SBIR/STTR Research Award
Deep Learning for Automated Aortic Stenosis and Valvular Heart Disease Detection Using a Digital Stethoscope
Award amount
$295,881Program and phase
SBIR · Phase IAward year
2018Award details
- Awarding agency
- Department of Health and Human Services
- Branch
- National Institutes of Health
- Recipient company
- EKO Devices, Inc.
- Proposal award date
- 2018-07-01
- Contract end date
- 2019-12-31
- UEI
- GM3UL6PBJKD3
- Solicitation number
- PA17-302
- Topic code
- NHLBI
Research abstract
ProjectSummary Abstract
ThisSBIRPhaseIprojectwilldevelopadeeplearning basedclinicaldecisionsupportalgorithm
foridentifyingaorticstenosisfromheartsoundsrecordedusingtheEkoCoreDigital
StethoscopeThisscreeningtoolwillhelptodecreasethenumberofpatientswithsevere
asymptomaticaorticstenosisthatremainundertreatedsimplybecausetheconditionisnot
diagnosedAuscultationiscommonlythemethodbywhichvalvularheartdiseaseisfirst
detectedbutcasesoftenfailtobereferredtoechocardiographyfordiagnosisbecause
cliniciansfailtodetectheartmurmursparticularlyinnoisyorrushedenvironmentsToaddress
thischallengeEkohaddevelopedtheCoreadigitalstethoscopeattachmentthatcanbeadded
in linetoaclinician sexistingstethoscopethatamplifiesheartsoundsandstreamsdigitized
phonocardiogramstoasmartphonetabletorpersonalcomputerTherethesignalcanbe
analyzedwiththedecisionsupportalgorithmwewilldevelopaspartofthisprojectThespecific
aimsofthisstudyaretocollectadatabasewithcondition specificrecordinglabelsto
enabledeeplearningforheartsoundsthoughclinicaldatacollectionatUCSFandto
developandevaluateadeepconvolutionalneuralnetwork basedalgorithmtrainedonthe
databaseByintegratingthisdeeplearningalgorithmintoEko smobileandcloudsoftware
platformcurrentlyusedbycliniciansatoverinstitutionsworldwideweanticipatethis
algorithmwillenablemoreaccuratescreeningforaorticstenosisleadingtoearlierdiagnosis
andbetterpatientoutcomes SBIRProjectNarrative
Valvularheartdiseaseandaorticstenosisinparticulararebecomingincreasinglyprevalent
manifestationsofpoorcardiovascularhealthinboththedevelopedanddevelopingworldA
highly accurateclinicaldecisionsupportalgorithmthatisabletodetectaorticstenosiswill
impactpublichealthbyreducingunnecessaryreferralsforechocardiographyandpromoting
earlyandaccuratediagnosisinunderservedareaswithlimitedaccesstosubspecialtycare
Technology keywords
Not reported
Other awards by this recipient
Verified by the same UEI. These are other public SBIR/STTR award pages, not a merged company record.
- Deep learning for algorithmic detection of pulmonary hypertension using a combined digital stethoscope and single-lead electrocardiogram
- Dialysis access monitoring using a digital stethoscope-based deep learning system
- Deep Learning for Automated Aortic Stenosis and Valvular Heart Disease Detection Using a Digital Stethoscope
Awards with the same topic code
Verified by an exact topic code match. This is not a text-similarity match.
- DUCTUS ARTERIOSUS STENT TO IMPROVE CONGENITAL HEART DEFECT MORTALITY
- Head Up CPR and Aortic Occlusion to Improve Survival after Refractory Cardiac Arrest
- Free-Breathing Dynamic Cardiopulmonary Function Imaging System to use with Xenon MRI
- The Next Wave of Asthma Therapeutics
- Bearingless flux reversal motor for neonatal and pediatric extracorporeal life support applications
Research funding history
4 SBIR/STTR records share this UEI (2018–2022). Reported award amounts total $6,376,175. Reported amounts are not federal obligations.
Phases: Phase II, Phase I
Agencies: Department of Health and Human Services