Search Results

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

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

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

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

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

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

Ask a specific question about this device

For In Vitro Diagnostic Use

MetaLite DX Digital Pathology Software is a software only device intended for viewing and management of digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue for the purposes of pathology primary diagnosis. It is an aid to the pathologist to review, interpret and manage digital images of pathology slides.

MetaLite DX Digital Pathology Software is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens.

It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the quality of the images obtained and, where necessary, use conventional light microscopy review when making a diagnostic decision. MetaLite DX Digital Pathology Software is intended for use with Philips Ultra Fast Scanner and the Barco MDPC-8127 display.

MetaLite DX Digital Pathology Software, Model MLDXUS, version 1.2.1 is software designed for viewing digital pathology images of glass slides from the Philips IntelliSite Pathology Solution Ultra-Fast Scanner (PIPS-UFS), version 1.8.4 on Barco MDPC-8127 display.

MetaLite DX Digital Pathology Software is operated as follows:

Before scanning the slide on the PIPS-UFS, the technician performs quality control on the tissue of interest. The images captured by the PIPS-UFS are compressed using Philips' proprietary iSyntax format and are transmitted to the Philips Image Management System (IMS).

(1) After the Whole Slide Images (WSIs) are successfully, acquired by using PIPS-UFS, the WSIs are stored in the Local file system. A qualified pathologist will upload compatible iSyntax format digital pathology images, and the software will load them to the "Main Viewer" area of the graphical interface for the pathologist to view.

(2) Once properly loaded, the pathologist will use the inherent features of the device (including tools that allow for adjusting the position and viewing angle of the image, measuring lengths between two coordinates, and adding annotations to specific regional areas).

(3) After viewing all images for a patient (case), the pathologist will make a diagnosis. The diagnosis will be documented in another system, e.g., a Laboratory Information System (LIS).

The software has various features such as zoom-in and zoom-out functions, scale display, thumbnail view, measurement function, annotation function, and panning function to help pathologists interpret, diagnose and manage digital whole slide images. The MetaLite DX Digital Pathology Software is validated for use with the components specified the tables below.

Let's break down the acceptance criteria and the study proving the device meets them based on the provided text.

Based on the provided text, the "MetaLite DX Digital Pathology Software" (MLDXUS) is a software-only device intended for viewing and managing digital images of scanned surgical pathology slides for primary diagnosis. The performance testing section describes the studies conducted to demonstrate its safety and effectiveness.

Here's the information organized as requested:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify the sample size for the test sets used in the pixel-wise comparison, turnaround time, measurement accuracy, or usability testing.

The document does not specify the provenance of the data (e.g., country of origin, retrospective or prospective). It only states that the images used were "iSyntax file generated from UFS 1.8.4," which refers to the Philips Ultra Fast Scanner, a compatible component.

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

The document does not explicitly state the number of experts used or their specific qualifications for establishing ground truth for any of the performance tests.

• For the pixel-wise comparison, the ground truth seems to be the output of the predicate device (PIPS IMS) for the same initial image file, rather than expert judgment on clinical images.
• For turnaround time and measurements, the ground truth would be objectively measurable (time, known distances on a calibration slide).
• For usability testing, ground truth typically involves observing user interactions and identifying errors or difficulties, rather than a clinical ground truth established by experts.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method (e.g., 2+1, 3+1, none) for the test set.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly conducted for the MetaLite DX Digital Pathology Software as described in this document. The studies performed focus on technical performance (pixel comparison, speed, measurement accuracy) and usability of the software as a viewing and management tool, not on its impact on human reader diagnostic accuracy or efficiency with and without AI assistance. The device is purely a viewer/manager and does not incorporate AI for diagnosis.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

The studies described are primarily standalone in the sense that they evaluate the software's technical performance attributes (pixel reproduction, speed, measurement accuracy) independent of a pathologist's diagnostic performance. The usability test involved human interaction but assessed the usability of the software interface, not the diagnostic accuracy of the human using it. The device itself is described as "software only" and an "aid to the pathologist," rather than an AI diagnostic algorithm.

7. Type of Ground Truth Used

• Pixel-wise comparison: The ground truth appears to be the output of a reference system (PIPS IMS) for the same iSyntax file. This is a technical ground truth based on image fidelity.
• Turnaround time: The ground truth is objective measurement of time.
• Measurements: The ground truth is objective, known distances on a calibration scale slide.
• Usability testing: The ground truth is based on observed user interactions, identification of use errors, and compliance with human factors principles, as guided by FDA guidelines.

There is no mention of clinical ground truth (e.g., expert consensus on pathology diagnoses, or outcomes data) being used for these particular performance tests, as the device is not a diagnostic AI algorithm.

8. Sample Size for the Training Set

The document does not provide any information regarding a training set size. This is consistent with the device being a viewer and manager of digital images, not an AI algorithm that requires a training set for model development.

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

As no training set is described for this type of device, this information is not applicable and not provided in the document.

Ask a specific question about this device

Pocguide Multi-Drug Test Panel OTC is competitive binding, lateral flow immunochromatographic assay for qualitative and simultaneous detection of Amphetamine, Buprenorphine, Secobarbital, Oxazepam, Cocaine, 2-ethylidene-1,5dimethyl-3,3-diphenylpyrrolidine, Methylenedioxy-methamphetamine, Morphine, Methadone, Oxycodone, Phencyclidine, Nortriptyline and Marijuana in human urine at the cutoff concentrations of:

The single or multi-test panels can consist of up to the above listed analytes in any combination. The tests provide only a preliminary result. A more specific alternative chemical must be used to obtain a confirmed positive result. Gas Chromatography-Mass Spectrometry (GC-MS), Liquid Chromatography-Mass Spectrometry (LC-MS), and their tandem mass-spectrometer versions are the preferred confirmatory methods. Careful consideration and judgment should be applied to any drugs of abuse screen test result, particularly when evaluating preliminary positive results.

For over-the-counter use. For in vitro diagnostic use only

Pocguide™ Multi-Drug Test Panel and Pocguide™ Multi-Drug Test Panel OTC are immunochromatographic assays that use a lateral flow system for the qualitative detection of single drugs in human urine at or above the cut-off levels as indicated. The products are single use in vitro diagnostic devices.

This device is a dipcard format in which the test strips are integrated into the plastic dipcard. After removing the cap of the dipcard, the absorbent end of the test strips is exposed and can be in direct contact with the urine sample. The device is in a ready-to-use format and no longer requires assembly before use.

The provided document describes the Pocguide Multi-Drug Test Panel and Pocguide Multi-Drug Test Panel OTC, which are in vitro diagnostic devices for qualitative and simultaneous detection of various drugs in human urine.

Here's an analysis of the acceptance criteria and the study proving the device meets those criteria, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for this type of qualitative diagnostic device are typically related to its analytical performance, specifically precision (reproducibility) around the cutoff concentration, and its ability to correctly identify positive and negative samples when compared to a confirmed method (method comparison).

Acceptance Criteria (Implied based on study design and regulatory context for qualitative drug tests):

• Precision/Reproducibility: A high percentage of agreement (e.g., typically >80%) for samples near the cutoff (e.g., +/- 25% cutoff, cutoff itself) over multiple lots and runs, and 100% agreement for samples far from the cutoff (e.g., +/- 100% cutoff).
• Method Comparison: High overall agreement (sensitivity and specificity) with a gold standard confirmatory method (LC/MS or GC/MS) for clinical samples, especially for true positive and true negative samples. Acceptable performance for samples near the cutoff where some discordance is expected due to the nature of qualitative assays.
• Analytical Specificity (Cross-Reactivity): No significant cross-reactivity with common substances or structurally similar compounds to avoid false positives.
• Interference: No interference from common physiological substances found in urine.
• Lay-User Study (for OTC devices): High agreement with trained professionals and ease of use for the intended lay user.

Reported Device Performance (from "Precision/Reproducibility" and "Method Comparison" sections):

• AMP 500: 82.0% Positive, 18.0% Negative
• BUP 10: 84.0% Positive, 16.0% Negative
• BAR 300: 82.7% Positive, 17.3% Negative
• And similar ranges for other drugs listed in Table 2. Each drug showed similar performance around the cutoff. |
  | Method Comparison | AMP 1000 ng/mL, AMP 500 ng/mL, BAR 300 ng/mL, etc. | Excellent agreement for Drug-Free, Low Negative, and High Positive Samples: Typically 100% correct classification by the device for these categories (e.g., "Viewer A Positive" for High Positive by LC/MS and "Viewer A Negative" for Drug-Free by LC/MS are 100% for almost all drugs).
  Expected Discordance Near Cutoff: As anticipated for qualitative tests, some samples near the cutoff (especially -25% and +25%) show mixed results (discordance) between the device and LC/MS, as detailed in Table 5 and Table 6 (Discordant results). These are typically within acceptable ranges for qualitative tests, acknowledging the inherent variation around a precise cutoff. |
  | Analytical Specificity | AMP, BUP, BAR, etc. | Tested numerous substances. Most showed no cross-reactivity or very low percentages at very high concentrations, indicating good specificity. Specific cross-reactivity percentages are provided in Table 3. |
  | Interference | N/A - broadly tested | No interference observed for a wide range of common substances and physiological conditions (urine specific gravity 1.000-1.035, pH 4-9) as listed in Tables 4. |
  | Lay-User Study | All Configuration 1 & 2 Drugs | Agreement (%):
• -100%, -75%, -50% Cutoff: 100% negative calls.
• +25%, +50%, +75% Cutoff: Mostly 100% positive calls, some 95% for +25% cutoff.
• -25% Cutoff: 95% negative calls for most drugs.
• Raw numbers show 19/20 or 20/20 correct calls for most categories.
  Ease of Use: All participants indicated instructions were easy to understand and follow (Flesch-Kincaid Grade Level 7). |

2. Sample Sizes and Data Provenance

• Test Set Sample Sizes:
  • Precision/Reproducibility: For each drug and each cutoff, 50 samples were tested at each concentration level (-100%, -75%, -50%, -25%, Cutoff, +25%, +50%, +75%, +100%). This was done across 3 lots, so $50 \text{ samples/level} \times 9 \text{ levels} \times 3 \text{ lots} = 1350$ tests per drug. (For AMP alone, this would be $1350 \times 2 \text{ cutoffs} = 2700$ tests).
  • Method Comparison: 100 unaltered clinical samples were used for each target drug (40 negative, 40 positive, and an additional 20 samples around the cutoff as seen in the breakdown of results). So, for 13 drug analytes, this would be $13 \times 100 = 1300$ clinical samples.
  • Cross-Reactivity / Interference: Specific numbers for each substance are not given, but samples were spiked at various concentrations and tested using three lots of each device.
  • Lay-User Study: For Configuration 1, 140 participants (58 male, 82 female). For Configuration 2, 140 participants (56 male, 84 female). Each participant tested 1 blind-labeled sample. For each drug within each configuration, 20 samples were prepared per concentration level (-100%, -75%, -50%, -25%, +25%, +50%, +75%).
• Data Provenance: The document does not explicitly state the country of origin for the data. The consulting firm is in Shanghai, China, and the applicant's address is Irvine, CA, USA. Given the FDA 510(k) submission, it's implied that the data is intended to be representative and valid for the US market. The studies are described as retrospective as they involve samples prepared at specific concentrations or existing clinical samples compared to a gold standard.

3. Number of Experts and their Qualifications

• For Precision/Reproducibility, Cross-Reactivity, Interference, and Method Comparison: The document does not explicitly state the number of "experts" used to establish ground truth or interpret results. These are quantitative/analytical laboratory tests where the ground truth (concentration by LC/MS or GC/MS) is established by analytical instrumentation. The "Viewers" (A, B, C) mentioned in the Method Comparison section appear to be individuals performing the visual interpretation of the device results, not necessarily independent experts establishing ground truth. Their qualifications are not specified but are implied to be trained laboratory personnel.
• For Lay-User Study: No "experts" were used to establish ground truth for the lay-user study. The ground truth for the samples used in this study was established by LC-MS/MS confirming the spiked drug concentrations.

