{"id":501592,"date":"2021-11-15T10:06:22","date_gmt":"2021-11-15T15:06:22","guid":{"rendered":"https:\/\/www.rochester.edu\/newscenter\/?p=501592"},"modified":"2025-11-19T07:59:32","modified_gmt":"2025-11-19T12:59:32","slug":"parkinsons-disease-symptoms-early-diagnosis-algorithm-501592","status":"publish","type":"post","link":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/","title":{"rendered":"Software uses selfies to detect early symptoms of Parkinson\u2019s disease"},"content":{"rendered":"<h2>Machine learning lets Rochester researchers accurately identify signs of the neurological disease by analyzing facial muscles.<\/h2>\n<div class=\"side-right\">\n<h2>What are the signs and symptoms of Parkinson\u2019s disease?<\/h2>\n<p>Although individuals may experience symptoms differently, the four common signs of Parkinson\u2019s disease are:<\/p>\n<ul>\n<li><strong>Muscle rigidity or stiffness<\/strong> when the arm, leg, or neck is moved back and forth.<\/li>\n<li><strong>Tremors\u2014<\/strong>involuntary movement from contracting muscles\u2014especially when at rest.<\/li>\n<li><strong>Slowness<\/strong> in initiating movement.<\/li>\n<li><strong>Poor posture and balance<\/strong> that may cause falls or problems with walking.<\/li>\n<\/ul>\n<p>Get more information about Parkinson\u2019s disease from <a href=\"https:\/\/www.urmc.rochester.edu\/neurosurgery\/services\/conditions\/parkinsons-disease.aspx\">UR Medicine Neurosurgery<\/a>.<\/p>\n<\/div>\n<p>Every day, millions of people take selfies with their smartphones or webcams to share online. And they almost invariably smile when they do so.<\/p>\n<p>To <a href=\"https:\/\/www.cs.rochester.edu\/people\/faculty\/hoque_m.ehsan\/index.html\">Ehsan Hoque<\/a> and his collaborators at the <a href=\"https:\/\/www.rochester.edu\/\">University of Rochester<\/a>, those pictures are worth far more than the proverbial \u201cthousand words.\u201d Computer vision software\u2014based on algorithms that the computer scientist and his lab have developed\u2014can analyze the brief videos, including the short clips created while taking selfies, detecting subtle movements of facial muscles that are invisible to the naked eye.<\/p>\n<p>The software can then predict with remarkable accuracy whether a person who takes a selfie is likely to develop Parkinson\u2019s disease\u2014as reliably as expensive, wearable digital biomarkers that monitor motor symptoms. The researchers\u2019 technology is described in <a href=\"https:\/\/www.nature.com\/articles\/s41746-021-00502-8\"><em>Nature Digital Medicine<\/em><\/a>.*<\/p>\n<p>\u201cParkinson\u2019s is the fastest growing neurological disorder,\u201d says Hoque, an associate professor of <a href=\"https:\/\/www.cs.rochester.edu\/\">computer science<\/a>. \u201cWhat if, with people\u2019s permission, we could analyze those selfies and give them a referral in case they are showing early signs?\u201d<\/p>\n<p>Though ethical and technological considerations still need to be addressed, the <a href=\"https:\/\/www.moore.org\/\">Gordon and Betty Moore Foundation<\/a> has agreed to fund this novel research through a $500,000 grant, effective November of 2021.<\/p>\n<p>\u201cThe foundation wants us to validate the feedback that we would give people if they did, indeed, show early signs of Parkinson\u2019s\u2014especially if they are performing the test at home,\u201d Hoque says. \u201cThe challenge is not only validating the accuracy of our algorithms but also translating the raw machine-generated output in a language that is humane, assuring, understandable, and empowering to the patients.\u201d<\/p>\n<style>.embed-container { position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden; max-width: 100%; } .embed-container iframe, .embed-container object, .embed-container embed { position: absolute; top: 0; left: 0; width: 100%; height: 100%; }<\/style>\n<div class='embed-container'><iframe src='https:\/\/www.youtube.com\/embed\/Cui0fnR5WTM' frameborder='0' allowfullscreen><\/iframe><\/div>\n<p>&nbsp;<\/p>\n<h3><strong>Software analyzes facial expressions, hand movements<\/strong><\/h3>\n<p>Smiles are not the only behaviors that Hoque and his lab can analyze for early symptoms of Parkinson\u2019s disease or related disorders.<\/p>\n<p>In collaboration with <a href=\"https:\/\/www.urmc.rochester.edu\/people\/26764214-earl-ray-dorsey\">Ray Dorsey<\/a>\u2014a leading expert in Parkinson\u2019s disease and the David M. Levy Professor of Neurology at Rochester\u2014and the University\u2019s <a href=\"https:\/\/www.urudallcenter.org\/\">Morris K. Udall Parkinson Disease Research Center<\/a>, the researchers have developed a five-pronged test that neurologists could administer to patients sitting in front of their computer webcams hundreds of miles away.