eMurmur ID - Clinical Performance Evaluation

NCT03227848 | Completed FDA Device

• 1 other identifier: OTT03
• Study Type: observational
• Target: 120
• Locations: 1 country
• Sites: 1

Brief Summary

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.

Conditions

Heart Murmurs; Pathologic Murmurs; Innocent Murmurs; Congenital Heart Defect; Systolic Murmurs; Diastolic Murmurs

Outcome Measures

Primary Outcomes (1)

• eMurmur ID sensitivity and specificity

  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.

  1 day

Interventions

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.

Also known as: eMurmur ID

Eligibility Criteria

• Age: 1 Day+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Study participants will be chosen based on the heart murmur types required to meet a specified target patient population. Pre-selection of AHA class I and AHA class III patients will be done to achieve a reasonably similar distribution of murmur types compared to a US patient population. All major pathological and innocent murmur types will be included and their occurrence depending on age will be considered. Number of participants drawn: 120 participants across all ages will be included, 75% pediatric and 25% adult.

You may qualify if:

• 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

You may not qualify if:

• 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).

Sponsors & Collaborators

• CSD Labs GmbH: lead

Study Sites (1)

Children's Hospital of Eastern Ontario

Ottawa, Canada

Location

Related Publications (1)

• Lai LS, Redington AN, Reinisch AJ, Unterberger MJ, Schriefl AJ. Computerized Automatic Diagnosis of Innocent and Pathologic Murmurs in Pediatrics: A Pilot Study. Congenit Heart Dis. 2016 Sep;11(5):386-395. doi: 10.1111/chd.12328. Epub 2016 Mar 15.

  PMID: 26990211 BACKGROUND

Related Links

• Computerized Automatic Diagnosis of Innocent and Pathologic Murmurs in Pediatrics: A Pilot Study.

MeSH Terms

Conditions

Heart Murmurs; Heart Defects, Congenital; Systolic Murmurs

Condition Hierarchy (Ancestors)

Signs and Symptoms; Pathological Conditions, Signs and Symptoms; Cardiovascular Abnormalities; Cardiovascular Diseases; Heart Diseases; Congenital Abnormalities; Congenital, Hereditary, and Neonatal Diseases and Abnormalities

Study Officials

• Lillian Lai, MD

  Children's Hopsital of Eastern Ontario, Canada

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: CROSS SECTIONAL
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: July 21, 2017
• First Posted: July 24, 2017
• Study Start: January 4, 2017
• Primary Completion: April 24, 2018
• Study Completion: April 30, 2018
• Last Updated: July 18, 2018

Record last verified: 2018-07

Data Sharing

• IPD Sharing: Will not share

Locations

CA (1)