At Duke University, Jessilyn Dunn with PhD student Brinnae Bent who is preparing to download information from a wearable health monitoring device

Master's Certificate in Biomedical Data Science

Giving biomedical engineers a competitive edge in industry and academia

Biomedical engineering has become a prime discipline for applying data science techniques—and the job market for biomedical engineers with data science skills is expanding rapidly.

With its pioneering expertise and leadership in biomedical engineering, machine learning, signal and image processing, and biostatistics, Duke is the ideal place to learn how to translate biomedical data into actionable health insights.

By collaborating with and learning from leading researchers, students who earn a Biomedical Data Science Certificate can increase their competitiveness for positions in industry and doctoral programs.

Enrollment in the four-course Master's Certificate in Biomedical Data Science is open to all Duke Master of Engineering (MEng) and Master of Science (MS) students intending to pursue careers or enter doctoral programs relating to biomedical data science.


Requirements

  1. Complete all departmental requirements for a master's degree
  2. Complete at least four (4) of the approved courses relevant to data science. At least two (2) of these courses must be offered through Duke BME
  3. Complete a biomedical data science-relevant project and submit a two-page abstract and poster to the Biomedical Data Science Committee. The project could result from previous course projects, independent study, or a master's thesis. It must have a non-trivial technical novelty and demonstrate proficiency in developing novel methodologies or scientifically utilizing a broad range of advanced data science tools to solve impactful biomedical problems

Duke BME Faculty

Sina Farsiu

Sina Farsiu

Professor in the Department of Biomedical Engineering
Chair of the Biomedical Data Science Committee

Sina Farsiu focuses on medical imaging and machine learning to improve overall health and vision outcomes for patients with ocular and neurological diseases (e.g., age-related macular degeneration, diabetic retinopathy, Alzheimer's, and ALS) through earlier and more personalized therapy.   More »

Jessilyn Dunn

Jessilyn Dunn

Assistant Professor of Biomedical Engineering

Jessilyn Dunn develops new tools and infrastructure for multimodal biomedical data integration to drive precision/personalized methods for early detection, intervention and prevention of disease. More »

Timothy Dunn

Timothy Dunn

Assistant Professor of Biomedical Engineering

Timothy Dunn and his team develop novel 3D behavior-tracking technologies to track and model animal movement more precisely to decipher neuronal activity better.   More »

Roarke Horstmeyer

Roarke Horstmeyer

Assistant Professor of Biomedical Engineering

Roarke Horstmeyer's work involves the development of new microscopes, cameras and computer algorithms to create better biomedical images.   More »

Daniel Reker

Daniel Reker

Assistant Professor in Biomedical Engineering

 Daniel Reker uses active machine learning to analyze and design new drug therapies against cancer and infectious diseases. More »


Courses

Courses for this master's certificate are offered by departments and programs within Duke's Pratt School of Engineering, School of Medicine, and Trinity College of Arts & Sciences.

Click for course lists and department website links. Be sure to review the Important Notes.

Biomedical Engineering

bme.duke.edu »

  • BME 590D: Deep Learning App HealthCare
  • BME 548L: Machine Learning and Imaging
  • BME 590L: Computational Foundations for Biomedical Simulations
  • BME 671L: Signal Processing and Applied Mathematics
  • BME/B&B 590: Intro Biomedical Data Science
  • BME 590: Machine Learning in Pharmacology
  • BME 544: Digital Image Processing
  • BME 503: Computational Neuroengineering
  • BME 574: Modeling and Engineering Gene Circuits
  • BME 590: Data Science and Health
  • EGR 590-06: AI for Everyone
  • BME 590: Deep Neural Network Models of the Nervous System
  • BME 790L: Linear Algebra

Biostatistics and Bioinformatics

biostat.duke.edu »
  • BIOSTAT 824: Case Studies in Biomedical Data Science
  • BIOSTAT 707: Statistical Methods for Learning and Discovery

Civil & Environmental Engineering

cee.duke.edu »
  • CEE 690-05: Health and Environmental Data Science

Computational Biology & Bioinformatics

genome.duke.edu/education/cbb »
  • CBB 540: Statistical Methods for Computational Biology
  • CBB 561, 662 or 663: Algorithms in Computational Biology

Computer Science

cs.duke.edu »
  • COMPSCI 527: Introduction to Computer Vision
  • COMPSCI 671D: Theory and Algorithms for Machine Learning

Electrical & Computer Engineering

ece.duke.edu »
  • ECE 685D: Introduction to Deep Learning
  • ECE 590: Advanced Deep Learning
  • ECE 590: Computer Engineering ML and Deep Neural Nets
  • ECE 590: Wearable and Ubiquitous Computing
  • ECE 588: Image & Video Processing

Important Notes

Course Content Overlap

Some of the courses listed above have a significant overlap. Thus, only one (1) course from each of the following course groups will be counted among the four (4) courses required for this certificate:

  • Group 1: BME 544, ECE 588
  • Group 2: BME/B&B 590 (Intro Biomedical Data Science), BIOSTAT 707 (Statistical Methods for Learning and Discovery), CBB540: Statistical Methods for Computational Biology
  • Group 3: BME 590: Data Science and Health, EGR 590-06: AI for Everyone and CEE690-05: Health and Environmental Data Science
  • Group 4: CBB 561, CBB 662 and CBB 663

Enrollment Prerequisites

There is no list of universal course prerequisites for this program. Instead, each instructor sets the prerequisites for enrollment in each course.

Before enrolling in a course, students are highly encouraged to contact the instructor to:

  • Learn the prerequisites for the course, including the required programming language background
  • Obtain and carefully review the course syllabus

Suggested Course Schedules

Because data science is so diverse, there is no mandate for a fixed course schedule. Click to see suggested schedules.

Data Science in Imaging and Image Analysis

Semester 1 Semester 2 Semester 3

BME/B&B 590: Intro Biomedical Data Science or ECE 685D: Introduction to Deep Learning

BME 544: Digital Image Processing, or COMPSCI 527: Introduction to Computer Vision BME 548L: Machine Learning and Imaging
    BME 590D: Deep Learning App HealthCare

Data Science in Pharmacology

Semester 1 Semester 2 Semester 3

BME/B&B 590: Intro Biomedical Data Science

CBB 662A: Algorithms in Structural Biology & Biophysics BME 590L: Machine Learning in Pharmacology
  BME 574: Modeling and Engineering Gene Circuits  

Data Science Theory

Semester 1 Semester 2 Semester 3

BME/B&B 590: Intro Biomedical Data Science, or ECE 685D: Introduction to Deep Learning

COMPSCI 671D: Theory and Algorithms for Machine Learning BME 590L: Computational Foundations for Biomedical Simulations
     ECE 590: Advanced Deep Learning

How to Apply

Enrollment is open to all Duke Master of Engineering (MEng) and Master of Science (MS) students intending to pursue careers or enter doctoral programs relating to biomedical data science.

  • Registration deadlines are July 1 for Fall graduation and November 1 for Spring graduation
  • To register, submit a Letter of Interest via email to the certificate program coordinator declaring your interest in the Biomedical Data Science Master's Certificate
  • The committee will communicate the date for submission/presentation of the biomedical data science-relevant project and the coursework checklist