Search Results

Eko Low Ejection Fraction Tool (ELEFT) is a software intended to aid clinicians in identifying individuals with Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%. ELEFT takes as input ECG and heart sounds and is intended for use on patients at risk for heart failure. This population includes, but is not limited to, patients with: coronary artery disease; diabetes mellitus; cardiomyopathy; hypertension; and obesity.

The interpretations of heart sounds and ECG offered by the software are meant only to assist healthcare providers in assessing Left Ventricular Ejection Fraction ≤ 40% , who may use the result in conjunction with their own evaluation and clinical judgment. It is not a diagnosis or for monitoring of patients diagnosed with heart failure. This software is for use on adults (18 years and older).

Eko Low Ejection Fraction Tool (ELEFT) is an algorithm that is intended to aid clinicians to identify individuals with Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%. ELEFT takes as input ECG and heart sounds from patients at risk for heart failure. The software uses signal processing as well as machine learning algorithms, to analyze the electrocardiogram (ECG) and heart sound/phonocardiogram (PCG) recording signals generated by FDA-cleared Eko Stethoscopes and saved as .WAV file recordings in the Eko Cloud. ELEFT is a machine learning based notification software which employs machine learning techniques to suggest the likelihood of LVEF

The Eko Low Ejection Fraction Tool (ELEFT) is a software intended to aid clinicians in identifying individuals with Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%. The device takes ECG and heart sound inputs and processes them using signal processing and machine learning algorithms.

Here's an analysis of its acceptance criteria and the study proving its performance:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document doesn't explicitly state "acceptance criteria" in a numerical target format (e.g., "Sensitivity must be >= X%"). However, the clinical performance results presented demonstrate the device's capability to detect Low EF. The acceptance effectively hinges on the presented sensitivity and specificity values.

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

• Test Set Sample Size: 3,456 unique subjects. After excluding 307 recordings due to poor ECG quality, the performance analysis was based on the remaining suitable recordings.
• Data Provenance: Retrospective data collected from:
  • US, 5 sites: 2,960 patients.
  • India, 1 site: 496 patients.

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

• Number of Experts: Not explicitly stated as a number, but the ground truth for ejection fraction was "overread by a board-certified cardiologist." This implies at least one, and potentially multiple, board-certified cardiologists were involved in reviewing the echocardiogram results.
• Qualifications of Experts: Board-certified cardiologists.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method like 2+1 or 3+1 for resolving discrepancies in ground truth establishment. It states that the "subject's true ejection fraction was measured by the echocardiogram machine's integrated cardiac quantification software at the echocardiogram and then overread by a board-certified cardiologist." This suggests a single expert review after automated measurement, with no mention of multiple reviewers or a formal reconciliation process if initial measurements or interpretations differed.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted. The study focuses solely on the standalone performance of the ELEFT algorithm without a human-in-the-loop component or evaluating the improvement of human readers with AI assistance.

6. Standalone (Algorithm Only) Performance

Yes, a standalone (algorithm only) performance study was conducted. The results for sensitivity, specificity, PPV, and NPV presented in Table 2 and the subsequent text (page 9) are for the ELEFT algorithm's performance in differentiating between Low EF (≤40%) and Normal EF (>40%).

7. Type of Ground Truth Used

The type of ground truth used was expert consensus / pathology based on instrumental measurements and expert review:

• Echocardiogram (Instrumental Measurement): The true ejection fraction was measured by the echocardiogram machine's integrated cardiac quantification software.
• Expert Overread: This measurement was "overread by a board-certified cardiologist."
• Categorization: Ejection status (Low EF or Normal EF) was then assigned based on these measured and reviewed values.

8. Sample Size for the Training Set

The sample size for the training set was 1,852 patients. This data was contributed from:

• US, 7 sites: 1,515 patients.
• India, 1 site: 337 patients.

9. How Ground Truth for the Training Set Was Established

The document does not explicitly detail the exact process for establishing ground truth for the training set. However, given the consistency in the data description and the validation methodology, it is highly probable that the ground truth for the training set was established using the same methodology as the test set: gold standard echocardiogram measurements, subsequently overread by board-certified cardiologists, and then categorized into Low EF (≤40%) or Normal EF (>40%).

Ask a specific question about this device

The Eko Murmur Analysis Software (EMAS) is intended to provide decision support to clinicians in their evaluation of patients' heart sounds. The software analyzes heart sounds and phonocardiograms (and ECG signals, when available). The software will automatically detect murmurs that may be present, and the murmur timing and character, including S1, S2, innocent heart murmurs, structural heart murmurs, and the absence of a heart murmur.

