BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Mobile Apps and Machine Learning for Improving Healthcare - Kather
 ine Heller (Duke University)
DTSTART:20170706T084500Z
DTEND:20170706T093000Z
UID:TALK73173@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span>The first part of this talk centers on the analysis of s
 tudent influenza data. Students in dormitories at the University of Michig
 an were given smartphones with mobile a mobile app\, called iEpi\, that ca
 ptured data about their locations\, interactions\, and disease symptoms. W
 e develop Graph-coupled Hidden Markov Models (GCHMMs) which use this data 
 to predict whether a student was likely to fall ill due to their interacti
 ons. Using a hierarchical version of GCHMMs we can combine with demographi
 c data and see that certain characteristics\, such as drinking\, and poor 
 sleep quality\, increased the likelihood of contracting influenza\, as wel
 l as recovery time.<br><br>The second part discusses the development of a 
 new mobile app\, MS Mosaic\, for tracking symptoms in multiple sclerosis (
 MS) patients. The app includes data in the form of daily surveys\, fitness
  tracker information\, and mobile phone task data. The daily surveys about
  symptoms and medications can potentially be completed with a single notif
 ication swipe\, sleep and activity data can be collected passively using H
 ealthKit\, and mobile phone tasks include finger tapping\, gait analysis\,
  as well as additional cognitive and motor tasks. Data collected provides 
 an opportunity for the development of novel machine learning methods for l
 earning about chronic disease\, and novel sensor types. The app will soon 
 be released to the Apple app store\, and piloted in clinic at Duke Univers
 ity.<br></span><br><span>If time remains we will briefly look at some of t
 he other healthcare work on using Gaussian Process models on EHR data\, go
 ing on currently at Duke.<br><br>Coauthors: Kai Fan\, Allison Aiello\, Lee
  Hartsell\, Joe Futoma\, and Sanjay Hariharan</span>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR