Search Results

EchoSolv AS is a machine learning (ML) and artificial intelligence (AI) based decision support software indicated for use as an adjunct to echocardiography for assessment of severe aortic stenosis (AS).

When utilized by an interpreting physician, this device provides information to facilitate rendering an accurate diagnosis of AS. Patient management decisions should not be made solely on the results of the EchoSolv AS analysis.

EchoSolv AS includes both the algorithm based AS phenotype analysis, and the application of recognized AS clinical practice quidelines.

Limitations: EchoSolv AS is not intended for patients under the age of 18 years or those who have previously undergone aortic valve replacement surgery

EchoSolv AS is a standalone, cloud-based decision support software which is intended to be used certified cardiologist to aid in the diagnosis of Severe Aortic Stenosis. EchoSolv AS analyzes basic patient demographic data and measurements obtained from a transthoracic echo examination to provide a categorical assessment as to whether the data are suggestive of a high, medium or low probability of Severe AS. EchoSolv AS is intended for patients who 18 years or older who have an echocardiogram performed as part of routine clinical care (i.e., for the evaluation of structural heart disease).

Patient demographic and echo measurement data is automatically processed through the artificial intelligence algorithm which provides an output regarding the probability of a Severe AS phenotype to aid in the clinical diagnosis of Severe AS during the review of the patient echo study and generation of the final study report, according to current clinical practice guidelines. The software provides an output on the following assessments:

1. Severe AS Phenotype Probability

Whether the patient has a high, medium, or low probability of exhibiting a Severe AS phenotype, based on analysis by the EchoSolv AS proprietary Al algorithm, that the determined predicted AVA is ≤1.0cm². The Al probability score requires a minimum set of data inputs to provide a valid output but is based on all available echocardiographic measurement data and does not rely on the traditional LVOT measurements used to in the continuity equation.

2. Severe AS Guideline Assessment

Whether the patient meets the definition for Severe AS based on direct evaluation of provided echocardiogram data measurements (AV Peak Velocity, AV Mean Gradient and AV Area) with current clinical practice guidelines (2020 ACC/AHA Guideline for the Management of Patients with Valvular Heart Disease).

EchoSolv AS is intended to be used by board-certified cardiologists who review echocardiograms during the evaluation and diagnosis of structural heart disease, namely aortic stenosis. EchoSolv AS is intended to be used in conjunction with current clinical practices and workflows to improve the identification of Severe AS cases.

Here's an analysis of the acceptance criteria and study detailed in the provided document for the EchoSolv AS device:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a tabulated format. However, based on the performance data presented, the implicit acceptance criteria can be inferred from the reported performance and comparison to a predicate device. The performance metrics reported are AUROC, Sensitivity, Specificity, Diagnostic Likelihood Ratios (DLR), and improvement in reader AUROC and concordance in the MRMC study.

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

• Standalone Performance Test Set:
  • Sample Size: 6,268 studies.
  • Data Provenance: The document states the dataset for model development was randomly split into training and test sets. The standalone performance testing was performed on an "independent retrospective cohort study" meaning the data was collected from past records. The country of origin for this specific retrospective cohort is not explicitly stated, but it's implied to be within a clinical setting that would allow for US board-certified cardiologists to review and verify the data.
• Clinical Performance (MRMC) Test Set:
  • Sample Size: 200 retrospective transthoracic echocardiogram (TTE) studies (100 disease cases, 100 control studies).
  • Data Provenance: Retrospective, performed at "one investigational site in the US."

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

• Standalone Performance Test Set:
  • Number of Experts: More than one, implied by "US board certified cardiologists" (plural).
  • Qualifications: "US board certified cardiologists." No specific years of experience are mentioned.
• Clinical Performance (MRMC) Test Set:
  • Number of Experts: Two.
  • Qualifications: "board certified cardiologists." No specific years of experience are mentioned.

4. Adjudication Method for the Test Set

• Standalone Performance Test Set: The ground truth was established by "US board certified cardiologists, who reviewed and verified the echocardio data and hemodynamic profile... and were blinded to the device output." This implies a consensus or majority rule adjudication among the "cardiologists" if multiple were involved per case. There is no explicit "2+1" or "3+1" method mentioned, but rather a verification process.
• Clinical Performance (MRMC) Test Set: "The total test dataset was reviewed by two board certified cardiologists to confirm the presence and severity of Severe AS." This suggests a 2-reader agreement for the ground truth. If there was disagreement, an implied adjudication process (e.g., a third reader or consensus discussion) would be needed, but it is not specified.

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

• Yes, a MRMC comparative effectiveness study was done.
• Effect Size of Improvement:
  • Mean AUROC Improvement: 0.018 (95% CI: 0.037-0.001; p=0.064).
  • Reader Concordance Improvement: 0.027 (from 0.641 unassisted to 0.667 assisted).

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

• Yes, a standalone performance testing was performed. The objective was to assess the "native system performance of the EchoSolv AS model in its ability to detect Severe AS."

7. The Type of Ground Truth Used

• Standalone Performance Test Set: Expert consensus based on "the assessment of the presence of severe aortic stenosis (defined as an AVA≤1 cm²) by US board certified cardiologists, who reviewed and verified the echocardio data and hemodynamic profile." This combines clinical assessment using a specific echocardiographic measurement (AVA) and expert review.
• Clinical Performance (MRMC) Test Set: Expert consensus. "The total test dataset was reviewed by two board certified cardiologists to confirm the presence and severity of Severe AS."

8. The Sample Size for the Training Set

• 442,276 individuals (from a total dataset of 631,824 individuals).

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

The document states: "The EchoSolv AS Al Model was developed on a dataset consisting of 631,824 individuals with 1,077,145 transthoracic echocardiograms (TTE)." It also notes that the model was trained "to detect severe AS cases." While implied that the training set also used ground truth related to severe AS detection, the specific methodology for establishing ground truth for the training set is not explicitly detailed in the provided text. It is reasonable to infer it would be similar to the test set ground truth (expert clinical assessment based on echocardiographic data), but this is not directly stated.

Ask a specific question about this device