The Eko Murmur Analysis Software is not intended as a sole means of diagnosis and is for use in environments where health care is provided by clinicians. The interpretations of heart sounds offered by the software are meant only to provide decision support to the clinician, who may use the result in conjunction with their own evaluation and clinical judgment. The interpretations are not diagnoses. The Eko Murmur Analysis Software is intended for use on pediatric and adult patients.

Eko Murmur Analysis Software (EMAS) is a cloud-based service that allows users to upload heart sound/phonocardiogram (PCG) and optional electrocardiogram (ECG) data via an application programming interface (API) for analysis. The software uses signal processing (such as waveform filtering), as well as algorithms derived from machine learning, to analyze the acquired data and generate clinical decision support output for clinicians. EMAS is designed to evaluate data derived by the company's two previously cleared devices, the Eko DUO (K170874) and Eko CORE (K151319, K200776). The heart sound data from those devices can be transmitted to the Eko Cloud using either the Eko mobile application or thirdparty applications that use a software development kit (SDK). The EMAS algorithm analyzes the heart sound data and outputs a JSON file with the algorithm results, which is passed down to the requesting application and displayed by the requesting application to the user in the humanreadable format.

The analysis will assess the signal quality of the phonocardiogram; detect heart murmurs and classify them as innocent or structural; determine the timing of S1 and S2 heart sounds; and distinguish between systolic and diastolic heart murmurs. As an integral part of a physical assessment, clinicians' interpretations of EMAS' output can help them rule in or out different pathological conditions in a patient.

The EMAS consists of the following algorithm components:

• Signal Quality Detection Algorithm:
  This pre-processing algorithm accepts as input the PCG sound from the API controller (e.g., a mobile smartphone application). The algorithm is used to classify PCG recordings based on their signal quality as good or poor.

• Heart Sound Timing Algorithm:
  This algorithm detects the presence and timing of specific heart sounds including S1, S2, the systole region, and the diastole region.

• Murmur Detection & Classification Algorithm: This algorithm is used to identify and classify heart sounds as having "No Murmur", an "Innocent Murmur" (i.e., not pathologic), or a "Structural Murmur" (i.e., pathologic).

• Murmur Timing Algorithm:

This algorithm is used to identify in which regions of the heart cycle (systole vs diastole) a heart murmur occurs if either an "Innocent Murmur" or "Structural Murmur" is identified by the Murmur Detection and Classification Algorithm.

Here's an analysis of the Eko Murmur Analysis Software (EMAS) acceptance criteria and the study proving its performance, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Size: The document does not explicitly state a separate "test set" size. However, it indicates that the clinical validation used a database of 2,380 unique heart sound recordings from 615 unique subjects.
  • Of these, "recordings identified as being good signal by the expert cardiologists" (meaning suitable for analysis) included:
    • 45.8% (approx. 1090 recordings) with a confirmed structural murmur.
    • 54.2% (approx. 1290 recordings) with confirmed no murmur or innocent murmur.
  • For heart sound timing, 299 heart sound recordings were annotated.
• Data Provenance: Retrospective analysis on a proprietary database. The country of origin is not specified, but the applicant (Eko Devices, Inc.) is based in Oakland, California, USA.

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

• Number of Experts: "Multiple cardiologists" were used. The exact number is not specified.
• Qualifications of Experts: "Cardiologists." No further details on their years of experience or specific subspecialties are provided.

4. Adjudication Method for the Test Set

• Recordings were "annotated by multiple cardiologists."
• There's no explicit mention of an adjudication method like 2+1 or 3+1. However, the ground truth for murmur classification was obtained via "pairing cardiologist annotations with gold standard echocardiogram," suggesting that the echocardiogram served as the definitive ground truth reference alongside expert opinion.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not reported. The study focuses on the standalone performance of the EMAS algorithm against a ground truth. There is no information provided about human readers improving with or without AI assistance.

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

• Yes, a standalone study was done. The reported performance metrics (Sensitivity, Specificity, PPV) are directly attributed to the "EMAS algorithm testing" and represent the algorithm's performance against the established ground truth. The device is intended as "decision support" and "not intended as a sole means of diagnosis," indicating it operates standalone and then informs a clinician.

7. The Type of Ground Truth Used

• For Murmur Classification: Ground truth was established by pairing cardiologist annotations with gold standard echocardiogram.
• For S1/S2 Timing: Ground truth was established via expert cardiologist annotations.

8. The Sample Size for the Training Set

• The document explicitly states: "No study subjects included in the training datasets were included in the test database." However, it does not provide the sample size for the training set. It only mentions that the algorithms were validated using "retrospective analysis on a proprietary database."

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 only refers to a "proprietary database" used for training and then tested on a separate, distinct set of subjects. Assuming a consistent approach, it's likely similar methods (expert annotations, potentially with echocardiogram correlation) were used, but this is not stated.

Ask a specific question about this device