<\/p>\n<p>This could be transformative for patients who are quarantined, immobile, or living in underdeveloped areas where access to a neurologist is limited, Hoque says.<\/p>\n<p>In addition to making the biggest smile, and alternating it with a neutral expression three times, patients taking the test are also asked to:<\/p>\n<ul>\n<li>Read aloud a complex written sentence<\/li>\n<li>Touch their index finger to their thumb 10 times as quickly as possible<\/li>\n<li>Make the most disgusted look possible, alternating with a neutral expression, three times<\/li>\n<li>Raise their eyebrows as high as possible, then lower them as far as they can, three times slowly<\/li>\n<\/ul>\n<p>Using machine learning algorithms, the computer program shows\u2014within minutes\u2014a percentage likelihood from each of the tests whether the patient is showing symptoms of Parkinson\u2019s disease or related disorders.<\/p>\n<p>What exactly does the program look for? When patients are making a smile, the software can detect whether they show less control over their facial muscles while doing so, a symptom of Parkinson\u2019s that clinicians refer to as \u201cmodularity.\u201d<\/p>\n<p>\u201cOne thing about Parkinson\u2019s is that you don\u2019t show all the symptoms all the time, and not every symptom is shown in every part of your body,\u201d says Rafayet Ali \u201920, lead author of the paper. \u201cFor example, you may not have hand tremors, but you may show a significant level of deviation in your smile.\u201d<\/p>\n<p>Hence the importance of testing other expressions and movements, according to Ali, a former postdoctoral associate in Hoque\u2019s lab who now is an associate data scientist at Sysco.<\/p>\n<figure id=\"attachment_502072\" aria-describedby=\"caption-attachment-502072\" style=\"width: 630px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-502072\" src=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-dorsey-hoque-630x378.jpg\" alt=\"Side-by-side smiling portraits of Ray Dorsey and Ehsan Hoque.\" width=\"630\" height=\"378\" srcset=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-dorsey-hoque-630x378.jpg 630w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-dorsey-hoque-193x117.jpg 193w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-dorsey-hoque-768x461.jpg 768w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-dorsey-hoque.jpg 1000w\" sizes=\"auto, (max-width: 630px) 100vw, 630px\" \/><figcaption id=\"caption-attachment-502072\" class=\"wp-caption-text\">(l to r) Ray Dorsey (University of Rochester Medical Center photo) and Ehsan Hoque (University of Rochester photo \/ J. Adam Fenster) brought their respective expertise to bear in order to apply data analytics to diagnosing Parkinson\u2019s disease.<\/figcaption><\/figure>\n<h3><b>From pen-and-paper evaluations to \u2018objective, digital assessments\u2019<\/b><\/h3>\n<p>Both Hoque and Ali have personal stakes in helping people with Parkinson\u2019s. Their mothers both have suffered from the disorder. Hoque\u2019s late mother in Bangladesh, for example, was put on leovodopa, a leading medication for the disorder, after finally finding one of the country\u2019s few neurologists. The tremors went away. \u201cWe were so happy,\u201d Hoque says. Unfortunately, it was difficult to make follow-up appointments, and the tremors eventually returned.<\/p>\n<p>That prompted Hoque to email Dorsey, \u201cjust to casually chat.\u201d When they finally met in 2016, Hoque recalls, Dorsey \u201ctook a big document and just threw it on the table.\u201d The pamphlet contained forms physicians need to fill out as part of the Movement Disorders Society\u2013Unified Parkinson\u2019s Disease Rating Scale (MDS-UPDRS).<\/p>\n<p>\u201cThat\u2019s the gold standard for measuring Parkinson\u2019s,\u201d Dorsey told him. \u201cEverything we do is pen and paper. Any automation, any data analytics that you can bring into this would be a contribution. And he immediately helped us see how we could do that,\u201d Hoque says.<\/p>\n<p>\u201cObjective, digital assessments of Parkinson\u2019s disease can help us diagnose people with the condition and evaluate new therapies for the condition faster,\u201d says Dorsey, an author of <a href=\"https:\/\/www.amazon.com\/Ending-Parkinsons-Disease-Prescription-Action\/dp\/1541724526\"><em>Ending Parkinson\u2019s Disease<\/em><\/a> (2020).