{"id":387,"date":"2013-11-18T14:40:42","date_gmt":"2013-11-18T03:40:42","guid":{"rendered":"http:\/\/blog.panicola.com\/?p=387"},"modified":"2013-11-18T14:48:47","modified_gmt":"2013-11-18T03:48:47","slug":"387","status":"publish","type":"post","link":"https:\/\/blog.panicola.com\/?p=387","title":{"rendered":"Hammerbacher heads big data at Mt Sinai"},"content":{"rendered":"<ul>\n<li>accountable care is a system in which hospitals are paid to keep people healthy<\/li>\n<li>the new economic incentives drive a need for data regarding the population being treated<\/li>\n<li>Joel Dudley (Director of Informatics at Mount Sinai Medical School) is running diabetic patient data through an algorithm to cluster them according to phenotype and genotype.<\/li>\n<li><span style=\"font-size: 1rem; line-height: 1.714285714;\">This work aims to to replace the general guidelines doctors often use in deciding how to treat diabetics and replace them with risk models\u2014powered by genomics, lab tests, billing records, and demographics\u2014making up-to-date predictions about the individual patient a doctor is seeing, not unlike how a Web ad is tailored according to who you are and sites you\u2019ve visited recently.<\/span><\/li>\n<\/ul>\n<p>Source:\u00a0<a href=\"http:\/\/www.technologyreview.com\/news\/518916\/a-hospital-takes-its-own-big-data-medicine\/\">http:\/\/www.technologyreview.com\/news\/518916\/a-hospital-takes-its-own-big-data-medicine\/<\/a><\/p>\n<p>MIT Technology Review Report:\u00a0<a href=\"http:\/\/blog.panicola.com\/wp-content\/uploads\/2013\/11\/Business-Report_A-Cure-for-Health-Care-Costs.pdf\">A Cure for Health Care Costs<\/a>\u00a0(good infographics)<\/p>\n<p><strong>A Hospital Takes Its Own Big-Data Medicine<\/strong><\/p>\n<aside><em>Experts from Facebook and genetics labs team up to help doctors make personalized predictions about their patients.<\/em><span style=\"line-height: 1.714285714; font-size: 1rem;\">On the ground floor of the Mount Sinai Medical Center\u2019s new behemoth of a research and hospital building in Manhattan, rows of empty black metal racks sit waiting for computer processors and hard disk drives. They\u2019ll house the center\u2019s new computing cluster, adding to an existing $3 million supercomputer that hums in the basement of a nearby building.<\/span><\/aside>\n<p>The person leading the design of the new computer is Jeff Hammerbacher, a 30-year-old known for being Facebook\u2019s first data scientist. Now Hammerbacher is applying the same data-crunching techniques used to target online advertisements, but this time for a powerful engine that will suck in medical information and spit out predictions that could cut the cost of health care.<\/p>\n<p>With $3 trillion spent annually on health care in the U.S., it could easily be the biggest job for \u201cbig data\u201d yet. \u201cWe\u2019re going out on a limb\u2014we\u2019re saying this can deliver value to the hospital,\u201d says Hammerbacher.<\/p>\n<p>Mount Sinai has 1,406 beds plus a medical school and treats half a million patients per year. Increasingly, it\u2019s run like an information business: it\u2019s assembled a biobank with 26,735 patient DNA and plasma samples, it finished installing a $120 million electronic medical records system this year, and it has been spending heavily to recruit computing experts like Hammerbacher.<\/p>\n<p>It\u2019s all part of a \u201cmonstrously large bet that [data] is going to matter,\u201d says Eric Schadt, the computational biologist who runs Mount Sinai\u2019s Icahn Institute for Genomics and Multiscale Biology, where Hammerbacher is based, and who was himself recruited from the gene sequencing company Pacific Biosciences two years ago.<\/p>\n<p>Mount Sinai hopes data will let it succeed in a health-care system that\u2019s shifting dramatically. Perversely, because hospitals bill by the procedure, they tend to earn more the sicker their patients become. But health-care reform in Washington is pushing hospitals toward a new model, called \u201caccountable care,\u201d in which they will instead be paid to keep people healthy.<\/p>\n<p>Mount Sinai is already part of an experiment that the federal agency overseeing Medicare has organized to test these economic ideas. Last year it joined 250 U.S. doctor\u2019s practices, clinics, and other hospitals in agreeing to track patients more closely. If the medical organizations can cut costs with better results, they\u2019ll share in the savings. If costs go up, they can face penalties.<\/p>\n<p>The new economic incentives, says Schadt, help explain the hospital\u2019s sudden hunger for data, and its heavy spending to hire 150 people during the last year just in the institute he runs. \u201cIt\u2019s become \u2018Hey, use all your resources and data to better assess the population you are treating,\u2019\u201d he says.