The eMurmur ID software system is a decision support device for the healthcare provider (the user) in the evaluation of patient heart sounds. eMurmur ID is used to record, display, analyze, and store the acoustic signal of the heart, recorded by means of an electronic stethoscope. The automated analysis will identify specific heart sounds that may be present, including S1, S2, physiological heart murmurs, pathological heart murmurs and absence of a heart murmur.

eMurmur ID 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 ID are only significant when considered in conjunction with healthcare provider over-read and including all other relevant patient data.

Device Description

eMurmur ID is a software system comprised of the following components:

The eMurmur ID Backend, running on a server environment, hosts the eMurmur ID Heart Sound Analysis Algorithm, an encrypted database for archiving patient and user information, and an application programming interface (API) for communication with the web portal and mobile application.
The eMurmur ID Mobile App, which runs on a mobile device. The app permits the following activities:
a. Electronic recording of heart sound signals via a compatible electronic stethoscope, the Littmann 3200
b. Visual and acoustic playback of heart and lung sounds
c. Capturing patient information
d. Transferring data to and from the eMurmur ID backend through a secure connection
e. Displaying heart sound analysis results
The eMurmur ID Web Portal, which provides the following functionalities:
a. Capturing and editing patient information
b. Displaying and editing patient encounters including heart sound analysis results
c. Visual and acoustic playback of heart and lung sounds
d. Downloading reports (PDF) and heart and lung sound recordings
e. Transferring data to and from the eMurmur ID backend through a secure connection

The acquisition of the acoustic data is carried out by the FDA-cleared off-the-shelf electronic stethoscope Littmann 3200 by 3M (MN, USA) (K083903).

For heart sounds to be analyzed by the heart sound analysis algorithm, a 20 second digital recording of the patient's heart sounds and the patient's date of birth are required. Heart sounds are recorded using the compatible, FDA-cleared, off-the-shelf electronic stethoscope Littmann 3200. The heart sounds are transmitted via Bluetooth to a mobile device running the eMurmur ID mobile app. The app then stores and sends the recorded data to the eMurmur ID backend for analysis. The results of the heart sound analysis are returned to the app within a few seconds, where they are displayed to the user together with the heart sound recording. The user can utilize the heart sound analysis results and the acoustic and visual representation of the heart sound recordings as decision support data in their decision-making process regarding the presence and type of a heart murmur.

AI/ML Overview

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

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for eMurmur ID were defined relative to a predicate device (SensiCardiac, the predecessor to SensiCardiac Mobi). The primary hypothesis was that eMurmur ID would perform "not worse than" the predicate device in distinguishing between AHA Class I (pathologic murmurs) and AHA Class III heart sounds (innocent murmurs and/or no murmurs) with respect to sensitivity and specificity.

Metric	Acceptance Criteria (Not worse than SensiCardiac)	Reported eMurmur ID Performance (95% CI)	Reported SensiCardiac Performance (95% CI)	p-value (eMurmur ID vs. SensiCardiac)
Sensitivity	≥ 58.3%*	85.0% (72.9%-92.5%)	58.3% (44.9%-70.7%)	0.0014 (Significantly better)
Specificity	≥ 58.3%*	86.7% (74.9%-93.7%)	58.3% (44.9%-70.7%)	0.0009 (Significantly better)
Accuracy	≥ 58.3%*	85.8% (78.0%-91.3%)	58.3% (49.0%-67.2%)	<0.0001 (Significantly better)

*Note: The "not worse than" criteria are inferred from the predicate's performance in the same study, as the text states the hypothesis was "not worse than that of the predicate device." The study explicitly showed eMurmur ID was significantly better than the predicate.

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

Sample Size: 120 subjects.
- 50% (60 subjects) had a confirmed pathological murmur (AHA Class I).
- 50% (60 subjects) had a confirmed innocent or no murmur (AHA Class III).
Data Provenance: The study was a prospective clinical investigation. The country of origin of the data is not explicitly stated, but the sponsor company is CSD Labs GmbH in Graz, Austria, which might suggest a European origin for the clinical study, though this is not confirmed.

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

The ground truth was established by an expert physician's auscultation-based diagnosis.
This diagnosis was independently verified by cardiac echocardiography.
The number of expert physicians is not specified (e.g., whether it was one physician or multiple in consensus for the initial diagnosis). The qualification is generally described as an "expert physician."

