eMurmur ID - Clinical Performance Evaluation

The differentiation between innocent and pathologic murmurs through traditional auscultation can often be challenging, which in the end makes the diagnosis strongly dependent on the clinitians experience and clinical expertise. With the development of technology it is now possible to help diagnose heart murmurs using computer aided auscultation systems (CAA). eMurmur ID is an investigational CAA system (not FDA cleared) and the investigators hypothesize that it 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 compared to a similar FDA cleared CAA system on market.

Completed

Looking for future studies?

Notify Me

Key information

Conditions

Heart Murmurs Cardiovascular Abnormalities Cardiovascular Diseases Congenital Abnormalities Congenital Heart Defect Congenital, Hereditary, and Neonatal Diseases and Abnormalities Diastolic Murmurs Heart Defects, Congenital Heart Diseases Innocent Murmurs Pathologic Murmurs Pathological Conditions, Signs and Symptoms Signs and Symptoms Systolic Murmurs

Age range

1 day and older

Sex eligibility

All sexes

Study type

Observational

Primary location

Children's Hospital of Eastern Ontario

Ottawa, Canada

Who can participate

Healthy volunteers accepted: Yes

Only the study team can determine whether someone qualifies for participation.

Inclusion criteria

All age groups of patients will be included from 1day old
Patients who are being followed for known congenital heart disease and are returning for follow up
Patients referred for a suspected heart murmur

Exclusion criteria

Mismatch between the expert physician's diagnosis (auscultation based) and the diagnosis resulting from echocardiography (independently read by a cardiologist blinded to the auscultation results). Note: both, the expert physician and echocardiography results must independently reach the same diagnosis, which is then accepted as the gold standard reference diagnosis to which both devices are compared to. This is necessary because not every pathology visible on an echocardiogram causes an audible murmur, and not every murmur heard by a medical expert might correlate to pathology.
Patient whose behaviour does not allow for a standard auscultation by the physician (e.g. a screaming fit).

Treatment and study plan

Automated Heart Murmur Detection AI

Device

Automated AI algorithm-based analysis of digital heart sound recordings to detect and classify heart murmurs. Heart sound recordings were fully blinded before undergoing one-time automated analysis. AI algorithm results for each recording include: AHA classification (Class I (pathologic heart murmur) versus class III (innocent heart murmur or no heart murmur), murmur timing, murmur grade, heart rate and S1/S2 identification.

Other names: eMurmur ID

Primary outcomes

eMurmur ID sensitivity and specificity

Time frame: 1 day

The primary endpoints of the study are sensitivity and specificity. The clinical reference gold standard diagnosis is defined as expert physicians' diagnosis confirmed by independently interpreted echocardiogram diagnosis.

True positive (TP), true negative (TN), false positive (FP) and false negative (FN) will be determined via comparison of the heart murmur classification results with the clinical gold standard (echocardiogram) diagnosis.

Sponsors and collaborators

Lead sponsor

CSD Labs GmbH

Other

Registry information

Important dates

Study start: 2017
Primary completion: 2018
Study completion: 2018
First posted: Jul 24, 2017
Registry last updated: Jul 18, 2018

OpenTrials presents study information sourced from ClinicalTrials.gov. The official registry record should be consulted for the latest information.

View the official ClinicalTrials.gov record (opens in a new tab)

This listing is for discovery and informational purposes only. It is not medical advice, does not guarantee that a study is recruiting, and does not determine eligibility. Contact the study team and a qualified healthcare professional when considering participation.

Published trials that share one or more normalized conditions with this study.

Completed