Search Results

The Edwards Lifesciences Acumen Assisted Fluid Management (AFM) Software Feature provides the clinician with physiological insight into a patient's estimated response to fluid therapy and the associated hemodynamics. The Acumen AFM Software Feature is intended for use in surgical patients ≥18 years of age, that require advanced hemodynamic monitoring. The Acumen AFM Software Feature offers suggestions regarding the patient's physiological condition and estimated response to fluid therapy. Acumen AFM fluid administration suggestions are offered to the clinician; the decision to administer a fluid bolus is made by the clinician, based upon review of the patient's hemodynamics. No therapeutic decisions should be made based solely on the Assisted Fluid Management suggestions.

The Acumen AFM Software Feature (core AFM algorithm + AFM Graphical User Interface) was originally granted in De Novo, DEN190029, on November 13, 2020, to inform clinicians about a patient's fluid responsiveness. The performance of the AFM Software Feature in predicting a patient's fluid responsiveness is measured using response rate and is calculated by reporting the percentage of followed AFM recommendations ("Fluid Bolus Suggested" and "Test Bolus Suggested" prompts) that have the desired change in stroke volume (SV), divided by the total number of AFM recommendations.

With this submission, Edwards is seeking clearance for the AFM Prompt Reclassifier algorithm (AFM PR algorithm) to the Acumen AFM Software Feature. The AFM Prompt Reclassifier algorithm is intended to be used in conjunction with the core AFM algorithm to re-assess the fluid bolus recommendations provided by the core alqorithm. It analyzes the patient's current hemodynamics for either confirming (corroborating) the original prompt or reclassifying the prompts (i.e., reclassify a "Test Bolus Suggested" prompt to a "Fluid Bolus Suggested" prompt or vice versa). In doing so, it acts as a secondary check for the fluid bolus prompts such that a greater number of the "Fluid Bolus Suggested" prompts lead to the desired change in stroke volume. Through refined prompt adjustments informed by real-time hemodynamic data, the AFM PR algorithm aims to improve patient responsiveness, thereby optimizing the impact of the AFM Software Feature on patient hemodynamics.

The FDA 510(k) summary for the Acumen Assisted Fluid Management (AFM) Software Feature describes the acceptance criteria and the study conducted to demonstrate the device meets these criteria.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The algorithm performance was analyzed on an archived dataset consisting of 1229 data points from 307 patients.
• Data Provenance: The data came from the US IDE Study, G170204. The study involved 9 independent U.S. sites. The data is retrospective as it was an "archived dataset."

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

• This information is not provided in the document. The study uses physiological response (change in stroke volume) as the outcome measure, implying a physiological ground truth rather than expert interpretation of images or other data.

4. Adjudication Method for the Test Set

• This information is not provided in the document. Given the nature of the ground truth (physiological response), a traditional adjudication method for subjective assessments might not be directly applicable.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

• A MRMC comparative effectiveness study was not explicitly mentioned or described.
• The study focuses on the algorithm's performance in improving the response rate of its suggestions, rather than comparing human reader performance with and without AI assistance. The device offers "suggestions" and the "decision to administer a fluid bolus is made by the clinician."

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Yes, a standalone algorithm performance study was done. The document states, "Algorithm performance was analyzed on the archived dataset... The validation was to demonstrate the impact on the response rate of the AFM Software Feature's fluid bolus prompts due to the addition of AFM Prompt Reclassifier algorithm." This implies evaluating the algorithm's predictions against the measured physiological outcomes.

7. The Type of Ground Truth Used

• The ground truth used is physiological response/outcomes data. Specifically, the "desired change in stroke volume (SV)" following AFM recommendations was used to measure the "response rate."

8. The Sample Size for the Training Set

• The document does not explicitly state the sample size for the training set. It only mentions the "archived dataset from the US IDE Study, G170204" used for algorithm performance analysis/validation.

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

• The document does not explicitly describe how the ground truth for the training set was established. It focuses on the validation of the AFM Prompt Reclassifier algorithm using an existing dataset. Given that the core AFM algorithm was granted in De Novo DEN190029, the ground truth for its original training would likely have involved similar physiological outcome data from clinical studies where fluid administration decisions were made and subsequent stroke volume changes were observed.

Ask a specific question about this device