4. Adjudication Method for the Test Set

• For Precision/Reproducibility, Cross-Reactivity, Interference: No adjudication method is described. The results are reported as counts of positive/negative readings against a known (spiked) concentration.
• For Method Comparison: No explicit "adjudication" among multiple readers is described. Results for the candidate device were observed by "Viewer A, B, C." The comparison is directly between the "Candidate Device Result" (presumably individual Viewer results, though aggregated in Table 5) and the LC/MS reference method. The discordant results in Table 6 specify which viewers made the discordant call (e.g., "Viewer A, B," "Viewer C"). This suggests independent readings by three viewers, but no formal adjudication process to resolve disagreements among them is mentioned; the individual viewer calls are presented relative to the ground truth.
• For Lay-User Study: No adjudication method is mentioned. The tables report the number of positive/negative results per concentration.

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

• No MRMC comparative effectiveness study was done. The study design is an analytical performance study and a comparison study against a laboratory reference method, along with a lay-user study for OTC claims. It assesses device performance in a standalone or simulated user setting, not direct human reader improvement with AI assistance. The device is a lateral flow immunoassay, not an AI-powered diagnostic.

6. Standalone (Algorithm Only) Performance

• This question is not applicable as the device is a lateral flow immunochromatographic assay, not an algorithm or software-based diagnostic. Its performance is inherent to the chemical reactions on the test strip and visual interpretation, not an algorithm.

7. Type of Ground Truth Used

• The primary ground truth used for performance evaluation (Precision/Reproducibility, Method Comparison, Lay-User Study) is analytical confirmation by Gas Chromatography-Mass Spectrometry (GC-MS) or Liquid Chromatography-Mass Spectrometry (LC-MS), and their tandem mass-spectrometer versions (LC-MS/MS), which are stated as the "preferred confirmatory methods." This is a highly accurate and quantitative method for determining drug concentrations.

8. Sample Size for the Training Set

• This question is not applicable. The device is a qualitative diagnostic test based on immunoassay principles, not a machine learning or AI-based device that requires a "training set" in the computational sense. The development of the immunoassay itself relies on antigen-antibody binding characteristics and optimization, not a deep learning model.

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

• This question is not applicable for the same reasons as #8. The "ground truth" for developing the test and optimizing its performance would be established through standard immunoassay R&D processes, involving controlled experiments with known concentrations of analytes and cross-reactants, guided by established analytical chemistry principles.

Ask a specific question about this device

PocguideTM Multi-Drug Test Cup OTC is competitive binding, lateral flow immunochromatographic assay for qualitative and simultaneous detection of Amphetamine, Butalbital, Oxazepam, Cocaine, 2-ethylidene-1,5-diphenylpyrrolidine, Methamphetamine, Methylenedioxymethamphetamine, Morphine, Methadone, Oxycodone, Phencyclidine, Nortriptyline and Marijuana in human urine at the cutoff concentrations of:

Drug (Identifier) Amphetamine (AMP) Buprenorphine (BUP) Secobarbital (BAR) Oxazepam (BZO) Benzoylecgonine (COC) 2-ethylidene-1,5-dimethyl-3,3-diphenylpyrrolidine (EDDP) Methamphetamine (MET) Methylenedioxymethamphetamine (MDMA) Morphine (OPI2000/MOP300) Methadone (MTD) Oxycodone (OXY) Phencyclidine (PCP) Nortriptyline (TCA) Marijuana (THC)
Cut-off level 1000 ng/mL or 500 ng/mL 10 ng/mL 300 ng/mL 300 ng/mL 300 ng/mL or 150 ng/mL 300 ng/mL 1000 ng/mL or 500 ng/mL 500 ng/mL 2000 ng/mL or 300 ng/mL 300 ng/mL 100 ng/mL 25 ng/mL 1000 ng/mL 50 ng/mL

The single or multi-test cups can consist of up to the above listed analytes in any combination. For over-the-counter use.

The tests provide only a preliminary result. A more specific alternative chemical method must be used to obtain a confirmed positive result. Gas Chromatography-Mass Spectrometry (GC-MS), Liquid Chromatography-Mass Spectrometry (LC-MS), and their tandem mass-spectrometer versions are the preferred confirmatory methods. Careful consideration and judgment should be applied to any drugs of abuse screen test result, particularly when evaluating preliminary positive results.

PocguideTM Multi-Drug Test Cup is competitive binding, lateral flow immunochromatographic assay for qualitative and simultaneous detection of Amphetamine, Butalbital, Oxazepam, Cocaine, 2-ethylidene-1,5-dimethyl-3,3-diphenylpyrrolidine, Methamphetamine, Methylenedioxymethamphetamine, Morphine, Methadone, Oxycodone, Phencyclidine, Nortriptyline and Marijuana in human urine at the cutoff concentrations of:

The single or multi-test cups can consist of up to the above listed analytes in any combination.

The tests may yield positive results for the prescription drugs when taken at or above prescribed doses. It is not intended to distinguish between prescription use or abuse of these drugs. Clinical consideration and professional judgment should be applied to any drug of abuse test result, particularly in evaluating a preliminary positive result.

The tests provide only a preliminary result. A more specific alternative chemical method must be used to obtain a confirmed positive result. Gas Chromatography-Mass Spectrometry (GC-MS), Liquid Chromatography-Mass Spectrometry (LC-MS), and their tandem mass-spectrometer versions are the preferred confirmatory methods. Careful consideration and judgment should be applied to any drugs of abuse screen test result, particularly when evaluating preliminary positive results.

Pocguide™ Multi-Drug Test Cup OTC and Pocguide™ Multi-Drug Test Cup are immunochromatographic assays that use a lateral flow system for the qualitative detection of single or multiple drugs in human urine. The devices are a cup format. Each test device is sealed with sachets of desiccant in an aluminum pouch. The device is in a ready-to-use format and no longer requires assembly before use.

The document describes the analytical and user performance of the Pocguide™ Multi-Drug Test Cup OTC and Pocguide™ Multi-Drug Test Cup, which are qualitative lateral flow immunochromatographic assays for detecting various drugs in human urine.

Here's an analysis of the acceptance criteria and the studies performed, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state pre-defined acceptance criteria for the analytical performance (e.g., specific percentages for precision or method comparison). Instead, it presents the results of these studies. For the lay user study, it presents agreement percentages.

However, based on the data presented, the implicit acceptance criteria for the qualitative detection of drugs would be high agreement (ideally 100% at concentrations sufficiently above or below the cutoff) for positive and negative samples, and a certain degree of variability (discordance) near the cutoff, which is expected for qualitative assays.

