<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
<div style="margin: 0in 0in 0.0001pt;" class="">The next Mobilize Center Seminar is scheduled for TODAY, Thursday, October 27, and will feature
<b class="">Jonathan Chen</b> from the Department of Medicine at Stanford Medicine. We look forward to seeing you!</div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class=""> <span class=""><br class="">
<b class="">TITLE:</b></span><b class=""> <span class="apple-tab-span"><o:p class=""></o:p></span></b></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class="">
<div style="margin: 0in 0in 0.0001pt;" class=""><u class=""><b class="">Wisdom of the Crowd or Tyranny of the Mob?</b></u></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><u class=""><b class="">Data-Mining Electronic Health Records for Clinical Decision Support</b></u></div>
</div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class=""> <br class="">
<b class=""><span class="">WHEN:</span> <span class="apple-tab-span"><o:p class=""></o:p></span></b></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class=""><span class=""><b class="">Thursday, October 27</b></span></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class=""><b class=""><span class="">noon - 1 pm</span> </b><br class="">
<br class="">
<b class=""><span class="">WHERE:</span> <span class="apple-tab-span"><o:p class=""></o:p></span></b></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class=""><span class=""><b class=""><span class="">Y2E2 300, Stanford University</span><span style="color: rgb(255, 38, 0);" class=""> </span></b></span><br class="">
<br class="">
<span class=""><b class="">Abstract:</b></span><o:p class=""></o:p></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class="">Medical decision making is fraught with both uncertainty and undesirable variability. The vast majority of our clinical decisions lack adequate evidence to determine their efficacy and inconsistent implementation
compromises quality and efficiency.</div>
<p class="MsoNormal" style="margin: 0in 0in 0.0001pt;"> </p>
<div style="margin: 0in 0in 0.0001pt;" class="">The current standards in clinical decision support reinforce best-practices but are limited in scalability by manual production. “Grand challenges” thus include mining clinical data sources to automatically generate
decision support content.</div>
<p class="MsoNormal" style="margin: 0in 0in 0.0001pt;"> </p>
<div style="margin: 0in 0in 0.0001pt;" class="">Statistical approaches allow us to learn patterns that reflect real-world standards of care vs. outliers. A current focus is developing systems to empower individual clinicians with the collective experience of
the many.</div>
<p class="MsoNormal" style="margin: 0in 0in 0.0001pt;"> </p>
<div style="margin: 0in 0in 0.0001pt;" class="">I will review my efforts developing a collaborative filtering machine-learning approach to clinical order entry, analogous to Netflix or <a href="http://amazon.com" style="color: rgb(149, 79, 114);" class="">Amazon.com</a>’s
“Customer’s who bought A also bought B” algorithm. This automatically generated decision support content can reproduce, and even optimize, manual constructs like order sets while remaining largely concordant with guidelines and avoiding inappropriate recommendations.
This has even more important implications for prevalent cases where well-defined guidelines do not exist. The same methodology is predictive of clinical outcomes comparable to state-of-the-art risk prediction models. Embedded randomization of such decision
support interventions could then allow us to explicitly build knowledge for the future, even as we enhance care today, in a closed-loop learning health system..</div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class=""> <span style="text-align: justify; text-indent: 0.5in;" class=""> </span></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class=""><span class=""><b class="">Bio:</b></span><o:p class=""></o:p></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class="">
<div style="margin: 0in 0in 0.0001pt;" class="">Jonathan H. Chen MD, PhD is an Instructor in the Stanford Department of Medicine. He is a practicing physician with research interests focused on data-mining electronic medical records for insights to inform medical
decision making.</div>
<p class="MsoNormal" style="margin: 0in 0in 0.0001pt;"> </p>
<div style="margin: 0in 0in 0.0001pt;" class="">Chen co-founded a company to translate his Computer Science graduate work into an expert system to solve organic chemistry problems, with applications from drug discovery to a practical education tool distributed
to students across the world. To gain first-hand perspective in tackling the greater societal problems in health care, he completed medical training in Internal Medicine and a VA Research Fellowship in Medical Informatics.</div>
<p class="MsoNormal" style="margin: 0in 0in 0.0001pt;"> </p>
<div style="margin: 0in 0in 0.0001pt;" class="">A current focus is automated generation of personalized decision support content. With the support of an NIH Big Data 2 Knowledge K01 Career Development Award, he is developing this approach to systematically
extract and disseminate the undocumented collective wisdom of practicing clinicians. This will translate endpoint clinical data into a reproducible and executable form of expertise and, deploying this right at the point-of-care, will close the loop of a continuously
learning health system.</div>
<div style="margin: 0in 0in 0.0001pt;" class=""><a href="http://web.stanford.edu/~jonc101" style="color: rgb(149, 79, 114);" class="">http://web.stanford.edu/~jonc101</a></div>
</div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class=""> <o:p class=""></o:p></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class=""><font class="">Please see<span style="color: rgb(56, 110, 255);" class=""> </span><a href="http://mobilize.stanford.edu/events/" style="color: purple;" class="">Mobilize Events</a> for a list of
upcoming speakers.<o:p class=""></o:p></font></span></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><o:p class=""><font class=""> </font></o:p></div>
<div class="">
<div class=""><span class=""><font class="">Diane Bush<br class="">
Assistant to Professor Scott Delp<br class="">
NMBL, Mobilize Center, OpenSim<br class="">
Stanford University<br class="">
<a href="mailto:dbush1@stanford.edu" class="">dbush1@stanford.edu</a><br class="">
</font></span></div>
</div>
<br class="">
</body>
</html>