Search Results

SB Soft Hood is intended for use with SB Knife for endoscopic submucosal dissection within the gastrointestinal tract and for use in keeping the suitable depth of endoscopic field of view.

Device Description

SB Soft Hood™ is a transparent distal attachment applied to the tip of an endoscope. It is used in endoscopic submucosal dissection (hereinatter ESD) procedures. The subject device is used for maintaining visualization during the dissection phase of the procedure. The subject device is disposable and in a variety of diameters that correspond to different endoscope sizes. Each model of the subject device contains a drainage side hole that allows egress of water and blood.

AI/ML Overview

This document is a 510(k) Summary for the SB Soft Hood™ device. It details the device's description, indications for use, comparison to a predicate device, and non-clinical testing performed to demonstrate substantial equivalence.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics in the format typically seen for algorithm performance (e.g., sensitivity, specificity, AUC). Instead, the "acceptance criteria" are implied by the non-clinical tests performed and the conclusion of "no new concern" or meeting "in-house standard which was determined based on expected worst-case."

Here's an interpretation of the implied acceptance criteria and reported performance:

Acceptance Criterion (Implied)	Reported Device Performance
Biocompatibility: No adverse biological reactions upon contact with tissue.	No biocompatibility concern was raised from tests (Cytotoxicity, Sensitization, Acute systemic toxicity, Irritation reactivity, Material-mediated pyrogenicity) per ISO 10993 standards and USPC 151.
Durability: Device remains attached to the endoscope during clinical use (unaged and aged).	All samples met in-house standard which was determined based on expected worst-case (Visual inspection, durability testing, detachment testing).
Sterility: Sterilization Assurance Level of 10^-6, no residual ETO/ECH, no endotoxin.	Sterilization Validation demonstrated SAL of 10^-6 per ISO 11135-1:2007. Residual EO and ECH were not detected per ISO10993-7:2008. Endotoxin was not detected per USP. Packaging integrity met ASTM F1929 and ASTM F88/F88M.
Design Integrity/Functionality: Proper functioning (e.g., maintaining visualization, not interfering with SB Knife).	Risks related to inadequate length, poor view, endoscope disturbance, and SB Knife interference were mitigated by proper design. (No quantitative performance metrics are provided for this, just design-based mitigation).
Material Safety: Materials are safe for intended use.	(Addressed by biocompatibility testing.)
Substantial Equivalence to Predicate Device: No new safety or effectiveness concerns compared to the predicate.	Based on risk analysis, biocompatibility testing, sterilization validation, and shelf-life testing, no new concern demonstrated. Concluded to be substantially equivalent.

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

This device is a physical medical device, not an AI/software device that processes data or images. Therefore, the concepts of "test set sample size" and "data provenance" (country of origin, retrospective/prospective) stemming from AI/machine learning studies are not applicable to this submission. The tests performed are non-clinical, laboratory-based tests on the device itself.

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)

Again, the device is a physical medical accessory for endoscopy, not an algorithm requiring expert-established ground truth from images or data. Therefore, this information is not applicable. The "ground truth" for the non-clinical tests is based on established engineering and biological standards (e.g., ISO, USP, ASTM).

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

Since this is not an AI/imaging study with subjective interpretation, an adjudication method for a "test set" is not applicable. The test results are objective measurements against established 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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This type of study is relevant for evaluating the impact of AI systems on human interpretation, which is not applicable to a physical endoscopic accessory. The document explicitly states: "Clinical testing was not performed for SB Soft Hood™."

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

No, a standalone performance study (algorithm only) was not done because this is a physical medical device, not an algorithm.

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

The concept of "ground truth" as typically used in AI/diagnostic studies (e.g., pathology, clinical outcomes) is not applicable here. For the non-clinical tests performed, the "truth" or reference is defined by:

Established international and national standards (e.g., ISO 10993-5, ISO 10993-10, ISO 10993-11, USPC 151, ISO 11135-1:2007, ASTM F1929, ASTM F88/F88M, ISO10993-7:2008, USP).
"In-house standard which was determined based on expected worst-case" for performance testing.

8. The sample size for the training set

This is not applicable as the device is not an AI/machine learning product and does not involve training data.

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

This is not applicable as the device is not an AI/machine learning product and does not involve training data or ground truth establishment for a training set.

Ask a Question

Ask a specific question about this device

Page 1 of 1