Cargando…

Natural language processing to identify reasons for sex disparity in statin prescriptions

BACKGROUND: Statins are the cornerstone of treatment of patients with atherosclerotic cardiovascular disease (ASCVD). Despite this, multiple studies have shown that women with ASCVD are less likely to be prescribed statins than men. The objective of this study was to use Natural Language Processing...

Descripción completa

Detalles Bibliográficos
Autores principales: Witting, Celeste, Azizi, Zahra, Gomez, Sofia Elena, Zammit, Alban, Sarraju, Ashish, Ngo, Summer, Hernandez-Boussard, Tina, Rodriguez, Fatima
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10147966/
https://www.ncbi.nlm.nih.gov/pubmed/37128554
http://dx.doi.org/10.1016/j.ajpc.2023.100496
_version_ 1785034897410228224
author Witting, Celeste
Azizi, Zahra
Gomez, Sofia Elena
Zammit, Alban
Sarraju, Ashish
Ngo, Summer
Hernandez-Boussard, Tina
Rodriguez, Fatima
author_facet Witting, Celeste
Azizi, Zahra
Gomez, Sofia Elena
Zammit, Alban
Sarraju, Ashish
Ngo, Summer
Hernandez-Boussard, Tina
Rodriguez, Fatima
author_sort Witting, Celeste
collection PubMed
description BACKGROUND: Statins are the cornerstone of treatment of patients with atherosclerotic cardiovascular disease (ASCVD). Despite this, multiple studies have shown that women with ASCVD are less likely to be prescribed statins than men. The objective of this study was to use Natural Language Processing (NLP) to elucidate factors contributing to this disparity. METHODS: Our cohort included adult patients with two or more encounters between 2014 and 2021 with an ASCVD diagnosis within a multisite electronic health record (EHR) in Northern California. After reviewing structured EHR prescription data, we used a benchmark deep learning NLP approach, Clinical Bidirectional Encoder Representations from Transformers (BERT), to identify and interpret discussions of statin prescriptions documented in clinical notes. Clinical BERT was evaluated against expert clinician review in 20% test sets. RESULTS: There were 88,913 patients with ASCVD (mean age 67.8±13.1 years) and 35,901 (40.4%) were women. Women with ASCVD were less likely to be prescribed statins compared with men (56.6% vs 67.6%, p <0.001), and, when prescribed, less likely to be prescribed guideline-directed high-intensity dosing (41.4% vs 49.8%, p <0.001). These disparities were more pronounced among younger patients, patients with private insurance, and those for whom English is their preferred language. Among those not prescribed statins, women were less likely than men to have statins mentioned in their clinical notes (16.9% vs 19.1%, p <0.001). Women were less likely than men to have statin use reported in clinical notes despite absence of recorded prescription (32.8% vs 42.6%, p <0.001). Women were slightly more likely than men to have statin intolerance documented in structured data or clinical notes (6.0% vs 5.3%, p=0.003). CONCLUSIONS: Women with ASCVD were less likely to be prescribed guideline-directed statins compared with men. NLP identified additional sex-based statin disparities and reasons for statin non-prescription in clinical notes of patients with ASCVD.
format Online
Article
Text
id pubmed-10147966
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-101479662023-04-30 Natural language processing to identify reasons for sex disparity in statin prescriptions Witting, Celeste Azizi, Zahra Gomez, Sofia Elena Zammit, Alban Sarraju, Ashish Ngo, Summer Hernandez-Boussard, Tina Rodriguez, Fatima Am J Prev Cardiol Original Research Contribution BACKGROUND: Statins are the cornerstone of treatment of patients with atherosclerotic cardiovascular disease (ASCVD). Despite this, multiple studies have shown that women with ASCVD are less likely to be prescribed statins than men. The objective of this study was to use Natural Language Processing (NLP) to elucidate factors contributing to this disparity. METHODS: Our cohort included adult patients with two or more encounters between 2014 and 2021 with an ASCVD diagnosis within a multisite electronic health record (EHR) in Northern California. After reviewing structured EHR prescription data, we used a benchmark deep learning NLP approach, Clinical Bidirectional Encoder Representations from Transformers (BERT), to identify and interpret discussions of statin prescriptions documented in clinical notes. Clinical BERT was evaluated against expert clinician review in 20% test sets. RESULTS: There were 88,913 patients with ASCVD (mean age 67.8±13.1 years) and 35,901 (40.4%) were women. Women with ASCVD were less likely to be prescribed statins compared with men (56.6% vs 67.6%, p <0.001), and, when prescribed, less likely to be prescribed guideline-directed high-intensity dosing (41.4% vs 49.8%, p <0.001). These disparities were more pronounced among younger patients, patients with private insurance, and those for whom English is their preferred language. Among those not prescribed statins, women were less likely than men to have statins mentioned in their clinical notes (16.9% vs 19.1%, p <0.001). Women were less likely than men to have statin use reported in clinical notes despite absence of recorded prescription (32.8% vs 42.6%, p <0.001). Women were slightly more likely than men to have statin intolerance documented in structured data or clinical notes (6.0% vs 5.3%, p=0.003). CONCLUSIONS: Women with ASCVD were less likely to be prescribed guideline-directed statins compared with men. NLP identified additional sex-based statin disparities and reasons for statin non-prescription in clinical notes of patients with ASCVD. Elsevier 2023-04-11 /pmc/articles/PMC10147966/ /pubmed/37128554 http://dx.doi.org/10.1016/j.ajpc.2023.100496 Text en © 2023 The Authors. Published by Elsevier B.V. https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Original Research Contribution
Witting, Celeste
Azizi, Zahra
Gomez, Sofia Elena
Zammit, Alban
Sarraju, Ashish
Ngo, Summer
Hernandez-Boussard, Tina
Rodriguez, Fatima
Natural language processing to identify reasons for sex disparity in statin prescriptions
title Natural language processing to identify reasons for sex disparity in statin prescriptions
title_full Natural language processing to identify reasons for sex disparity in statin prescriptions
title_fullStr Natural language processing to identify reasons for sex disparity in statin prescriptions
title_full_unstemmed Natural language processing to identify reasons for sex disparity in statin prescriptions
title_short Natural language processing to identify reasons for sex disparity in statin prescriptions
title_sort natural language processing to identify reasons for sex disparity in statin prescriptions
topic Original Research Contribution
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10147966/
https://www.ncbi.nlm.nih.gov/pubmed/37128554
http://dx.doi.org/10.1016/j.ajpc.2023.100496
work_keys_str_mv AT wittingceleste naturallanguageprocessingtoidentifyreasonsforsexdisparityinstatinprescriptions
AT azizizahra naturallanguageprocessingtoidentifyreasonsforsexdisparityinstatinprescriptions
AT gomezsofiaelena naturallanguageprocessingtoidentifyreasonsforsexdisparityinstatinprescriptions
AT zammitalban naturallanguageprocessingtoidentifyreasonsforsexdisparityinstatinprescriptions
AT sarrajuashish naturallanguageprocessingtoidentifyreasonsforsexdisparityinstatinprescriptions
AT ngosummer naturallanguageprocessingtoidentifyreasonsforsexdisparityinstatinprescriptions
AT hernandezboussardtina naturallanguageprocessingtoidentifyreasonsforsexdisparityinstatinprescriptions
AT rodriguezfatima naturallanguageprocessingtoidentifyreasonsforsexdisparityinstatinprescriptions