CHIP2022 Shared Task Overview: Medical Causal Entity Relationship Extraction

Zihao Li; Mosha Chen; Kangping Yin; Yixuan Tong; Chuanqi Tan; Zhenzhen Lang; Buzhou Tang

doi:10.1007/978-981-99-4826-0_5

CHIP2022 Shared Task Overview: Medical Causal Entity Relationship Extraction

Zihao Li
, Mosha Chen^*
, Kangping Yin
, Yixuan Tong
, Chuanqi Tan
, Zhenzhen Lang
, Buzhou Tang

^*Corresponding author for this work

Alibaba Group Holding Ltd.
Harbin Institute of Technology Shenzhen
Pengcheng Laboratory

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Modern medicine emphasizes interpretability and requires doctors to give reasonable, well-founded and convincing diagnostic results when diagnosing patients. Therefore, there are a large number of causal correlations in medical concepts such as symptoms, diagnosis and treatment in the text of the results of the inquiry. Explanation of relationships, and mining these relationships from text is of great help in improving the accuracy and interpretability of medical search results. Based on this, this paper constructs a new medical causality extraction dataset CMedCausal (Chinese Medical Causal dataset) and it is used in the CHIP2022 shared task, which defines three key types of medical causal relationships: causal relationship, conditional relationship, and hypothetical relationship. It consists of 9,153 medical texts with a total of 79,244 entity relationships annotated. Participants need to correctly label these correct reasoning relationships and corresponding subject-object entities. A total of 49 teams submitted results for the preliminary round with the highest Macro-F1 value of 0.4510. A total of 25 teams submitted results for final round with the highest Macro-F1 value of 0.4416.

Original language	English
Title of host publication	Health Information Processing. Evaluation Track Papers - 8th China Conference, CHIP 2022, Revised Selected Papers
Editors	Buzhou Tang, Qingcai Chen, Hongfei Lin, Fei Wu, Lei Liu, Tianyong Hao, Yanshan Wang, Haitian Wang, Jianbo Lei, Zuofeng Li, Hui Zong
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	51-56
Number of pages	6
ISBN (Print)	9789819948253
DOIs	https://doi.org/10.1007/978-981-99-4826-0_5
State	Published - 2023
Externally published	Yes
Event	Proceedings of the 8th China Conference on China Health Information Processing Conference 2022 - Hangzhou, China Duration: 21 Oct 2022 → 23 Oct 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1773 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	Proceedings of the 8th China Conference on China Health Information Processing Conference 2022
Country/Territory	China
City	Hangzhou
Period	21/10/22 → 23/10/22

Keywords

causal relationship
interpretability
relation extraction

Access to Document

10.1007/978-981-99-4826-0_5

Cite this

Li, Z., Chen, M., Yin, K., Tong, Y., Tan, C., Lang, Z., & Tang, B. (2023). CHIP2022 Shared Task Overview: Medical Causal Entity Relationship Extraction. In B. Tang, Q. Chen, H. Lin, F. Wu, L. Liu, T. Hao, Y. Wang, H. Wang, J. Lei, Z. Li, & H. Zong (Eds.), Health Information Processing. Evaluation Track Papers - 8th China Conference, CHIP 2022, Revised Selected Papers (pp. 51-56). (Communications in Computer and Information Science; Vol. 1773 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-4826-0_5

Li, Zihao ; Chen, Mosha ; Yin, Kangping et al. / CHIP2022 Shared Task Overview : Medical Causal Entity Relationship Extraction. Health Information Processing. Evaluation Track Papers - 8th China Conference, CHIP 2022, Revised Selected Papers. editor / Buzhou Tang ; Qingcai Chen ; Hongfei Lin ; Fei Wu ; Lei Liu ; Tianyong Hao ; Yanshan Wang ; Haitian Wang ; Jianbo Lei ; Zuofeng Li ; Hui Zong. Springer Science and Business Media Deutschland GmbH, 2023. pp. 51-56 (Communications in Computer and Information Science).

@inproceedings{7664b6762f6249f6a951b614d7eae839,

title = "CHIP2022 Shared Task Overview: Medical Causal Entity Relationship Extraction",

abstract = "Modern medicine emphasizes interpretability and requires doctors to give reasonable, well-founded and convincing diagnostic results when diagnosing patients. Therefore, there are a large number of causal correlations in medical concepts such as symptoms, diagnosis and treatment in the text of the results of the inquiry. Explanation of relationships, and mining these relationships from text is of great help in improving the accuracy and interpretability of medical search results. Based on this, this paper constructs a new medical causality extraction dataset CMedCausal (Chinese Medical Causal dataset) and it is used in the CHIP2022 shared task, which defines three key types of medical causal relationships: causal relationship, conditional relationship, and hypothetical relationship. It consists of 9,153 medical texts with a total of 79,244 entity relationships annotated. Participants need to correctly label these correct reasoning relationships and corresponding subject-object entities. A total of 49 teams submitted results for the preliminary round with the highest Macro-F1 value of 0.4510. A total of 25 teams submitted results for final round with the highest Macro-F1 value of 0.4416.",

keywords = "causal relationship, interpretability, relation extraction",

author = "Zihao Li and Mosha Chen and Kangping Yin and Yixuan Tong and Chuanqi Tan and Zhenzhen Lang and Buzhou Tang",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.; Proceedings of the 8th China Conference on China Health Information Processing Conference 2022 ; Conference date: 21-10-2022 Through 23-10-2022",

year = "2023",

doi = "10.1007/978-981-99-4826-0\_5",

language = "英语",

isbn = "9789819948253",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "51--56",

