(232 days)
InnoSEAL Hemostatic Pad is intended for the local management of bleeding wounds and for the promotion of rapid control of bleeding. InnoSEAL Hemostatic Pad is intended for use under the care of a healthcare professional.
The dressing is indicated for following wounds; lacerations, abrasions and the skin surface puncture sites for vascular procedures, percutaneous catheters/tubes.
InnoSEAL Hemostatic Pad is a hydrophilic, lyophilized sponge pad for local management of bleeding wound made of proprietary formulation of chitosan and catechol conjugated chitosan which are biocompatible. InnoSEAL Hemostatic Pad is applied topically as an adjunct to manual compression. InnoSEAL Hemostatic Pad is a single use device individually packaged by PET mold and Aluminum lid and sterilized with gamma irradiation.
The provided text describes the InnoSEAL Hemostatic Pad and its substantial equivalence determination, but it does not contain a specific table or study explicitly detailing acceptance criteria and reported device performance for a typical AI/ML medical device submission.
Instead, the document focuses on demonstrating substantial equivalence to predicate devices through various performance tests, rather than setting and meeting specific quantitative acceptance criteria for a novel AI/ML algorithm.
Therefore, I cannot provide a direct answer to the request based on the provided text, as the necessary information (acceptance criteria table, study proving device meets criteria, sample sizes for test/training sets of an AI model, expert ground truth details, MRMC study, standalone performance, etc.) is not present for an AI/ML device.
However, I can extract information about the performance data provided for the InnoSEAL Hemostatic Pad and summarize what is available:
Summary of Performance Data for InnoSEAL Hemostatic Pad (as presented in the document):
The submission for the InnoSEAL Hemostatic Pad does not present performance data in the typical format of acceptance criteria and reported performance for an AI/ML device. Instead, it relies on a series of tests to demonstrate equivalence to predicate devices. The studies mentioned are primarily pre-clinical (bench and animal) rather than clinical efficacy trials with human subjects.
Here's a breakdown of the available information:
1. Table of Acceptance Criteria and Reported Device Performance:
- Not Applicable / Not Present. The document does not define specific "acceptance criteria" (e.g., minimum sensitivity, specificity, or AUC) that an AI/ML model would typically need to meet, nor does it present device performance against such criteria. The submission is for a physical medical device (hemostatic pad), not an AI/ML algorithm.
2. Sample Sizes Used for the Test Set and Data Provenance:
- Test Set (Animal Study): "In-vivo hemostasis test using swine femoral artery hemorrhage model was performed to demonstrate the effectiveness and safety of InnoSEAL Hemostatic Pad."
- Sample Size: Not explicitly stated, though it refers to "Study 15-KE-136." The number of swine or specific arteries tested is not provided.
- Data Provenance: Animal study (swine model), likely prospective within the context of the study. Country of origin not specified, but the submitter is InnoTherapy Inc. from Seoul, Republic of Korea.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications:
- Not applicable. For the animal study, "Gross necropsy and histopathological evaluations" were performed. The "ground truth" here would likely be determined by veterinary pathologists or researchers involved in the animal model. The number and qualifications of these experts are not provided.
4. Adjudication Method for the Test Set:
- Not explicitly stated. For the animal study, it mentions "Gross necropsy and histopathological evaluations," suggesting standard veterinary pathology practices were followed. No specific adjudication method like "2+1" or "3+1" is mentioned, as this is typically for human reader studies.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:
- No. This type of study is specifically for evaluating human readers, often with and without AI assistance, and is not relevant to the evaluation of a physical hemostatic pad.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Not applicable. The device is a physical pad, not an algorithm.
7. The Type of Ground Truth Used:
- Animal Outcomes/Histopathology/Gross Necropsy: For the animal study, the effectiveness and safety were assessed through observations of hemostasis, and subsequent gross and histopathological evaluations of tissues.
8. The Sample Size for the Training Set:
- Not applicable. As this is not an AI/ML device, there is no "training set."
9. How the Ground Truth for the Training Set was Established:
- Not applicable. There is no training set for a physical hemostatic pad.
Summary of Other Performance Data (Bench Tests):
The document also lists several bench tests conducted to demonstrate the device's characteristics and safety:
- Biocompatibility tests: Acute systemic toxicity, Cytotoxicity, Skin Sensitization, Intracutaneous Reactivity, Endotoxin. (Results "met all relevant requirements.")
- Comparative liquid absorption test: (Results: "equivalent to predicate device.")
- Identification tests: Comparative FT-IR analysis, Gelation test.
- Physical/Chemical tests: Appearance, Residue on ignition, Degree of oxidation, Loss on drying, Heavy metal, pH, Residual solvent, Deacetylation degree.
- Packaging tests: Qualification, Burst, Tensile/Tearing/Heat-sealing strength, Dye penetration.
- Sterility and Shelf life tests: Sterilization validation, Accelerated stability, Real-time stability.
- Microbiological safety tests: Virus clearance tests (demonstrated "efficient virus inactivation").
These tests are designed to show that the InnoSEAL Hemostatic Pad is safe, performs as expected technologically, and is substantially equivalent to existing, legally marketed predicate devices. The "acceptance criteria" for these tests would be the specific standards and limits defined in the respective test protocols and relevant consensus standards. The "reported performance" is that the device "met all relevant requirements" or was "equivalent to predicate device." However, specific numerical acceptance criteria and performance metrics for each of these diverse tests are not tabulated in the provided text.
N/A