{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T13:02:11Z","timestamp":1784984531542,"version":"3.55.0"},"reference-count":18,"publisher":"IOP Publishing","issue":"8","license":[{"start":{"date-parts":[[2017,7,31]],"date-time":"2017-07-31T00:00:00Z","timestamp":1501459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2017,7,31]],"date-time":"2017-07-31T00:00:00Z","timestamp":1501459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Physiol. Meas."],"published-print":{"date-parts":[[2017,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    : Automatic heart sound analysis has the potential to improve the diagnosis of valvular heart diseases in the primary care phase, as well as in countries where there is neither the expertise nor the equipment to perform echocardiograms. An algorithm has been trained, on the PhysioNet open-access heart sounds database, to classify heart sounds as normal or abnormal.\n                    <jats:italic>Approach<\/jats:italic>\n                    : The heart sounds are segmented using an open-source algorithm based on a hidden semi-Markov model. Following this, the time-frequency behaviour of a single heartbeat is characterized by using a novel implementation of the continuous wavelet transform, mel-frequency cepstral coefficients, and certain complexity measures. These features help detect the presence of any murmurs. A number of other features are also extracted to characterise the inter-beat behaviour of the heart sounds, which helps to recognize diseases such as arrhythmia. The extracted features are normalized and their dimensionality is reduced using principal component analysis. They are then used as the input to a fully-connected, two-hidden-layer neural network, trained by error backpropagation, and regularized with DropConnect.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:italic>Main results<\/jats:italic>\n                    : This algorithm achieved an accuracy of 85.2% on the test data, which placed third in the PhysioNet\/Computing in Cardiology Challenge (first place scored 86.0%). However, this is unrealistic of real-world performance, as the test data contained a dataset (dataset-e) in which normal and abnormal heart sounds were recorded with different stethoscopes. A 10-fold cross-validation study on the training data (excluding dataset-e) gives a mean score of 74.8%, which is a more realistic estimate of accuracy. With dataset-e excluded from training, the algorithm scored only 58.1% on the test data.\n                  <\/jats:p>","DOI":"10.1088\/1361-6579\/aa6a3d","type":"journal-article","created":{"date-parts":[[2017,7,31]],"date-time":"2017-07-31T06:39:54Z","timestamp":1501483194000},"page":"1645-1657","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":73,"title":["DropConnected neural networks trained on time-frequency and inter-beat features for classifying heart sounds"],"prefix":"10.1088","volume":"38","author":[{"given":"Edmund","family":"Kay","sequence":"first","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anurag","family":"Agarwal","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2017,7,31]]},"reference":[{"key":"pmeaaa6a3dbib001","author":"Bishop","year":"1995","type":"book"},{"key":"pmeaaa6a3dbib002","first-page":"609","type":"journal-article","article-title":"Classification of normal\/abnormal heart sound recordings: the PhysioNet\/Computing in Cardiology Challenge 2016","volume":"43","author":"Clifford","year":"2016","journal-title":"Proc. Computers in Cardiology"},{"key":"pmeaaa6a3dbib003","doi-asserted-by":"publisher","author":"Constant","year":"2003","DOI":"10.1007\/978-1-59259-338-5","type":"book"},{"key":"pmeaaa6a3dbib004","author":"Huang","year":"2001","type":"book"},{"key":"pmeaaa6a3dbib005","first-page":"617","type":"journal-article","article-title":"Drop connected neural network trained with diverse features for classifying heart sounds","volume":"43","author":"Kay","year":"2016","journal-title":"Proc. Computers in Cardiology"},{"key":"pmeaaa6a3dbib006","doi-asserted-by":"publisher","first-page":"1638","DOI":"10.1378\/chest.124.5.1638","type":"journal-article","article-title":"Assessment of severity of aortic stenosis through time-frequency analysis of murmur","volume":"124","author":"Kim","year":"2003","journal-title":"CHEST"},{"key":"pmeaaa6a3dbib007","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.1088\/0967-3334\/37\/12\/2181","type":"journal-article","article-title":"An open access database for the evaluation of heart sound algorithms","volume":"37","author":"Liu","year":"2016","journal-title":"Physiol. Meas."},{"key":"pmeaaa6a3dbib008","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/S0002-9343(00)00673-2","type":"journal-article","article-title":"Cardiac auscultatory skills of physicians-in-training: a comparison of three English-speaking countries","volume":"110","author":"Mangione","year":"2001","journal-title":"Am. J. Med."