4. Adjudication Method for the Test Set

The provided text describes the ground truth as the "expert physician's auscultation-based diagnosis, independently verified by cardiac echocardiography." This suggests a two-step process where the physician's assessment is cross-referenced with objective imaging data. It doesn't explicitly mention a consensus or multi-reader adjudication process for the physician's diagnosis itself beyond the single "expert physician" mentioned.

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

No, an MRMC comparative effectiveness study involving human readers with vs. without AI assistance was not explicitly described in this context.
The study described was a standalone performance comparison between the eMurmur ID algorithm and the predicate device's algorithm, both compared against a clinical gold standard. The device is a "decision support device for the user," but the study evaluated the algorithm's performance, not human-in-the-loop improvement.

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

Yes, a standalone performance study was done. The study's results (sensitivity, specificity, accuracy for eMurmur ID vs. SensiCardiac) directly reflect the performance of the algorithms in distinguishing heart murmurs against a clinical gold standard. The output of eMurmur ID's algorithm was directly compared to the predicate's algorithm output.

7. The Type of Ground Truth Used

The ground truth used was a combination of expert clinical assessment and objective imaging data: "expert physician's auscultation-based diagnosis, independently verified by cardiac echocardiography."

8. The Sample Size for the Training Set

The sample size for the training set is not provided in the document. The text focuses solely on the pivotal clinical study used for validation.

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

The method for establishing the ground truth for the training set is not provided in the document.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image contains the logos of the U.S. Department of Health & Human Services and the U.S. Food & Drug Administration (FDA). The Department of Health & Human Services logo is on the left, and the FDA logo is on the right. The FDA logo includes the letters "FDA" in a blue box, followed by the words "U.S. Food & Drug Administration" in blue text. The word "Administration" is in a smaller font size than the other words.

April 17, 2019

CSD Labs GmbH % Yarmela Pavlovic Partner Hogan Lovells US LLP 3 Embarcadero Center San Francisco, California 94501

Re: K181988

Trade/Device Name: eMurmur ID Regulation Number: 21 CFR 870.1875 Regulation Name: Stethoscope Regulatory Class: Class II Product Code: DOD, DOC Dated: March 19, 2019 Received: March 19, 2019

Dear Yarmela Pavlovic:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part

{1}------------------------------------------------

801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/CombinationProducts/GuidanceRegulatoryInformation/ucm597488.htm); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4. Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely.

Stephen C. Browning -S5

for

Bram D. Zuckerman, M.D. Director Division of Cardiovascular Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K181988

Device Name eMurmur ID

Indications for Use (Describe)

The eMurmur ID software system is a decision support device for the user) in the evaluation of patient heart sounds. eMurmur ID is used to record, display, and store the acoustic signal of the heart, recorded by means of an electronic stethoscope. The automated analysis will identify specific heart sounds that may be present, including S1, S2, physiological heart murmurs, pathological heart murmurs and absence of a heart murmur.

Type of Use (Select one or both, as applicable)

X Prescription Use (Part 21 CFR 801 Subpart D)

Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Druq Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

510(k) SUMMARY

CSD Labs' eMurmur ID (K181988)

SPONSOR

Company name: CSD Labs GmbH Company address: Nikolaiplatz 4 8020 Graz Austria Contact Person: Andreas Reinisch Date Prepared: March 19, 2019

DEVICE

Trade Name: eMurmur ID Computer Aided Auscultation, Heart Sounds Analyzer Common or usual name: Classification name: Electronic Stethoscope; Phonocardiograph; Requlation number: 21 CFR 870.1875, 870.2390 Product code: DQD, DQC Device class: Class II Reviewing panel: Cardiology PREDICATE DEVICE

Company	Product	510(k)
Diacoustic Medical Devices	SensiCardiac Mobi	K131044 (Primary Predicate)
Discoustic Medical Devices	SensiCardiac	K121617 (Reference Device)

INDICATIONS FOR USE

DEVICE DESCRIPTION

eMurmur ID is a software system comprised of the following components:

1. The eMurmur ID Backend, running on a server environment, hosts the eMurmur ID Heart Sound Analysis Algorithm, an encrypted database for archiving patient and user information, and an application programming interface (API) for communication with the web portal and mobile application.

