Matthew McDermott, Xuhai "Orson" Xu
Excited To Join DBMI Faculty In 2025

Matthew McDermott, PhD, and Xuhai “Orson” Xu, PhD, will both join the Columbia University Department of Biomedical Informatics faculty in 2025 to enhance both the research and training at one of the nation’s oldest biomedical informatics departments. McDermott focuses his research in representation learning and foundation models over medical data, while Xu’s research straddles multiple disciplines, including human-computer interaction, ubiquitous computing, artificial intelligence, and health.

McDermott received his PhD in Computer Science from MIT, studying representation learning for health and biomedicine with Professor Pete Szolovits. Subsequently, as a Berkowitz Postdoctoral Fellow at Harvard Medical School in Professor Zak Kohane’s lab, he built high-capacity “foundation models” and other representation learning systems over EHR data. Some of his key prior works include Clinical BERT, one of the most widely used pre-trained clinical language models; Structure-inducing Pre-training, a framework for pre-training that enables incorporating domain-specific external knowledge with provable guarantees; and multiple software packages for performing machine learning at scale over structured EHR data, including the recent ESGPT package and MEDS framework.

Prior to his graduate studies, McDermott earned his undergraduate degree in mathematics at Harvey Mudd College, then worked as a software engineer at Google and as a co-founder of Guesstimate before his time at MIT. In addition to research, McDermott is also a leader in the machine learning for healthcare community at large, having served as a board member for the non-profit the Association for Health, Learning, and Inference (AHLI) since its inception and taking on numerous leadership roles for notable events such as the Machine Learning for Health (ML4H) Symposium, including general chair in 2021, and the Conference on Health, Inference, and Learning (CHIL), including as general chair in both 2024 and in the upcoming 2025 conference.

“I don’t think there is anywhere better positioned today than Columbia DBMI to lead the medical foundation model revolution,” said McDermott, who will join DBMI in July 2025. “I couldn’t be more pleased to work with the fantastic faculty there to realize the tremendous benefits machine learning can offer to patients and biomedical scientists everywhere.”

Xu, currently a postdoc at the MIT Department of Electrical Engineering and Computer Science, has served as a visiting faculty researcher at Google Health. He earned his PhD degree in Information Science at the University of Washington and his bachelor’s degree in Industrial Engineering and Computer Science at Tsinghua University.

Using everyday sensor data and health records, Xu develops deployable behavior modeling algorithms to monitor various health and well-being conditions. Leveraging these models, he further designs and deploys intelligent intervention and interaction techniques that help end-users and patients achieve personal health and well-being goals, as well as support health experts in making decisions.

Xu has earned several awards, including 10 Best Paper, Best Paper Honorable Mention, and Best Artifact awards. His research has been covered by media outlets such as The Washington Post, Communication of ACM, and ACM News. He was recognized as the Gaetano Borriello Outstanding Student Award Winner at UbiComp 2022 and the UW Distinguished Dissertation Award in 2023.

“I can’t think of a better place in the world that bridges human-centered computing and health applications so well,” said Xu, who will join DBMI in January 2025. “Columbia DBMI offers the ideal environment to transform my research into tangible, real-world impacts in health & medical domains. I cannot wait to work with the amazing faculty there.”

McDermott and Xu will join a department that has produced academic and industrial leaders throughout the field. An information partner to NewYork-Presbyterian Hospital, a major healthcare provider in greater New York City, DBMI is comprised of world-class faculty and collaborative research opportunities with top leaders throughout Columbia University and other renowned medical centers, and it has a research mission of producing theoretical and practical advances in AI, data science, and human computer interaction, which will lead to better health and new biomedical knowledge.