{"id":17119,"date":"2015-04-13T14:07:46","date_gmt":"2015-04-13T18:07:46","guid":{"rendered":"http:\/\/www.bu.edu\/systems\/?p=17119"},"modified":"2021-09-07T11:29:42","modified_gmt":"2021-09-07T15:29:42","slug":"big-data-and-improving-health-care","status":"publish","type":"post","link":"https:\/\/www.bu.edu\/cise\/big-data-and-improving-health-care\/","title":{"rendered":"Big Data and Improving Health Care"},"content":{"rendered":"
\"Big
Big Data Meets Healthcare: Bill Adams, a physician and medical informatician, and Yannis Paschalidis, a data scientist and engineer, are working together to use data from electronic health records to reduce preventable hospitalizations and cut health care costs. Photo by Jackie Ricciardi<\/figcaption><\/figure>\n

Data scientist and physician team up to reduce preventable hospitalizations<\/strong>
\nBy Suzanne Jacobs, BU Research<\/em>
\nBig Data Meets Healthcare: Bill Adams<\/strong>, a physician and medical informatician, and Yannis Paschalidis, a data scientist and engineer, are working together to use data from electronic health records to reduce preventable hospitalizations and cut health care costs. Photo by Jackie Ricciardi
\nProfessor Yannis Paschalidis<\/a> (ECE, SE, BME)<\/strong>, a data scientist, has built a career on making things run smoothly and efficiently\u2014transportation systems, communication networks, supply chains, sensor networks\u2014and now he\u2019s taking on perhaps his most ambitious challenge yet: the US health care system.
\nIt all started about three years ago. Paschalidis, a Distinguished Faculty Fellow at Boston University\u2019s College of Engineering (ENG), read in a study by the US Department of Health and Human Service\u2019s\u00a0Agency for Healthcare Research and Quality<\/a>\u00a0(AHRQ) that in 2006, the US spent about $30.8 billion on hospitalizations that could have been prevented through better patient care, healthier patient behavior, or improved ambulatory services.
\n\u201cI was reading a lot of things about the sorry state of the health care system in the US and how inefficient it is, and I thought it\u2019s an opportunity to do something,\u201d says Paschalidis, who also directs BU\u2019s\u00a0Center for Information & Systems Engineering<\/a>. \u201cI thought people like me that have a quantitative, more optimization-oriented background could contribute something.\u201d
\nAnd so, having never worked in medicine before, Paschalidis teamed up with William G. Adams<\/a>, a Boston Medical Center (BMC) physician and BU School of Medicine professor of pediatrics. With a team of graduate students and nearly $2 million from the\u00a0National Science Foundation<\/a>, the two set out to build a piece of software that could automatically flag patients at increased risk for medical emergencies by using data from their electronic health records (EHRs). They decided to start with heart diseases, which alone cost the US more than $9.5 billion in preventable hospitalizations in 2006, according to the AHRQ study.
\nTo understand how Paschalidis works, think of how an autopilot controls an airplane. As a plane flies, autopilot software takes in data about its position and uses that data to adjust the plane\u2019s trajectory as necessary. It\u2019s a constant flow of data intake, analysis, and feedback. Similarly, when Paschalidis sets out to improve, say, a network of sensors, he and his research team write computer software that takes in data about how the system is working and then finds ways to correct or improve it.
\nIn this project, hospital patients are the systems.
\nFortunately, EHRs offer plenty of data\u2014test results, diagnoses, prescriptions, emergency room (ER) visits, previous hospitalizations, demographic information. It\u2019s far too much for doctors and nurses to comb through manually, but enough to feed an algorithm that automatically processes the information and flags at-risk patients. The software works by sifting through records of patients who were previously hospitalized and learning which risk factor\u2014a certain number of chest complaints or an unusual level of a particular enzyme in the heart, for example\u2014might have been red flags. The algorithm then uses those red flags to warn of future hospitalizations.
\nThe challenge for Paschalidis was understanding how to properly use medical data and how to incorporate this kind of software in an actual hospital. That\u2019s where Adams comes in.
\nA pediatrician and medical informatician (someone who uses information technology to improve health care), Adams has spent the past 20 years thinking about how to use data from EHRs to improve patients\u2019 health outcomes, especially among families in Boston\u2019s urban communities. He\u2019s also one of the lead scientists at BU\u2019s\u00a0Clinical & Translational Science Institute<\/a>\u00a0(CTSI), one of 60 such sites across the country that aim to accelerate medical advances by encouraging researchers in disparate fields to collaborate on medical research.
\n\u201cThis is a perfect example of translational research collaboration,\u201d Adams says. \u201cYannis and his lab have exceptional skills in data mining that we don\u2019t have, but we have extraordinary data and clinical expertise.\u201d
\nTo use that data, Paschalidis and his team first needed a crash course in medical terminology to make sure they understood what they were working with. Much of EHR data is contained in a kind of \u201cclinical language\u201d that only doctors understand, Adams says. Sometimes, he says, even the same term can have different meanings, depending on the context in which the doctor records it. For example, a diagnosis of hypertension (high blood pressure) can be recorded as either a diagnosis made during a visit or a problem on the patient\u2019s problem list. Both could be recorded with the same code (ICD-9 401.9), but users would need to know to look further to decide which of the two meanings the data represents. Cleaning up \u201cmessy\u201d data\u2014figuring out what it means, what to use, and how to represent it in the software\u2014is time-consuming but important, Paschalidis says. \u201cIf you fit garbage to an algorithm,\u201d he says, \u201cyou\u2019ll get garbage as output.\u201d
\nThe researchers remove any identifying information from the EHRs using open-source software from a National Institutes of Health-funded center at Harvard University called\u00a0i2b2<\/a> (Informatics for Integrating Biology & the Bedside).
