Skip to main content

Home

 

Find us on

facebook youtube flickr twitter itunes u logo

Upcoming Events

Sal Stolfo

Salvatore J. Stolfo Columbia University
A Brief History of Symbiote DefenseTuesday, October 31st
Rockefeller 003
5:00 PM

 Fright Night Imge

Wanna See Something REALLY Scary?
ISTS Looks at the Dark Web on Halloween Night
Tuesday, October 31st
Sudikoff  045 Trust Lab (dungeon)
7:30 PM - RSVP
Space is Limited 

   

Recent Talks

Dan Wallach

STAR-Vote: A Secure, Transparent, Auditable and Reliable Voting System

Professor Dan Wallach
Rice University
Thursday April 27, 2017
Carson L01, 5:00 PM

Ben Miller Dragos

Pandora's Power Grid - What Can State Attacks Do and What Would be the Impact?

Ben Miller
Chief Threat Officer, Dragos, Inc.
Tuesday May 2, 2017
Kemeny 007, 4:30 PM
Brendan Nyhan

 

 

 

Factual Echo Chambers? Fact-checking and Fake News in Election 2016.

Professor Brendan Nyhan
Dartmouth College
Thursday May 4, 2017
Rocky 001, 5:00 PM

Dickie George

 

Espionage and Intelligence

Professor Dickie George
Johns Hopkins University
Thursday May 11, 2017
Rocky 001, 5:00 PM

Dan Wallach

A Nation Under Attack: Advanced Cyber-Attacks in Ukraine

Ukrainian Cybersecurity Researchers
Thursday April 6, 2017
Oopik Auditorium 5:30 PM

ISTS Information Pamphlet


2012BrochureCover

 

Institute for Security, Technology, and Society
Dartmouth College
6211 Sudikoff Laboratory
Hanover, NH 03755 USA
info.ists@dartmouth.edu
HomeEvents >

Leveraging Data Across Time and Space to Build Predictive Models for Healthcare-Associated Infections

Friday, October 31, 2014 at 1:45pm
Steele 006
Jenna Wiens
Assistant Professor, EECS Department, The University of Michigan
Co-sponsored by the Trustworthy Health and Wellness project (thaw.org) and ISTS

Abstract

Jenna Weins
Jenna Weins

The proliferation of electronic medical records holds out the promise of using machine learning and data mining to build models that will help healthcare providers improve patient outcomes. However, building useful models from these datasets presents many technical problems. The task is made challenging by the large number of factors, both intrinsic and extrinsic, influencing a patient's risk of an adverse outcome, the inherent evolution of that risk over time, and the relative rarity of adverse outcomes.

In this talk, I will describe the development and validation of hospital-specific models for predicting healthcare-associated infections (HAIs), one of the top-ten contributors to death in the US. I will show how by adapting techniques from time-series classification, transfer learning and multi-task learning one can learn a more accurate model for patient risk stratification for the HAI Clostridium difficile (C. diff).

Applied to a held-out validation set of 25,000 patient admissions, our model achieved an area under the receiver operating characteristic curve of 0.81 (95%CI 0.78-0.84). On average, we can identify high-risk patients five days in advance of a positive test result. Clinicians at the hospital are now considering ways in which that information can be used to reduce the incidence of HAIs.

Bio

I am an Assistant Professor in EECS at the University of Michigan. In the fall of 2014, I joined the CSE division after completing my PhD at MIT.

My primary research interests lie at the intersection of machine learning and medicine. I especially enjoy solving the technical challenges that arise when considering the practical application of machine learning in clinical settings. Currently, I'm focused on developing accurate patient risk stratification approaches that leverage data across time and space, with the ultimate goal of reducing the rate of healthcare-associated infections among patients admitted to hospitals in the US.

In addition to this work, I've had the privilege of working with a unique dataset from the NBA. Recently, I've had a lot of fun applying many of the same techniques we use in the medical work to the world of sports analytics. In general, I enjoy tackling the challenges that develop when working with large complex datasets.

Last Updated: 10/13/14