},{"key":"pmeaaa6a3dbib009","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1016\/S0140-6736(06)69208-8","type":"journal-article","article-title":"Burden of valvular heart diseases: a population-based study","volume":"368","author":"Nkomo","year":"2006","journal-title":"Lancet"},{"key":"pmeaaa6a3dbib010","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1088\/0967-3334\/31\/4\/004","type":"journal-article","article-title":"Segmentation of heart sound recordings by a duration-dependent hidden Markov model","volume":"31","author":"Schmidt","year":"2010","journal-title":"Physiol. Meas."},{"key":"pmeaaa6a3dbib011","doi-asserted-by":"publisher","first-page":"2611","DOI":"10.1109\/TBME.2015.2432129","type":"journal-article","article-title":"Acoustic features for the identification of coronary artery disease","volume":"62","author":"Schmidt","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmeaaa6a3dbib012","first-page":"163","type":"journal-article","article-title":"Echocardiography or auscultation? How to evaluate systolic murmurs","volume":"49","author":"Shub","year":"2003","journal-title":"Can. Family Physician"},{"key":"pmeaaa6a3dbib013","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1109\/TBME.2015.2475278","type":"journal-article","article-title":"Logistic regression-HSMM-based heart sound segmentation","volume":"63","author":"Springer","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmeaaa6a3dbib014","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1109\/TBME.2006.889189","type":"journal-article","article-title":"A framework for the analysis of acoustical cardiac signals","volume":"54","author":"Syed","year":"2007","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmeaaa6a3dbib015","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1161\/CIRCULATIONAHA.105.591149","type":"journal-article","article-title":"Cardiac auscultation: a glorious past\u2014and it does have a future!","volume":"113","author":"Tavel","year":"2006","journal-title":"Circulation"},{"key":"pmeaaa6a3dbib016","first-page":"1058","type":"journal-article","article-title":"Regularization of neural networks using drop Connect","volume":"28","author":"Wan","year":"2013","journal-title":"Int. Conf. on Machine Learning"},{"key":"pmeaaa6a3dbib017","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/s10439-006-9232-3","type":"journal-article","article-title":"Phonocardiographic signal analysis method using a modified hidden Markov model","volume":"35","author":"Wang","year":"2006","journal-title":"Ann. Biomed. Eng."},{"key":"pmeaaa6a3dbib018","first-page":"613","type":"journal-article","article-title":"Heart sound anomaly and quality detection using ensemble of neural networks without segmentation","volume":"43","author":"Zabihi","year":"2016","journal-title":"Proc. Computers in Cardiology"}],"container-title":["Physiological Measurement"],"original-title":[],"link":[{"URL":"http:\/\/stacks.iop.org\/0967-3334\/38\/i=8\/a=1645\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/stacks.iop.org\/0967-3334\/38\/i=8\/a=1645?key=crossref.adfb3ce701e106dceeb69a0265e0a8a3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aa6a3d","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aa6a3d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aa6a3d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/stacks.iop.org\/0967-3334\/38\/i=8\/a=1645\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/stacks.iop.org\/0967-3334\/38\/i=8\/a=1645?key=crossref.adfb3ce701e106dceeb69a0265e0a8a3","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aa6a3d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T12:35:31Z","timestamp":1784982931000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aa6a3d"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,31]]},"references-count":18,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2017,7,31]]},"published-print":{"date-parts":[[2017,8,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6579\/aa6a3d","relation":{},"ISSN":["0967-3334","1361-6579"],"issn-type":[{"value":"0967-3334","type":"print"},{"value":"1361-6579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,31]]},"assertion":[{"value":"DropConnected neural networks trained on time-frequency and inter-beat features for classifying heart sounds","name":"article_title","label":"Article Title"},{"value":"Physiological Measurement","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2017 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2017-01-21","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2017-03-30","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2017-07-31","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}