<\/p>\n<h3><strong>Progress toward FDA approval <\/strong><\/h3>\n<p>It will be a while yet, however, before Hoque and his researchers can start seeking permission to analyze people\u2019s selfies, or even before neurologists can deploy the five-pronged test that the researchers have developed.<\/p>\n<p>\u201cAn algorithm will never be 100 percent accurate,\u201d Hoque says. \u201cWhat if it makes a mistake? We want to be very careful and follow guidance from the FDA if we want anybody from any part of the world to try this and get an assessment.\u201d<\/p>\n<p>Moreover, there is a whole family of movement disorders that are closely related to Parkinson\u2019s disease, including ataxia, Huntington\u2019s disease, progressive supranuclear palsy, and multiple dystrophy.<\/p>\n<div class=\"pullquote\">\u201cObjective, digital assessments of Parkinson\u2019s disease can help us diagnose people with the condition and evaluate new therapies for the condition faster.\u201d<\/div>\n<p>\u201cThey all share similar symptoms of tremor, but the tremors are very different in nature,\u201d Hoque says. \u201cHowever, even expert neurologists find it very, very difficult to distinguish among them.\u201d<\/p>\n<p>The researchers have made great progress in detecting Parkinson\u2019s disease by automatically analyzing expressions, voice and motor movements. Yet further work is needed to develop algorithms to differentiate how these involuntary tremors differ across other movement disorders, including Ataxia and Huntington\u2019s.<\/p>\n<p>\u201cWe can\u2019t tell that just yet,\u201d Hoque says. \u201cBut we are in a pursuit of differentiating those tremors using AI to prevent the potential harm of misdiagnosis while maximizing benefit.\u201d<\/p>\n<hr style=\"width: 50%;\" \/>\n<h3><strong>And speaking of timely Parkinson\u2019s disease diagnosis . . .<\/strong><\/h3>\n<p>Turns out it\u2019s not just selfies and videos that can help with diagnosing Parkinson\u2019s disease.<\/p>\n<p>More and more, people are using speech-activated smart devices, such as Alexa, Apple Watch, and Google Voice Assistant, to accomplish everyday tasks. Could these devices analyze our speech and voices to alert us if we show early warning signs of Parkinson\u2019s disease?<\/p>\n<p>Recent work by Rochester researchers suggests it\u2019s entirely possible. Wasifur Rahman, Sangwu Lee, Md. Saiful Islam, and other students in Hoque\u2019s lab published findings in the Journal of Medical Internet Research that show how an online tool can be used to help screen almost anyone anywhere for Parkinson\u2019s disease remotely using video- or audio-enabled speech tasks.<\/p>\n<p>Taken together, the Rochester researchers\u2019 efforts are contributing to a future in which equity and access to neurological care is as ubiquitous as owning a smart phone or other internet-enabled device.<\/p>\n<p><em>*Editor\u2019s note: As of February 2023, the authors have retracted the article published in\u00a0<\/em>npj Digital Medicine<em>\u00a0that established\u00a0the relationship between smiles and the early onset of Parkinson\u2019s disease because the classification described in the paper was performed on an inaccurate use of a data pre-processing tool. Please see the authors\u2019\u00a0<a href=\"https:\/\/urldefense.com\/v3\/__https:\/\/www.nature.com\/articles\/s41746-023-00761-7__;!!CGUSO5OYRnA7CQ!f-ulB-sewdeWzxJUPFNwhqBvOd93ehro92pmo-NMvh2Rw_uB22BJkc6GrNfpnFXz0EFSuojDdgwte_WtMtLIJA$\" target=\"_blank\" rel=\"noopener noreferrer\">retraction note<\/a> for more information. <\/em><em>In June 2025, a <a href=\"https:\/\/ai.nejm.org\/doi\/full\/10.1056\/AIoa2400950?query=featured_home\">follow-up study<\/a> was published in <\/em>NEJM AI<em>\u00a0demonstrating that smiling videos can effectively differentiate between individuals with and without Parkinson\u2019s disease.<\/em><\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Rochester computer scientist Ehsan Hoque and his colleagues have harnessed machine learning to accurately identify signs of the neurological disease by analyzing facial muscles.