K Number
K984593
Date Cleared
1999-03-01

(63 days)

Product Code
Regulation Number
N/A
Panel
SU
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Cutinova thin is a dressing indicated for the management of surface wounds with low to moderate exudate, such as: Minor burns Abrasions Cutinova thin may also be used under the direction of a health care professional for partial thickness wounds such as: Second degree burns Leg ulcers Pressure ulcers Post-op wounds Donor sites

Device Description

Cutinova thin is a polyurethane dressing that is indicated for the management of wounds with low to moderate exudate. The current modification involves a change in the material used to make the urethane from an aromatic diisocyanate to an aliphatic diisocyanate and does not affect the indications for use.

AI/ML Overview

The provided text is a 510(k) summary for a medical device modification, specifically for the Cutinova® thin wound dressing. It details regulatory information and a brief summary of testing, but it does not contain the specific information requested in the prompt regarding acceptance criteria and a detailed study's results.

Here's an analysis based on the provided text, Highlighting the information that is not present:

1. Table of acceptance criteria and the reported device performance:

  • Not present in the document. The document states "Performance characteristics were also comparable to the currently marketed product," but it does not define these characteristics, their acceptance criteria, or the specific quantitative results achieved.

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

  • Not present in the document. The document mentions "Biological tests were done in accordance with ISO 10993" and "Performance characteristics were comparable," but it does not specify the sample sizes used for these tests, the type of study (retrospective or prospective), or the data's origin.

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 / Not present. This type of information is typically relevant for studies involving human interpretation (e.g., image analysis, diagnoses). The described tests are biological and performance characteristic tests for a wound dressing, which do not involve human expert consensus for ground truth as would be seen in diagnostic device studies.

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

  • Not applicable / Not present. Similar to point 3, adjudication methods are for expert consensus on subjective assessments. The tests described are laboratory-based biological and performance tests.

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 device is a wound dressing, not an AI-powered diagnostic tool, so an MRMC study is not relevant.

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

  • Not applicable. This device is a wound dressing, not an algorithm, so standalone performance is not relevant.

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

  • Implied by the tests, but not explicitly stated as 'ground truth'. For biological tests (ISO 10993), the ground truth generally refers to established biological safety standards or predetermined acceptable ranges for various biological responses (e.g., cytotoxicity, sensitization, irritation). For performance characteristics, the "ground truth" would be the established performance metrics of the predicate device. However, the document doesn't detail how these were specifically established.

8. The sample size for the training set:

  • Not applicable / Not present. Training sets are relevant for machine learning/AI models. This document describes a physical medical device.

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

  • Not applicable. As above, training sets and ground truth establishment for them are not relevant to this type of device.

In summary, the provided K984593 510(k) summary focuses on demonstrating substantial equivalence through:

  • Biological testing: "Biological tests were done in accordance with ISO 10993 and showed no negative effects for the modified Cutinova thin." (This implies a comparison against safety standards).
  • Performance characteristics comparison: "Performance characteristics were also comparable to the currently marketed product." (This implies a comparison against the predicate device's performance).
  • Material change justification: The primary change is a material alteration (aromatic to aliphatic diisocyanate) and the addition of a small amount of Vitamin E for thermal stability, which the submission argues does not affect the indications for use or safety/effectiveness.

The document does not provide the detailed study results, specific acceptance criteria values, or sample sizes common in a detailed study report for a diagnostic or AI-powered device. Its purpose is to demonstrate substantial equivalence to a predicate device for regulatory clearance, not to publish a comprehensive scientific study.

N/A