Deep Learning for Automated Aortic Stenosis and Valvular Heart Disease Detection Using a Digital Stethoscope

Information

  • Research Project
  • 9621223
  • ApplicationId
    9621223
  • Core Project Number
    R43HL144297
  • Full Project Number
    1R43HL144297-01
  • Serial Number
    144297
  • FOA Number
    PA-17-302
  • Sub Project Id
  • Project Start Date
    7/1/2018 - 6 years ago
  • Project End Date
    12/31/2018 - 6 years ago
  • Program Officer Name
    EVANS, FRANK
  • Budget Start Date
    7/1/2018 - 6 years ago
  • Budget End Date
    12/31/2018 - 6 years ago
  • Fiscal Year
    2018
  • Support Year
    01
  • Suffix
  • Award Notice Date
    6/24/2018 - 6 years ago
Organizations

Deep Learning for Automated Aortic Stenosis and Valvular Heart Disease Detection Using a Digital Stethoscope

Project? ?Summary/Abstract This? ?SBIR? ?Phase? ?I? ?project? ?will? ?develop? ?a? ?deep? ?learning-based? ?clinical? ?decision? ?support? ?algorithm for? ?identifying? ?aortic? ?stenosis? ?from? ?heart? ?sounds? ?recorded? ?using? ?the? ?Eko? ?Core? ?Digital Stethoscope.? ?This? ?screening? ?tool? ?will? ?help? ?to? ?decrease? ?the? ?number? ?of? ?patients? ?with? ?severe asymptomatic? ?aortic? ?stenosis? ?that? ?remain? ?undertreated? ?simply? ?because? ?the? ?condition? ?is? ?not diagnosed.? ?Auscultation? ?is? ?commonly? ?the? ?method? ?by? ?which? ?valvular? ?heart? ?disease? ?is? ?first detected,? ?but? ?cases? ?often? ?fail? ?to? ?be? ?referred? ?to? ?echocardiography? ?for? ?diagnosis? ?because clinicians? ?fail? ?to? ?detect? ?heart? ?murmurs,? ?particularly? ?in? ?noisy? ?or? ?rushed? ?environments.? ?To? ?address this? ?challenge,? ?Eko? ?had? ?developed? ?the? ?Core,? ?a? ?digital? ?stethoscope? ?attachment? ?that? ?can? ?be? ?added in-line? ?to? ?a? ?clinician?s? ?existing? ?stethoscope? ?that? ?amplifies? ?heart? ?sounds? ?and? ?streams? ?digitized phonocardiograms? ?to? ?a? ?smartphone,? ?tablet? ?or? ?personal? ?computer.? ?There,? ?the? ?signal? ?can? ?be analyzed? ?with? ?the? ?decision? ?support? ?algorithm? ?we? ?will? ?develop? ?as? ?part? ?of? ?this? ?project.? ?The? ?specific aims? ?of? ?this? ?study? ?are? ?(1)? ?to? ??collect? ?a? ?database? ?with? ?condition-specific? ?recording? ?labels? ?to enable? ?deep? ?learning? ?for? ?heart? ?sounds? ?though? ?clinical? ?data? ?collection? ?at? ?UCSF? ?and? ?(2)? ?to develop? ?and? ?evaluate? ?a? ?deep? ?convolutional? ?neural? ?network-based? ?algorithm? ?trained? ?on? ?the database.? ?By? ?integrating? ?this? ?deep? ?learning? ?algorithm? ?into? ?Eko?s? ?mobile? ?and? ?cloud? ?software platform,? ?currently? ?used? ?by? ?clinicians? ?at? ?over? ?700? ?institutions? ?worldwide,? ?we? ?anticipate? ?this algorithm? ?will? ?enable? ?more? ?accurate? ?screening? ?for? ?aortic? ?stenosis,? ?leading? ?to? ?earlier? ?diagnosis and? ?better? ?patient? ?outcomes.

IC Name
NATIONAL HEART, LUNG, AND BLOOD INSTITUTE
  • Activity
    R43
  • Administering IC
    HL
  • Application Type
    1
  • Direct Cost Amount
  • Indirect Cost Amount
  • Total Cost
    295881
  • Sub Project Total Cost
  • ARRA Funded
    False
  • CFDA Code
    837
  • Ed Inst. Type
  • Funding ICs
    NHLBI:295881\
  • Funding Mechanism
    SBIR-STTR RPGs
  • Study Section
    ZRG1
  • Study Section Name
    Special Emphasis Panel
  • Organization Name
    EKO DEVICES, INC.
  • Organization Department
  • Organization DUNS
    079670921
  • Organization City
    BERKELEY
  • Organization State
    CA
  • Organization Country
    UNITED STATES
  • Organization Zip Code
    947102597
  • Organization District
    UNITED STATES