{4}------------------------------------------------

1. The eMurmur ID Mobile App, which runs on a mobile device. The app permits the following activities:
- a. Electronic recording of heart sound signals via a compatible electronic stethoscope, the Littmann 3200
- b. Visual and acoustic playback of heart and lung sounds
- Capturing patient information C.
- d. Transferring data to and from the eMurmur ID backend through a secure connection
- Displaying heart sound analysis results e.
1. The eMurmur ID Web Portal, which provides the following functionalities:
- a. Capturing and editing patient information
- Displaying and editing patient encounters including heart sound analysis results b.
- C. Visual and acoustic playback of heart and lung sounds
- d. Downloading reports (PDF) and heart and lung sound recordings
- Transferring data to and from the eMurmur ID backend through a secure connection e.

The acquisition of the acoustic data is carried out by the FDA-cleared off-the-shelf electronic stethoscope Littmann 3200 by 3M (MN, USA) (K083903).

TECHNOLOGICAL CHARACTERISTICS

eMurmur ID has technological characteristics that are comparable to the predicate and reference devices:

1. Each of the systems host a heart sound analysis algorithm, a web API and a database on a backend server.
1. Each of the systems provide the user with a mobile app, which is used to record heart sounds and patient information. The mobile app transfers the data to the backend through a secure connection and displays the analysis results to the user.
1. Each of the systems require an FDA-cleared off-the-shelf electronic stethoscope for the acquisition of the heart sounds.
1. Each of the devices provide similar heart sound analysis output and similar additional supporting information to the user.

{5}------------------------------------------------

	eMurmur ID (K181988)	SensiCardiac Mobi (K131044)(Primary Predicate)	SensiCardiac (K121617)(Reference Device)
Intended Use /Indications forUse	The eMurmur ID software system is adecision support device for thehealthcare provider (the user) in theevaluation of patient heart sounds.eMurmur ID is used to record, display,analyze, and store the acoustic signalof the heart, recorded by means of anelectronic stethoscope. The automatedanalysis will identify specific heartsounds that may be present, includingS1, S2, physiological heart murmurs,pathological heart murmurs andabsence of a heart murmur.eMurmur ID is indicated for use in asetting where auscultation wouldtypically be performed by a healthcareprovider. It is not intended as a solemeans of diagnosis. The heart soundinterpretations offered by eMurmur IDare only significant when considered inconjunction with healthcare providerover-read and including all otherrelevant patient data.	The SensiCardiac Mobi Diagnostic is anelectronic auscultatory device, intendedto provide support to the physician in theevaluation of patients' heart sounds.The product acquires and records theacoustic signals of the heart andanalyzes these signals. The analysisprocedure will identify specific heartsounds that may be present. Identifiedsounds include S1, S2, and suspectedmurmurs. The device is indicated for usein a clinical setting, by a physician or bytrained personnel who are acting on theorder of a licensed physician. It is notintended as a sole means of diagnosis.The interpretation of heart sounds offeredby the SensiCardiac Mobi are onlysignificant when used in conjunction withphysician over-read as well asconsideration of all other relevant patientdata.	Sensi is a decision support softwarepackage intended to assist medicalexaminers in heart auscultation.The Sensi Diagnostic Heart MurmurSoftware distinguishes betweennormal/physiological andpathological heart murmurs byanalyzing the acoustic heart signalscaptured with an electronicstethoscope. The device will recordthe acoustic sound of the heart at thefour main auscultation positions. Theacoustic heart signal is analyzed toidentify heart sounds that may bepresent, identified sounds includeS1, S2 and suspected murmurs.
User Population	Healthcare provider licensed orauthorized to perform auscultation	Healthcare provider licensed orauthorized to perform auscultation	Healthcare provider licensed orauthorized to perform auscultation
Acquires andRecords HeartSounds	Yes – acoustic signal of heart bymeans of electronic stethoscope andmobile app	Yes – acoustic signal of heart by meansof electronic stethoscope and mobile app	Yes – acoustic signal of heart bymeans of electronic stethoscope andWindows desktop app
Analyzes HeartSounds	Yes – distinguishes betweennormal/physiological and pathologicalheart murmurs	Yes - distinguishes betweennormal/physiological and pathologicalheart murmurs	Yes - distinguishes betweennormal/physiological andpathological heart murmurs

