Search Results

The Esophageal Stent System is intended for maintaining esophageal strictures caused by intrinsic and/or extrinsic malignant tumors, and occlusion of concurrent esophageal fistula.

The Esophageal Stent System consists of a self-expanding metal stent and a stent introduction system. The stent is provided pre-loaded in the introduction system. The handle allows for desheathing to deploy the stent and resheathing recapturing the stent during stent deployment. The stent is woven from nitinol wire. The stent is formed with a flange at either end. The increased diameter of the stent ends helps provide resistance to migration. A silicone membrane applied to the stent covers the complete body of the stent along with part or fully of both flanges. The covering is intended to reduce the risk of tissue ingrowth and provides a seal for esophageal fistulas. To aid in visibility under fluoroscopy there are four bands at either end of the stent. The stent has a lasso loop 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.

The provided text is a 510(k) summary for the Micro-Tech (Nanjing) Co., Ltd. Esophageal Stent System (K172813). It details the device, its intended use, comparison to a predicate device, and performance data. However, this document does not describe the acceptance criteria or a study that proves the device meets the acceptance criteria in the context of an AI/algorithm-based medical device.

The questions posed in the request (e.g., sample size for test set, number of experts, MRMC studies, standalone performance, ground truth establishment) are relevant to the evaluation of AI/ML-based medical devices, which typically involve performance metrics like sensitivity, specificity, AUC, etc., derived from studies comparing algorithm output to established ground truth.

This 510(k) submission is for a physical medical device (an esophageal stent) and its material and mechanical properties. The "Performance Data" section in the document refers to:

• Biocompatibility Testing: Evaluating the biological safety of the materials used in the stent.
• Device-specific performance tests: Visual inspection, dimension testing, deployment force, expansion force, compression force, corrosion testing, tensile strength, sterility, shelf life, and MR compatibility.

There is no mention of an AI/ML algorithm, or any study design that would involve a "test set," "training set," "ground truth" derived from expert consensus, or "human readers improving with AI assistance."

Therefore, I cannot answer the specific questions about acceptance criteria for an AI device or a study proving its performance from the provided text. The document explicitly states: "No clinical study is included in this submission." This further indicates that the type of performance evaluation relevant to AI/ML devices (which often involves clinical data and observer studies) was not part of this 510(k) submission.

Ask a specific question about this device

The Endoscopic Ultrasound Aspiration Needle is designed to sample targeted submucosal and extraluminal gastrointestinal lesions through the accessory channel of suitable ultrasound videoendoscope in adult patients only.

The proposed Endoscopic Ultrasound Aspiration Needle is a sterile single-use device, designed to sample targeted submucosal and extraluminal gastrointestinal lesions through the accessory channel of suitable ultrasound videoendoscope.

It consists of three parts, Aspiration Needle, Syringe and Stopcock. The aspiration needle is offered with multiple types with different dimension, needle tip design and needle material. Syringe and stopcock are accessories to provide and control the vacuum suction to aspirate the sample.

There are 12 specifications, the difference is the diameter, material and tip design of needle.

The proposed devices are EO sterilized to achieve the Sterility Assurance Level (SAL) of 10t and placed in a sterility maintenance package to ensure a shelf life of 2 years.

This document is a 510(k) summary for the Endoscopic Ultrasound Aspiration Needle, which is a medical device. It does not contain information about the acceptance criteria or a study proving the device meets performance criteria for an AI/ML powered device. The document focuses on regulatory approval for this specific type of medical device by demonstrating substantial equivalence to predicate devices, not on proving performance through specific metrics associated with AI/ML.

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

• Acceptance criteria in terms of AI/ML performance metrics (e.g., sensitivity, specificity, AUC).
• A study that proves the device meets such acceptance criteria.
• Sample sizes for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, or ground truth types related to an AI/ML algorithm.
• Training set sample size or how ground truth for a training set was established.

This document describes a traditional medical device approval process based on comparison to existing legally marketed devices, not an AI/ML product.

Ask a specific question about this device

The LuminScan(TM) Imaging System is is indicated for use as an imaging tool in the evaluation of human tissue microstructure by providing two dimensional, cross sectional, real-time depth visualization.

LuminScan™ Imaging System is a general imaging system comprised of LuminScan™ Imaging System Console and LuminScan™ Disposable Imaging Kit.

The provided document is a 510(k) Summary for the LuminScan™ Imaging System. This type of submission is for demonstrating substantial equivalence to a legally marketed predicate device, rather than providing comprehensive clinical study data for new claims.

Based on the provided text, the following information can be extracted regarding acceptance criteria and performance:

1. Table of Acceptance Criteria and Reported Device Performance:

The document states, "all the tests were found to be within their test acceptance criteria (passing test result)" for the Disposable Imaging Kit testing, System Performance Testing, and Reliability Testing. However, specific numerical acceptance criteria (e.g., minimum values, ranges, tolerances) are not detailed in the provided text. The tables only list the tests performed and a general "passing test result."

