Classification of Vascular Anomalies using Continuous Doppler Ultrasound and Machine Learning

Project Summary

Over ten weeks, BME and ECE majors Serge Assaad and Mark Chen joined forces with Mechanical Engineering Masters student Guangshen Ma to automate the diagnosis of vascular anomalies from Doppler Ultrasound data, with goals of improving diagnostic accuracy and reducing physician time spent on simple diagnoses. They worked closely with Duke Surgeon Dr. Leila Mureebe and Civil and Environmental Engineering Professor Wilkins Aquino.

Themes and Categories
Year
2017
Contact
Ashlee Valente
Duke Center for Applied Genomics & Precision Medicine
ashlee.valente@duke.edu

Project Results: Working with a Duke Hospital dataset of 5 Doppler ultrasound recordings taken from each of 38 patients, the team used machine-learning to predict whether or not a patient was healthy from the recordings. They extracted features from the recordings using a variety of tools from signal processing, visualized the separation of healthy and unhealthy patients in this feature space, and built a competitive classifier using standard supervised-learning tools. They had the opportunity to present their findings to Duke's Provost and to senior leadership within Duke Hospital and the Duke Clinical Research Institute.

Faculty Leads: Wilkins AquinoLeila Mureebe

Project Manager: Kyle Burris

Click here for the Executive Summary

"Participating in Data+ definitely changed my perception of Data Science research. It was more interdisciplinary than I expected, and the opportunity to work with experts across different fields (Medicine, Civil Engineering, Statistics) was a defining aspect of my Data+ experience." - Serge Assad, Biomedical Engineering, Electrical & Computer Engineering

"The project mentor was fantastic. The three students I worked with were superb. We were able to make great progress that will lead to journal publications and grant proposals." — Wilkins Aquino, Professor in the Department of Civil and Environmental Engineering. Pratt School of Engineering

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.

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)?