editor = "Buzhou Tang and Qingcai Chen and Hongfei Lin and Fei Wu and Lei Liu and Tianyong Hao and Yanshan Wang and Haitian Wang and Jianbo Lei and Zuofeng Li and Hui Zong",

booktitle = "Health Information Processing. Evaluation Track Papers - 8th China Conference, CHIP 2022, Revised Selected Papers",

address = "德国",

}

Li, Z, Chen, M, Yin, K, Tong, Y, Tan, C, Lang, Z & Tang, B 2023, CHIP2022 Shared Task Overview: Medical Causal Entity Relationship Extraction. in B Tang, Q Chen, H Lin, F Wu, L Liu, T Hao, Y Wang, H Wang, J Lei, Z Li & H Zong (eds), Health Information Processing. Evaluation Track Papers - 8th China Conference, CHIP 2022, Revised Selected Papers. Communications in Computer and Information Science, vol. 1773 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 51-56, Proceedings of the 8th China Conference on China Health Information Processing Conference 2022, Hangzhou, China, 21/10/22. https://doi.org/10.1007/978-981-99-4826-0_5

CHIP2022 Shared Task Overview: Medical Causal Entity Relationship Extraction. / Li, Zihao; Chen, Mosha; Yin, Kangping et al.
Health Information Processing. Evaluation Track Papers - 8th China Conference, CHIP 2022, Revised Selected Papers. ed. / Buzhou Tang; Qingcai Chen; Hongfei Lin; Fei Wu; Lei Liu; Tianyong Hao; Yanshan Wang; Haitian Wang; Jianbo Lei; Zuofeng Li; Hui Zong. Springer Science and Business Media Deutschland GmbH, 2023. p. 51-56 (Communications in Computer and Information Science; Vol. 1773 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - CHIP2022 Shared Task Overview

T2 - Proceedings of the 8th China Conference on China Health Information Processing Conference 2022

AU - Li, Zihao

AU - Chen, Mosha

AU - Yin, Kangping

AU - Tong, Yixuan

AU - Tan, Chuanqi

AU - Lang, Zhenzhen

AU - Tang, Buzhou

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

PY - 2023

Y1 - 2023

N2 - Modern medicine emphasizes interpretability and requires doctors to give reasonable, well-founded and convincing diagnostic results when diagnosing patients. Therefore, there are a large number of causal correlations in medical concepts such as symptoms, diagnosis and treatment in the text of the results of the inquiry. Explanation of relationships, and mining these relationships from text is of great help in improving the accuracy and interpretability of medical search results. Based on this, this paper constructs a new medical causality extraction dataset CMedCausal (Chinese Medical Causal dataset) and it is used in the CHIP2022 shared task, which defines three key types of medical causal relationships: causal relationship, conditional relationship, and hypothetical relationship. It consists of 9,153 medical texts with a total of 79,244 entity relationships annotated. Participants need to correctly label these correct reasoning relationships and corresponding subject-object entities. A total of 49 teams submitted results for the preliminary round with the highest Macro-F1 value of 0.4510. A total of 25 teams submitted results for final round with the highest Macro-F1 value of 0.4416.

AB - Modern medicine emphasizes interpretability and requires doctors to give reasonable, well-founded and convincing diagnostic results when diagnosing patients. Therefore, there are a large number of causal correlations in medical concepts such as symptoms, diagnosis and treatment in the text of the results of the inquiry. Explanation of relationships, and mining these relationships from text is of great help in improving the accuracy and interpretability of medical search results. Based on this, this paper constructs a new medical causality extraction dataset CMedCausal (Chinese Medical Causal dataset) and it is used in the CHIP2022 shared task, which defines three key types of medical causal relationships: causal relationship, conditional relationship, and hypothetical relationship. It consists of 9,153 medical texts with a total of 79,244 entity relationships annotated. Participants need to correctly label these correct reasoning relationships and corresponding subject-object entities. A total of 49 teams submitted results for the preliminary round with the highest Macro-F1 value of 0.4510. A total of 25 teams submitted results for final round with the highest Macro-F1 value of 0.4416.

KW - causal relationship

KW - interpretability

KW - relation extraction

UR - https://www.scopus.com/pages/publications/85172736990

U2 - 10.1007/978-981-99-4826-0_5

DO - 10.1007/978-981-99-4826-0_5

M3 - 会议稿件

AN - SCOPUS:85172736990

SN - 9789819948253

T3 - Communications in Computer and Information Science

SP - 51

EP - 56

BT - Health Information Processing. Evaluation Track Papers - 8th China Conference, CHIP 2022, Revised Selected Papers

A2 - Tang, Buzhou

A2 - Chen, Qingcai

A2 - Lin, Hongfei

A2 - Wu, Fei

A2 - Liu, Lei

A2 - Hao, Tianyong

A2 - Wang, Yanshan

A2 - Wang, Haitian

A2 - Lei, Jianbo

A2 - Li, Zuofeng

A2 - Zong, Hui

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 21 October 2022 through 23 October 2022

ER -

Li Z, Chen M, Yin K, Tong Y, Tan C, Lang Z et al. CHIP2022 Shared Task Overview: Medical Causal Entity Relationship Extraction. In Tang B, Chen Q, Lin H, Wu F, Liu L, Hao T, Wang Y, Wang H, Lei J, Li Z, Zong H, editors, Health Information Processing. Evaluation Track Papers - 8th China Conference, CHIP 2022, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2023. p. 51-56. (Communications in Computer and Information Science). doi: 10.1007/978-981-99-4826-0_5

CHIP2022 Shared Task Overview: Medical Causal Entity Relationship Extraction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this