Browsing Artikler, rapporter og annet (informatikk) by Author "Melbye, Hasse"

Now showing items 1-2 of 2

    • Algorithm for predicting valvular heart disease from heart sounds in an unselected cohort 

      Waaler, Per Niklas Benzler; Melbye, Hasse; Schirmer, Henrik; Johnsen, Markus Kreutzer; Dønnem, Tom; Ravn, Johan Fredrik; Andersen, Stian; Davidsen, Anne Herefoss; Aviles Solis, Juan Carlos; Stylidis, Michael; Bongo, Lars Ailo Aslaksen (Journal article; Tidsskriftartikkel; Peer reviewed, 2024-01-24)
      Objective: This study aims to assess the ability of state-of-the-art machine learning algorithms to detect valvular heart disease (VHD) from digital heart sound recordings in a general population that includes asymptomatic cases and intermediate stages of disease progression.<p> <p>Methods: We trained a recurrent neural network to predict murmurs from heart sound audio using annotated recordings ...

    • Convolutional Neural Network for Breathing Phase Detection in Lung Sounds 

      Jacome, Cristina; Ravn, Johan; Holsbø, Einar; Aviles-Solis, Juan Carlos; Melbye, Hasse; Ailo Bongo, Lars (Journal article; Tidsskriftartikkel; Peer reviewed, 2019-04-15)
      We applied deep learning to create an algorithm for breathing phase detection in lung sound recordings, and we compared the breathing phases detected by the algorithm and manually annotated by two experienced lung sound researchers. Our algorithm uses a convolutional neural network with spectrograms as the features, removing the need to specify features explicitly. We trained and evaluated the ...