Heart Sound Classification via Convolutional Neural Network
Heart auscultation is the primary tool for screening and diagnosis in primary health care. Availability of digital stethoscopes and mobile devices provides clinicians an opportunity to record and analyze heart sounds (PCG) for diagnostic purposes. We proposed to combine feature-based and convolutional neural network-based classifiers for the classification of abnormal/normal heart sounds. Our classifier ensemble approach obtained the highest score of the 2016 Physionet/CinC data challenge competition.
Saman Parvaneh received his Bachelors in electrical engineering in 2003 followed by MSc and PhD degrees in biomedical engineering in 2005 and 2011, respectively. He is currently a Senior Research Scientist at Philips Research – North America in Cambridge, Massachusetts. His research interests include the development of personal health solutions and development of clinical decision support systems and predictive modeling. He is author on more than 30 scientific papers published in peer-reviewed journals and has presented at international conferences. His recent work on classification of heart sounds was awarded first place at the data challenge competition organized by Physionet/CinC in 2016.