Here's a summary of the reported performance, primarily from the "Precision/Reproducibility" and "Method Comparison" sections:

Implicit Acceptance Criteria (based on typical assay performance and the provided data)

• Precision/Reproducibility: Consistent qualitative results (Positive/Negative) across multiple runs and lots, especially for concentrations sufficiently above or below the stated cutoff levels. Some variability (mix of positive and negative results) is expected and acceptable around the cutoff concentration, as this is the region where the device is designed to transition between positive and negative readings.
• Method Comparison (Accuracy vs. LC-MS/MS):
  • 100% agreement for Drug-Free samples (true negatives).
  • High agreement for "Low Negative" samples (true negatives well below cutoff).
  • High agreement for "High Positive" samples (true positives well above cutoff).
  • Expected discordance (mix of +/- results) for "Near Cutoff Negative" and "Near Cutoff Positive" samples.
• Lay Person Study: High percentage of agreement on results, demonstrating ease of use and accurate interpretation by lay users. High Flesch-Kincaid reading score/grade level for instructions indicating understandability.

Reported Device Performance

Precision/Reproducibility (See Tables in Section 12.A.a, e.g., Page 8)

• For concentrations at +100%, +75%, +50%, +25% cutoff: Across all drugs and lots, the device consistently reported 0 negative results and 50 positive results (0-/50+) which indicates 100% agreement for samples well above the cutoff.
• For concentrations at -25%, -50%, -75%, -100% cutoff: Across all drugs and lots, the device consistently reported 50 negative results and 0 positive results (50-/0+) which indicates 100% agreement for samples well below the cutoff.
• For the "Cutoff" concentration: As expected for a qualitative test, there was a mix of negative and positive results across all drugs and lots, ranging from 8-/42+ to 17-/33+ (e.g., for AMP 500 Lot 1, 12-/38+ means 12 negative and 38 positive results out of 50 total). This demonstrates appropriate performance around the threshold.

Method Comparison (Accuracy vs. LC-MS/MS) (See Tables in Section 12.B, e.g., Page 19-20)

• Drug-Free Samples: For all drugs and all three operators, the device consistently reported 0 positive results and showed 100% agreement (e.g., 0+ / 13- for AMP 500).
• Low Negative Samples (less than -50% of cutoff): For all drugs and all operators, the device consistently reported 0 positive results and showed 100% agreement (e.g., 0+ / 7- for AMP 500).
• High Positive Samples (greater than +50% of cutoff): For all drugs and all operators, the device consistently reported 100% positive results (e.g., 23+ / 0- for AMP 500).
• Near Cutoff Negative (Between -50% and cutoff) & Near Cutoff Positive (Between cutoff and +50%): As expected for a qualitative assay, there was a mix of positive and negative results in these ranges, indicating the test's activity around the cutoff. The discordant results table (Pages 22-23) provides specific examples of samples that differ from the LC-MS/MS result near the cutoff. For instance, for AMP 500, samples like AL243 (441.6 ng/mL) were read as Positive by the device, while AL036 (501.2 ng/mL) was read as Negative. This is typical for qualitative tests at the cutoff.

Lay Person Study (See Tables in Section 12.C, e.g., Page 25-27)

• Agreement Percentages: For concentrations well below (-100%, -75%, -50% cutoff) and well above (+50%, +75% cutoff) the cutoff, the agreement with the expected result was consistently 100% for all drugs and configurations.
• Near Cutoff: At the -25% and +25% cutoff concentrations, there was slight variability, with agreement mostly at 95.00% (e.g., 19 negative out of 20 at -25% for AMP 500, or 19 positive out of 20 at +25% for AMP 500). This confirms appropriate performance around the cutoff by lay users.
• Instruction Clarity: "All participants indicated that the device instruction is easy to understand and follow. A Flesch-Kincaid reading analysis was performed on each package insert and the scores revealed a reading Grade Level of 7," indicating strong performance against this unstated criterion.

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

• Precision/Reproducibility:
  • Sample Size: For each drug, 9 concentration levels were tested (from -100% cutoff to +100% cutoff, including the cutoff). For each concentration, tests were performed two runs per day for 25 days using three lots of test cups. This means 50 tests per concentration per lot, totaling 450 tests per drug per lot for analytical precision. As there are multiple drugs/cutoffs, the total number of individual tests is substantial. (e.g., for AMP 500, 9 concentrations * 50 tests/concentration * 3 lots = 1350 individual tests for AMP 500 alone).
  • Data Provenance: The document doesn't explicitly state the country of origin. Samples were "prepared by spiking target drug in drug-free urine samples," suggesting controlled laboratory conditions rather than native clinical samples. The study appears to be prospective in nature, as it involves preparing samples and running specific experiments.
• Method Comparison Study:
  • Sample Size: 80 "unaltered urine clinical samples" were used for each drug (40 negative and 40 positive). These were compared across three operators. Thus, for each drug, 80 unique clinical samples were tested, with data collected from 3 operators, meaning 240 results per drug.
  • Data Provenance: "Unaltered urine clinical samples" suggests real-world urine specimens. The document doesn't specify the country of origin of these samples. It implies a retrospective use of collected samples or a prospective collection for this specific study.
• Lay Person Study:
  • Sample Size: 280 lay persons participated. Urine samples were prepared at 7 concentration levels per drug (from -100% to +75% cutoff).
  • Data Provenance: The study was likely conducted in a controlled environment as samples were "prepared by spiking drug(s) into drug free-pooled urine specimens." The location (country) of the lay user study is not specified, but it suggests a controlled, prospective study.

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

• Ground Truth for Precision/Reproducibility and Lay Person Study: "Each drug concentration was confirmed by LC-MS/MS." and "The concentrations of the samples were confirmed by LC-MS/MS." LC-MS/MS (Liquid Chromatography-Mass Spectrometry/Mass Spectrometry) is a highly accurate analytical chemistry technique. This is an objective, quantitative measurement; therefore, human expert subjective interpretation for ground truth establishment is not typically required.
• Ground Truth for Method Comparison Study: "The samples were blind labeled and compared to LC-MS/MS results." Again, LC-MS/MS is the ground truth, not human experts.

