In Public Health, Grad Students Learn How AI Can Be Research Rx

Huang (Frederick) Lin knows firsthand how artificial intelligence (AI) can support advances in public health: The assistant professor of biostatistics and epidemiology uses a variant known as machine learning daily in his own research analyzing the trillions of microbes living in our guts, looking for those that contribute to major diseases such as inflammatory bowel disease, HIV/AIDS and various cancers. Instead of arduously hand-programming every parameter of investigation, the system can discern patterns and draw inferences that the human brain likely wouldn’t spot without algorithmic help.

This semester, he’s been sharing these methods with students in the first machine-learning class offered in the University of Maryland School of Public Health.

Housed in SPH, the class is open to all UMD graduate students. It will be offered again in Spring 2026, after a pilot phase for evaluation, student feedback and fine-tuning. The class is part of one of SPH’s newest degrees, the doctorate in biostatistics.

“Machine-learning classes are everywhere now, but I want to give students a specific perspective. Once they learn theoretical foundations, they look at how to adapt these methods specifically to public health projects, applying machine learning to analyze health-related data,” said Lin.

Machine learning allows researchers to rapidly analyze large datasets, process complex data with multiple variables and create predictive models to inform real-world decision-making – processing far beyond what the human brain or traditional statistical methods can achieve.

Ria Warrier, graduating this spring with an MPH, with a concentration in epidemiology, said entering the job market with knowledge of AI and public health will help her stand out. She also appreciates Lin’s approach.

“I’ve never touched on machine learning nor have I taken an intensive computer science class,” Warrier said. “Professor Lin’s class was easier for me to digest because the material was taught in a public health framework.”

Rong Pan, a first-year biostatistics Ph.D. student, is excited to gain the skills she needs to analyze huge datasets relating to her subject area: bioinformatics.

“My research is mainly focused on developing statistical and computational methods for genetics and epigenetics data, and so it is clearly linked to AI. And in this class, I get to learn hands-on coding using AI,” she said.

Lin believes this new class will prepare students as they head into careers in public health, where employers are often on the lookout for machine-learning experience.

“I hope this course will benefit students beyond those studying biostatistics. And I also would love in the future to see us offer more advanced machine-learning courses in public health, for example, deep learning in health and biomedicine and AI for health equity and ethics.”