Embedded Files
Announcement (25 August 2025):
We are delighted to share that authors of outstanding and innovative papers presented at this workshop will have the opportunity to be considered for inclusion in a special collection of BMJ Health & Care Informatics.
Selected submissions will undergo a thorough peer-review process in accordance with the journal’s standards.
For submission guidelines and eligibility criteria, please refer to the following link:
Workshop information
This international workshop will be held as a closing event for the SREDH/AI-Cup 2025 Deidentification competition. The workshop will be held during the 2025 MedInfo 2025 ( 9th to 13th August 2025, Taipei, Taiwan). The workshop will have presentations from top performing teams that participated in SREDH/AI-Cup 2025 Deidentification competition
Artificial intelligence (AI) and natural language processing (NLP) have played transformative roles in advancements in healthcare, with large language models (LLMs) proven to be prominent in clinical decision-making and electronic health record (EHR) processing. LLM-driven systems analyse complex medical data and assist with diagnosis, treatment planning, and personalized medicine. However, safeguarding sensitive health information (SHI) embedded in EHRs and exchanged during doctor-patient interactions remains challenging. The first International Workshop on Deidentification of Electronic Medical Records Notes (IW-DMRN), which focused on LLM-based approaches for SHI deidentification, was held on 15th January 2024. By considering the outcomes of the first workshop [1-3], the 2nd IW-DMRN workshop is proposed with the primary objective of developing advanced AI algorithms capable of identifying and replacing SHIs effectively from medical speech datasets.
** Final date and venue**
Time: Based on Taiwan Time Zone (GMT+8) Friday, August 10,
Venue: Taipei International Convention Center (TICC), Taipei, Taiwan 2025 201F, 2F
** Agenda **
Workshop WS14
Super Theme:
TRACK 3: Health Data Science & Artificial Intelligence
Theme:
Theme 2 - Applications
Organisers:
Jitendra JONNAGADDALA, Hong-Jie DAI, Ching-Tai CHEN, Liang-Chun Fang, Zheng-Hao Li, Liang-Kai Chen and Yuan-Chi Hsu
Time: 09:00-10:30 (GMT+8)
Chair(s): Ching-Tai Chen
09:00-09:05
Ching-Tai Chen
Chair Opening Remarks
Welcome message and introduction (host & participants)
09:05-09:15
Liang-Chun Fang
Presentation Topic: Overview of the AI CUP 2025 Medical Speech Sensitive Personal Data Recognition Competition
09:15-09:25
Zheng-Hao Li
Presentation Topic: A Generative Approach to Sensitive Data Identification in Medical Speech using Large Language Models
09:25-09:35
Liang-Kai Chen
Presentation Topic: Prompt Engineering and Post-processing for Sensitive Health Information Recognition
09:35-09:45
Jing Jin (Online)
Presentation Topic: Instruction-Tuned LLMs for Multilingual Medical ASR and Privacy Entity Extraction
09:45-09:55
Lien-hung Su
Presentation Topic: Named Entity Recognition in Chinese-English Speech via Automatic Speech Recognition and Large Language Models
09:55-10:05
Yan-Jun Chen (Online)
Presentation Topic: Speech Privacy and Personal Information Recognition
10:05-10:15
Yuan-Chi Hsu
Presentation Topic: Chinese Models for De-identifying Mixed Chinese-English- Minnan Speech
10:15-10:25
Chao-Long Huang (Online)
Presentation Topic: Temporal Subword De-identification of Medical Speech for Privacy Protection Leveraging ASR and LLMs
10:25-10:30
Group Photo and Closing
** Submission information ** (deadline 1st August 11:59PM GMT+8)
https://www.sredhconsortium.org/sredh-workshops/2025-iw-dmrn/submission-information
References
Jonnagaddala.J , Z.S.-Y.W., Privacy-preserving Strategies for Electronic Health Records in the Era of Large Language Models. npj Digital medicine, 2025. https://doi.org/10.1038/s41746-025-01429-0
Jonnagaddala.J, Dai.H.-J., Chen.C-T . SREDH. Large Language Models for Automatic Deidentification of Electronic Health Record Notes. Springer CCIS 2025.https://doi.org/10.1007/978-981-97-7966-6 .
Jonnagaddala, J., Chen, A., Batongbacal, S., & Nekkantti, C. (2021). The OpenDeID corpus for patient de-identification. Scientific reports, 11(1), 19973. https://doi.org/10.1038/s41598-021-99554-9
Chen, A., Jonnagaddala, J., Nekkantti, C., & Liaw, S. T. (2019). Generation of Surrogates for De-Identification of Electronic Health Records. Studies in health technology and informatics, 264, 70–73. https://doi.org/10.3233/SHTI190185
Alla, N. L. V., Chen, A., Batongbacal, S., Nekkantti, C., Dai, H., & Jonnagaddala, J. (2021). Cohort selection for construction of a clinical natural language processing corpus. Computer Methods and Programs in Biomedicine Update, 1, 100024. https://doi.org/10.1016/j.cmpbup.2021.100024
Liu, J., Gupta, S., Chen, A., Wang, C. K., Mishra, P., Dai, H. J., Wong, Z. S., & Jonnagaddala, J. (2023). OpenDeID Pipeline for Unstructured Electronic Health Record Text Notes Based on Rules and Transformers: Deidentification Algorithm Development and Validation Study. Journal of medical Internet research, 25, e48145. https://doi.org/10.2196/48145
Chair
Chair
Jitendra Jonnagaddala – UNSW Sydney, Australia
Organizing and editorial committee
Organizing and editorial committee
Jitendra Jonnagaddala – UNSW Sydney, Australia
Hong-Jie Dai - National Kaohsiung University of Science and Technology, Taiwan
Ching-Tai Chen - Asia University, Taiwan
Yung-Chun CHANG - Taipei Medical University
Organizers
Sponsors
Page updated
Google Sites
Report abuse