Call for Papers for China Conference on Health Information Processing(CHIP2023)

The 9th China Conference on Health Information Processing (CHIP2023) is an annual event organized by the Medical Health and Bioinformatics Processing Committee of the China Computer Federation (CIPS). It is one of the most significant academic conferences in the field of health information processing in China, focusing on technologies such as medical, health, and biological information processing, as well as data mining. The conference aims to gather top scholars in medical information processing and healthcare experts from across the country to collectively explore trends and challenges in the development of intelligent healthcare in the era of big models. This includes new pathways for the application of AI in healthcare and novel approaches to medical research. The 2023 China Conference on Health Information Processing(The official website link is: http://cips-chip.org.cn/2023 )will be held on October 27th to 29th, 2023.

Since 2018, China Conference on Health Information Processing has accepted papers every year. The accepted articles will be transferred to SCI indexed journals (JMIR Medical Informatics, etc.) and relevant evaluations of health and medical information technology will be organized. This CHIP2023 technical evaluation announced 3 tasks, including "CHIP-PromptCBLUE Medical Large Model Evaluation Task", "Named Entity Recognition Evaluation Task on Small Sample of Chinese Medical Text" and "Task for Recognition of Drug-related Information in Physical Documents and Entity Relation Extraction". At that time, teams that have achieved excellent results in the evaluation will be invited to report and award awards in the evaluation session of the conference. The conference will also provide an official award certificate, and each task has a certain amount of bonus rewards. In addition, the evaluation-winning team will also be invited to write technical papers, which will be published in China core journals under the guidance of the special committee. Researchers in related fields are welcome to participate in the evaluation competition.

Paper submission instructions:

Submission address: https://easychair.org/conferences/?conf=chip2023

Submission deadline: September 20, 2023

Acceptance Notification: October 15, 2023

Deadline for final papers: October 20, 2023

Paper Template (Chinese, Using Chinese Journal of Information Templates): http://jcip.cipsc.org.cn/

Paper Template (English, Word/Latex): https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines

The specific evaluation tasks are described as follows:

Task 1: CHIP-PromptCBLUE Medical Large Model Evaluation Task

Task Address: http://cips-chip.org.cn/2023/eval1

Task Introduction: In order to promote the development and application of Large Language Models (LLMs) in the medical field, Professor Wang Xiaoling's team from East China Normal University, in collaboration with Alibaba Cloud Tianchi, Professor Tang Buchou from Harbin Institute of Technology (Shenzhen) Pengcheng Laboratory, and other experts and scholars, have launched the PromptCBLUE-v2 benchmark. The PromptCBLUE-v2 benchmark is a secondary development of the CBLUE benchmark. It transforms 18 different medical scenario Natural Language Processing (NLP) tasks into prompt-based language generation tasks. This forms the first Chinese medical scenario LLM evaluation benchmark, which is conducive to assisting the open-source community and industry in rapidly evaluating publicly available or proprietary LLM models. PromptCBLUE-v2 will serve as one of the evaluation tasks for CHIP-2023 and will be assessed on the Tianchi competition platform.

Task Organizer:
  Wei Zhu, East China Normal University, China, wzhu@stu.ecnu.edu.cn
  Mosha Chen, Professional Committee on Biomedical and Medical Information Processing, Chinese Society of Information Processing (This work was completed during the tenure at Alibaba), 51205901094@cs.ecnu.edu.cn
  Xiaoling Wang, East China Normal University, China, xlwang@cs.ecnu.edu.cn

Task 2: Named Entity Recognition Evaluation Task on Small Sample of Chinese Medical Text

Task Address: http://cips-chip.org.cn/2023/eval2

Task Introduction: Chinese medical named entity recognition is a fundamental task for enabling smart healthcare, involving the extraction of a wealth of information related to diseases, symptoms, and treatments from text. While deep learning techniques have made significant progress in this task, acquiring data in the medical domain is often challenging, which hinders domain adaptation and model training. Few-shot learning aligns better with practical applications, focusing on maintaining high accuracy with a limited amount of annotated data and exhibiting strong generalization capability.

Task Organizer:
   Hongying Zan, Zhengzhou University, Natural Language Processing Laboratory
   Kunli Zhang, Zhengzhou University, Natural Language Processing Laboratory

Task Contact:
   Chenghao Zhang: zchcolorful@163.com
   Yunlong Li: 1457527772@qq.com

Task 3: Task for Recognition of Drug-related Information in Physical Documents and Entity Relation Extraction

Task Address: http://cips-chip.org.cn/2023/eval3

Task Introduction: In the pharmaceutical distribution industry, a significant accumulation of paper documents occurs during business operations, such as drug registration certificates, drug GMP certificates, drug manufacturing licenses, and drug package inserts. Among these, the drug package insert is a legally mandated document containing vital information about the drug. It serves as a statutory guide for drug selection and holds substantial value.
The update frequency of drug package inserts is often higher than that of common sources like clinical practice guidelines and medical textbooks. Additionally, their extraction presents challenges. While drug package inserts from different manufacturers contain similar content, they exhibit substantial formatting differences. These documents contain both structured and unstructured information. Extracting relationships between drugs and other entities from unstructured text to construct a medical knowledge graph can better serve downstream tasks like prescription review, diagnostic assistance, and patient health education.

Task Organizer:
Qian Chen, Jia Wang, China National Pharmaceutical Group Digital Technology Co., Ltd.

Task 4: CHIP-YIER Medical Large-scale Model Evaluation Task

Task Address: http://cips-chip.org.cn/2023/eval4

Task Introduction: In modern healthcare, the application of medical big data models has become an important tool for improving patient care and diagnosis. However, ensuring the accuracy and reliability of these models in clinical practice is crucial. The aim of this evaluation task is to examine the performance of medical big data models in logical reasoning, medical terminology, medical knowledge, clinical practice guidelines, and medical calculations, among other medical aspects.

Task Organizer:
   Zengtao Jiao, Yiduyun (Beijing) Technology Co., Ltd. zengtao.jiao@yiducoud.cn
Xiaozhen Zhang, Yiduyun (Beijing) Technology Co., Ltd. xiaozhen.zhang@yiducloud.cn