Artificial Intelligence Applications for Health Data

Designed for professionals keen to harness the power of contemporary AI technologies

Artificial Intelligence is fundamentally changing how the world operates. There is probably no sector or discipline, from agriculture and finance to humanities and autonomous driving, that has not used AI. Professionals with AI skills are highly sought-after; the US Bureau of Labor Statistics predicts the demand to increase by 28% or 11.5 million new jobs through 2026, outpacing all other industries. One of AI’s undisputable advantages over most other technologies is its high transferability, significantly lowering industry-specific barriers to its applications.

The Advanced Learning Certificate in Artificial Intelligence Applications for Health Data is designed for professionals interested in contemporary AI technologies and seeking to build skills with AI’s applications to health or other “big data” for their work or research. This program is designed to take you from an AI novice to a confident practitioner with integrated case studies and programming demonstrations using Google Colab. It will provide hands-on, step-by-step guidance, and ample real-world practice opportunities for professionals to learn and apply AI tools and models to solve real-world health and social problems.

Program details and prerequisites are listed below.

Is this program for me?

This program is intended for individuals who have a demonstrated interest in increasing their skills in applying the power of AI techniques to health data for research or industry purposes. You do not have to be an alum of the Brown School to apply for consideration.

This is an online program, with scheduled class meetings on Thursday mornings conducted by Zoom and self-paced content, such as readings and assignments.  Applicants should be prepared to commit 5 hours of total effort per week. Reading assignments come from provided texts, which are included in the program fee.

The program presupposes a basic knowledge of statistics and previous experience working with a statistical software package. Students should have passed an introductory statistics class and have experience with R, SAS, SPSS, or Stata, or otherwise using basic quantitative skills within the last five years. Experience with Python is helpful but not required.

The certificate program is divided into three parts, building from basic tools to more advanced applications:

  • Weeks 1-2 – Participants will receive an overview of artificial intelligence, unveil the mystery of AI and machine learning, learn to code in Python, use NumPy and Pandas to master data wrangling, and use Matplotlib for data visualization.
  • Weeks 3-7 – Class content will focus on machine learning applications. We will learn topics including classification and regression, model training and validation, support vector machines, decision trees, ensemble methods like Random Forest and XGBoost, dimensionality reduction, unsupervised learning, and auto ML.
  • Weeks 8-15 – The final portion of the program considers deep learning applications (i.e., neural networks). Topics covered include a foundation with neural networks; computer vision for image classification, object detection, image segmentation, and image generation; natural language processing for text classification (sentiment analysis), language generation, text translation, chatbot, and prompt engineering; introduction to recommender systems; introduction to time series forecasting; and creating synthetic data for research and analysis.

Weekly assignments will help participants master the topics covered in the lectures/labs using real-world datasets related to health and beyond.

By the end of the program, participants will:

  • Gain a deep understanding of the key concepts and elements of AI, machine learning, and deep learning (neural networks)
  • Be familiar with a comprehensive pool of popular, state-of-the-art AI models and their applications in public health and beyond
  • Understand the strengths, limitations, and tradeoffs of different AI models and best practices in implementing them
  • Understand sources of data biases, principles of data ethics, and how to avoid or reduce biases to build ethical, responsible AI models
  • Be proficient using Python in conjunction with popular APIs and cloud platforms to implement state-of-the-art AI models on various data types
  • Be able to apply AI models to better understand and address health data-related concerns or other social problems

Successful completion of the certificate program includes attendance and participation in weekly class meetings, as well as completion of weekly-oriented application assignments.

​How to Apply

Complete program applications include:

  • Submission of your current resume and applicant information
  • Educational history – a transcript is not required

Admissions decisions will be made on a rolling basis. Generally it is possible to provide an admissions decision within two weeks of receipt of a completed application. Once your application is reviewed and approved, you will receive an acceptance email with further instructions on how to enroll online. Keep track of your application status in your profile under My Applications.

Admission prerequisites:

  • Applicants should have (or be able to obtain) access to a computer, along with a webcam and reliable internet service.
  • Introductory knowledge of statistics, including working with a statistical software package such as R, SAS, SPSS, Stata, or equivalent.​​
  • All students must be willing to comply with Washington University policies.
  • Please note that pursuing the AI Certificate course while on OPT (Optional Practical Training) is not permitted. For questions, email us at browncertificates@wustl.edu or through WeChat (ID: WUSTLBrownSchool).

More Info

Meet Your Instructor

Ruopeng An

Ruopeng An, PhD, MPP, FACE
Associate Professor, Brown School

Professor Ruopeng An is the Faculty Lead of Brown School’s PhD Program in Public Health Sciences. He hosts the “Artificial Intelligence in the Social Sciences” Open Classroom series, teaches Applied Machine Learning Using Python and Applied Deep Learning Using Python courses, and founded the Artificial Intelligence and Big Data Analytics for Public Health (AIBDA) Certificate program. With over 200 peer-reviewed journal publications, Dr. An is recognized as one of Elsevier’s top 2% most cited scientists. His work has been highlighted by various media outlets, including TIME, New York Times, Los Angeles Times, Washington Post, Reuters, USA Today, Bloomberg, Forbes, Atlantic, Guardian, FOX, NPR, and CNN. He serves on various research grants and expert panels for NIH, CDC, NSF, HHS, and the French National Research Agency. He was elected as a Fellow of the American College of Epidemiology in 2018. Professor An has repeatedly been recognized for teaching excellence, receiving student evaluations in the top 10% of University faculty.

Join Professor Ruopeng An for an introductory glimpse into the Artificial Intelligence Applications for Health Data Certificate program.

AI

“”I am excited to have a new toolbox with AI to think about my patients and their care. Thank you for this training and guidance.””

–David Molter, MD​ Professor of Pediatric Otolaryngology AI Certificate Alum 22′

Brown School Professional Development
One Brookings Drive, MSC 1196-251-46, St. Louis, MO 63130
(314) 935-7573 | brownprofdev@wustl.edu

ABOUT US | DIRECTIONS | FAQ’s | JOIN EMAIL LIST | POLICIES