Discrimination of normal and abnormal heart sounds using probability assessment

0474793 - ÚPT 2018 RIV CA eng C - Conference Paper (international conference)
Plešinger, Filip - Jurčo, Juraj - Jurák, Pavel - Halámek, Josef
Discrimination of normal and abnormal heart sounds using probability assessment.
Computing in Cardiology (CinC) 2016. Vol. 43. Vencouver: Computing in Cardiology, 2016, s. 801-804. ISBN 978-1-5090-0896-4. ISSN 2325-8861.
[Computing in Cardiology (CinC) 2016. Vencouver (CA), 11.09.2016-14.09.2016]
R&D Projects: GA ČR GAP102/12/2034; GA MŠMT(CZ) LO1212; GA MŠMT ED0017/01/01
Institutional support: RVO:68081731
Keywords : heart * feature extraction * training * histograms
OECD category: Medical engineering

According to the “2016 Physionet/CinC Challenge”, we propose an automated method identifying normal or abnormal phonocardiogram recordings. Method: Invalid data segments are detected (saturation, blank and noise tests). The record is transformed into amplitude envelopes in five frequency bands. Systole duration and RR estimations are computed, 15-90 Hz amplitude envelope and systole/RR estimations are used for detection of the first and second heart sound (S1 and S2). Features from accumulated areas surrounding S1 and S2 as well as features from the whole recordings were extracted and used for training. During the training process, we collected probability and weight values of each feature in multiple ranges. For feature selection and optimization tasks, we developed C# application PROBAfind, able to generate the resultant Matlab code. Results: The method was trained with 3153 Physionet Challenge recordings (length 8-60 seconds, 6 databases). The results of the training set show the sensitivity, specificity and score of 0.93, 0.97 and 0.95, respectively. The method was evaluated on a hidden Challenge dataset with sensitivity and specificity of 0.77 and 0.91, respectively. These results led to an overall score of 0.84.
Permanent Link: http://hdl.handle.net/11104/0271747