Efficient screening for severe aortic valve stenosis using understandable artificial intelligence: a prospective diagnostic accuracy study.
Hisaki MakimotoTakeru ShiragaBenita KohlmannChristofori Eleni MagnisaliShqipe GerguriNobuaki MotoyamaLukas ClasenAlexandru BejinariuKathrin KleinAsuka MakimotoChristian JungRalf WestenfeldTobias ZeusMalte KelmPublished in: European heart journal. Digital health (2022)
Our CNN model combining multiple auscultation locations and exported on smartphone application could efficiently identify severe AS based on heart sounds. The visual explanation of AI decisions for heart sounds was interpretable. These technologies may support medical training and remote consultations.
Keyphrases
- artificial intelligence
- aortic valve
- machine learning
- big data
- transcatheter aortic valve replacement
- deep learning
- transcatheter aortic valve implantation
- aortic valve replacement
- aortic stenosis
- heart failure
- early onset
- healthcare
- atrial fibrillation
- convolutional neural network
- left ventricular
- coronary artery disease