avatar

Jungwoo Oh

Postdoctoral Researcher
KAIST AI
ojw0123 (at) kaist.ac.kr
ojw3280 (at) gmail.com


About Me

I am a postdoctoral researcher at KAIST AI, working with Prof. Edward Choi. I received my Ph.D. in Artificial Intelligence from KAIST in 2026, also advised by Prof. Edward Choi, and my B.S. in Computer Science and Engineering from Korea University in 2021.

My research focuses on medical AI, especially for electrocardiograms (ECG) and electronic health records (EHR). I have worked on self-supervised representation learning for ECG signals, predictive modeling across heterogeneous EHR systems, and question answering datasets for clinical data. More recently, I have been building benchmarks to evaluate the clinical reasoning of multimodal large language models.

Building on my experience in constructing ECG datasets, I am currently working on agentic workflows for conversational ECG agents. Most of my research so far has been built on healthcare data, and my work on LLMs has centered on evaluation and benchmarking. Although I have not yet trained LLMs at scale, I am eager to gain experience in large-scale LLM training.

Research Interests

News

Publications

  1. ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
    Jungwoo Oh, Hyunseung Chung, Min-Gyu Kim, Hangyul Yoon, Ki Seong Lee, Youngchae Lee, Muhan Yeo, Edward Choi
    Conference on Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track, 2026.
    PDF Code

  2. MEDS — An Emerging Data Standard and Ecosystem for Health AI Research
    Matthew BA McDermott, Ethan Steinberg, Jason A Fries, Robin P van de Water, Chao Pang, Patrick Rockenschaub, Pawel Renc, Jungwoo Oh, Kamilė Stankevičiūtė, Justin Xu, Tom J Pollard, Nassim Oufattole, Michael Wornow, Teya S Bergamaschi, Hyewon Jeong, Simon A Lee, Vincent Jeanselme, Kiril V Klein, Mikkel Odgaard, Maria E Montgomery, Arkadiusz Sitek, Mads Nielsen, Jeffrey N Chiang, Noa Dagan, Isaac Kohane, Shalmali Joshi, Edward Choi, Nigam H Shah
    NEJM AI, 2026.
    PDF

  3. ECG-Agent: On-Device Tool-Calling Agent for ECG Multi-Turn Dialogue
    Hyunseung Chung, Jungwoo Oh, Daeun Kyung, Jiho Kim, Yeonsu Kwon, Min-Gyu Kim, Edward Choi
    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026.
    PDF

  4. LabTOP: A Unified Model for Lab Test Outcome Prediction on Electronic Health Records
    Sujeong Im*, Jungwoo Oh*, Edward Choi (*Equal contribution)
    Conference on Health, Inference, and Learning (CHIL), 2025.
    PDF Best Paper Award

  5. Learning Under Label Noise Through Few-shot Human-in-the-loop Refinement
    Aaqib Saeed, Dimitris Spathis, Jungwoo Oh, Edward Choi, Ali Etemad
    Scientific Reports, 2025.
    PDF

  6. Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes
    Sunjun Kweon*, Junu Kim*, Jiyoun Kim, Sujeong Im, Eunbyeol Cho, Seongsu Bae, Jungwoo Oh, Gyubok Lee, Jong Hak Moon, Seng Chan You, Seungjin Baek, Chang Hoon Han, Yoon Bin Jung, Yohan Jo, Edward Choi (*Equal contribution)
    Findings of the Association for Computational Linguistics (ACL), 2024.
    PDF Code

  7. GenHPF: General Healthcare Predictive Framework for Multi-task Multi-source Learning
    Kyunghoon Hur, Jungwoo Oh, Junu Kim, Min Jae Lee, Eunbyeol Cho, Jiyoun Kim, Seong-Eun Moon, Young-Hak Kim, Louis Atallah, Edward Choi
    IEEE Journal of Biomedical and Health Informatics (JBHI), 2024.
    PDF

  8. EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images
    Seongsu Bae*, Daeun Kyung*, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, Jungwoo Oh, Lei Ji, Eric I-Chao Chang, Tackeun Kim, Edward Choi (*Equal contribution)
    Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2023.
    PDF Code

  9. ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram
    Jungwoo Oh, Seongsu Bae, Gyubok Lee, Joon-myoung Kwon, Edward Choi
    Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2023.
    PDF Code

  10. Lead-agnostic Self-supervised Learning for Local and Global Representations of Electrocardiogram
    Jungwoo Oh, Hyunseung Chung, Joon-myoung Kwon, Dong-gyun Hong, Edward Choi
    Conference on Health, Inference, and Learning (CHIL), 2022.
    PDF Code

  11. Unifying Heterogeneous Electronic Health Records Systems via Text-Based Code Embedding
    Kyunghoon Hur*, Jiyoung Lee*, Jungwoo Oh, Wesley Price, Young-Hak Kim, Edward Choi (*Equal contribution)
    Conference on Health, Inference, and Learning (CHIL), 2022.
    PDF

  12. Gradually Applying Weakly Supervised and Active Learning for Mass Detection in Breast Ultrasound Images
    Jooyeol Yun, Jungwoo Oh, Ildong Yun
    Applied Sciences, 2020.
    PDF

Education

Services

Conference Reviewers