{"616715":{"#nid":"616715","#data":{"type":"news","title":"New Deep Learning Approach Improving Access to Sleep Diagnostic Testing","body":[{"value":"\u003Cp\u003EA new deep learning approach can automatically analyze and score sleep tests as effectively as sleep technologists, according to researchers from Georgia Tech\u0026rsquo;s\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cse.gatech.edu\/\u0022\u003ESchool of Computational Science and Engineering\u003C\/a\u003E\u0026nbsp;(CSE) and the\u0026nbsp;\u003Ca href=\u0022https:\/\/www.massgeneral.org\/neurology\/\u0022\u003ENeurology Department of Massachusetts General Hospital\u003C\/a\u003E\u0026nbsp;(MGH).\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe breakthrough \u0026ndash; outlined in\u0026nbsp;\u003Ca href=\u0022https:\/\/academic.oup.com\/jamia\/article\/25\/12\/1643\/5185596\u0022\u003Ea paper\u003C\/a\u003E\u0026nbsp;published in the December 2018 issue of the\u0026nbsp;\u003Ca href=\u0022https:\/\/academic.oup.com\/jamia\u0022\u003EJournal of American Medical Informatics Association\u003C\/a\u003E\u0026nbsp;(JAMIA) \u0026ndash; will enable greater access to critically needed diagnostic testing for the 40 million people in the United States who suffer from chronic long-term sleep disorders.\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECurrently, it\u0026nbsp;takes a certified sleep technologist one to two hours to manually assess and score a\u0026nbsp;polysomnography (PSG) test, a key test in sleep disorder studies, from just one night of sleep.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe new automated approach uses a combination of deep recurrent and convolutional neural networks (RCNN) and was trained on 10,000 MGH sleep studies, one of\u0026nbsp;the world\u0026rsquo;s largest clinical data sets of sleep study information. According to the study, the model produces results that are as accurate as those of an experienced sleep technologist in a fraction of the time.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Timely and accurate diagnosis of sleep disorders is critical to pursue appropriate treatment and improve health outcomes, yet most sleep disorders remain undiagnosed,\u0026rdquo; said CSE Associate Professor\u0026nbsp;\u003Ca href=\u0022http:\/\/sunlab.org\/\u0022\u003E\u003Cstrong\u003EJimeng Sun\u003C\/strong\u003E\u003C\/a\u003E, a member of the research team leading the study.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;The amount of time required to manually score sleep charts creates a bottleneck in the sleep assessment process, which often prevents patients from having access to sleep diagnostic testing for longer durations [between appointments] or all together.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMGH researchers and neurologists\u0026nbsp;\u003Cstrong\u003E\u003Ca href=\u0022https:\/\/www.massgeneral.org\/doctors\/doctor.aspx?id=19222\u0022\u003EDr. Brandon Westover\u003C\/a\u003E\u0026nbsp;\u003C\/strong\u003Eand\u0026nbsp;\u003Ca href=\u0022http:\/\/www.mghsleep.com\/matt-bianchi-md-phd-mmsc.html\u0022\u003E\u003Cstrong\u003EDr.\u003C\/strong\u003E\u003Cstrong\u003EMatt Bianchi\u003C\/strong\u003E\u003C\/a\u003E\u0026nbsp;noticed the unmet need with sleep study access and an opportunity with its data labeling process more than 10 years ago.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;One of our problems with the way medicine is done generally, and in our own specialty of neurology, is that there is a lot of subjectivity,\u0026rdquo; said Westover. \u0026ldquo;We realized that sleep scoring was a perfect procedure to automate because the data is routinely labeled by experts.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAfter collecting sleep study data at MGH for a decade,\u0026nbsp;Bianchi and Westover began collaborating with Georgia Tech colleagues, Sun and Ph.D. student\u0026nbsp;\u003Ca href=\u0022https:\/\/github.com\/sidsearch\u0022\u003E\u003Cstrong\u003ESiddharth Biswal\u003C\/strong\u003E\u003C\/a\u003E, to craft a powerful computer algorithm with enough information to adequately represent the diversity of clinical sleep signals, removing the subjective element of sleep data interpretation entirely.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;In the past, most of the work in designing [sleep study] algorithms focused cleaning data, deciding which features to extract, and finally training algorithms on small data sets. But the dozens of algorithms in the literature that take this approach don\u0026rsquo;t work in the real world. Our approach was to collect truly big data, from thousands of real patients \u0026mdash; not carefully selected research subjects. This rich data let us train a very flexible, powerful machine learning algorithm, directly from the raw data, that works across the entire range of ages and sleep problems that we encounter in patients with sleep problems,\u0026rdquo; said Westover.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;We believe this new method will increase the throughput of the sleep clinics that exists now and help extend the reach of sleep medicine to more patients beyond sleep clinics,\u0026rdquo; he said.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EWith the research published, the new automated assessment and scoring tool will be helping real-world patients in the short term.\u0026nbsp;According to Sun, a longer-term project will combine new sensors to apply the new approach to at-home methods of sleep diagnostics.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"CSE Associate Professor Jimeng Sun and Ph.D. student Siddharth Biswal are part of a research team with Massachusetts General Hospital that have created a deep learning algorithm to perform sleep diagnostic testing."}],"uid":"34540","created_gmt":"2019-01-22 19:10:33","changed_gmt":"2019-01-22 21:06:40","author":"Kristen Perez","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2019-01-22T00:00:00-05:00","iso_date":"2019-01-22T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"616713":{"id":"616713","type":"image","title":"Deep Learning for Sleep Medicine","body":null,"created":"1548183826","gmt_created":"2019-01-22 19:03:46","changed":"1548183826","gmt_changed":"2019-01-22 19:03:46","alt":"An image courtesy of Wikimedia Commons\u00a0of the testing measurement apparatus for sleep studies.","file":{"fid":"234723","name":"Image Courtesy of Wkimedia Commons.jpg","image_path":"\/sites\/default\/files\/images\/Image%20Courtesy%20of%20Wkimedia%20Commons.jpg","image_full_path":"http:\/\/tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/Image%20Courtesy%20of%20Wkimedia%20Commons.jpg","mime":"image\/jpeg","size":78663,"path_740":"http:\/\/tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/Image%20Courtesy%20of%20Wkimedia%20Commons.jpg?itok=tsUqycV-"}}},"media_ids":["616713"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[],"keywords":[{"id":"109581","name":"deep learning"},{"id":"180266","name":"sleep studies"},{"id":"180264","name":"Sleep Diagnostics"}],"core_research_areas":[{"id":"39441","name":"Bioengineering and Bioscience"},{"id":"39431","name":"Data Engineering and Science"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EKristen Perez\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECommunications Officer I\u003C\/p\u003E\r\n","format":"limited_html"}],"email":["kristen.perez@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}