BIOSTAT 826
Deep Learning for Health Data
Matt Morrow Engelhard
Description from DukeHub
This course explores deep learning methods and their application to multi-modal and longitudinal health data. Students will learn to design, implement, and evaluate deep neural network architectures for tasks such as medical image analysis, natural language processing of clinical texts, and predictive modeling of patient outcomes from electronic health records. Emphasis is placed on selecting an approach and evaluation strategy that fit the healthcare context. By the end of the course, students will be equipped to develop advanced deep learning models to solve real-world healthcare challenges. Prerequisite(s): BIOSTAT 707 or similar class. Non-program students require permission from the director of graduate studies or instructor. Instructor: Matt Engelhard. Credits: 3
Skills
- data and statisticsdepartment: BIOSTAT
- ai and machine learningdescription: "deep learning" and 2 more
- clinicaldescription: "clinical" and 1 more
- programmingAI review: "design, implement, and evaluate deep neural network architectures"
AI-resilient: 2 of 5
- No: Physical, lab or field work
- Yes: Live work with people · "clinical"
- Yes: Judgment someone is accountable for · "strategy"
- No: A craft you practice with your hands or body
- No: Small, in-person format
The checks lean on Microsoft Research, Working with AI (2025), which found generative AI applies least to physical work and hands-on work with people. A signal, not a promise. How the score works
More in BIOSTAT
- Introduction to Statistical Theory and Methods II BIOSTAT 704
- Applied Biostatistical Methods II BIOSTAT 705
- Introduction to the Practice of Biostatistics II BIOSTAT 706
- Clinical Trial Design and Analysis BIOSTAT 708
- Introduction to Causal Inference BIOSTAT 709
- Analysis of Correlated and Longitudinal Data BIOSTAT 718