Natural language word embeddings as a glimpse into healthcare language and associated mortality surrounding end of life.
data science
documentation
electronic health records
medical records
patient-centered care
Journal
BMJ health & care informatics
ISSN: 2632-1009
Titre abrégé: BMJ Health Care Inform
Pays: England
ID NLM: 101745500
Informations de publication
Date de publication:
Oct 2021
Oct 2021
Historique:
received:
05
08
2021
accepted:
08
10
2021
entrez:
29
10
2021
pubmed:
30
10
2021
medline:
9
11
2021
Statut:
ppublish
Résumé
To clarify real-world linguistic nuances around dying in hospital as well as inaccuracy in individual-level prognostication to support advance care planning and personalised discussions on limitation of life sustaining treatment (LST). Retrospective cross-sectional study of real-world clinical data. Secondary care, urban and suburban teaching hospitals. All inpatients in 12-month period from 1 October 2018 to 30 September 2019. Using unsupervised natural language processing, word embedding in latent space was used to generate phrase clusters with most similar semantic embeddings to 'Ceiling of Treatment' and their prognostication value. Word embeddings with most similarity to 'Ceiling of Treatment' clustered around phrases describing end-of-life care, ceiling of care and LST discussions. The phrases have differing prognostic profile with the highest 7-day mortality in the phrases most explicitly referring to end of life-'Withdrawal of care' (56.7%), 'terminal care/end of life care' (57.5%) and 'un-survivable' (57.6%). Vocabulary used at end-of-life discussions are diverse and has a range of associations to 7-day mortality. This highlights the importance of correct application of terminology during LST and end-of-life discussions.
Identifiants
pubmed: 34711578
pii: bmjhci-2021-100464
doi: 10.1136/bmjhci-2021-100464
pmc: PMC8557276
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : Alzheimer's Society
ID : 171
Pays : United Kingdom
Organisme : Medical Research Council
ID : MC_PC_17214
Pays : United Kingdom
Informations de copyright
© Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY. Published by BMJ.
Déclaration de conflit d'intérêts
Competing interests: The authors have received research funding support from the Cicely Saunders Institute on Palliative Care, NIHR Applied Research Centre South London and the NIHR Maudsley Biomedical Research Centre.
Références
PLoS One. 2019 Nov 25;14(11):e0225625
pubmed: 31765395
Wellcome Open Res. 2018 Feb 22;3:15
pubmed: 29881785
BMC Med Inform Decis Mak. 2018 Jun 25;18(1):47
pubmed: 29941004
Artif Intell Med. 2021 Jul;117:102083
pubmed: 34127232
Br J Gen Pract. 2017 Mar;67(656):104-105
pubmed: 28232333
BMJ. 2015 Jan 22;350:h386
pubmed: 25616280
PLoS One. 2018 Jun 7;13(6):e0198687
pubmed: 29879201
BMJ Open. 2015 Jun 29;5(6):e007492
pubmed: 26124510
BMJ Open. 2015 Sep 14;5(9):e008242
pubmed: 26369795
J Palliat Med. 2017 Aug;20(8):857-861
pubmed: 28388341
BMJ. 2017 Feb 28;356:j813
pubmed: 28246084
BMC Med. 2013 Oct 01;11:213
pubmed: 24083470