Introduction

In the past few decades, growing adoption of electronic health records (EHRs) systems have made massive clinical narrative data available electronically. Natural language processing (NLP) technologies that can unlock information from narrative text have received great attention in the medical domain. Many clinical NLP methods and systems have been developed and showed promising results in various information extraction tasks. These methods and tools have also been successfully applied to facilitate clinical research, as well as to support healthcare applications. At the same time, the availability and use of health information online has exploded through use of social media, question-answering and community discussion forums, and health-related websites. These present additional challenges and opportunities for further development of new methodologies and healthcare applications.

The goal of this workshop is to provide a unique platform to bring together researchers and practitioners in healthcare informatics working with health-related free text, and facilitate close interaction among students, scholars, and industry professionals on health NLP challenges worldwide. This is a one-day workshop that consists of invited speakers, podium talks, and poster presentations. The workshop will be held on August 9th, 2021, virtually at Victoria, Canada, in conjunction with the IEEE International Conference on Healthcare Informatics (ICHI 2021). Due to the uncertainty of current pandemics, we are going virtual with the workshop.

We invite papers and short abstracts on novel approaches, works in progress, comparative analyses of tools, and original state-of-the-art work in health NLP methods, tools, and applications. Selected papers will be presented as podium talks, and other interesting submissions and abstracts will be showcased as poster presentations.

Audience

Target audience includes both health NLP researchers and consumers. Anyone interested in NLP-based approaches, solutions, and applications in clinical, biomedical, and consumer health informatics is welcome. Researchers and students working on health NLP projects and others interested in learning about and sharing NLP knowledge and resources are strongly encouraged to attend. We also welcome students who wish to closely interact with NLP experts. Potential attendees may come from NLP communities in the medical domain (e.g., AMIA NLP Working Group, BioNLP) and computer and information scientists and linguists working on health-related text processing (e.g., with interests in ACL, EMNLP, NAACL, TREC Precision Medicine and Clinical Decision Support tracks, etc.), as well as general health informatics professionals and researchers.

Agenda

HealthNLP is scheduled as: 7:00 am - 13:00 pm, Victoria time (14:00 pm - 20:00 pm UTC), Aug 9th
7:00am Opening marks, Rui Zhang
7:10am Keynote: Summarization for medical question answering
Dina Demner Fushman, NLM/NIH
7:45am Contrastive Representations Pre-Training for Enhanced Discharge Summary BERT
Daeyeon Won, Youngjun Lee, Hojin Choi and Yuchae Jung
8:00am A HIE-BERT Model for Diagnosis Assistant Based
Kunli Zhang, Bin Hu and Xu Zhao
8:15am Deep Transfer Learning for Medical Question Matching
Yedan Shen, Xiaowei Huang, Buzhou Tang, Xiaolong Wang, Qingcai Chen and Yuan Ni
8:30am A Comparative Study of Pre-trained Language Models for Named Entity Recognition in Clinical Trial Eligibility Criteria from Multiple Corpora
Jianfu Li, Qiang Wei, Omid Ghiasvand, Miao Chen, Victor Lobanov, Chunhua Weng and Hua Xu
8:45am Developing an Interpretable Etiology Classification Model for Ischemic Stroke Based on Chinese Clinical Practice Guideline
Xiaowei Xu, Lu Qin, Zixiao Li and Jiao Li
9:00am Break
9:30am Topic Extraction from A Cancer Health Forum
Samuel Miles, Lixia Yao, Weilin Meng, Christopher M. Black and Zina Ben-Miled
9:45am Applying Bayesian hyperparameter optimization towards accurate and efficient topic modeling in clinical notes
Minghao Li, Kyeryoung Lee, Zongzhi Liu, Meng Ma, Qi Pan, Rong Chen, Eric Schadt and Xiaoyan Wang
10:00am Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models
Sicheng Zhou, Dalton Schutte, Aiwen Xing, Jiyang Chen, Julian Wolfson, Zhe He, Fang Yu and Rui Zhang
10:15am Robustly Pre-Trained Neural Model for Direct Temporal Relation Extraction
Hong Guan, Murthy Devarakonda, Jianfu Li and Hua Xu
10:30am Identify Diabetic Retinopathy-related Clinical Concepts Using Transformer-based Natural Language Processing Methods
Zehao Yu, Xi Yang, Gianna L Sweeting, Yinghan Ma, Ruogu Fang, Yonghui Wu and Skylar E Stolte
11:00am Break
11:30am Clinical Trial Information Extraction with BERT
Xiong Liu, Greg Hersch, Iya Khalil and Murthy Devarakonda
11:45am An empirical study of using radiology reports and images to improve ICU-mortality prediction
Mingquan Lin, Song Wang, Ying Ding, Lihui Zhao, Fei Wang and Yifan Peng
12:00pm Dementia Detection using Transformers-Based Deep Learning and Natural Language Processing Models
Ploypaphat Saltz, Shih Yin Lin, Sunny Chieh Cheng and Dong Si
12:15pm Self-supervised extractive text summarization for biomedical literatures
Tianyi Xie, Yi Zhen, Tianqi Li, Chuqin Li and Yaorong Ge
12:30pm Impact of detecting clinical trial elements in exploration of COVID-19 literature
Simon Suster, Karin Verspoor, Timothy Baldwin, Jey Han Lau, Antonio Jimeno, David Martinez and Yulia Otmakhova

Important dates

Submission and Review

Authors may submit regular papers (4-10 pages, including references) and abstracts (2 pages, including references) in the format used for the ICHI submissions. Developers of NLP tools may submit a demo paper (up to 4 pages, including references) describing the tool, along with a link to a web demonstration (interactive website or a demonstration video). As with ICHI, the workshop will follow single-blind reviewing, therefore submissions should have the names and affiliations of authors listed on the paper. Papers must adhere to the IEEE Proceedings Format available for LaTeX and Word, and submitted as a single PDF file. Submissions will be handled electronically through EasyChair (https://easychair.org/conferences/?conf=healthnlp2021). For more information, please read the detailed submission instructions (link here).

All submissions will undergo a peer review by at least two domain experts from the program committee. The selection of papers and posters will be primarily based on the potential to generate discussion and impact future research directions. Accepted papers will be included in the ICHI 2021 Proceedings and IEEE Digital Library. Selected papers will be invited to publish an extended version of their work in a special issue of BMC Medical Informatics and Decision Making journal (IF=2.317) with a discount publication fee.

Organizers

Chairs:

Publication Chair:

Steering committee:

Program Committee:

Past workshops