No, an MRMC comparative effectiveness study was not done. The submission is for a medical device (stent) and relies on bench testing and substantial equivalence.

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

• Not applicable. This is not an AI/algorithm-based device. It is a physical medical implant.

7. The type of ground truth used:

• The "ground truth" for this submission comes from bench testing specifications, engineering principles, and comparison to the known performance of the predicate device. For example, the "ground truth" for expansion force is a measurable mechanical property verified against engineering standards and the predicate device's performance. There is no clinical "ground truth" (e.g., pathology, clinical outcomes, expert consensus) presented in this 510(k) summary.

8. The sample size for the training set:

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

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

• Not applicable. There is no training set for this device.

Ask a specific question about this device

The HANAROSTENT LowAxTM Colon/Rectum (NNN) is indicated for the palliative treatment of colorectal strictures produced by malignant neoplasms and to relieve large bowel obstruction prior to colectomy in palignant structures.

The HANAROSTENT LowAxTM Duodenum/Pylorus (NNN) is indicated for the palliative treatment of pyloric or duodenal obstructions caused by malignant neoplasms.

This self-expanding tubular prosthesis designed to maintain patency of colorectal or duodenal obstructions caused by malignant tumors. It consists of a self-expandable metal stent and a delivery system. The self-expandable metal stent is made of nickel titanium alloy (Nitinol) wire and the delivery system is made of polymeric materials. The stent is loaded into the distal part of the delivery system. The HANAROSTENT® LowAx™ Colon/Rectum (NNN) and HANAROSTENT® LowAx™ Duodenum/Pylorus (NNN) are intended for single use only.

This document (a 510(k) summary) describes a submission for a medical device re-clearance rather than a de novo submission. The primary purpose of this submission is to demonstrate substantial equivalence to a previously cleared predicate device (K180180), not to prove de novo clinical efficacy or safety of a fundamentally new device through extensive clinical trials.

Therefore, the typical components of acceptance criteria and the detailed study proving the device meets those criteria (especially regarding human-in-the-loop AI performance, ground truth establishment for large datasets, etc.) are not present in this type of regulatory document. The focus shifts to demonstrating that the new version of the device is essentially the same as the previously cleared version, with any minor changes like MR compatibility testing still ensuring safety and effectiveness.

Here's a breakdown based on the provided text, explaining why certain requested information is absent or not applicable:

Key Takeaway: The device in question (HANAROSTENT LowAx™ Colon/Rectum and Duodenum/Pylorus) is a self-expanding metal stent. Its performance is assessed through bench testing (physical and material properties) and by demonstrating identical characteristics to a previously cleared device, not through studies involving AI, human reader improvement, or large-scale clinical outcomes data in the way a diagnostic AI device would be.

Acceptance Criteria and Device Performance (Based on "Substantial Equivalence" and "Performance Testing" sections):

This submission leverages the substantial equivalence pathway. The primary "acceptance criteria" are demonstrating that the subject device is identical or nearly identical to its predicate device (K180180) in critical aspects, and that any small change (MR compatibility) does not compromise safety or effectiveness.

Here's a table reflecting what is implicitly stated as "met" by virtue of substantial equivalence and new testing:

Regarding the Absence of Specific Study Details (as related to AI/Diagnostic Devices):

This submission is for a medical device (physical stent), not a diagnostic algorithm or AI software for image analysis. Therefore, many of the requested details related to AI study design are not applicable or not part of this type of submission.

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

   • N/A (for AI/diagnostic data). This device is a physical stent. Performance testing involves bench tests (e.g., force measurements, corrosion) on device samples, not patient data sets or images. The "test set" in this context refers to the physical devices or components tested. There are no "patients" or "data" in the sense of a diagnostic study.

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

   • N/A. Ground truth for a physical stent is established by engineering specifications, material science, and established test methods (e.g., ASTM standards for mechanical properties). No human experts are adjudicating "ground truth" on images or clinical outcomes for this device in this submission.

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

   • N/A. Applies to human reading/AI performance studies, not physical device testing.

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:

   • N/A. This device does not involve human readers, AI assistance, or image interpretation.

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

   • N/A. This is not an algorithm or AI device. Its "standalone performance" refers to its physical characteristics and functionality as a stand-alone stent and delivery system, assessed via bench tests.

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

   • For the physical properties: Engineering specifications, established test methods (e.g., ISO, ASTM standards), and material science principles.
   • For comparison to the predicate: The previously cleared predicate device (K180180) itself serves as the "ground truth" for substantial equivalence regarding its established safety and effectiveness.

7. The sample size for the training set:

   • N/A. This is not an AI/machine learning device that requires a "training set."

