Sihang Zeng

PhD, Biomedical Informatics and Medical Education

University of Washington

• Dissertation: “Towards Trustworthy Modeling of Patient Trajectory with Longitudinal Electronic Health Records” — interpretable and generalizable frameworks for patient trajectory modeling
• Committee: Ruth Etzioni (co-chair), Meliha Yetisgen (co-chair), Matthew Thompson, Hoifung Poon, Noemi Kreif
• Degree conferred June 2026

BEng, Electronic Engineering — minor in Statistics

Tsinghua University

• Research on biomedical term representation and algorithmic knowledge graph construction

Postdoctoral Research Fellow

Department of Biomedical Informatics, Harvard Medical School

Working with Tianxi Cai on patient trajectory modeling over longitudinal EHR and on computational drug repurposing from multi-modal clinical and biological data.

Machine Learning Intern

Truveta

Patient-journey foundation models and multi-agent risk prediction over large-scale de-identified clinical data, with results presented at ASCO and ISPOR.

Graduate Research Assistant

University of Washington and Fred Hutchinson Cancer Center

Trajectory modeling for cancer early detection and survival prediction in the Etzioni Lab and UW BioNLP.

Undergraduate Researcher

Tsinghua University

Biomedical term representation learning and construction of the BIOS knowledge graph with Sheng Yu; language models for scientific and biomedical reasoning with Bowen Zhou.

1st place, ChemoTimelines 2025 shared task (subtask 2)

Clinical NLP Workshop, ACL — best official score of 0.678

Spotlight, NeurIPS Datasets and Benchmarks Track

UltraMedical: building specialized generalists in biomedicine