Outcome Prediction and Murmur Detection in Sets of Phonocardiograms by a Deep Learning-Based Ensemble Approach

Gideon Stein1, Sven Festag2, Tim Büchner3, Maha Shadaydeh3, Joachim Denzler1, Cord Spreckelsen2
1Computer Vision Group, Institute for Computer Science, Friedrich Schiller University Jena, 2Institute of Medical Statistics, Computer and Data Sciences, Jena University Hospital, Germany, 3Computer Vision Group, Institute for Computer Science, Friedrich Schiller University Jena, Germany


Abstract

We, the team UKJ FSU, propose a deep learning system for the prediction of congenital heart diseases. Our method is able to predict the clinical outcomes (normal, abnormal) of patients as well as to identify heart murmur (present, absent, unclear) based on phonocardiograms recorded at different auscultation locations. The system we propose is an ensemble of four temporal convolutional networks with identical topologies, each specialized in identifying murmurs and predicting patient outcome from a phonocardiogram taken at one specific auscultation location. Their intermediate outputs are augmented by the manually ascertained patient features such as age group, sex, height and weight. The outputs of the four networks are combined to form a single final decision as demanded by the rules of the George B. Moody PhysioNet Challenge 2022. On the first task of this challenge, the murmur detection, our model reached a weighted accuracy of 0.567 with respect to the unknown validation set. On the outcome prediction task (second task) the ensemble led to a mean outcome cost of 10679. By focusing on the clinical outcome prediction and tuning some of the hyper-parameters only for this task, our model reached a validation score of 9031.