'Cardiac acoustics and a smart stethoscope' by Edmund Kay (Cambridge)

Duration: 30 mins 23 secs

Share this media item:

Embed this media item:

<iframe width="_width_" height="_height_" src="https://sms.cam.ac.uk/media/2590438/embed" frameborder="0" scrolling="no" allowfullscreen></iframe>

Choose size:

About this item

Available Formats

About this item

'Cardiac acoustics and a smart stethoscope' by Edmund Kay (Cambridge)'s image

Description:	Talk given by Edmund Kay (CUED) at Department of Engineering, University of Cambridge, 20 October 2017, as part of the CUED Fluids seminar series. The talk describes techniques to analyse heart sound spectra to detect murmurs and infer valvular heart disease.


Created:	2017-10-24 11:25
Collection:	Cambridge Engineering Dept Fluids Seminars
Publisher:	University of Cambridge
Copyright:	Edmund Kay
Language:	eng (English)
Keywords:	sound spectra; heart murmur; heart disease; machine learning algorithm; stethoscope; cardiac acoustics;


Abstract:	Cardiovascular disease is the leading cause of mortality worldwide, causing 31% of all deaths. We investigate valvular heart diseases which create characteristic sounds, called murmurs. Using an in-vitro model of aortic stenosis (the most common valvular heart disease) we analyse the sound spectra of the murmur it produces. Using our understanding of this and other common murmurs, we have produced a machine learning algorithm which can detect these murmurs with an accuracy of up to 95%. This algorithm will be used to build an intelligent stethoscope, capable of automatically analysing heart sounds, to improve diagnosis worldwide.

Abstract:

Cardiovascular disease is the leading cause of mortality worldwide, causing 31% of all deaths. We investigate valvular heart diseases which create characteristic sounds, called murmurs. Using an in-vitro model of aortic stenosis (the most common valvular heart disease) we analyse the sound spectra of the murmur it produces. Using our understanding of this and other common murmurs, we have produced a machine learning algorithm which can detect these murmurs with an accuracy of up to 95%. This algorithm will be used to build an intelligent stethoscope, capable of automatically analysing heart sounds, to improve diagnosis worldwide.

Available Formats

Format	Quality	Bitrate	Size
MPEG-4 Video	1280x720	1.92 Mbits/sec	438.40 MB	View	Download
MPEG-4 Video	640x360	817.26 kbits/sec	181.87 MB	View	Download
WebM	1280x720	1.32 Mbits/sec	302.17 MB	View	Download
WebM	640x360	360.83 kbits/sec	80.34 MB	View	Download
iPod Video	480x360	503.66 kbits/sec	112.08 MB	View	Download
MP3	44100 Hz	249.74 kbits/sec	55.88 MB	Listen	Download
Auto *	(Allows browser to choose a format it supports)