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

   • N/A. No training set is involved.

In summary, this 510(k) submission leverages the "Substantial Equivalence" pathway for a physical medical device. The "study that proves the device meets the acceptance criteria" primarily consists of:

• A detailed comparison demonstrating identical technological characteristics to a previously cleared predicate device (K180180).
• Reliance on the performance testing data submitted for that predicate device.
• New bench testing specifically for MR compatibility to support new labeling.

The document explicitly states: "The subject device in this Traditional 510(k) submission is the exact same, identical device as predicate device K180180." This claim, supported by the comparison of characteristics and leveraging prior testing, is the core of demonstrating it meets the implicit "acceptance criteria" for clearance via substantial equivalence.

Ask a specific question about this device

The HANAROSTENT LowAxTM Colon/Rectum (NNN) is indicated for the palliative treatment of colorectal strictures produced by malignant neoplasms and to relieve large bowel obstruction prior to colectomy in patients with malignant structures.

The HANAROSTENT LowAxTM Duodenum/Pylorus (NNN) is indicated for the palliative treatment of pyloric or duodenal obstructions caused by malignant neoplasms.

This self-expanding tubular prosthesis is designed to maintain patency of colorectal or duodenal obstructions caused by malignant tumors. It consists of a self-expandable metal stent and a delivery system. The self-expandable metal stent is made of nickel titanium alloy (Nitinol) wire, and the delivery system is made of polymeric materials. The stent is loaded into the distal part of the delivery system, and expanded in the body by pulling the outer sheath of the delivery system. The HANAROSTENT® LowAx™ Colon/Rectum (NNN) and HANAROSTENT® LowAxTM Duodenum/Pylorus (NNN) are intended for single use only.

The provided text describes a 510(k) premarket notification for two devices: HANAROSTENT LowAx™ Colon/Rectum (NNN) and HANAROSTENT LowAx™ Duodenum/Pylorus (NNN). This notification aims to demonstrate substantial equivalence to previously cleared predicate devices.

However, the document does not contain information about acceptance criteria for device performance based on a clinical study or a study proving that the device meets such criteria. Instead, it focuses on demonstrating technological equivalence and presents the results of bench testing to confirm safety and effectiveness.

Therefore, I cannot provide a table of acceptance criteria and reported device performance derived from a clinical study, nor can I answer questions about sample sizes for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, or standalone algorithm performance, as these pertain to clinical or AI performance studies which are not detailed in this document.

The document does provide information pertinent to physical and material performance, as outlined in the "Performance Summary" section.

Here's what can be extracted from the document regarding the performance validation performed:

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

The document describes bench testing performed to confirm safety and effectiveness compared to predicate devices, but it does not explicitly list quantitative acceptance criteria or specific reported performance values for these tests. It only lists the types of tests conducted.

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

Not applicable. The document describes bench testing, not a clinical study with human subjects.

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 document describes bench testing, not a clinical study requiring expert ground truth for interpretation.

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

Not applicable. The document describes bench testing, not a clinical study requiring adjudication of expert interpretations.

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

Not applicable. The document describes a medical device (stent) and does not involve AI or human readers for diagnostic interpretation.

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

Not applicable. The document describes a medical device (stent) and does not involve an algorithm with standalone performance.

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

For the bench testing, the "ground truth" would be the expected physical or mechanical properties and behaviors of the stent as per engineering specifications and relevant standards. This is inherent in the design control system and the performance tests themselves.

8. The sample size for the training set:

Not applicable. The document describes a medical device (stent) and its physical and mechanical performance testing, not a machine learning model requiring a training set.

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

Not applicable. The document describes a medical device (stent) and its physical and mechanical performance testing, not a machine learning model requiring a training set.

Summary of available information related to performance (bench testing):

The document states that "Appropriate bench testing was performed to confirm the safety and effectiveness of the proposed devices as compared to the identified predicate device." This testing was conducted "as per the design control system" and consulted "Guidance for the content of premarket notifications for esophageal and tracheal prostheses issued April 28th, 1998."

Types of Bench Tests Conducted:

• Axial force
• Compression force
• Corrosion
• Deployment force
• Deployment accuracy
• Dimensions
• Expansion force
• Repositioning force
• Stent separation
• Tensile strength
• Trackability

Biocompatibility Assessment:

• Assessed in accordance with ISO 10993-1:2003, 2012.

Conclusion from Bench Testing:
The non-clinical data (bench testing) supports the safety of the proposed devices and demonstrates that they are safe and effective and will perform as intended in the specified use conditions. It also concludes that the proposed device is substantially equivalent to the predicate devices based on these tests and technological characteristics.