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

• Disposable Imaging Kit Testing: The specific sample sizes for each individual test (e.g., balloon burst, tensile strength) are not provided.
• Reliability Testing: The specific sample sizes for environmental and vibration testing are not provided.
• System Performance Testing: The specific sample size is not provided.
• Animal Testing: The sample size was 2 Bama miniature pigs (one male, one female). The provenance is implied to be internal testing by Micro-Tech (Nanjing) Co., Ltd., which is located in Nanjing, China. This was a prospective animal study as part of the device evaluation.
• No clinical performance data (human studies) was included in this 510(k) submission. Therefore, there is no human test set or data provenance mentioned for clinical performance.

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

• No human "test set" in the context of clinical images with expert-established ground truths is mentioned. The submission explicitly states: "This section is not applicable because there is not including any clinical performance data with this 510(k) Submission."
• For the animal testing, the "ground truth" was the in vivo imaging procedure itself and the assessment of image quality against design requirements. The document does not specify the number or qualifications of experts who evaluated the animal images.

4. Adjudication Method for the Test Set:

• Not applicable as no clinical performance data with human test sets and expert adjudication is presented.

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

• No, an MRMC comparative effectiveness study was not done. The submission states "there is not including any clinical performance data with this 510(k) Submission." Thus, no comparison of human readers with or without AI assistance was performed or reported here.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) was done:

• The LuminScan™ Imaging System is described as an "imaging tool" to provide 2D, cross-sectional, real-time depth visualization. It is an Optical Coherence Tomography (OCT) device, which generates images for human interpretation, not an AI algorithm that provides automated diagnoses or standalone performance metrics. Therefore, a standalone algorithm-only performance study as typically understood for AI/ML devices is not applicable here. The "System Performance Testing" and "Animal Testing" were likely evaluations of the device's ability to produce clear images suitable for human interpretation and meet its specified imaging capabilities.

7. The Type of Ground Truth Used:

• For the technical performance tests (Disposable Imaging Kit, Reliability, System Performance): The ground truth was based on engineering specifications, recognized standards (e.g., ISO, IEC), and design requirements.
• For animal testing: The "ground truth" was the visual assessment of the captured two-dimensional and cross-sectional OCT images of the animal esophagus, ensuring they met the device's design requirements for imaging procedure and image quality. This is an observational, expert-evaluated ground truth against technical specifications.

8. The Sample Size for the Training Set:

• The LuminScan™ Imaging System is an OCT imaging device, not explicitly an AI/ML-driven diagnostic algorithm that typically relies on large training datasets for image interpretation. While it contains software, the 510(k) summary classifies it as having a "Minor" level of concern for software failures, implying its primary function is image acquisition and display rather than complex automated analysis requiring extensive image training sets. Therefore, a "training set" in the context of machine learning is not discussed or specified in this document.

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

• Not applicable, as no training set for a machine learning algorithm is mentioned or implied by the device's description in this submission.

Ask a specific question about this device

The Sterile Repositionable Hemostasis Clipping Device is indicated for endoscopic clip placement within the gastrointestinal tract for the purpose of:
(1) endoscopic marking,
(2) hemostasis for
(a) mucosal / sub-mucosal defects < 3cm,
(b) bleeding ulcers,
(c) polyps < 1.5cm in diameter,
(d) diverticula in the colon,
(3) as a supplementary method, closure of Gl tract luminal perforations <20mm that can be treated conservatively.

The proposed device Sterile Repositionable Hemostasis Clipping Device is a sterile, single-use endoscopic clipping device, intended to be used for endoscopic marking, hemostasis for mucosal/submucosal defects in digestive tract. It consists of two main components, delivery system and clip assembly. And it is offered in different dimensions.

The provided text describes a 510(k) premarket notification for a medical device, the "Sterile Repositionable Hemostasis Clipping Device". This document is submitted to the FDA to demonstrate substantial equivalence to a predicate device, not typically to prove a device meets specific clinical performance acceptance criteria through a study with ground truth. Therefore, many of the requested categories for AI/algorithm performance studies are not directly applicable.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria or a direct performance table in the typical sense of algorithm-based device performance (e.g., sensitivity, specificity). Instead, it lists bench tests performed to demonstrate equivalence to a predicate device. The general acceptance criterion is that the device "meets the requirements" of relevant ISO standards and that "the testing performed demonstrated that the proposed and predicate delivery systems are equivalent."

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

Not applicable. This is a medical device for physical intervention, not an AI/algorithm-based diagnostic or prognostic device that uses a test set of data. The "tests" mentioned are bench tests on the physical device.

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

Not applicable. This device does not rely on expert-established ground truth for its performance evaluation in the context of this 510(k) submission.

4. Adjudication method 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

No. The document explicitly states: "No clinical study is included in this submission." This is not an AI-assisted device.

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

No. This is a physical hemostasis clipping device, not an algorithm.

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

Not applicable in the context of AI/algorithm performance. For the bench tests, the "ground truth" would be the engineering specifications and performance characteristics of the predicate device and the relevant ISO standards.

8. The sample size for the training set

Not applicable. This is not an AI/algorithm device.

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

Not applicable.

Ask a specific question about this device