Researchers, clinicians, and engineers working at the crossroads of artificial intelligence and medicine got together once again this summer, and CCADD (Prof. Howard, David, Seeun) was there to join them. The occasion was the Conference on Health, Inference, and Learning (CHIL) 2026, a three-day gathering hosted in Seattle, Washington from June 28th through 30th.

Among a handful of research groups that were extended an invitation to the conference, Prof. Howard traveled together with his team Dr. David and Seeun. What made the trip especially meaningful this year was the publication of a paper from the lab, "Generation of Biingual Synthetic Clinical Notes for Realistic Data Augmentation," which the team unveiled to the community at the conference. Standing beside their poster, they walked visitors through the motivation and findings of the work, answering questions from curious attendees.

This year marked the seventh gathering of CHIL, jointly hosted by Sage Bionetworks and Seattle Children's Research Institute and hosted at the Institute's B. Wayne Hughes Building. As always, the program spanned a broad cross-section of issues shaping AI's role in healthcare. The conference opened with a keynote from Dr. Chris Longhurst, CEO of Seattle Children's, who spoke on "Evidence-based Medicine in the AI Era" and made the case for grounding AI adoption in real clinical implementation rather than hype. Dr. Pang Wei Koh followed with an invited talk on reinforcement learning approaches for deep research, and Dr. Jessilyn Dunn later delivered a keynote on wearable technology for disease detection titled "The Digital Physiome." A track devoted entirely to mental health also drew particular attention, weaving together talks on evaluating harm in AI safety, personalizing psychotherapy through language models, and building governance frameworks informed by practitioners, which were all capped off with a lively panel discussion.

For the team, the days in Seattle offered far more than a chance to share their research. They came away with new perspectives, new connections, and a renewed sense of how much further this field still has to grow.

CCADD, led by Professor Howard Lee, attended the 2026 Spring Conference of the Korean Society of Medical Informatics (KOSMI). The conference was held over three days, from June 24 to June 26, 2026, at OSCO in Cheongju and co-hosted by KOSMI and the Korea Health Industry Development Institute (KHIDI). This year’s theme was “From Operating System to Operating Society: Next Mission of Medical Informatics.” The sessions focused on artificial intelligence (AI) and large language models (LLMs) in medical informatics. Topics ranged from trustworthy medical AI to lifelog analysis and digital healthcare.

David Seung U Lee, a postdoctoral researcher at CCADD, gave an oral presentation in Session 2 (LLM-based Clinical Decision Support) on “DDI-Expert: Explainable Prediction of Pharmacokinetic Drug Interaction in Humans using Mixture of Experts.” His work moves beyond the limits of conventional drug–drug interaction (DDI) prediction. Using a Mixture of Experts (MoE) architecture that combines domain adaptation with domain application, it predicts pharmacokinetic DDI outcomes while also explaining their underlying mechanisms.

Yujin Kim, a student at CCADD, presented in the e-poster session (Generative AI and Clinical Text) on “Information Extraction and Structuring from Drug Approval Review Reports Using Large Language Models.” Her study introduced a pipeline that accurately extracts and structures information from drug approval review reports, which often have complex, multi-table layouts, while keeping costs low and performance high. The work covered the full process from model adaptation to evaluation.

Both presentations were well received at the conference. David Seung U Lee received the Best Oral Presentation Award, and Yujin Kim received the Best Poster Award. The awards mark another step in CCADD’s continued efforts to advance medical informatics through LLMs and AI-based approaches. CCADD will continue its research toward reliable and practical AI applications in healthcare and drug development.

A new research article, entitled “Assessing the representativeness of single-center EMR data on ten cancer types: A comparative analysis with national statistics from South Korea (2011–2021)”, authored by Won Jung-Hyun and Howard Lee, was published in the International Journal of Medical Informatics(IJMI). IJMI is a leading international journal that publishes high-impact research on the development, implementation, and real-world evaluation of health information systems and clinical informatics technologies.

This study evaluated whether single-center electronic medical record (EMR) data from Seoul National University Hospital (SNUH) could represent a real-world data source for oncology research in South Korea. To address this, the study analyzed annual incidence and prevalence patterns for ten major cancer types (e.g., breast, gallbladder/biliary tract, gastric, kidney, liver, lung, pancreatic, prostate, thyroid cancers, and leukemia) from 2011 to 2021 using national cancer statistics from the Korean Statistical Information Service (KOSIS) as reference. The study also examined age and gender distributions between two datasets. The results showed that the SNUH EMR data included 8.2% of national incident cancer cases and 10.7% of prevalent cases. The study also found no significant differences in age and gender distributions across all cancer types between the SNUH EMR and national data. In addition, strong correlations in annual trends were observed for several major cancers, including breast, lung, and pancreatic cancers. Overall, this study showed that single-center EMR data can be a valuable, representative clinical resource for oncology research in South Korea. At the same time, the study emphasizes that the underrepresentation of certain cancer types and external temporal factors, such as changes in clinical guidelines or major healthcare disruptions, should be carefully considered when generalizing findings from a single institution to broader populations.