<\/p>\n","protected":false},"author":286,"featured_media":501632,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[42472,116],"tags":[24292,18802,24962,18632,18882,24752,18572],"class_list":["post-501592","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-health-medicine","category-sci-tech","tag-artificial-intelligence","tag-department-of-computer-science","tag-ehsan-hoque","tag-hajim-school-of-engineering-and-applied-sciences","tag-parkinsons-disease","tag-ray-dorsey","tag-research-finding"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Software uses selfies to detect early symptoms of Parkinson\u2019s disease<\/title>\n<meta name=\"description\" content=\"Machine learning lets University of Rochester researchers accurately identify Parkinson&#039;s disease symptoms early by analyzing facial muscles.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Software uses selfies to detect early symptoms of Parkinson\u2019s disease\" \/>\n<meta property=\"og:description\" content=\"Machine learning lets University of Rochester researchers accurately identify Parkinson&#039;s disease symptoms early by analyzing facial muscles.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/\" \/>\n<meta property=\"og:site_name\" content=\"News Center\" \/>\n<meta property=\"article:published_time\" content=\"2021-11-15T15:06:22+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-11-19T12:59:32+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-parkinsons-symptoms-algorithm.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"600\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Bob Marcotte\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Bob Marcotte\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/\"},\"author\":{\"name\":\"Bob Marcotte\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e0d8d271cd290d592461fa9cefca013b\"},\"headline\":\"Software uses selfies to detect early symptoms of Parkinson\u2019s disease\",\"datePublished\":\"2021-11-15T15:06:22+00:00\",\"dateModified\":\"2025-11-19T12:59:32+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/\"},\"wordCount\":1442,\"image\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2021\\\/11\\\/fea-parkinsons-symptoms-algorithm.jpg\",\"keywords\":[\"artificial intelligence\",\"Department of Computer Science\",\"Ehsan Hoque\",\"Hajim School of Engineering and Applied Sciences\",\"Parkinson's disease\",\"Ray Dorsey\",\"research finding\"],\"articleSection\":[\"Health &amp; Medicine\",\"Science &amp; Technology\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/\",\"name\":\"Software uses selfies to detect early symptoms of Parkinson\u2019s disease\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2021\\\/11\\\/fea-parkinsons-symptoms-algorithm.jpg\",\"datePublished\":\"2021-11-15T15:06:22+00:00\",\"dateModified\":\"2025-11-19T12:59:32+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e0d8d271cd290d592461fa9cefca013b\"},\"description\":\"Machine learning lets University of Rochester researchers accurately identify Parkinson's disease symptoms early by analyzing facial muscles.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2021\\\/11\\\/fea-parkinsons-symptoms-algorithm.jpg\",\"contentUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2021\\\/11\\\/fea-parkinsons-symptoms-algorithm.jpg\",\"width\":1000,\"height\":600,\"caption\":\"To Ehsan Hoque and his collaborators at the University of Rochester, selfie photos are worth far more than the proverbial \u201cthousand words.\u201d Computer vision software\u2014based on algorithms that the computer scientist and his lab have developed\u2014can analyze them to predict whether a person is likely to develop Parkinson\u2019s disease. (University of Rochester illustration \\\/ Julia Joshpe)\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Software uses selfies to detect early symptoms of Parkinson\u2019s disease\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#website\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/\",\"name\":\"News Center\",\"description\":\"University of Rochester\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e0d8d271cd290d592461fa9cefca013b\",\"name\":\"Bob Marcotte\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/author\\\/bmarcotte\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Software uses selfies to detect early symptoms of Parkinson\u2019s disease","description":"Machine learning lets University of Rochester researchers accurately identify Parkinson's disease symptoms early by analyzing facial muscles.