Search Results

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

The eKuore One Wireless electronic interface for stethoscope is intended to be used as a part of a patient by healthcare professionals for diagnostic decision support in clinical settings. eKuore One Wireless is intended for use on pediatric and adult patients. It can electronically filter and transfer sounds to the accompanying mobile software application.

It can be used to record heart sounds and cardiac murmurs, bruits, respiratory sounds and abdominal sounds during physical examination in normal patients or those with suspected diseases of the cardiac, vascular, pulmonary or abdominal organ systems.

The equipment consists of a stethoscope attachment, which will let the sound flow through the stethoscope's tube, so the stethoscope can continue working as usual, and the sound will be collected by a little hole in the piece, where a microphone will be placed. Then, this piece will be covered by a plastic case. A Bluetooth module is placed for a wireless transition of the data to a mobile (Android/IOS) or tablet. The eKuore One Wireless electronic interface for stethoscope gets the power supply from an internal rechargeable battery.

The application allows the user to visualize audio streaming received from the stethoscope. The connection is established between the smartphone application and the selected device, and after this event, the selected device starts to stream audio to the smartphone application.

The application also allows the user to record the current audio streaming, storing it in the internal storage of the Android/iOS device. The recordings can be viewed, shared and deleted after that.

The application does not store or collect any personal data of the users or patients. The only generated artifacts generated with the use of the application, the auscultations stored in the internal storage of the Android/iOS device, can only be identified by its name, which is a combination of the time and date when the auscultation was performed, which is insufficient to identify uniquely a patient or gets its personal information.

The provided text is a 510(k) Premarket Notification for the "eKuore One Wireless Electronic Interface for Stethoscope" and focuses on demonstrating substantial equivalence to a predicate device. It does not contain information about acceptance criteria or a study proving the device meets specific performance criteria related to diagnostic accuracy, sensitivity, specificity, or other clinical efficacy metrics. Instead, the document discusses technical characteristics and regulatory compliance to demonstrate equivalence to a previously cleared device.

Therefore, most of the requested information regarding acceptance criteria and clinical study details cannot be extracted from this document.

Here's what can be gathered, along with what is missing:

1. Table of Acceptance Criteria and Reported Device Performance:

• Acceptance Criteria: Not explicitly stated as pass/fail metrics for clinical performance. The document focuses on demonstrating substantial equivalence to a predicate device based on technical characteristics and regulatory compliance.

• Reported Device Performance: The document lists technical characteristics of the eKuore One Wireless electronic interface for stethoscope and compares them to a predicate device. This is not "performance" in the sense of diagnostic accuracy or clinical outcomes.

  Elements of Comparison (as per provided text)	eKuore One Wireless electronic interface for stethoscope (Candidate Device)	Eko electronic stethoscope system (Reference Device)	Comparison
  Regulatory data
  Regulatory Class	Class II	Class II	Identical
  Device Classification name	Electronic Stethoscope	Electronic Stethoscope	Identical
  Regulation Number	21 CFR 870.1875	21 CFR 870.1875	Identical
  Classification Product code	DQD	DQD	Identical
  FDA Clearance	Pending	K151319	-
  USE
  Intended use	Diagnostic decision support... record heart sounds, cardiac murmurs, bruits, respiratory, and abdominal sounds.	Diagnostic decision support... record heart sounds, cardiac murmurs, bruits, respiratory, and abdominal sounds.	Similar (Predicate also amplifies sound)
  Characteristics
  Principles of operation	Microphone & electronics for digitalization/codification, wireless (Bluetooth) to mobile.	Dispositive introduced in acoustic stethoscope, sound amplification, audio transmission to smartphone via Bluetooth.	Similar (Both acquire and transmit sound to a mobile app)
  Clinical conditions	Human body sounds related	Human body sounds related	Identical
  Use	Electronic stethoscope	Electronic stethoscope	Identical
  Compatibility	-Littmann 3M Cardiology III/IV -Littmann 3M classic II/III	-Littmann 3M Cardiology II/III -Welch Allyn Harvey Elite -ADC601 lines of analog stethoscopes	Similar (Both compatible with Littmann 3M Cardiology III)
  Prescription/OTC	Prescription use	Prescription use	Identical
  Intended for Direct Connection to Patient	No	No	Identical
  Use environment	Clinical	Clinical	Identical
  Type of users	Health-care personnel	Health-care personnel	Identical
  Target population	All types of patients	All types of patients	Identical
  Cleaning & Maintenance	Detach, alcohol wipe cleaning of eKuore One. Stethoscope cleaned between each patient.	Stethoscope and CORE cleaned between each patient. External parts with 70% isopropyl alcohol wipes.	Identical
  Technical equivalence
  Sound track transfer function	Yes	Yes	Identical
  Signal transmission for visualization	Bluetooth transmission to compatible smartphones/tablets	Bluetooth transmission to compatible smartphones/tablets	Identical
  Energy Source	Rechargeable Lithium Ion Battery	Rechargeable Lithium Ion Battery	Identical
  System required	Android and iOS	Android and iOS	Identical
  Hardware and software platforms	Mobile devices or tablets	Mobile devices or tablets	Identical
  Connections	Micro USB connector only to charge internal battery	Micro USB connector only to charge internal battery	Identical
  Frequency range	20 Hz to 2 KHz	20 Hz to 2 kHz	Identical
  Signal Input Method	Sound collected via a Transducer. MEMS	Sound waves collected via a Transducer. Electro microphone	Identical
  Audio Output Method	Earbuds and 3.5mm Jack when connected with smartphone/tablets	Earbuds and 3.5mm Jack when connected with smartphone/tablets	Identical
  Signal Storage	Allows signal storage depending on technical features of connected device.	Allows signal storage depending on technical features of connected device.	Identical
  Performance requirements	Temp range: -20℃ to +45℃ Humidity range: 0% to 90%	The operating range is 10℃ to 40℃, and 0% to 90% relative humidity	Similar
  Biological Equivalence
  Materials	Cover: ABS and EPDM; Pushbutton: PMMA; Gasket: EPDM	Body: ABS (Acrylonitrile Butadiene Styrene).	Similar
  Contact with human tissues or body fluids	Does not contact patient's body. Attached stethoscope does.	Does not contact patient's body. Attached stethoscope does.	Identical
  Sterility	Sterility considerations are not applicable	Sterility considerations are not applicable	Identical