Ask a specific question about this device

The HANAROSTENT® BILIARY (NNN) is indicated for the palliation of malignant strictures in the biliary tree.

The HANAROSTENT® Biliary (NNN) is a self-expanding uncoated tubular prosthesis designed to maintain patency of bile duct strictures caused by malignant tumors. It consists of a self-expanding metal stent and delivery system. The Biliary stent is made of Nickel Titanium alloy (Nitinol) wire, which expands at body temperature. The stent is deployed with supplied introducers for percutaneous and endoscopic use.

The Stent is available in two diameters (8 and 10mm) and eight lengths (40mm, 50mm, 60mm, 70mm, 80mm, 90mm, 100mm, and 120mm). User preference, individual patient condition and/or anatomy determine the appropriate type and size for use. The HANAROSTENT® Biliary (NNN) is intended for single use only.

This document describes a 510(k) premarket notification for the HANAROSTENT® Biliary (NNN) device, a self-expanding metal stent indicated for the palliation of malignant strictures in the biliary tree. The submission focuses on demonstrating substantial equivalence to a predicate device (Niti-S Biliary Stent & Introducer) rather than providing detailed acceptance criteria and a standalone human factors study.

Here's an analysis of the provided information, addressing your specific points:

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

The provided document does not explicitly state specific acceptance criteria (e.g., numerical thresholds for performance) for general device functionality, nor does it provide a direct table of reported device performance in this format.

Instead, the submission relies on demonstrating substantial equivalence to an existing predicate device (Niti-S Biliary Stent & Introducer) through comparison of design, materials, and intended use. The performance summary refers to "bench testing" that was performed to "confirm the safety and effectiveness" as compared to the predicate device.

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

The document does not mention any clinical study involving a "test set" of patient data. The performance claims are based on bench testing and biocompatibility assessment, not on clinical outcomes with a specific sample size. Therefore, there's no information on data provenance (country, retrospective/prospective).

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

This question is not applicable as there was no clinical "test set" and thus no ground truth established by experts in a clinical context for this submission. The evaluation was based on engineering bench testing and regulatory assessment of substantial equivalence.

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

This question is not applicable as there was no clinical "test set" requiring adjudication.

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

This question is not applicable. The device is a medical stent, not an AI-powered diagnostic or assistive technology. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance is irrelevant to this submission.

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

This question is not applicable. The device is a medical stent, not an algorithm.

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

As this submission relies primarily on bench testing and comparison to a predicate device, the "ground truth" for the device's technical performance would be based on engineering standards and measurements, and for biocompatibility, ISO 10993-1:2003 standards. There is no mention of clinical ground truth like pathology or outcomes data.

8. The sample size for the training set

This question is not applicable. The device is a physical medical device, not an AI model, so there is no "training set."

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

This question is not applicable as there is no training set for this device.

In summary:

This 510(k) submission for the HANAROSTENT® Biliary (NNN) is a predication-based submission. The "study that proves the device meets the acceptance criteria" is fundamentally a comparison to a legally marketed predicate device (Niti-S Biliary Stent & Introducer) supported by bench testing and biocompatibility assessments. The submission's core argument is that the new device has "the same device characteristics, composition, function, and intended use" as the predicate, with minor differences not raising new questions of safety or efficacy. The FDA's letter concurs with the substantial equivalence claim, allowing the device to proceed to market with specific labeling limitations regarding vascular use.

Ask a specific question about this device

HANAROSTENT® Esophagus (CCC) is intended for maintaining esophageal luminal patency in esophageal strictures caused by intrinsic and/or extrinsic malignant tumors, and occlusion of concurrent esophageal fistula.

HANAROSTENT® Esophagus (CCC) is a self-expanding polygon mesh surface, tubular prosthesis designed to maintain patency of esophageal strictures caused by malionant tumors. The stent is made of Nitinol wire (hook and cross wire structure) and a silicon membrane designed in such a way as to prevent migration and tumor in-growth. The stent is symmetrical in shape, with the diameter of both ends of the stent extending beyond the diameter of the stent body (larger banded flanges). This band design has become standard practice and aids in preventing stent migration.

Based on the provided text, the device in question, HANAROSTENT® Esophagus (CCC), is a medical device, specifically an esophageal stent, and not an AI/ML powered device. As such, the concept of "acceptance criteria" and "device performance" in the context of AI models (e.g., accuracy, sensitivity, specificity) and human reader studies (MRMC) does not directly apply here.

The document describes a 510(k) submission for substantial equivalence to predicate devices, focusing on physical and mechanical properties, as well as intended use.

However, I can extract information related to the device's technical specifications and compare them to predicate devices, which serves as the basis for its "acceptance" by the FDA as substantially equivalent.

