Natural Language Word-Embeddings as a glimpse into healthcare at the End Of Life

Abstract

AbstractIntroductionPlanning in advance and personalised discussions on limitation of life sustaining treatment (LST) is an indicator of good care. However, there are many linguistic nuances and misunderstandings around dying in hospital as well as inaccuracy in individual-level prognostication.MethodsUsing unsupervised natural language processing (NLP), we explored real-world terminology using phrase clusters with most similar sematic embeddings to “Ceiling of Treatment” and their prognostication value in the electronic health record of an urban teaching hospital.ResultsWord embeddings with most similar to “Ceiling of Treatment” clustered around phrases describing end-of-life care, ceiling of care and resuscitation discussions. The phrases have differing prognostic profile with the highest 7-day mortality in the phrases most implicitly referring to end of life -“terminal care”, “end of life care” (57.5%) and “unsurvivable” (57.6%).ConclusionNLP can quantify and analyse real-world end of life discussions around prognosis and appropriate LST.Patient-friendly Summary(by expert patients: Sherry Charing, Alan Quarterman, Harold Parkes)Discussions between doctors, patients and family in deciding what is the appropriate maximum treatment a specific patient should have based on their clinical condition is complex. Discussions, often involving expressions regarding “End Of Life” care are used to describe the maximum invasive treatments a patient should have or would want. There are a range of expressions used, many with overlapping meanings which can be confusing, not only for the patient and family, but also for doctors reading the patient’s clinical notes. In this study, a computational approach using Artificial Intelligence to read clinical patient notes was carried out by looking at thousands of patient records from a large urban hospital. Expressions that doctors use to describe these discussions were analysed to show the associations of particular words and phrases in relation to mortality. Using a computer analysis for this study it was possible to quantify the use of these expressions and their relation to the “End Of Life”. Through this AI-based approach, real-world use of phrases and language relating “End Of Life” can be analysed to understand how doctors and patients are communicating, and about any possible misunderstandings of language.