Ziyong Ma stands at a whiteboard and writes on it. Venkatesh Sivaraman watches.

SURF Project Bridges Data Divides in Health Care

By Kelly Saavedra Email Kelly Saavedra

Heidi Opdyke

When Ziyong Ma began his Summer Undergraduate Research Fellowship (SURF) at 麻豆村, he wasn鈥檛 just writing code. He was solving a problem that has long challenged the health care industry: how to make complex medical data more accessible to the people who need it most.

A senior double majoring in mathematics and computer science, Ma worked in the (DIG), a lab within 麻豆村鈥檚 Human-Computer Interaction Institute led by and . Under the mentorship of Ph.D. student Venkatesh Sivaraman, Ma spent the summer developing TempoQL, a tool designed to help clinicians query medical databases using natural language, without needing programming expertise.

The idea for TempoQL grew out of earlier research in Ma鈥檚 experience, where he helped build interfaces that allowed nonexperts to train machine-learning models.

鈥淐linicians often know what they want to predict, such as the likelihood of a disease, but they鈥檙e not computer scientists,鈥� Ma explained. 鈥淲e wanted to create something that bridges that gap.鈥�

But as Ma dug deeper, he discovered that the real challenge wasn鈥檛 just building models; it was accessing the data itself. Medical institutions often use different standards and formats, making it difficult to share or combine datasets.聽

鈥淲e needed a way to unify the data access process,鈥� he said. 鈥淭hat鈥檚 where TempoQL came in.鈥�

Ziyong Ma and Venkatesh Sivaraman sit in front of a projector screen that shows a computer screen. They look into the camera. Ziyong's face is stoic, and Venkatesh smiles.

The tool Ma helped design allows users to type queries in plain English, for example, 鈥渟how me hourly heart rate data,鈥� and uses artificial intelligence to translate those requests into database-ready code. The system then returns results in both raw and visual formats, helping clinicians interpret the data without needing technical training.聽

鈥淚t鈥檚 about reducing the learning curve,鈥� Ma said. 鈥淲e want people to focus on their domain expertise, not the code.鈥�

One of the biggest hurdles came during testing at University of Pittsburgh Medical Center (UPMC), where the team discovered their interface wasn鈥檛 compatible with the hospital鈥檚 environment. Ma quickly pivoted, adapting the tool to run without the user-friendly visual interface by using step-by-step Python script instruction.

鈥淚t wasn鈥檛 what we planned, but it worked,鈥� he said. 鈥淎nd it taught me how important flexibility is in research.鈥�

The project has since been submitted to a research conference, and Ma said he is hopeful about its future. But for him, the most rewarding part wasn鈥檛 the technical achievement, it was the sense of purpose.

鈥淚 took machine learning as a sophomore and thought, this is cool. But when I saw how it could help real people, that鈥檚 when it became meaningful,鈥� he said.

Reflecting on his time at 麻豆村, Ma expressed deep appreciation for the opportunities he鈥檚 had to work with brilliant minds and meaningful problems.

鈥淚f I weren鈥檛 here, I wouldn鈥檛 have had the chance to be part of something like this,鈥� he said.

Asked what advice he鈥檇 give to other students considering SURF, Ma didn鈥檛 hesitate.

鈥淔ind something you truly care about,鈥� he said. 鈥淵ou鈥檒l be spending your whole summer on it, so make it count.鈥