{"id":28109,"date":"2020-09-09T09:47:25","date_gmt":"2020-09-09T13:47:25","guid":{"rendered":"https:\/\/www.bu.edu\/cise\/?p=28109"},"modified":"2021-09-21T20:00:56","modified_gmt":"2021-09-22T00:00:56","slug":"ai-in-medicine-advances-with-bu-mit-research-team","status":"publish","type":"post","link":"https:\/\/www.bu.edu\/cise\/ai-in-medicine-advances-with-bu-mit-research-team\/","title":{"rendered":"AI in Medicine Advances with BU-MIT Research Team"},"content":{"rendered":"

\"\"<\/p>\n

Researchers from Boston University and the Massachusetts Institute of Technology have pioneered an AI method that learns from existing data how to make specific recommendations (\u201cprescriptions\u201d) to optimize a certain outcome. Their research findings have been published in this month in\u00a0PLOS ONE<\/em>.\u00a0\u00a0<\/span><\/p>\n

The paper titled \u201cPrescriptive Analytics for Reducing 30-day Hospital Readmissions after General Surgery\u201d proposes<\/span>\u00a0<\/span>an innovative solution for reducing re-hospitalization rates. Combining predictive and prescriptive statistical modeling, researchers\u00a0<\/span>Ioannis (Yannis) Paschalidis<\/a><\/span>\u00a0<\/span>and\u00a0<\/span>Taiyao Wang<\/a><\/span>\u00a0<\/span>of Boston University, and\u00a0<\/span>Dimitris Bertsimas<\/a><\/span>\u00a0<\/span>and\u00a0<\/span>Michael Lingzhi Li<\/a><\/span>\u00a0<\/span>of MIT, identify the factors behind re-hospitalization rates and suggest an effective treatment: targeted preoperative blood transfusions.<\/p>\n

\u201cThe vast majority of AI in medicine develops models that learn how to predict some outcome,\u201d says Dr. Paschalidis, Professor of the College of Engineering (ECE, BME, SE, CDS) and Director of the Center for Information & Systems Engineering at BU. \u201cWhat is novel in this work is that we train a model that offers personalized recommendations\/prescriptions aimed at improving patient outcomes. The approach has broad applicability and the potential to improve medical decision making.\u201d<\/span><\/p>\n

The method results from thorough research and application. Using data from more than 700,000 surgeries from the\u00a0American College of Surgeons National Surgical Quality Improvement Program<\/a>\u00a0(NSQIP), the researchers analyzed how pre-operative factors (such as underlying medical conditions) and post-operative factors (including complications from surgery) affect current re-hospitalization rates.<\/span><\/p>\n

By incorporating both pre-operative and post-operative factors in their prescriptive models, the researchers discovered pre-operative hematocrit levels significantly affected re-hospitalization rates. From there, they created a prescriptive model that suggested targeted pre-operative transfusions to increase hematocrit. As a result, the blood transfusions reduced the likelihood of a re-hospitalization.<\/span><\/p>\n

As it stands, the U.S. spends over $3 trillion annually on healthcare, with a large portion resulting from re-hospitalization rates. However, with the presented research, that number could fall. The researchers estimate a 12% decrease in 30-day rehospitalization rates if one were to follow the model, potentially saving the U.S. over $20 million on an annual basis.<\/span><\/p>\n

\u201cThe use of AI in medicine is likely to increase, helping to improve patient outcomes and reduce costs,\u201d adds Dr. Paschalidis. \u201cThis paper is an example of how AI could be used to affect modifiable factors that improve outcomes through personalized medicine.\u201d<\/span><\/p>\n

To learn more about the research and methods of this publication, read the full paper\u00a0<\/span>here<\/a>.<\/u><\/p>\n

PLOS ONE<\/em>\u00a0<\/span>is the world\u2019s first multidisciplinary Open Access journal.\u00a0 The journal\u2019s publication criteria are based on high ethical standards and the rigor of the methodology and conclusions reported.<\/p>\n","protected":false},"excerpt":{"rendered":"

Researchers from Boston University and the Massachusetts Institute of Technology have pioneered an AI method that learns from existing data how to make specific recommendations (\u201cprescriptions\u201d) to optimize a certain outcome. Their research findings have been published in this month in\u00a0PLOS ONE.\u00a0\u00a0 The paper titled \u201cPrescriptive Analytics for Reducing 30-day Hospital Readmissions after General Surgery\u201d […]<\/p>\n","protected":false},"author":18553,"featured_media":28486,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[76],"tags":[],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/28109"}],"collection":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/users\/18553"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/comments?post=28109"}],"version-history":[{"count":4,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/28109\/revisions"}],"predecessor-version":[{"id":33499,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/28109\/revisions\/33499"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/media\/28486"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/media?parent=28109"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/categories?post=28109"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/tags?post=28109"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}