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

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


  • 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

Aaron Chai (Computer Sciece, Math) and Victoria Worsham (Economics, Math) spent ten weeks building tools to understand characteristics of successful oil and gas licenses in the North Sea. The team used data-scraping, merging, and OCR method to create a dataset containing license information and work obligations, and they also produced ArcGIS visualizations of license and well locations. They had the chance to consult frequently with analytics professionals at ExxonMobil.

Click here to read the Executive Summary


Project Lead: Kyle Bradbury

Project Manager: Artem Streltsov

Yueru Li (Math) and Jiacheng Fan (Economics, Finance) spent ten weeks investigating abnormal behavior by companies bidding for oil and gas rights in the Gulf of Mexico. Working with data provided by the Bureau of Ocean Energy Management and ExxonMobil, the team used outlier detection methods to automate the flagging of abnormal behavior, and then used statistical methods to examine various factors that might predict such behavior. They had the chance to consult frequently with analytics professionals at ExxonMobil.


Click here to read the Executive Summary


Project Lead: Kyle Bradbury

Project Manager: Hyeongyul Roh