Diagnosing Diabetes and Predicting Complications

Project Summary

Priya Sarkar (Computer Science), Lily Zerihun (Biology and Global Health), and Anqi Zhang (Biostatistics) spent ten weeks utilizing Duke Electronic Medical Record (EMR) data to identify subgroups of diabetic patients, and predict future complications associated with Type II Diabetes.

Themes and Categories
Year
2016

Project Results

The team utilized t-Distributed Stochastic Neighbor Embedding (t-SNE) for dimensionality reduction of prescribed medications, medical diagnoses, laboratory tests, and patient outcomes. They then performed K-means clustering to identify meaningful clusters of similar patients and explored the sources of similarities. The team also constructed and tested statistical models to predict 13 common complications in diabetic patients, and found high predictive accuracy for several such complications when leveraging the rich data available in EMR.

Project Video:

Download the Executive Summary (PDF)

Faculty Sponsor

Project Manager

  • Liz Lorenzi, Ph.D. Candidate, Statistics

"Data+ provided an invaluable opportunity to work with motivated, hard-working students on exciting and challenging data problems. I learned so much about working with others, communicating effectively, and managing students with a variety of backgrounds. Though each of my students had a different level of statistics and coding experience, they made mentoring so easy with their hard work and interest in the project, as well as the effective organization of the summer as a whole. It was a great experience that I highly recommend to other graduate students!" Liz Lorenzi, Ph.D. Candidate, Statistics

Participants

  • Lillian Zerihun, Duke University Biology & Global Health
  • Priya Sarkar, Duke University Computer Science
  • Anqi Zhang, Duke University Biostatistics

Disciplines Involved

  • Biostatistics
  • Public Health
  • All quantitative STEM

 

Related People

Related Projects

A team of students collaborating with Duke School of Medicine's Root Causes Fresh Produce Program, community members, and physicians throughout the Duke Health network will help integrate data from food deliveries to Duke Health patients with patient health record data and other available data sources to create a dashboard that can analyze, predict, and manage the Root Causes' "Food as Medicine" program. Specific outcomes will contribute to improving the Program's quantitative evaluation of its health impact as well as efficiency and satisfaction for its patients. Students will be assisted with IRB approval and mentorship from faculty and community advisors.

Project Leads: Esko Brummel, Willis Wong

 

A team of students led by researchers at the Duke Marine Lab will explore the changing distribution of krill around the Antarctic Peninsula. Krill are a key prey species in this ecosystem, supporting a number of animals including whales, seals, and penguins, but they are dependent on winter sea ice and may be in trouble as climate change progresses. Using data from acoustic zooplankton surveys, students will create maps and other products to visualize the spatial distribution of krill over the past 20 summers, then create metrics that allow us to quantify the way that krill distribution around the Antarctic Peninsula is changing as the climate shifts and ice melts. These results will be key to our understanding of the impacts of climate change on this polar ecosystem.

 

Project Lead: Douglas Nowacek

Project Manager: Amanda Lohmann

 

A team of students will partner closely with the City of Durham's newly formed Community Safety Department.  The Community Safety Department's mission is to identify, implement, and evaluate new approaches to enhance public safety that may not involve a law enforcement response or the criminal justice system. The student team will (1) analyze and identify geographic and temporal patterns in 911 calls for service, (2) conceptualize and build an abstracted data pipeline and tools that would enrich currently available 911 data with other social, economic, and health-related data, (3) explore associations between areas of high call volume, indicators of mental health distress, and histories of dispossession; and (4) identify methods by which future researchers could examine connections between varied 911 incident responses (e.g. police response, unarmed response, joint police, and mental health response) and life trajectories (e.g. arrest, jail time, hospitalization, unemployment, etc.).

 

Project Lead: Greg Herschlag, Anise Van, City of Durham

Project Manager: Deekshita Saikia