{6}------------------------------------------------

Y
1819
88

	eMurmur ID (K181988)	SensiCardiac Mobi (K131044)(Primary Predicate)	SensiCardiac (K121617)(Reference Device)
User Interface	Android app for recording heartsounds, sending analysis requests andreceiving analysis results. Web portalfor reviewing and editing user andpatient data, OS independent.	Recording and analysis are conducted onan iOS mobile app, which is also used forreviewing auscultations.	Recording and analysis areconducted on a Windows desktopapp, which is also used for reviewingauscultations.
Backend	Server analyzes (algorithm) and stores(database) patient-related data andcommunicates with the othercomponents of eMurmur ID. Theinterface to the other components is aREST/JSON web API.	Equivalent architecture. The API uses theXML data format instead of JSON. Isequipped with algorithm identical toK121617.	Equivalent architecture. Instead of amobile app, a desktop app is used.The API uses the XML data formatinstead of JSON. The equivalence ofalgorithm performance isdemonstrated in a clinical trial.
Safety Features	Encrypted internet traffic, data stored inthe database on the backend isencrypted, data in the database isduplicated to another database in adifferent datacenter, no protectedhealth information is stored on theuser's devices, user needs toauthenticate, user can only accessauthorized data	Identical regarding aspects that areverifiable by CSD Labs.	Identical regarding aspects that areverifiable by CSD Labs.

{7}------------------------------------------------

PERFORMANCE DATA

Performance data included software verification and validation testing, electromagnetic compatibility, electrical safety, wireless coexistence, and bench validation testing using existing heart sound databases. It also included a pivotal clinical study. The pivotal clinical study was conducted comparing eMurmur ID to the reference device, SensiCardiac (K121617) — the predecessor to the primary predicate, SensiCardiac Mobi (K131044), which was not yet commercially available for comparison at the time of testing — in a prospective clinical investigation. It verified the hypothesis that eMurmur ID can distinguish between AHA class I (pathologic murmurs) and AHA class III heart sounds (innocent murmurs and/or no murmurs) with a sensitivity and specificity not worse than that of the predicate device.

The study population consisted of 120 subjects across all ages where 50% had a confirmed pathological murmur (class )) and 50% had a confirmed innocent or no murmur (class III). Patient's heart sounds were recorded by the expert physician and analyzed by both eMurmur ID and the predicate device. The findings for both devices were compared to clinical gold standard reference, defined as the expert physician's auscultation-based diagnosis, independently verified by cardiac echocardiography.

The following table shows the results of the primary (sensitivity, specificity) and secondary (accuracy) endpoints of the study with their respective 95% confidence intervals. The results were compared using the 95%-Fleiss confidence interval method for paired binary data.

	eMurmur ID	SensiCardiac
Sensitivity (95% CI)	85.0% (72.9%-92.5%)	58.3% (44.9%-70.7%)
Specificity (95% CI)	86.7% (74.9%-93.7%)	58.3% (44.9%-70.7%)
Accuracy (95% CI)	85.8% (78.0%-91.3%)	58.3% (49.0%-67.2%)

The results of the study met the criteria for successfully demonstrating that eMurmur ID performance was not worse than the predicate device. In fact, the actual study results demonstrated that the eMurmur ID performed statistically significantly better than the predicate with respect to both sensitivity (p=0.0014) and specificity (p=0.0009), as well as with respect to overall accuracy (p<0.0001).

In all instances, eMurmur ID functioned as intended, and the electromagnetic compatibility, bench testing, and clinical performance observed were as expected.

CONCLUSIONS

Performance data demonstrate that the eMurmur ID software system performs in a manner that is comparable to the reference device, meeting the criteria that it be at least non-inferior. eMurmur ID has the same intended uses and similar indications, technological characteristics, and principles of operation as the predicate device. The minor technological differences between eMurmur ID and its predicate device raise no new questions of safety or effectiveness. Thus, eMurmur ID is substantially equivalent.

Regulation Number and Section

§ 870.1875 Stethoscope.

(a)
Manual stethoscope —(1)Identification. A manual stethoscope is a mechanical device used to project the sounds associated with the heart, arteries, and veins and other internal organs.(2)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 870.9.(b)
Electronic stethoscope —(1)Identification. An electronic stethoscope is an electrically amplified device used to project the sounds associated with the heart, arteries, and veins and other internal organs.(2)
Classification. Class II (special controls). The device, when it is a lung sound monitor, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 870.9.