CCADD members attended the 2026 Graduate School of Convergence Science and Technology Convergence Academic Festival, held on March 26, 2026, at the Faculty Hall of Seoul National University. This academic festival aimed to promote the exchange of research achievements among the Department of Applied Bioengineering, the Department of Molecular Medicine and Biopharmaceutical Sciences, and the Department of Health Science and Technology, while also providing a forum for presentation and discussion on bio-convergence research. The event brought together faculty members, researchers, and students from diverse fields to share recent research progress. The festival began with opening remarks delivered by Prof. Howard Lee, setting the stage for academic exchange among the participating departments.

More importantly, CCADD members presented one oral presentation and four poster presentations at the festival.

David gave an oral presentation titled “Mechanistic Reasoning Framework for Predicting Multi-Mechanism Pharmacokinetic Drug Interactions”. His work introduced a framework for predicting complex pharmacokinetic drug interactions involving multiple mechanisms.

Yujin’s poster “Annotation-Level Validation and Error Taxonomy for LLM-Assisted Korean–English Pharmaceutical Regulatory Corpus Construction”, focused on validation and error patterns in building a Korean–English pharmaceutical regulatory corpus using LLMs.

In a poster titled “LLM-Based Extraction of Adverse Drug Reactions from Real-World Clinical Notes”, Seoyoon presented an LLM-based approach for extracting adverse drug reaction information from real-world clinical notes.

Suhyun’s poster “Improving Causality Assessment of ADRs in Large Language Models through Rationale-Based Knowledge Distillation”, explored a method for improving the accuracy of causality assessment in LLMs through rationale-based knowledge distillation.

Seeun delivered a poster presentation titled “Generation of Multi-Lingual Synthetic Clinical Notes for Realistic Data Augmentation”, which proposed a framework for generating multilingual synthetic clinical notes to support realistic data augmentation.

Through this academic festival, CCADD members shared their recent research and exchanged ideas with researchers from related fields. The event provided an opportunity to present ongoing work, receive feedback, and engage in discussion on current topics in bio-convergence research.

Join us in congratulating David Seung U Lee on his successful graduation with a PhD in Medical Science!

On February 25, David attended the 80th Commencement Ceremony of Seoul National University (SNU), where he received his PhD degree under the supervision of Prof. Howard Lee. He was also awarded with the Best Dissertation Award in recognition of his outstanding research achievements. His dissertation was entitled “Mechanistic Understanding and Prediction of Drug–Drug Interactions in Humans using LLM-Based Multimodal Explainable Framework”.

Dr. Lee is the first PhD graduate of CCADD, who received his degree in the Department of Molecular Medicine and Biopharmaceutical Sciences at the Graduate School of Convergence Science and Technology, Seoul National University. He will continue his academic career at CCADD as a postdoctoral researcher, focusing on clinical natural language processing and artificial intelligence–based drug development.

A research article entitled “Beyond Fine-Tuning: Leveraging Domain-Aware In-Context Learning with Large Language Models for Clinical Named Entity Recognition” has been published in the Journal of Biomedical Informatics (Volume 174, February 2026). The Journal of Biomedical Informatics is a leading international journal in the field of biomedical and clinical informatics that publish high-impact research at the intersection of medicine, data science, and artificial intelligence. Our study presents a comprehensive evaluation of large language model (LLM) based in-context learning (ICL) for clinical named entity recognition (NER) under realistic clinical constraints.

The study compared ICL with conventional encoder-based fine-tuning approaches using manually annotated real-world clinical notes. ICL configurations were optimized across task instructions, output formats, demonstration selection methods, sorting strategies, and demonstration pool sizes using the open-source LLaMA-3.3-70B model, while encoder-based fine-tuning was performed with RoBERTa-large as the strongest baseline.

The results showed that optimized demonstration selection played a major role in determining ICL performance, and improved macro F1 scores compared to random selection. In moderate-resource settings, ICL outperformed encoder-based fine-tuning and remained competitive across a wide range of labeled data sizes. Moreover, ICL demonstrated superior data efficiency and achieved substantial gains in cross-institutional transfer without requiring any parameter updates.

Overall, the study highlights the potential of domain-aware ICL as a flexible and data-efficient alternative to encoder-based fine-tuning for clinical NER. By enabling rapid adaptation through demonstration pools rather than retraining, the proposed approach offers a practical solution for real-world clinical natural language processing in dynamic and resource-limited healthcare environments.