As such, for an in-vitro diagnostic device of this nature, the "ground truth" is established by highly precise analytical instruments (LC-MS/MS), not by human experts. Therefore, the number and qualifications of human experts establishing ground truth are not applicable in the traditional sense of medical image interpretation or clinical diagnosis.

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

Not applicable. The ground truth method (LC-MS/MS) for defining the precise concentration of drugs is an objective chemical analysis, not a subjective human interpretation requiring adjudication. For the device's output, it is a qualitative "positive" or "negative" reading based on visual lines, directly observable without complex adjudication. The method comparison study uses results from 3 operators, but their results are compared against the LC-MS/MS, not adjudicated against each other to define a 'truth'.

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 an in-vitro diagnostic (IVD) device, specifically a point-of-care, qualitative multi-drug test cup, not an AI-assisted diagnostic tool for human image readers (like radiology AI). Therefore, an MRMC study related to AI assistance for human readers is not relevant to this product.

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

Not applicable. This is a physical, self-contained immunochromatographic test cup that provides a visual reading (lines appearing/disappearing). It does not involve a software algorithm that performs detection independently. Its performance is the "standalone" performance, as it relies on chemical reactions and visual interpretation.

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

The primary ground truth used for performance evaluation is Gas Chromatography-Mass Spectrometry (GC-MS) or Liquid Chromatography-Mass Spectrometry (LC-MS), and their tandem mass-spectrometer versions (LC-MS/MS), which are considered the preferred confirmatory methods for drug detection in urine. This is an objective, quantitative chemical analysis.

8. The sample size for the training set

Not applicable. This is a direct chemical/immunological assay device, not a machine learning or AI model. Therefore, there is no "training set" in the context of data-driven model development.

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

Not applicable, as there is no "training set" for this type of medical device. The device operates based on established chemical and immunological principles, not learning from data.

Ask a specific question about this device

Rx: The coactiv+™ Antimicrobial Wound Gel is indicated for management of ulcers (including diabetic foot and leg ulcers and pressure ulcers), 1st and 2nd degree burns, partial & full thickness wounds and surgical incisions for adult populations.

OTC: The coactiv+™ Antimicrobial Wound Gel is indicated for management of minor lacerations, minor burns (1st degree burns) and abrasions for adult populations.

The coactiv+™ Antimicrobial Wound Gel is a white, odorless gel that provides a moist wound environment conducive to wound healing. The coactiv+™ Antimicrobial Wound Gel provides preservative properties through an antimicrobial (PHMB) to help inhibit microbial colonization within the gel during shelf storage. Chronic wounds are known to contain non-viable tissue. The coactiv+™ Antimicrobial Wound Gel can facilitate debridement through a moist wound environment.

The coactiv+™ Antimicrobial Wound Gel contains water, Poloxamer 407, Glycerol, Trisodium citrate, PHMB (0.1% w/w), Citric acid, Disodium EDTA.

The coactiv+™ Antimicrobial Wound Gel dressing will be supplied in 0.7 oz. (21 g) white/opaque polypropylene (19 x 100 mm) screw cap tubes.

The device will be available as both a Rx and OTC product.

This FDA 510(k) summary describes the coactiv+™ Antimicrobial Wound Gel and its substantial equivalence to a previously cleared predicate device (K223259). The submission is a special 510(k) for a change to the submitter's own legally marketed device, specifically a labeling change to remove a usage restriction.

Acceptance Criteria and Device Performance:

The document primarily focuses on demonstrating the continued safety and effectiveness of the device after a labeling change. The "performance" in this context refers to the device maintaining its original safety and functional characteristics despite the change.

Study Details:

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

   • Biocompatibility Testing: Not specified, but standard ISO 10993 tests for cytotoxicity, sensitization, intracutaneous reactivity, implantation, acute systemic toxicity, pyrogenicity, and genotoxicity are usually performed on representative samples of the final device material. No human subjects are involved.
   • Performance Testing (USP , stability): Not specified. These are laboratory-based tests on product batches.
   • Animal Testing (Wound Healing): A "porcine model" was used. The exact number of animals or wounds tested is not specified. This is a preclinical study.
   • Toxicological Risk Assessment: This is a theoretical assessment based on chemical composition and potential exposure, not directly a "test set" with a sample size in the traditional sense. It would utilize existing toxicological data for the components. The provenance is internal to the manufacturer.

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

   • Not applicable in the conventional sense for these types of non-clinical, laboratory, and animal studies. Ground truth is established by the accepted scientific standards and methodologies (e.g., ISO, USP guidelines).
   • The Toxicological Risk Assessment would be performed by qualified toxicologists, but the number of "experts" to establish a ground truth for a test set is not relevant here.

3. Adjudication method for the test set:

   • Not applicable. The studies mentioned are laboratory tests, animal studies, and toxicological assessments. These do not typically involve human adjudication of results in the way clinical studies or diagnostic AI algorithms do. Results are based on direct measurement and interpretation against predefined criteria.

4. Multi-reader multi-case (MRMC) comparative effectiveness study:

   • No, an MRMC comparative effectiveness study was not done. This device is a wound gel, not a diagnostic imaging device or an AI algorithm intended to assist human readers. Therefore, the concept of human readers improving with AI assistance is not relevant.

5. Standalone (i.e., algorithm only without human-in-the-loop performance) study:

   • No, this is not an AI/algorithm-based device. It is a medical device (wound gel). Therefore, a standalone algorithm performance study is not applicable.

6. Type of ground truth used:

   • Biocompatibility: Established scientific standards and methodologies (ISO 10993 series).
   • Performance Testing: Pharmacopoeial standards (USP , , , , ).
   • Animal Testing: Physiological wound healing as observed and measured in a porcine model.
   • Toxicological Risk Assessment: Toxicology databases, literature, and expert knowledge on chemical safety.

7. Sample size for the training set:

   • Not applicable. This device does not involve machine learning or AI, so there is no "training set."

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

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

Ask a specific question about this device

The Biodesign Otologic Butterfly Graft is intended for use as an implant material to aid in the natural healing process in myringoplasty and tympanoplasty procedures.

The Biodesign Otologic Butterfly Graft is a self-securing butterfly-style graft structure with the same underlay component as the predicate device, attached to an external stabilizing component with an absorbable knotted thread, all made from the same SIS (small intestinal submucosa) ECM material as that of the predicate device. This self-securing structure maintains the location and close tissue approximation of the underlay component across the tympanic membrane (TM) defect as an implant material to aid in the natural healing process in myringoplasty and tympanoplasty procedures.

