A Shared Embedding Strategy Based System for Clinical Findings Classification in Medical Dialogues

Corresponding author: ChenXu, chen_xu@winning.com.cn

DOI: 10.12201/bmr.202207.00009

•  

  Abstract: The classification of positive and negative clinical findings in online medical dialogues is an essential task in automated diagnostic systems. This paper proposes a system for clinical findings classification in medical dialogues. The system consists of a speak-er-aware input sequence and a shared embedding strategy based auxiliary sequence at the input. A regularization approach and an alternating normalization postprocessing technique are applied to further improve the performance of the system. The experimental results show that the Macro-F1 score of the proposed method achieves 77.87% in the 7th China Health Information Processing Conference (CHIP 2021) Classifying Positive and Negative Clinical Findings in Medical Dialogues Task.

  Key words: medical dialogues; positive and negative classification; pre-trained language model

  Submit time: 4 July 2022

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• xie jia qi. Leveraging Pre-trained Language Model for Consumer Health Question Classification. 2021. doi: 10.12201/bmr.202101.00017

  Xiong Ying, Chen Mosha, Chen Qingcai, Tang Buzhou. Overview of the CHIP2021 Shared Task 1: Classifying Positive and Negative Clinical Findings in Medical Dialog. 2022. doi: 10.12201/bmr.202207.00010

  kangyishuai, shaochenjie. An Algorithm for Generating TCM Document Questions Based on Unified Language Model. 2022. doi: 10.12201/bmr.202110.00044

  limei. Construction and Effect of Hainan Medical Library Consortia Sharing System ——Based on the?Visual?Angle of Literature Information Resources Construction. 2021. doi: 10.12201/bmr.202110.00007

  gongwei, wentingxiao. Research on the development status and promotion strategy of medical information education in China in 5G era: An investigation based on the visual perspective. 2020. doi: 10.12201/bmr.202007.00014

  pangzhen, GuJiYu, WuYuFei, YanSshiXing, LiWangYang, SunYue. A study on the solution of the problem of extracting essential substance of TCM diagnosis and treatment of hypertension based on triple extraction strategy. 2021. doi: 10.12201/bmr.202107.00015

  limengxiang, xuyang, chenlei. Research on construction and application of online intelligent pre-consultation system. 2021. doi: 10.12201/bmr.202110.00026

  ruanxuling, liuqi, guo zhiheng, yanjunfeng. Research on prediction model of breast cancer based on LDA and XGBoost algorithm. 2022. doi: 10.12201/bmr.202106.00007

  Wu Xi, Yang Feng, Li Jiarui, Li wenfen, Zhu Junmin. Discussion on the Development Strategy of Internet Hospital Based on 4C Theoretical Model. 2021. doi: 10.12201/bmr.202101.00009

  chenquan, hu hongpu. Construction of Mobile Health Intervention Strategy for Elderly Diabetes Patients Based on Behavior. 2020. doi: 10.12201/bmr.202005.00245

• ID	Submit time	Number	Download
  1	2022-03-30	10.12201/bmr.202207.00009V1	Download

• Public  Anonymous  To author only Submit Comments