In Gim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
In Gim has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Lin Zhong
Yale University, New Haven, USA
2 shared publications - Aaron Y. Lee
John F. Hardesty M.D. Department of Ophthalmology and Visual Sciences, Washington University in St Louis School of Medicine, St. Louis MO
1 shared publication - Cecilia Sungmin Lee
John F. Hardesty MD Department of Ophthalmology and Visual Sciences, Washington University in St. Louis, St. Louis, MO, USA
1 shared publication - Marian Blazes
University of Washington
1 shared publication Nayoon Gim
University of Washington
1 shared publication- Seung-Seob Lee
Yale University, New Haven, USA
1 shared publication
Latest Publications
- Open Access
An LLM-assisted framework for accelerated and verifiable clinical hypothesis testing from electronic health records
Acquiring insights from electronic health records (EHRs) is slowed by manual analytical workflows that limit scalability and reproducibility. We present LATCH (LLM-Assisted Testing of Clinical Hypotheses), an agentic framework that converts natural language clinical hypotheses into fully auditable analyses on structured EHR data. LATCH integrates LLM-assisted semantic layers with deterministic execution pipelines to automate cohort construction, statistical analysis, and result reporting, while isolating patient-level data from LLM-involved steps. Using diabetes as a model disease, LATCH reproduced findings from 20 published studies within 3-15 minutes per study. Beyond replication, LATCH enabled study extensions and new insight generation through simple natural language hypothesis modifications. We demonstrated LATCH across 102 hypothesis tests spanning reproduction, extension, and insight generation. We systematically stress-tested LATCH to characterize its limitations and operational boundaries. LATCH provides a scalable framework for reproducible real-world evidence generation, reducing analytical bottlenecks and improving reliability of AI-assisted biomedical discovery while preserving human oversight.
Open AccessAn LLM-assisted framework for accelerated and verifiable clinical hypothesis testing from electronic health records
Acquiring insights from electronic health records (EHRs) is slowed by manual analytical workflows that limit scalability and reproducibility. We present LATCH (LLM-Assisted Testing of Clinical Hypotheses), an agentic framework that converts natural language clinical hypotheses into fully auditable analyses on structured EHR data. LATCH integrates LLM-assisted semantic layers with deterministic execution pipelines to automate cohort construction, statistical analysis, and result reporting, while isolating patient-level data from LLM-involved steps. Using diabetes as a model disease, LATCH reproduced findings from 20 published studies within 3-15 minutes per study. Beyond replication, LATCH enabled study extensions and new insight generation through simple natural language hypothesis modifications. We demonstrated LATCH across 102 hypothesis tests spanning reproduction, extension, and insight generation. We systematically stress-tested LATCH to characterize its limitations and operational boundaries. LATCH provides a scalable framework for reproducible real-world evidence generation, reducing analytical bottlenecks and improving reliability of AI-assisted biomedical discovery while preserving human oversight.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 415-430
Pie: A Programmable Serving System for Emerging LLM Applications
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 415-430
Open AccessPie: A Programmable Serving System for Emerging LLM Applications
- Open Access
- 14 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 179-186
Serve Programs, Not Prompts
- 14 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 179-186
Open AccessServe Programs, Not Prompts