The provided text does not describe an acceptance criteria table or a study that specifically "proves" the device meets acceptance criteria in the typical sense of a single, definitive study with a direct comparison against a set of performance metrics. Instead, it describes a Substantial Equivalence (SE) determination for a new device, the "Biodesign Otologic Butterfly Graft," by comparing it to a legally marketed predicate device (K161000).

The concept of "acceptance criteria" here is implicitly tied to demonstrating that the new device is as safe and effective as the predicate, despite some design changes. The studies conducted are largely comparative, aiming to show that the changes do not introduce new risks or diminish performance relative to the predicate.

Here's an attempt to extract the requested information based on the provided text, acknowledging that some details might be inferred or not explicitly stated as they would be in a direct performance study against a predefined acceptance criterion.

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document focuses on demonstrating substantial equivalence to a predicate device rather than meeting pre-defined numerical acceptance criteria for a novel device. The "acceptance criteria" for the animal study are explicitly stated and are the closest to what was requested.

Summary of Comparative Equivalence: The overall "acceptance criterion" for the device, in the context of this 510(k) submission, is to demonstrate that its design changes do not introduce new questions of safety or effectiveness and that it performs as well as, or better than, the predicate device. The various studies and tests listed are all geared towards supporting this claim of substantial equivalence.

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

For the animal study:

• Sample Size: 14 tympanic membrane perforations implanted with the subject device.
• Data Provenance: Prospective GLP animal study in a chinchilla model. The location/country is not specified.

For bench testing (mechanical performance, usability, packaging/shelf-life): Specific sample sizes are not provided, only that "Product verification testing was performed," "Summative Usability Report which utilized simulated-use testing," and "Non-clinical bench testing was performed on accelerated-aged representative SHS conditioned packaging system samples."

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

For the animal study:

• Number of Experts: At least one "Veterinary Pathologist."
• Qualifications: "Veterinary Pathologist's review of the histologic sections of the grafted/implanted tympanic membranes." No specific years of experience are mentioned.

For other testing, specific expert numbers or qualifications for ground truth establishment are not provided.

4. Adjudication method for the test set

For the animal study:

• The text mentions a "Veterinary Pathologist's review of the histologic sections." This implies a single expert's determination for the histological ground truth. It does not describe a multi-reader adjudication method (e.g., 2+1, 3+1).
• Visual healing was determined "via endoscopy," and functional healing by "typanogram technique." It's unclear if these assessments involved multiple readers or an adjudication process.

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

• No, an MRMC comparative effectiveness study was not done. This document pertains to a medical device (graft) and its biological/mechanical performance, not an AI or imaging diagnostic device where MRMC studies involving human readers and AI assistance would be relevant.

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

• Not applicable. This is a physical medical device (graft), not an algorithm or AI system.

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

For the animal study:

• Pathology: Histological assessment by a Veterinary Pathologist.
• Clinical Observation: Visual assessment (no perforation observed via endoscopy).
• Physiological/Functional Data: Tympanogram waveform analysis.

8. The sample size for the training set

• Not applicable. This document describes the evaluation of a physical medical device. There is no concept of a "training set" in the context of an animal study for a medical implant like there would be for an AI algorithm.

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

• Not applicable. As there is no training set for this type of device evaluation, no ground truth was established for one.

Ask a specific question about this device

The Chemtrue® Multi-Panel Drug Screen Cup Tests are rapid lateral flow immunoassays for the qualitative detection of Amphetamine, Barbiturates, Benzodiazepines, Buprenorphine, Cocaine, Norfentanyl, Marijuana, Methamphetamine, Morphine, Opiates, Phencyclidine, Ecstasy, Methadone, Oxycodone, Propoxyphene , Tramadol and Trivyclic Antidepressants (TCA) drugs in human urine. The test cut-off concentrations and the tests are calibrated to are as follows:

The multi test panels can consist of any analytes listed above in any combination. Only one cut-off concentration will be included per analyte per device.

The tests provide only a preliminary result. A more specific alternative chemical must be used in order to obtain a confirmed assay result. Gas Chromatography / Mass Spectrometry (GC/MS) or Liquid Chromatography / Mass Spectrometry (LC/MS) are the preferred confirmatory methods. Clinical consideration and professional judgment should be applied to any drugs of abuse test result, particularly when preliminary positive results are indicated.

The tests are not intended to differentiate between drugs of abuse and prescription use of Benzodiazepines, Buprenorphine, Oxycodone, Propoxyphene and Tricyclic Antidepressants.

The Chemtrue® Drug Screen Fentanyl / Tramadol Dip Card Tests are rapid lateral flow immunoassays for the qualitative detection of Norfentanyl 5 and Tramadol 100 drugs in human urine. The test cut-off concentrations and the compounds the tests are calibrated to are as follows:

The Chemtrue® Drug Screen Fentany! / Tramadol Dip Card Test detects and is calibrated against norfentanyl, the major metabolite of fentanyl in human urine. The test is available in Single and multi-panels.

The tests provide only a preliminary result. A more specific alternative chemical must be used in order to obtain a confirmed assay result. Gas Chromatography / Mass Spectrometry (GC/MS) or Liquid Chromatography / Mass Spectrometry (LC/MS) are the preferred confirmatory methods. Clinical consideration and professional judgment should be applied to any drugs of abuse test result, particularly when preliminary positive results are indicated.

The test is not intended to differentiate between drugs of abuse and prescription use of Fentanyl/ Tramadol. The test is for in vitro diagnostic use only.

The Chemtrue® Drug Screen Fentanyl / Tramadol Cup Tests are rapid lateral flow immunoassays for the qualitative detection of Norfentanyl 5 and Tramadol 100 drugs in human urine. It is an in vitro diagnostic device. The test cut-off concentrations and the compounds the tests are calibrated to are as follows:

The Chemtrue® Drug Screen Fentany1 / Tramadol Cup Test detects and is calibrated against norfentany1, the major metabolite of fentanyl in human urine. The test is available in Single and multi-panels.