This research was supported by grants from the MSIT (IITP), the Ministry of Health and Welfare (KHIDI), and the Ministry of Education (NRF) of the Republic of Korea.

On Friday, December 26, 2025, CCADD had the annual Year-End Workshop at Seoul National University, Seoul, South Korea. The workshop brought together all current CCADD members, part-time students and winter interns. Throughout a full day of presentations and discussions, CCADD members reflected on the year 2025 and looked ahead to 2026.

The workshop began with arrival and reception, followed by a series of presentations covering research progress, academic development, and practical lessons learned. As the first speaker, Seoyoon opened the program with a session titled “Looking Back on the Year 2025,” highlighting CCADD’s accomplishments in 2025 and celebrating the achievements of its members.

The yearly report was followed by Suhyun, who shared key takeaways from a year of full-time work at CCADD across two phases, from undergraduate research to the first semester of the master’s program. Then, Seeun presented “Preparation for the 1st Oral Presentation,” reflecting on her year-long research and walking through her conference-presentation preparation process. After that, Sunyoung delivered a presentation titled “Life in the Industry vs. Graduate School,” in which she introduced the role of a Clinical Project Leader at Daewoong Pharmaceutical Company highlighting key differences between life in industry and life as a master’s student. As the last session before lunch, David delivered a talk about the things he wished he had known early on, including having a daily habit of reading papers and making a usable personal template to take notes of what you learned from papers.

Following the morning sessions, participants took a break for lunch and then toured the main library at Seoul National University’s Gwanak Campus, exploring its study spaces, archives, and facilities. After the tour, members gathered for a photo time and captured group photos inspired by this year’s Pantone Color theme.

Soyoung presented “How I Learned Actually to Write” and explained what she learned while writing during the second half of 2025 under the supervision of Prof. Howard Lee. Then, Sungwook delivered a workshop talk titled “How I Became the Pre-crastinator at CCADD.” In the talk, he defined a “pre-crastinator” as someone who finishes tasks early and stays in the lab late to keep studying. It was followed by Chaeyoung, who shared her journey for the 2025 Google Solution Challenge, from ideation and development to presenting at the Asian Development Bank in the Philippines. She also reflected on pitching on an international stage and the lessons learned through receiving the award.

After a short break, the workshop continued with sessions focused on practical milestones and next-year planning. In the afternoon session, Seoyoon presented “First Grant Proposal: What I Learned and What I Wish I’d Known,” sharing key challenges and lessons from her first grant project management experience. In the tenth session, Yujin led “Looking Ahead to 2026 at CCADD,” presenting a vision for the center’s research trajectory in the coming year.  It also compiled target conferences for future submissions and concluded with a shared aspiration for deeper research in 2026.

Moreover, in the session, "AI 2027: Where we were, where we are, and where we will be", David went over the prospective report, "AI 2027," in which the authors made predictions on what will happen to the state of AI arms race between US and China. In addition to peeking into the future of AI, David emphasized the need for shifting gears toward using agentic AIs and understanding their inner workings by briefly discussing important developments in the field of agentic AI.

The most significant part of the workshop came in the closing talk, where Prof. Howard presented a paradigm shift from +AI to AI+. He contrasted a domain-first approach with an AI first approach and explaining how research strategy changes under an AI+ framework. He emphasized CCADD’s future direction toward AI-centered approach and proposed holding a “CCADD AI+ Conversion Meeting” in the early 2026 to brainstorm and define core research themes and strategies.

The workshop concluded with closing remarks from Prof. Howard, and everyone gathered for dinner. The 2025 CCADD Year-End Workshop provided members with an opportunity to exchange ideas, reflect on progress, and align on shared goals for the year ahead.

David Seung U Lee, a Ph.D. student at CCADD, and Seeun Park, an undergraduate researcher and the soon-to-be Master’s student at CCADD, received the Outstanding Presentation Awards at the 2025 Fall Conference of the Korean Society of Medical Informatics (KOSMI).

David presented his study titled "Improving Large Language Model-Based Drug-Drug Interaction Prediction Using Conformal Prediction." His research demonstrated that incorporating input features with coverage guarantees, verified through conformal prediction, significantly improves the performance of LLM-based DDI prediction in both in-context learning and fine-tuning settings.

Seeun Park, presented her study titled “Improving Synthetic Clinical Note Generation via Expert Prompting Reflecting Linguistic and Structural Characteristics.” Her research proposes a data augmentation framework that incorporates the knowledge of medical professionals into LLM-based prompting, coupled with a feedback-driven iterative generation loop. This approach enables the model to produce synthetic clinical notes that more closely reflect the characteristics of real-world clinical notes.

These awards highlight the growing importance of LLMs in the healthcare industry and recognizes the potential impact of our work in advancing AI-driven medical text generation.