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/","og_locale":"en_US","og_type":"article","og_title":"Software uses selfies to detect early symptoms of Parkinson\u2019s disease","og_description":"Machine learning lets University of Rochester researchers accurately identify Parkinson's disease symptoms early by analyzing facial muscles.","og_url":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/","og_site_name":"News Center","article_published_time":"2021-11-15T15:06:22+00:00","article_modified_time":"2025-11-19T12:59:32+00:00","og_image":[{"url":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-parkinsons-symptoms-algorithm.jpg","width":1000,"height":600,"type":"image\/jpeg"}],"author":"Bob Marcotte","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Bob Marcotte","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/#article","isPartOf":{"@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/"},"author":{"name":"Bob Marcotte","@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e0d8d271cd290d592461fa9cefca013b"},"headline":"Software uses selfies to detect early symptoms of Parkinson\u2019s disease","datePublished":"2021-11-15T15:06:22+00:00","dateModified":"2025-11-19T12:59:32+00:00","mainEntityOfPage":{"@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/"},"wordCount":1442,"image":{"@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/#primaryimage"},"thumbnailUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-parkinsons-symptoms-algorithm.jpg","keywords":["artificial intelligence","Department of Computer Science","Ehsan Hoque","Hajim School of Engineering and Applied Sciences","Parkinson's disease","Ray Dorsey","research finding"],"articleSection":["Health &amp; Medicine","Science &amp; Technology"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/","url":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/","name":"Software uses selfies to detect early symptoms of Parkinson\u2019s disease","isPartOf":{"@id":"https:\/\/www.rochester.edu\/newscenter\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/#primaryimage"},"image":{"@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/#primaryimage"},"thumbnailUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-parkinsons-symptoms-algorithm.jpg","datePublished":"2021-11-15T15:06:22+00:00","dateModified":"2025-11-19T12:59:32+00:00","author":{"@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e0d8d271cd290d592461fa9cefca013b"},"description":"Machine learning lets University of Rochester researchers accurately identify Parkinson's disease symptoms early by analyzing facial muscles.","breadcrumb":{"@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/#primaryimage","url":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-parkinsons-symptoms-algorithm.jpg","contentUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2021\/11\/fea-parkinsons-symptoms-algorithm.jpg","width":1000,"height":600,"caption":"To Ehsan Hoque and his collaborators at the University of Rochester, selfie photos are worth far more than the proverbial \u201cthousand words.\u201d Computer vision software\u2014based on algorithms that the computer scientist and his lab have developed\u2014can analyze them to predict whether a person is likely to develop Parkinson\u2019s disease. (University of Rochester illustration \/ Julia Joshpe)"},{"@type":"BreadcrumbList","@id":"https:\/\/www.rochester.edu\/newscenter\/parkinsons-disease-symptoms-early-diagnosis-algorithm-501592\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.rochester.edu\/newscenter\/"},{"@type":"ListItem","position":2,"name":"Software uses selfies to detect early symptoms of Parkinson\u2019s disease"}]},{"@type":"WebSite","@id":"https:\/\/www.rochester.edu\/newscenter\/#website","url":"https:\/\/www.rochester.edu\/newscenter\/","name":"News Center","description":"University of Rochester","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.rochester.edu\/newscenter\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e0d8d271cd290d592461fa9cefca013b","name":"Bob Marcotte","url":"https:\/\/www.rochester.edu\/newscenter\/author\/bmarcotte\/"}]}},"_links":{"self":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/501592","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/users\/286"}],"replies":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/comments?post=501592"}],"version-history":[{"count":33,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/501592\/revisions"}],"predecessor-version":[{"id":658332,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/501592\/revisions\/658332"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/media\/501632"}],"wp:attachment":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/media?parent=501592"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/categories?post=501592"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/tags?post=501592"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}