eMurmur Artificial Intelligence

As part of any routine physical exam, a healthcare provider will listen to a patients’ heart with a stethoscope. This procedure – cardiac auscultation – is a 200+ year old method to screen for heart defects, and requires the examining provider to have acute hearing and extensive experience.

Traditional cardiac auscultation relies 100% on the subjective interpretation of heart sounds by the examiner.

An accurate diagnosis remains challenging for reasons including faint heart sounds, noise, breathing, high heart rates, and having to distinguish innocent from pathological murmurs.

eMurmur AI puts expert level heart murmur detection capabilities into the hands of primary care providers.

eMurmur AI can be utilized by anyone trained in auscultation, does not require specialty training for use, and eliminates the need of excellent hearing and interpretation of heart sounds by the provider. Within seconds, the algorithms detect the presence of a murmur in a heart sound recording, and determine if it is innocent or pathological with expert-level accuracy. It also provides an accurate heart rate and S1/S2 heart sound markers.

Utilizing eMurmur AI

Record via eMurmur Connect App & eScope


Heart sounds are recorded via the eMurmur Connect app which receives the sounds from an electronic stethoscope. During recording a real-time signal quality check ensures that good recording quality is achieved.

Heart Sound Analysis via eMurmur AI


The recorded data is transmitted to the eMurmur cloud for AI analysis. Results (murmur type, heart rate, S1/S2 markers) are returned to the eMurmur Connect app within seconds. All data is encrypted at rest and in transit.

Auscultation Records Available Online


An electronic record for each patient session is created in the eMurmur Connect Web Portal. Users can review heart and lung recordings, eMurmur AI findings, provider notes, patient history and more at any time from anywhere.

Evidence-Based Algorithms

eMurmur is proud to be the leader in AI-powered auscultation technology. The team made up of PhDs and scientists is continuously pushing the boundaries of what is possible in digital cardiac auscultation.

eMurmur is focused on producing the clinical performance evidence for its AI algorithms that patients and providers expect and deserve.

Clinical studies completed: 5
Clinical studies ongoing: 3
Data from patients analyzed: 1,000+
Heart sound recordings analyzed: 3,000+
Heart murmurs classified: 1,500+
Heart beats analyzed: 50,000+
Heart rate ranges detected: 50-180 bpm
Patient populations: newborns, children, youth, adults, elderly
Clinically observed sensitivity: 85.0%
Clinically observed specificity: 86.7%

 

Papers & abstracts

Mar 2020 | Clinical data on using eMurmur ID and telemedicine to improve referrals in children with heart murmurs to be presented at the PAS 2020 Meeting

Data from a telemedicine innovation study lead by Dr. Reid Thompson, Johns Hopkins Medicine, will be presented at the Pediatric Academic Societies Meeting in Philadelphia (April 29-May 6, 2020). The study involved 137 subjects and yielded a net feasibility of 93%, concluding that a new paradigm of screening heart murmurs with an AI-enabled electronic stethoscope and remote listening by a cardiologist was feasible and accurate.
Conference link

Nov 2019 | Clinical data from Johns Hopkins telemedicine study presented at 2019 Architecture of High Value Health Care Conference

Objectives: This study explores whether incorporating an artificial intelligence (AI) algorithm (eMurmur ID) and telemedicine to assist referral decision-making can decrease the number of inappropriate echocardiograms and improved clinical outcomes for patients with heart murmurs when compared to current referral behavior and outcomes.

Conclusions: Accuracy of AI-algorithm is similar to a trained cardiologist (132 patients, 84% accuracy). A new paradigm to screen for pathologic heart murmurs in primary care settings is feasible and could reduce the number of patients with only innocent heart murmurs being referred inappropriately to cardiology or echocardiography by up to 50-75%. It could help confirm the clinician’s suspicion of important pathologic heart murmurs while providing evidence to reassure parents of children with innocent murmurs that their children’s hearts are normal.
Read the abstract

Dec 2018 | Johns Hopkins study demonstrates 88% accuracy of eMurmur, as published in Pediatric Cardiology

Results from a study called "Artificial Intelligence-Assisted Auscultation of Heart Murmurs: Validation by Virtual Clinical Trial" have been published in the peer-reviewed journal of Pediatric Cardiology. This is the first reported comprehensive and objective evaluation of an AI-based murmur detection algorithm, and included 3180 heart sound recordings from 603 outpatient visits. Algorithm estimation of heart rate was similar to gold standard. Sensitivity and specificity for detection of pathologic cases were 93% (CI 90–95%) and 81% (CI 75–85%), respectively, with accuracy 88% (CI 85–91%). In conclusion, the eMurmur algorithm tested has high sensitivity and specificity for detection of pathologic murmurs, similar to levels reported for specialist auscultation, making it a potentially useful screening tool for heart disease.
Read the publication

Nov 2017 | Data from comparative clinical study presented at AHA Scientific Sessions 2017

Dr. Lillian Lai of Children’s Hospital Eastern Ottawa presented a study today titled “Performance Evaluation of Two Heart Murmur Detection Applications by Prospective Clinical Trial” at the AHA Scientific Session 2017 today.
The study included 93 patients and demonstrated a sensitivity and specificity for automated detection of pathologic murmurs of 84.4% and 85.9%, respectively, with the gold standard being echocardiography, with eMurmur significantly outperform the other device.
Read the abstract
Read more on Business Wire

Nov 2017 | Results from Johns Hopkins study presented at AHA Scientific Sessions 2017

In the AHA Scientific Session “Best Abstracts in Health Tech ”, Dr. W. Reid Thompson, associate professor of pediatrics at Johns Hopkins University, today presented a study titled “Validation of a Heart Murmur Algorithm by Virtual Clinical Trial” which used the eMurmur algorithm to blindly analyze 3,180 heart sound recordings from the Johns Hopkins Cardiac Auscultatory Recording Database (CARD). Study results showed a sensitivity of 93% and a specificity of 81%, as well as an accuracy of 88%.
Read the Abstract
Read more on Business Wire

July 2017 | eMurmur’s heart murmur detection algorithm scores 89% sensitivity in an elderly population clinical trial

eMurmur announces completion of a clinical trial evaluating the performance of its heart murmur detection algorithms on an elderly population with congenital heart disease. The algorithm’s sensitivity for autonomous detection of pathologic murmurs was 89%. No high severity cases were missed by the algorithm. Further, it yielded accurate heart rate estimation and S1/S2 detection, despite the presence of significant environmental noise.
Read the abstract

Nov 2016 | eMurmur’s heart murmur detection algorithm scores 94% accuracy in clinical pilot study

eMurmur announces impressive pilot study of its AI platform on 106 children at Children’s Hospital of Eastern Ontario, Canada, where it differentiated pathologic from innocent heart murmurs with high sensitivity (87%) and specificity (100%), a positive predictive value of 100%, a negative predictive value of 90%, and high accuracy (94%) when compared with echocardiography as the gold standard for diagnosing murmurs.
Read more on Business Wire
Read the publication