The test provides only a preliminary result. A more specific alternative chemical must be used in order to obtain a confirmed assay result. Gas Chromatography / Mass Spectrometry (GC/MS) or Liquid Chromatography / Mass Spectrometry (LC/MS) are the preferred confirmatory methods. Clinical consideration and professional judgment should be applied to the drug test result, particularly when preliminary positive result is indicated.

The test is not intended to differentiate between drugs of abuse and prescription use of Fentany/ Tramadol. The test is for in vitro diagnostic use only.

The Chemtrue® Multi-Panel Drug Screen Dip Card Test is a rapid lateral flow immunoassay for the qualitative detection of Amphetamine, Barbiturates, Benzodiazepines, Buprenorphine, Cocaine, Ecstasy, Norfentany, Marijuana, Methadone, Morphine, Opiates, Oxycodone, Phencyclidine, Propoxyphene, Tramadol and Tricyclic Antidepressants (TCA) drugs in human urine. The test cut-off concentrations and the compounds the tests are calibrated to are as follows:

The multi test panels can consist of any drug analytes listed above in any combination. Only one cutoff concentration will be included per analyte per device.

The test provides only a preliminary result. A more specific alternative chemical must be used in order to obtain a confirmed assay result. Gas Chromatography / Mass Spectrometry (GC/MS) or Liquid Chromatography / Mass Spectrometry (LC/MS) are the preferred confirmatory methods. Clinical consideration and professional judgment should be applied to any drugs of abuse test result, particularly when preliminary positive results are indicated.

The tests are not intended to differentiate between drugs of abuse and prescription use of Barbiturates, Buprenorphine, Oxycodone, Propoxyphene and Tricyclic Benzodiazepines, Antidepressants.

The Chemtrue® Multi-Panel Drug Screen Cup Test is a rapid lateral flow immunoassay for the qualitative detection of Amphetamine, Barbiturates, Benzodiazepines, Buprenorphine, Cocaine, Ecstasy, Norfentanyl, Marijuana, Methamphetamine, Morphine, Opiates, Oxycodone, Phencyclidine, Propoxyphene, Tramadol and Tricyclic Antidepressants (TCA) drugs in human urine. The test cut-off concentrations and the compounds the tests are calibrated to are as follows:

The multi test panels can consist of any drug analytes listed above in any combination. Only one cutoff concentration will be included per analyte per device.

The test provides only a preliminary result. A more specific alternative chemical must be used in order to obtain a confirmed assay result. Gas Chromatography / Mass Spectrometry (GC/MS) or Liquid Chromatography / Mass Spectrometry (LC/MS) are the preferred confirmatory methods. Clinical consideration and professional judgment should be applied to any drugs of abuse test result, particularly when preliminary positive results are indicated.

The tests are not intended to differentiate between drugs of abuse and prescription use of Tricyclic Benzodiazepines, Barbiturates, Buprenorphine, Oxycodone, Propoxyphene and Antidepressants.

The Chemtrue® Drug Screen Tests are colloidal gold-based lateral flow immunoassays for the rapid, qualitative detection of drugs of abuse in human urine. The tests are single-use, in vitro diagnostic devices, which come in Dip Card or Cup formats, as indicated by the test name.

The provided text describes the performance characteristics of the Chemtrue® Drug Screen Fentanyl/Tramadol Cup Test and Dip Card Test. Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for qualitative immunoassay diagnostic devices typically involve high levels of agreement with a reference method, especially around the cutoff concentration. While explicit acceptance criteria ("Pass/Fail" thresholds) are not directly stated in the provided text, the reported performance demonstrates very high agreement.

Note: The tables below focus on the Fentanyl (FYL) and Tramadol (TML) tests as these are the new additions being evaluated in this submission. Previous analytes were cleared under older 510(k)s. The percentages under "Reported Device Performance" are calculated from the provided raw counts.

Method Comparison (Accuracy) Studies vs. LC/MS Reference Method

The agreement is calculated as (Number of correct results / Total number of samples in that category) * 100%.

Ask a specific question about this device

HealiAid® Dental Collagen Wound Dressing is indicated for the management of oral wounds and sores, including:

1. Denture sores
2. Oral ulcers (non-infected or viral)
3. Periodontal surgical wounds
4. Extraction sites
5. Surgical wounds.
6. Traumatic wounds

The subject device is HealiAid® Dental Collagen Wound Dressing (HealiAid Dental) that is a white, porous, pliable and absorbable collagen wound dressing. HealiAid Dental is fabricated by fibrous collagen matrix purified from bovine Achilles tendons. HealiAid Dental is pliable and can be applied easily to oral wounds to protect the wound bed. The product is supplied in a sterile, nonpyrogenic package, and is indicated for single use only.

The provided text describes the regulatory clearance (510(k)) for the HealiAid® Dental Collagen Wound Dressing. This is a medical device, not an AI/ML software device, and therefore the concepts of acceptance criteria for AI performance metrics (like sensitivity, specificity, AUC), sample size for test sets, ground truth establishment by experts, adjudication methods, MRMC studies, or training sets are not applicable here.

Instead, the acceptance criteria for this medical device are related to its physical and biological properties, and its performance in pre-clinical studies to demonstrate substantial equivalence to a legally marketed predicate device.

Here's a breakdown of the information provided, framed to address the prompt's categories where applicable for a medical device without AI/ML components:

1. Table of Acceptance Criteria and Reported Device Performance

For medical devices like wound dressings, "acceptance criteria" are typically defined by demonstrating compliance with established standards (like ISO 10993 for biocompatibility) and exhibiting comparable performance to predicate devices in pre-clinical tests.

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

• Test Set (Pre-clinical Studies): The document does not specify exact sample sizes for each pre-clinical test (e.g., number of animals for toxicity or implantation studies). These studies are typically conducted according to standardized protocols outlined in documents like ISO 10993, which define appropriate sample sizes for each test type.
• Data Provenance: The studies were pre-clinical (laboratory and animal studies) rather than human clinical trials. The bovine Achilles tendons are the source material.

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

• This is not applicable as the "ground truth" for this type of device is established through standardized laboratory tests and animal models, adhering to recognized international standards (e.g., ISO 10993, USP 151, ISO 22442). These tests have defined endpoints and criteria, and their interpretation is generally performed by qualified laboratory personnel following strict protocols, rather than a consensus of human "experts" evaluating an outcome like an image.

