(171 days)
The V.A.C.® Therapy System is an integrated wound management system for use in acute, extended and home care settings. It is intended to create an environment that promotes wound healing by secondary or tertiary (delayed primary) intention by preparing the wound bed for closure, reducing edema, promoting granulation tissue formation and perfusion, and by removing exudate and infectious material. It is indicated for patients with chronic, acute, traumatic, subacute and dehisced wounds, partial-thickness burns, ulcers (such as diabetic or pressure), flaps and grafts.
The V.A.C.® GranuFoam® Silver™ Dressing is an effective barrier to bacterial penetration and may help reduce infection in the above wound types.
The InfoV.A.C.® Therapy System is designed for the application of V.A.C.® Therapy in the acute, extended and home care settings. The software-controlled therapy unit applies negative pressure to the wound bed. The open cells of the V.A.C.® foam dressing to which the therapy unit is connected enable distribution of the negative pressure across the surface of the wound, while the tubing transfers accumulated fluids to the canister. The software monitors and maintains target pressure and alarms as needed to help assure target pressure is maintained and constant therapy is delivered. The safety features of the system include additional alarms, such as those that signal for tubing blockages, a full or missing collection canister, inactive therapy, low battery, and leaks in the seal of the dressing. Optional features include: Seal Check™ for identifying dressing leaks, a Therapy Settings Guide that provides options for therapy settings based on the recommendations in the KCI Clinical Guidelines, a Screen Guard feature that prevents unintentional screen changes, an exportable Therapy History Report, and a Log Tool for recording canister changes, dressing changes and dressing pieces used. Another new optional feature is the ability to receive and store digital images of the patient's wound throughout the healing process. By tracing the wound perimeter on the digital image, wound area can be calculated by the software. If the user inputs a wound depth value, wound volume can also be calculated. Wound images and area/volume calculations can be electronically transferred via a Patient History Report.
The provided text describes the InfoV.A.C.® Therapy Unit, a negative pressure wound therapy device. It does not contain specific acceptance criteria or details of a study that directly proves the device meets such criteria in a quantitative manner as typically requested for AI/ML device evaluations. Instead, the document focuses on demonstrating substantial equivalence to predicate devices and detailing the new optional features.
However, I can extract information related to the device's performance assertions and the general nature of the studies conducted.
Here's a breakdown of the available information based on your requested categories:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table with quantitative acceptance criteria (e.g., specific sensitivity, specificity, or AUC targets) nor does it report specific numerical performance metrics for the InfoV.A.C.® Therapy Unit in the context of wound analysis. The performance is primarily assessed through verification and validation testing to assure "performance and conformance to design specifications" for its new features, and through a comparative analysis to predicate devices for its core function.
| Feature/Characteristic | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Negative pressure delivery | Equivalent to predicate devices (V.A.C.® ATS and V.A.C. Freedom®) | "Same technology and performance specifications for the delivery of negative pressure wound therapy." |
| Alarms (tubing blockages, full/missing canister, inactive therapy, low battery, leaks) | Functionality as designed to assure target pressure and constant therapy, and to signal issues. | "additional alarms... help assure target pressure is maintained and constant therapy is delivered." |
| Seal Check™ (optional) | Ability to identify dressing leaks. | Designed to identify dressing leaks. |
| Therapy Settings Guide (optional) | Provides options based on KCI Clinical Guidelines. | Provides options for therapy settings. |
| Screen Guard feature (optional) | Prevents unintentional screen changes. | Prevents unintentional screen changes. |
| Exportable Therapy History Report (optional) | Generates a report of therapy history. | Generates an exportable report. |
| Log Tool (optional) | Records canister changes, dressing changes, and dressing pieces used. | Records specified events. |
| Digital image storage and wound analysis (area/volume calculation) (optional) | Ability to receive and store digital images, calculate wound area, and optionally wound volume. | "ability to receive and store digital images...By tracing the wound perimeter...wound area can be calculated...If the user inputs a wound depth value, wound volume can also be calculated." |
| Electronic transfer of wound data (optional) | Ability to transfer images and calculations via Patient History Report. | Wound images and area/volume calculations can be electronically transferred. |
| Safety and Usability (Home Care) | Equivalent to or improved over V.A.C. Freedom® in elements affecting safety and usability. | "InfoV.A.C.® improves upon V.A.C. Freedom® in the elements that affect safety and usability in the home care setting." |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not specify a distinct "test set" in the context of evaluating an AI/ML algorithm with a specific sample size. The "non-clinical tests" involved "verification and validation tests," but no sample sizes for these tests (e.g., number of wound images or wound measurements) are provided.
For the clinical context, the document states: "A review of a large body of clinical data from prospective randomized controlled trials, comparative and retrospective studies, payor/provider data, and retrospective review of independent electronic medical record data documents the safe use of the V.A.C. Freedom® Therapy Unit in the home care setting." This refers to clinical data for the predicate device, which is then extrapolated to the new device based on equivalence in core function and improved features. The provenance of this large body of clinical data is not specified beyond being "clinical data." Given the manufacturer, it is likely to include data from the USA, but no specific countries are mentioned.
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 information is not provided. The document outlines that the wound area is calculated by the software by "tracing the wound perimeter on the digital image," which implies a user-inputted tracing rather than an automated algorithm establishing a ground truth that needs expert validation. If wound depth is input, wound volume is calculated. The clinical data referenced is for the predicate device's overall safety and effectiveness, not for validating the accuracy of the new wound measurement feature.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
No adjudication method is mentioned for any "test set" related to the wound measurement capabilities.
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 such MRMC comparative effectiveness study is mentioned. The AI-like functionality (wound measurement) in this device is presented as a tool for the user (caregiver/patient), not as an assistive AI for human readers/clinicians, nor is its impact on human performance quantified.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device's wound measurement capability described involves human input ("By tracing the wound perimeter on the digital image, wound area can be calculated by the software. If the user inputs a wound depth value, wound volume can also be calculated."). This indicates a human-in-the-loop process, not a standalone algorithm that automatically detects and measures wounds without user interaction. Therefore, a standalone performance study as typically understood for an AI algorithm was not applicable or performed according to the provided text.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the wound measurement features, the ground truth is established by the user's tracing of the wound perimeter and input of wound depth. This is not an external, independent ground truth like pathology or expert consensus on image analysis. For the broader clinical effectiveness, the "large body of clinical data" for the predicate device likely relied on clinical outcome data as ground truth.
8. The sample size for the training set
The document does not describe the use of a "training set" in the context of an AI/ML algorithm. The wound measurement function appears to be based on geometric calculations performed after user input (tracing and depth).
9. How the ground truth for the training set was established
As there is no mention of an algorithm training set, this information is not applicable.
§ 878.4780 Powered suction pump.
(a)
Identification. A powered suction pump is a portable, AC-powered or compressed air-powered device intended to be used to remove infectious materials from wounds or fluids from a patient's airway or respiratory support system. The device may be used during surgery in the operating room or at the patient's bedside. The device may include a microbial filter.(b)
Classification. Class II.