Search Results

The 'eMurmur Heart AI' software is a decision support system in the evaluation of recorded patient heart sounds. The automated analysis by eMurmur Heart Al identifies specific heart sounds that may be present, including S1, S2, physiological heart murmurs, pathological heart murmurs and the absence of a heart murmur.

eMurmur Heart AI is indicated for use in a setting where auscultation would typically be performed by a healthcare provider. It is not intended as a sole means of diagnosis. The heart sound interpretations offered by eMurmur Heart AI are only significant when considered in conjunction with healthcare provider over-read and including all other relevant patient data.

To analyze heart sounds via the eMurmur Heart AI, a digital recording of a patient's heart sounds is required. Recordings are made using a supported digital stethoscope, connected to a front-end client like, e.g., the eMurmur app or the eMurmur web portal. The recorded auscultation data are transmitted from the front-end client to the eMurmur backend, which hosts the eMurmur Heart Al. After analysis by the eMurmur Heart Al, the results of the analysis are returned to the front-end client where they are displayed to the user. The user can utilize the eMurmur Heart AI results to support their decision-making process regarding the potential presence and type of a heart murmur.

eMurmur is a non-medical device software platform which includes the eMurmur backend, eMurmur apps and eMurmur web portal. The platform is used to stream, record, display. replay, and store auscultation data, recorded by means of supported digital stethoscopes.

The eMurmur software platform has functions subject to FDA premarket review, i.e., eMurmur Heart AI, as well as functions that are not subject to FDA premarket review. For this application. FDA assessed those functions only to the extent that they could adversely impact the safety and effectiveness of the functions subject to FDA premarket review.

The provided text describes the eMurmur Heart AI device, but it mainly focuses on its substantial equivalence to a predicate device (eMurmur ID) and states that no new performance data was required because the core algorithm is the same. Therefore, the information needed to fully answer your request regarding acceptance criteria and a new study proving the device meets those criteria is not explicitly present for eMurmur Heart AI.

However, based on the information provided, we can infer some details and present the "Clinical Performance" data listed for the predicate device, eMurmur ID, as it's stated that eMurmur Heart AI shares the same heart sound analysis algorithm and thus identical clinical performance.

Here's the breakdown of the information that can be extracted or reasonably inferred from the document:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state "acceptance criteria" but lists "Clinical Performance" metrics for the "eMurmur ID" predicate device, which are then declared identical for eMurmur Heart AI. These would serve as the de facto performance metrics considered acceptable for substantial equivalence.

Note: The document explicitly states: "eMurmur Heart AI and the predicate, eMurmur ID (K181988), utilize the same heart sound analysis algorithm, hence no new performance data is required." This implies that the performance established for eMurmur ID is directly applicable and "accepted" for eMurmur Heart AI.

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

The provided text does not specify the sample size used for the test set for either eMurmur Heart AI or the predicate eMurmur ID, nor does it mention data provenance (country of origin, retrospective/prospective). This information would typically be detailed in the original 510(k) submission for eMurmur ID (K181988).

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

The provided text does not specify the number of experts used or their qualifications for establishing ground truth for the test set of the predicate eMurmur ID.

4. Adjudication Method for the Test Set

The provided text does not specify the adjudication method used for the test set of the predicate eMurmur ID.

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

The provided text does not mention a multi-reader multi-case (MRMC) comparative effectiveness study, nor does it discuss the effect size of human readers improving with AI assistance.

6. Standalone Performance

Yes, a standalone performance study was done based on the predicate device (eMurmur ID). The listed Sensitivity and Specificity (85.0% and 86.7% respectively) represent the algorithm's performance without explicit mention of human-in-the-loop assistance during the reported performance evaluation. The device is described as a "decision support system," emphasizing its role in aiding healthcare providers.

7. Type of Ground Truth Used

The type of ground truth used is not explicitly stated in this document. It mentions the algorithm identifies specific heart sounds, including physiological and pathological murmurs. Typically, for such devices, ground truth would be established by expert consensus based on clinical examination, potentially complemented by other diagnostic tests (e.g., echocardiography) for heart murmur validation.

8. Sample Size for the Training Set

The provided text does not specify the sample size for the training set.

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

The provided text does not specify how the ground truth for the training set was established.

Summary of what's missing and why:

The core reason for much of the missing information is that this document is a 510(k) summary for "eMurmur Heart AI" which leverages the substantial equivalence pathway. It argues that because "eMurmur Heart AI" uses the same heart sound analysis algorithm as the already cleared "eMurmur ID," no new performance data is required. Therefore, the detailed study design, sample sizes, expert qualifications, and ground truth methodologies would have been part of the original 510(k) submission for "eMurmur ID" (K181988), not explicitly reiterated in this document beyond the summary performance metrics.

Ask a specific question about this device