<\/p>\n<aside>\n<div id=\"dfp-ad-tr_www_body_content_portrait_in_story-wrapper\"><\/div>\n<\/aside>\n<p>One way Mount Sinai is doing that already is with a computer model where factors like disease, past hospital visits, even race, are used to predict which patients stand the highest chance of returning to the hospital. That model, built using hospital claims data, tells caregivers which chronically ill people need to be showered with follow-up calls and extra help. In a pilot study, the program cut readmissions by half; now the risk score is being used throughout the hospital.<\/p>\n<p>Hammerbacher\u2019s new computing facility is designed to supercharge the discovery of such insights. It will run a version of Hadoop, software that spreads data across many computers and is popular in industries, like e-commerce, that generate large amounts of quick-changing information.<\/p>\n<p>Patient data are slim by comparison, and not very dynamic. Records get added to infrequently\u2014not at all if a patient visits another hospital. That\u2019s a limitation, Hammerbacher says. Yet he hopes big-data technology will be used to search for connections between, say, hospital infections and the DNA of microbes present in an ICU, or to track data streaming in from patients who use at-home monitors.<\/p>\n<p>One person he\u2019ll be working with is Joel Dudley, director of biomedical informatics at Mount Sinai\u2019s medical school. Dudley has been running information gathered on diabetes patients (like blood sugar levels, height, weight, and age) through an algorithm that clusters them into a weblike network of nodes. In \u201chot spots\u201d where diabetic patients appear similar, he\u2019s then trying to find out if they share genetic attributes. That way DNA information might add to predictions about patients, too.<\/p>\n<p>A goal of this work, which is still unpublished, is to replace the general guidelines doctors often use in deciding how to treat diabetics. Instead, new risk models\u2014powered by genomics, lab tests, billing records, and demographics\u2014could make up-to-date predictions about the individual patient a doctor is seeing, not unlike how a Web ad is tailored according to who you are and sites you\u2019ve visited recently.<\/p>\n<p>That is where the big data comes in. In the future, every patient will be represented by what Dudley calls \u201clarge dossier of data.\u201d And before they are treated, or even diagnosed, the goal will be to \u201ccompare that to every patient that\u2019s ever walked in the door at Mount Sinai,\u201d he says. \u201c[Then] you can say quantitatively what\u2019s the risk for this person based on all the other patients we\u2019ve seen.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"<p>accountable care is a system in which hospitals are paid to keep people healthy the new economic incentives drive a need for data regarding the population being treated Joel Dudley (Director of Informatics at Mount Sinai Medical School) is running diabetic patient data through an algorithm to cluster them according to phenotype and genotype. This &hellip; <a href=\"https:\/\/blog.panicola.com\/?p=387\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">Hammerbacher heads big data at Mt Sinai<\/span> <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5,9,3,7],"tags":[],"class_list":["post-387","post","type-post","status-publish","format-standard","hentry","category-data-saving-lives","category-healthcare","category-rapid-learning-health-systems","category-technology"],"_links":{"self":[{"href":"https:\/\/blog.panicola.com\/index.php?rest_route=\/wp\/v2\/posts\/387","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.panicola.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.panicola.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.panicola.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.panicola.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=387"}],"version-history":[{"count":4,"href":"https:\/\/blog.panicola.com\/index.php?rest_route=\/wp\/v2\/posts\/387\/revisions"}],"predecessor-version":[{"id":392,"href":"https:\/\/blog.panicola.com\/index.php?rest_route=\/wp\/v2\/posts\/387\/revisions\/392"}],"wp:attachment":[{"href":"https:\/\/blog.panicola.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=387"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.panicola.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=387"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.panicola.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=387"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}