4. Adjudication Method for the Test Set

• Not applicable. The pre-clinical tests have objective measurements and pass/fail criteria based on established standards, not subjective assessments requiring adjudication.

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

• Not applicable. MRMC studies are specific to diagnostic devices (often imaging-based AI) where multiple human readers interpret cases, and their performance is compared with and without AI assistance. The HealiAid® Dental Collagen Wound Dressing is a therapeutic/wound management device, not a diagnostic one.

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

• Not applicable. This device is a physical wound dressing and does not involve an algorithm or AI functionality.

7. The Type of Ground Truth Used

• For the pre-clinical studies, the "ground truth" is established by the objective results of standardized biological and chemical tests (e.g., cell viability in cytotoxicity, presence/absence of mutagenic activity in genotoxicity, tissue reactions in implantation, absorption values, degradation rates). These are verifiable scientific outcomes, not interpretations of medical images or pathology.

8. The Sample Size for the Training Set

• Not applicable. This device does not use AI/ML and therefore does not have a "training set."

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

• Not applicable for the same reason as above.

Ask a specific question about this device

SurgiAid® Collagen Wound Dressing is indicated for use in patients who have surgical wounds, donor sites/grafts, podiatric wound, wound dehiscence, traumatic wounds, abrasions, lacerations, partial thickness burns or skin tears. SurgiAid® Collagen Wound Dressing can be applied to wounds with depth less than 0.3 cm.

SurgiAid Collagen Wound Dressing (SurgiAid) is white, porous pliable and absorbable collagen wound dressing. It is fabricated by fibrous collagen matrix which is purified from bovine Achilles tendon. SurgiAid is pliable and can be applied easily to clean wound. The product is supplied in sterile, non-pyrogenic package, and is indicated for single use only.

The provided text describes a 510(k) submission for a medical device called "SurgiAid® Collagen Wound Dressing" (K223126). This submission focuses on demonstrating substantial equivalence to a previously cleared predicate device, rather than a de novo approval requiring extensive clinical efficacy studies. Therefore, the "study" described and the "acceptance criteria" are primarily related to non-clinical performance data and comparison to the predicate device.

Here's an analysis of the requested information based on the provided text:

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

The document provides a comparison table (Table 1) between the subject device (K223126), the predicate device (K100927), and a reference device (K122325). The acceptance criteria are implied by the "Comparison" column, which states "Identical to Predicate Device" or similar, indicating that the subject device's performance should match that of the predicate. For specifications (dimensions), the acceptance is that the new sizes "fall within the size range of the reference device."

The Study that Proves the Device Meets the Acceptance Criteria:

The "study" here is a series of non-clinical tests and a comparison to the predicate device to demonstrate substantial equivalence, rather than a clinical trial.

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 primarily discusses non-clinical performance and material characteristics.

• Sample size: The specific sample sizes for each non-clinical test (e.g., how many dressings were tested for water absorption, porosity, sterilization validation, etc.) are not explicitly provided in the summary.
• Data provenance: The document states the manufacturer is Maxigen Biotech Inc. in Taoyuan City, Taiwan. The non-clinical tests would have been conducted by or for this manufacturer. It does not specify whether these tests were performed in Taiwan or elsewhere. The data is "retrospective" in the sense that the new device's characteristics were compared to already established characteristics of the predicate and reference devices, and tested against established standards (ISO10993, etc.). These are typically laboratory tests, not patient data trials.

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 question is not applicable to this type of submission. The "ground truth" for non-clinical performance data (e.g., water absorption, porosity, biocompatibility) is established according to recognized international standards (e.g., ISO 10993 for biocompatibility) and validated laboratory methods. It does not involve expert consensus on medical images or clinical outcomes.

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

This question is not applicable. Adjudication methods are typically used in clinical trials involving subjective interpretation of data (like imaging studies where multiple readers agree/disagree on a finding). For non-clinical tests, results are typically quantitative and objective measurements against predefined criteria/standards.

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. An MRMC study is relevant for diagnostic devices, especially those incorporating AI, where human readers interpret medical images. This document describes a collagen wound dressing, which is a therapeutic device, and does not mention any AI component or diagnostic function.

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 physical wound dressing, not an algorithm or software.

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

For the non-clinical tests:

• Standards/Specifications: The "ground truth" for characteristics like water absorption, porosity, density, sterilization, packaging integrity, and biocompatibility is based on established international standards (e.g., ISO10993-1:2018) and predefined acceptance criteria derived from the predicate device's performance and general recognized medical device safety and efficacy principles.
• Predicate Device Data: The performance of the predicate device (K100927) serves as a key "ground truth" for comparison to establish substantial equivalence.

8. The sample size for the training set

This question is not applicable. There is no "training set" in the context of this 510(k) submission for a wound dressing. Training sets are used in machine learning for AI algorithms.

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

This question is not applicable as there is no training set.

Ask a specific question about this device

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

Single bare stent has straight and round cylinder form made of a Nitinol wire. It is woven twice in V-hook type by one wire. The cell size is approximately 2 mm. The end of wire is tied by the both wires. No bonding material is used. Single Bare Stent is manufactured by continuous works, V and Twist structure manufacturing process. From these processes, design of Single bare stent has the 12 bends and 2mm cell size. 2mm cell size has the merit to prolong the time that tissue grows up into the stent. In addition, Single Bare Stent designed to have the Radial force, Flexibility and conformability. Single Bare Stent has 6 markers in diameter 6, 7, and 8mm in size and 8 markers in diameter 10mm in size; 2 or 3 markers at both sides and 2 markers at the center. Markers are made of Gold-plated Tungsten wire. They are intended to identify the location of the loaded stent through X-ray.

The provided document is a 510(k) summary for a medical device (EGIS Biliary Single Bare Stent). It does not describe acceptance criteria for an AI/ML-based medical device, nor does it detail a study proving such a device meets acceptance criteria.

The document states: "Clinical testing was not required for this submission." This explicitly indicates that the submission did not include a clinical study (which would be necessary to establish acceptance criteria for an AI/ML device's performance in a clinical setting).

Therefore, I cannot extract the requested information regarding acceptance criteria and a study proving device performance for an AI/ML device from this document. The document focuses on demonstrating substantial equivalence to a predicate device through non-clinical bench testing and material comparisons for a physical medical device (a stent), not an AI/ML algorithm.

Ask a specific question about this device