Artificial Intelligence has no role in palliative care…or does it?

It would be easy to assume that there many things which could contribute to the development of palliative care, but Artificial Intelligence (AI) isn’t one of them.  Yet, today we hear from Dr.Max Sarmet and Dr. Ambereen K. Mehta – both passionate about technology, and who make the case that AI can make a unique contribution to advancing palliative care.

Artificial Intelligence (AI) has been playing an increasingly important role in our daily life. In healthcare, AI algorithms can analyse large amounts of complex medical data, helping medical professionals to make more informed decisions, such as predicting patient outcomes, diagnoses, and treatment plans.1,2 AI-powered tools and systems can also be used for drug discovery, medical imaging, and disease monitoring, among other applications.1,2,3 By using AI in these diverse ways, researchers and clinicians can process vast amounts of data, identify patterns, and make predictions that are not possible through manual analysis alone. As a result, AI has the potential to revolutionise the way healthcare is delivered and improve patient outcomes.1,2,3

As researchers in palliative care and passionate about technology, we decided to explore how AI tools have been used in our field in recent years. We focused on Natural Language Processing (NLP), a subfield of AI and computer science that deals with human-computer interaction using natural language.3 NLP involves developing algorithms and models to understand, interpret, and generate human language (called ‘natural language’), such as speech and text, enabling computers to process and analyse it. NLP is used in a variety of applications such as virtual assistants (e.g., Siri and Alexa) to understand and respond to user commands or queries. Chatbots (e.g., ChatGPT and online customer service) use NLP to converse with users in a natural, human-like way. NLP is also used in ‘sentiment analysis’ to analyse and understand the emotions or opinions expressed in text or audio. Overall, this technology has the potential to improve human-computer communication, meaning that AI will have even more uses in our everyday lives.

According to our scoping review findings, the use of NLP in palliative care research has been growing in recent years. A review of 82 papers on this topic found that NLP has been used in various ways, from analysing text from electronic health records to assessing quality benchmarks for processes of care (for example, treatments performed, length of stay in ICU or time from hospitalisation to discharge). Thirty-two different NLP software and 33 different machine learning methods were identified within palliative care research, used alone or in combination to extract and analyse data. The most frequent use of AI in palliative care was mortality and prognosis prediction. Algorithms were employed in this case to predict the progression of a disease or the life expectancy of a patient by utilising electronic health record (EHR) data. This facilitates clinicians in making well-informed decisions, resulting in better care for end-of-life patients. We also identified a trend where natural language processing was frequently used in analysing clinical serious illness conversations extracted from audio recordings. There are numerous AI-based software applications that can process thousands of recorded audio conversations in just a few minutes. These applications are capable of identifying trends, the most commonly discussed topics, and even the emotions expressed within the conversations.

In comparison to traditional research methods, NLP provides more accurate and in-depth analysis, with more comprehensive data sources and less interpretation bias.1,2,3 The increasing interest from funding agencies in studies using NLP for palliative care research and the fact that this article was selected as February’s Palliative Medicine’s Editor’s Choice highlights the potential for this method to have a significant impact on the field.

In our review, NLP showed its potential to overcome challenges associated with symptom identification and quality assessment in large datasets, promote research in policy-making and improve outcomes for patients, care partners, and healthcare workers. With its ability to analyse a wider range of subjects and larger amounts of data,1 NLP has been used in palliative care studies to identify outcomes which are more specific and more meaningful to patients and their relatives.

Incorporating AI into our lives and work can significantly increase our potential as humans by augmenting our capabilities and allowing us to tackle complex problems more efficiently and effectively. By harnessing the power of AI, we can gain new insights, make more informed decisions, and achieve outcomes that would otherwise be difficult or impossible to achieve. We hope that our study will support others to harness the power of AI in palliative care research while upholding the fundamental human principles of the field, which will never be fully replicated or substituted by AI.


‘The Use of Natural Language Processing in Palliative Care Research: a Scoping Review’ Max Sarmet, Aamna Kabani, Luis Coelho, Sara Seabra dos Reis, Jorge L Zeredo, and Ambereen K Mehta. First published:  Palliative Medicine 2023, Vol. 37(2) 275–290. EAPC members can access a FREE copy from the EAPC website here.


1.         Morin L, Onwuteaka-Philipsen BD. The promise of big data for palliative and end-of-life care research. Palliative medicine 2021; 35: 1638–1640.

2.         Nwosu AC, Collins B, Mason S. Big Data analysis to improve care for people living with serious illness: The potential to use new emerging technology in palliative care. Palliative medicine 2018; 32: 164–166.

3.         Yim W-W, Yetisgen M, Harris WP, et al. Natural Language Processing in Oncology: A Review. JAMA Oncol 2016; 2: 797–804.

Links and resources

  • Learn more about technology, science, and AI at the MIT Technology Review website here.
  • Read other Palliative Medicine Editor’s Choice posts on the EAPC blog.
  • Follow Palliative Medicine on Twitter: @palliativemedj

About the authors

Dr.Max Sarmet, SLP, MSc is a Speech-Language Pathologist from Brazil working with Neuropalliative care. He is also a PhD candidate at the University of Brasília in the field of Health Science and Technology. He is the Social Media Task Force Lead for the Strategic Communications Committee of the International Neuropalliative Care Society (INPCS) @Neuropalcare.  Twitter: @MaxSarmet. ORCID: 0000-0003-3029-8912.  

Dr. Ambereen K. Mehta, MD, MPH is an Associate Professor of Palliative Medicine at Johns Hopkins School of Medicine. She developed the palliative care program for the Johns Hopkins Center for ALS Specialty Care. She is currently co-chair of the Palliative Committee for the Northeast ALS Association and Chair of the Strategic Communications Committee for the INPCS. Twitter: @AMehtaMD. ORCID: 0000-0001-7834-2279.

This entry was posted in EAPC-LINKED JOURNALS, Journal of Palliative Medicine, Palliative Medicine: Editor's Choice, RESEARCH. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.