# A Short Review of Ethical Challenges in Clinical Natural Language Processing

## TL;DR

This paper reviews ethical challenges in clinical NLP, focusing on privacy concerns, data accessibility, biases, and their impact on research validity and societal harm.

## Contribution

It highlights key ethical issues in clinical NLP, discusses privacy measures, sources of less sensitive data, and emphasizes bias mitigation for responsible research.

## Key findings

- Privacy concerns hinder data access for research
- Biases in clinical NLP can compromise validity
- Less sensitive data sources can facilitate ethical research

## Abstract

Clinical NLP has an immense potential in contributing to how clinical practice will be revolutionized by the advent of large scale processing of clinical records. However, this potential has remained largely untapped due to slow progress primarily caused by strict data access policies for researchers. In this paper, we discuss the concern for privacy and the measures it entails. We also suggest sources of less sensitive data. Finally, we draw attention to biases that can compromise the validity of empirical research and lead to socially harmful applications.