Healthcare NLP: where are we and what is next?

Abstract

This tutorial focuses on Healthcare Domain Applications of NLP, what we have achieved around HealthcareNLP and the challenges that lie ahead for the future.

Existing reviews in this domain either overlook some important tasks, such as synthetic data generation for addressing privacy concerns, or explainable clinical NLP for improved integration and implementation, or fail to mention important methodologies, including retrieval augmented generation and the neural symbolic integration of large language models (LLMs) and knowledge graphs (KGs).

In light of this, the goal of this tutorial is to provide an overview introduction of the most important sub-areas of a patient and resource/data-oriented

HealthcareNLP, with three layers of hierarchy: 1) data/resource layer: annotation guidelines, ethical approvals, governance, synthetic data; 2) NLP-Eval layer: NLP tasks NER, relation extraction (RE), sentiment analysis, and linking/coding with categorised methods, leading to explainable HealthAI; 3) patients layer: Patient Public Involvement and Engagement (PPIE), health literacy, translation, simplification, and summarisation (\textit{aka} NLP tasks), shared decision making support. A hands-on session or group discussion will be included in the tutorial for audiences to use HealthcareNLP applications or engage in discussing the challenges and issues in the field. The target audiences include NLP practitioners in the healthcare application domain, NLP researchers who are interested in domain applications, Healthcare researchers (HealthcareNLP users), and students from NLP fields. The type of tutorial is ``Introductory to CL/NLP topics (HealthcareNLP)'' and audiences do not need prior knowledge to attend this. Tutorial materials will be available at \url{https://github.com/4dpicture/HealthNLP}