Validating a Topic Model that Predicts Pancreatic Cancer from Latent Structures in the Electronic Medical Record

Project Summary

Furthering the work of a 2016 Data+ team in predictive modeling of pancreatic cancer from electronic medical record (EMR) data, students Siwei Zhang (Masters Biostatistics) and Jake Ukleja (Computer Science) spent ten weeks building a model to predict pancreatic cancer from Electronic Medical Records (EMR) data. They worked with nine years worth of EMR data, including ICD9 diagnostic codes, that contained records from over 200,000 patients.

Themes and Categories
Year
2017
Contact
Paul Benich
bendich@math.duke.edu

Project Results: The team began with exploratory data analysis that illustrated median times of appearance and frequency of specific ICD9 codes, with an eye toward understanding the relation between these statistics and pancreatic cancer diagnosis. They then trained a topic model which predicted past pancreatic cancer diagnosis with high accuracy (93 percent AUC) from ICD9 codes. Finally, they used the topic model outcomes to identify a pool of high-risk patients for potential future study.

Click here for the Executive Summary

Project Leads:

Lisa Satterwhite, PhD

James Abbruzzese, MD

Joseph Lucas, PhD

Project Manager: Tyler Massaro

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