2. Sample size used for the test set and the data provenance: Not provided. The submission relies on non-clinical test data and comparison to a predicate device, not a clinical test set for diagnostic performance.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable, as no such clinical test set or ground truth establishment is described.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.

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: Not applicable. This document does not describe an AI device or a comparative effectiveness study. The device is a "Wireless Electronic Interface for stethoscope" which electronically filters and transfers sounds.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not applicable. The device is an electronic interface for a stethoscope, meant to be used by healthcare professionals. It's not a standalone diagnostic algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable, as no clinical performance study requiring ground truth is described.

8. The sample size for the training set: Not applicable, as no machine learning algorithm requiring a training set is described.

9. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device

The SimpleSENSE System is intended for use at home, or at a healthcare facility, under the direction of a licensed medical professional, to record, display and store the following physiological data: a) 2 leads of Electrocardiogram; b) Respiration rate measured through thoracic impedance; c) Heart Sounds; and d) Activity including posture. The device is intended for use when the clinician decides to evaluate the physiologic signals as an aid to diagnosis and treatment. The SimpleSENSE System is intended to be used by patients at rest and not performing any activities or movements. ECG recordings are indicated for the manual assessment of cardiac rhythm disturbances. The device does not produce alarms and is not intended for active patient monitoring (real-time). The device is not intended for use as life supporting equipment on high-risk patients such as critical care patients. The device is not intended for use in the presence of a pacemaker.

The Nanowear SimpleSENSE device is the next generation diagnostic monitoring technology that captures electrocardiographic (ECG) signals, respiration rate though thoracic impedance, heart sounds, activity including posture with sensors embedded on a wearable textile garment. The signals are stored and wirelessly transmitted to a smartphone, and forwarded to a medical professional for review. The garment is designed to be unobtrusive to everyday activity and provide an easy and efficient means of capturing ECG, respiration rate, heart sounds and activity data from patients. The garment is designed to be unobtrusive to everyday activity and provide an easy and efficient means of capturing ECG data from patients. The device consists of three (3) components:

• The SimpleSENSE Garment: an integrated network of nanosensor electrodes for measuring ECG and respiratory rate from thoracic impedance, and incorporating a MEMS microphone for measuring heart sounds.
• The SimpleSENSE Signal Acquisition Unit (SAU): data acquisition, storage, and transmission to an iPhone 7 using iOS 13.4. Incorporates an accelerometer to measure activity.
• The SimpleSENSE Mobile Application: mobile application for to start/stop a recording and to forward the test report to the medical professional.

Here's a breakdown of the acceptance criteria and study information for the Nanowear SimpleSENSE device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA 510(k) summary provided does not explicitly list acceptance criteria in a quantitative table format with corresponding reported performance values for clinical metrics. Instead, it describes various performance evaluations against design specifications and equivalence to predicate devices.

However, based on the Performance testing section, we can infer some key areas of evaluation:

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

The summary states that "Equivalency testing against predicate/reference devices" was performed as part of the performance testing. However, it does not provide any details regarding the sample size used for clinical testing or the data provenance (e.g., country of origin, retrospective or prospective) for this equivalency testing.

3. Number of Experts and Qualifications for Ground Truth

The document does not specify the number of experts or their qualifications used to establish ground truth for any clinical test sets. The indications for use mention evaluation by a "licensed medical professional" and "physician who is skilled in rhythm interpretation" for the ECG data, but this pertains to the intended clinical use of the device, not necessarily how the ground truth for regulatory testing was established.

4. Adjudication Method

The document does not mention any adjudication method (e.g., 2+1, 3+1) for establishing ground truth in clinical test sets.

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

The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance. The SimpleSENSE system is a data acquisition and display device intended for manual assessment, not an AI-driven interpretive device.

6. Standalone (Algorithm Only) Performance

The SimpleSENSE system itself is described as a device that records, displays, and stores physiological data for manual assessment by a clinician. It does not appear to have an inherent AI algorithm that provides interpretations or diagnoses. Therefore, a standalone (algorithm only) performance study as typically understood for AI devices would not be applicable or described for this device. The phrase "manual assessment of cardiac rhythm disturbances" reinforces this.

7. Type of Ground Truth Used

The document does not explicitly state the type of ground truth used for any clinical testing (e.g., expert consensus, pathology, outcomes data). Given the nature of the device as a data recorder for manual assessment, it is implied that the "ground truth" for equivalency would come from comparisons to the outputs of the predicate devices or conventionally accepted methods for measuring parameters like ECG, respiration rate, and heart sounds.

8. Sample Size for the Training Set

The document does not mention a training set or its sample size. As the device is for data acquisition and display rather than AI interpretation, a separate training set for an algorithm is not discussed.

9. How Ground Truth for the Training Set Was Established

Since no training set for an AI algorithm is mentioned, the method for establishing ground truth for such a set is also not applicable or described in this summary.

Ask a specific question about this device