ANAHEIM, Calif.--(BUSINESS WIRE)--CSD Labs has announced that data from two clinical studies of its eMurmur auscultation technology were presented this week at the American Heart Association Scientific Sessions 2017 in Anaheim, Calif. A medical software technology designed to serve as an aid in identifying heart murmurs, eMurmur ID showed strong performance in detection of murmurs among studied patient populations and cardiac recordings.
In a Nov. 13 session titled “Validation of a Heart Murmur Algorithm by Virtual Clinical Trial,” Dr. W. Reid Thompson, associate professor of pediatrics at Johns Hopkins University, presented a study that used a test algorithm to analyze 3,180 heart sound recordings from the Johns Hopkins Cardiac Auscultatory Recording Database (CARD). Built by CSD Labs during the development of its clinical product, eMurmur ID, the algorithm was developed without prior exposure to any CARD recordings and was blinded to the clinical data associated with each file. Study results showed that the algorithm was able to analyze 2,823 (89%) of the files with a sensitivity of 93% and a specificity of 81%, as well as an accuracy of 88%.
“I’ve been looking at ways to improve screening for heart disease via auscultation for many years, and I am encouraged by how well this test algorithm performed against our gold standard CARD database,” said Dr. Thompson. “I’m hopeful that algorithms may improve our ability to detect heart murmurs in the future.”
Also on Nov. 13, Dr. Lillian Lai of Children’s Hospital Eastern Ottawa presented a study titled “Performance Evaluation of Two Heart Murmur Detection Applications by Prospective Clinical Trial.” In the session, she shared with attendees the preliminary results of a study evaluating performance of eMurmur ID and another auscultation software (SensiCardiac) with the gold standard echocardiography in a study of 93 pediatric patients. Preliminary results from this partial dataset demonstrated that eMurmur ID’s sensitivity and specificity for automated detection of pathologic murmurs were 84.4% and 85.9%, respectively, versus sensitivity and specificity of 68.9% and 57.7%, respectively, for the first generation SensiCardiac device.
“These study data clearly indicate a promising future for the use of auscultation software,” said Dr. Lai, assistant professor and pediatric cardiologist, Division of Cardiology, University of Ottawa and principal investigator of the study. “We are encouraged by how the technology has continued to advance not only in its accuracy, but also in its ease of use.”
Studies have shown that up to 60 percent of heart murmurs are missed, in part due to clinicians’ training, skills and experience.1 Designed to assist physicians during auscultation, eMurmur ID is a mobile application powered by a proprietary artificial intelligence algorithm. The application is designed to record, analyze, store and share heart sounds captured during routine patient exams. The eMurmur ID clinical product is investigational and has not been cleared or approved for sale in the U.S.
“We are pleased to be sharing these preliminary studies with the attendees of AHA Scientific Sessions 2017 and hope to be able to offer eMurmur ID to physicians across the U.S. in the near future,” said Andreas Schriefl, CEO of CSD Labs.
CSD Labs is currently awaiting CE marking for eMurmur ID in Europe, and plans to file a 510(k) submission to the U.S. Food and Drug Administration expected in the coming months. In addition to eMurmur ID, CSD Labs has developed auscultation education products called eMurmur University, a heart sounds learning platform for teaching institutions, and eMurmur Primer, an iPhone- and Android-based training and testing app for purchase by medical students and other interested parties doing auscultation. eMurmur Primer will launch commercially in the U.S. in December 2017, with eMurmur University following in the first quarter of 2018.
About CSD Labs
Founded in 2014, CSD Labs develops high-end medical technology applications by combining machine intelligence with state-of-the-art computational engineering and in-house pioneering research and development. For more information, visit www.emurmur.com.