\nOnce the data is cleaned up and anonymized, Paschalidis and his graduate students can enter it into their software. The algorithm they built classifies patients as either at risk or not at risk for heart-related hospitalizations within one year. An elderly patient or someone who visited the ER in the previous year, for example, might be at risk, while a younger person who hasn\u2019t been to the hospital in a few years might not be at risk. How the algorithm will ultimately present this information to doctors is still under development.
\nTo test the software, Paschalidis and his students collected the EHRs of just over 45,500 patients from BMC. They used about 60 percent of the records to train their so-called machine learning software, teaching it which factors had put patients at risk for hospitalizations in the past. Then, they used the remaining data to test the software\u2019s ability to make predictions. They found that it could correctly predict up to 82 percent of heart-related hospitalizations, while falsely predicting hospitalizations in about 30 percent of patients who weren\u2019t actually at risk. Paschalidis says that it\u2019s possible to reduce the number of false predictions, but doing so would correspondingly lower the number of accurate predictions. A false prediction rate of 10 percent, for example, would correspond to an accurate prediction rate of 65 percent.
\n\u201cIn medicine, we\u2019re constantly trying to balance between something that\u2019s concerning and something that might be a false positive,\u201d Adams says. In many cases, however, the recommendations that would come of a false positive\u2014healthy eating, exercise, an extra check-in with the doctor, extra visits from a nurse\u2014could still benefit the patient. And, Paschalidis says, preventing hospital visits that each cost thousands of dollars is worth the occasional unnecessary checkup that only costs a couple hundred dollars.
\nAdams and Paschalidis\u00a0published<\/a>\u00a0their findings about the machine learning software\u2019s success in predicting heart-related hospitalizations in March 2015 in the\u00a0International Journal of Medical Informatics<\/em>. Their co-authors included\u00a0Professor Venkatesh Saligrama<\/a> (ECE, SE);<\/strong> Wuyang Dai and Theodora Brisimi, ENG PhD students working with Paschalidis; and\u00a0Theofanie Mela<\/a>, a cardiologist at Massachusetts General Hospital.
\n\u201cIf coupled with preventive interventions, our methods have the potential to prevent a significant number of hospitalizations by identifying patients at greatest risk and enhancing their patient care\u00a0before<\/em>\u00a0they are hospitalized,\u201d the researchers write in the study. \u201cThis can lead to better patient care, but also to substantial health care cost savings. In particular, if even a small fraction of the $30.8 billion spent annually on preventable hospitalizations can be realized in savings, this would offer significant results.\u201d
\nUltimately, Adams says, having this kind of ongoing, automated analysis within electronic medical records could not only help doctors, nurses, and case managers monitor their patients more effectively, it could also elucidate disease risk factors previously undetected by doctors.
\n\u201cAll of us know that a serious problem like diabetes is always going to increase your likelihood of being admitted to the hospital,\u201d Adams says, \u201cbut the trick is to determine whether it\u2019s about the thing that\u2019s happening to your diabetes or something else unrelated to your diabetes that has substantially increased the likelihood of being hospitalized. The machine learning software has the potential to learn new associations.\u201d These could be associations between some clinical features that make it more likely for the patient to develop serious complications from diabetes.
\nIn the coming year, Paschalidis and Adams will be interviewing doctors, trying to figure out how best to put this kind of predictive software to work in an actual hospital.
\n\u201cI\u2019m confident that it will work,\u201d Paschalidis says. \u201cThe issue is, what is the best way of incorporating something like that in the practice? Will the doctors use it or ignore it?\u201d
\nEventually, Paschalidis says, he\u2019d like to expand the software to predict other, non-heart-related hospitalizations. He\u2019s also currently working with BMC\u2019s surgery department on software designed to flag patients at risk for readmission within 90 days, so hospitals could perhaps monitor those patients more closely. The 90-day window is of particular interest to hospitals because Medicare doesn\u2019t reimburse for readmissions within that timeframe.
\nDown the road, Paschalidis says, it might also be possible to use data from wearable technologies in addition to EHR data. The data is there, he says; it\u2019s just a matter of getting access to it.
\n\u201cWe carry these smartphones and now these smart watches and all of these fitness trackers and other devices that know much more than the hospital knows about our state of health,\u201d he says. \u201cYou now have a much richer record about the patient, and the richer the record is, the better prediction you can make.\u201d
\nThroughout his career, Paschalidis has put his data analysis skills to use in a lot of different areas. For the past three years, he\u2019s been applying those skills to developing sensor networks for \u201csmart cities.\u201d He says he thinks he\u2019ll be working in health care for a while.
\n\u201cI feel that health care is an important area,\u201d he says, \u201cand the contributions that you make are somehow more tangible in terms of the potential outcome.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"

Data scientist and physician team up to reduce preventable hospitalizations By Suzanne Jacobs, BU Research Big Data Meets Healthcare: Bill Adams, a physician and medical informatician, and Yannis Paschalidis, a data scientist and engineer, are working together to use data from electronic health records to reduce preventable hospitalizations and cut health care costs. Photo by […]<\/p>\n","protected":false},"author":1500,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[26],"tags":[],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/17119"}],"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\/1500"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/comments?post=17119"}],"version-history":[{"count":2,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/17119\/revisions"}],"predecessor-version":[{"id":33975,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/17119\/revisions\/33975"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/media?parent=17119"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/categories?post=17119"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/tags?post=17119"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}