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

"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

Social and environmental contexts are increasingly recognized as factors that impact health outcomes of patients. This team will have the opportunity to collaborate directly with clinicians and medical data in a real-world setting. They will examine the association between social determinants with risk prediction for hospital admissions, and to assess whether social determinants bias that risk in a systematic way. Applied methods will include machine learning, risk prediction, and assessment of bias. This Data+ project is sponsored by the Forge, Duke's center for actionable data science.

Project Leads: Shelly Rusincovitch, Ricardo Henao, Azalea Kim

Project Manager: Austin Talbot

Producing oil and gas in the North Sea, off the coast of the United Kingdom, requires a lease to extract resources from beneath the ocean floor and companies bid for those rights. This team will consult with professionals at ExxonMobil to understand why these leases are acquired and who benefits. This requires historical data on bid history to investigate what leads to an increase in the number of (a) leases acquired and (b) companies participating in auctions. The goal of this team is to create a well-structured dataset based on company bid history from the U.K. Oil and Gas Authority; data which will come from many different file structures and formats (tabular, pdf, etc.). The team will curate these data to create a single, tabular database of U.K. bid history and work programs.

Project Lead: Kyle Bradbury

Project Manager: Artem Streltsov

Producing oil and gas in the Gulf of Mexico requires rights to extract these resources from beneath the ocean floor and companies bid into the market for those rights. The top bids are sometimes significantly larger than the next highest bids, but it’s not always clear why this differential exists and some companies seemingly overbid by large margins. This team will consult with professionals at ExxonMobil to curate and analyze historical bid data from the Bureau of Ocean Energy Management that contains information on company bid history, infrastructure, wells, and seismic survey data as well as data from the companies themselves and geopolitical events. The stretch goal of the team will be to see if they can uncover the rationale behind historic bidding patterns. What do the highest bidders know that other bidders do not (if anything)? What characteristics might incentivize overbidding to minimize the risk of losing the right to produce (i.e. ambiguity aversion)?

Project Lead: Kyle Bradbury

Project Manager: Hyeongyul Roh