Here's an interpretation based on the provided text, framed to align as closely as possible with your request, even though it's a medical device rather than an AI system:

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

The "acceptance criteria" for a 510(k) submission for a non-AI medical device like this are generally demonstrating substantial equivalence to a legally marketed predicate device. This involves comparing intended use, technological characteristics, and performance data to ensure no new safety or effectiveness concerns are raised.

In this case, the reported "device performance" is a comparison of key physical and mechanical properties to predicate devices. The "acceptance criteria" are implied to be that these characteristics are similar enough to not introduce new risks.

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

The document states "The results of bench and test laboratory testing indicate that the new device is as safe and effective as the predicate devices." and mentions "analyzing both bench as well as laboratory testing to applicable standards".

• Sample size for test set: Not explicitly stated. The testing appears to be on the physical device itself (material, mechanical properties, etc.), not a clinical "test set" of patients.
• Data provenance: Not explicitly stated. It's bench and laboratory testing, likely conducted by the manufacturer, M. I. Tech Co., Ltd. (Korea), given their address is provided.
• Retrospective or prospective: Not applicable as it's bench/lab testing, not a clinical study.

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 is not applicable as the study involves bench and laboratory testing of a physical medical device's properties, not the evaluation of a diagnostic or predictive algorithm. There isn't a "ground truth" to be established by medical experts in this context.

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

Not applicable. There's no adjudication method in the context of physical property testing for substantial equivalence.

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

Not applicable. This is a physical medical device (esophageal stent), not an AI-powered diagnostic tool. Therefore, MRMC studies and "human readers improve with AI" are irrelevant to this submission.

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

Not applicable. There is no algorithm or AI component in this device.

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

For the bench and laboratory testing, the "ground truth" would be established by validated scientific methods and accepted engineering standards for measuring physical and mechanical properties (e.g., using calibrated instruments to measure force, diameter, corrosion resistance). It's not a clinical "ground truth."

8. The sample size for the training set

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

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

Not applicable. As above, there is no training set for a traditional medical device like this.

Ask a specific question about this device

The CHOOSTENT™ covered esophageal stent is intended for maintaining esophageal luminal patency in esophageal strictures caused by intrinsic and or extrinsic malignant tumors only and occlusion of concurrent esophageal fistula.

This stent is a self-expanding tubular prosthesis designed to maintain patency of esophageal stricture caused by malignant tumors. The unique structure of the membrane connects the several segments to increase the flexibility of the stent and to prevent migration and tumor in-growth. Since the both ends of stent have larger bands, the stent can be fixed firmly within the esophagus. There are totally 12 excellent radiopaque markers made of gold wires; 4 each on both ends of the stents and another 4 at the center. Two retrieval lassos attached to the both ends play a role in removing the stent when necessary or pulling the stent up to the right position in case the stent has been deployed deeply down the stricture. The fully expanded diameter is 18mm for the body and 24mm for both larger bands. There are four standard lengths: 80mm, 110mm, 140mm, 170mm.

This is a 510(k) premarket notification for a medical device, the CHOOSTENT™ covered Esophageal Stent. The document focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study with specific acceptance criteria and performance metrics for a standalone AI or human-in-the-loop system.

Therefore, many of the requested fields are not applicable (N/A) because the provided information is for a physical medical device (esophageal stent) and not an AI/software as a medical device.

Here's the breakdown based on the provided text:

Acceptance Criteria and Device Performance

Note: The acceptance criteria for the CHOOSTENT™ are implicitly defined by showing comparable or superior performance to the predicate device across these metrics. The conclusion explicitly states that "the CHOOSTENT™ covered Esophageal Stent is as safe and effective as the predicate devices, has few technological differences, and has no new indications for use, thus rendering it substantially equivalent to the predicate devices."

Study Details (Applicable to AI/Software as a Medical Device - N/A for this Stent)

1. Sample size used for the test set and the data provenance: N/A (This is a physical medical device, not an AI/software requiring a test dataset of patient data. The "tests" mentioned are bench and laboratory tests on the device itself.)

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: N/A (Ground truth as understood for AI is not applicable here.)

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

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: N/A (This is not an AI-assisted diagnostic or therapeutic device.)

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: N/A (This device is implanted by a human physician, not an autonomous algorithm.)

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the physical device, the "ground truth" is defined by established engineering and material science standards for device performance, biocompatibility, and safety. This is demonstrated through bench and laboratory testing. The regulatory standard is substantial equivalence to a legally marketed predicate device.

7. The sample size for the training set: N/A (No AI training set.)

8. How the ground truth for the training set was established: N/A (No AI training set.)

Ask a specific question about this device