Ascertaining provider-level implicit bias in electronic health records with rules-based natural language processing: A pilot study in the case of prostate cancer.

<h4>Purpose</h4>Implicit, unconscious biases in medicine are personal attitudes about race, ethnicity, gender, and other characteristics that may lead to discriminatory patterns of care. However, there is no consensus on whether implicit bias represents a true predictor of differential c...

Full description

Saved in:
Bibliographic Details
Main Authors: Ashwin Ramaswamy, Michael Hung, Joe Pelt, Parsa Iranmahboub, Lina P Calderon, Ian S Scherr, Gerald Wang, David Green, Neal Patel, Timothy D McClure, Christopher Barbieri, Jim C Hu, Charlotta Lindvall, Douglas S Scherr
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0314989
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841525907334889472
author Ashwin Ramaswamy
Michael Hung
Joe Pelt
Parsa Iranmahboub
Lina P Calderon
Ian S Scherr
Gerald Wang
David Green
Neal Patel
Timothy D McClure
Christopher Barbieri
Jim C Hu
Charlotta Lindvall
Douglas S Scherr
author_facet Ashwin Ramaswamy
Michael Hung
Joe Pelt
Parsa Iranmahboub
Lina P Calderon
Ian S Scherr
Gerald Wang
David Green
Neal Patel
Timothy D McClure
Christopher Barbieri
Jim C Hu
Charlotta Lindvall
Douglas S Scherr
author_sort Ashwin Ramaswamy
collection DOAJ
description <h4>Purpose</h4>Implicit, unconscious biases in medicine are personal attitudes about race, ethnicity, gender, and other characteristics that may lead to discriminatory patterns of care. However, there is no consensus on whether implicit bias represents a true predictor of differential care given an absence of real-world studies. We conducted the first real-world pilot study of provider implicit bias by evaluating treatment parity in prostate cancer using unstructured data-the most common way providers document granular details of the patient encounter.<h4>Methods and findings</h4>Patients ≥18 years with a diagnosis of very-low to favorable intermediate-risk prostate cancer followed by 3 urologic oncologists from 2010 through 2021. The race Implicit Association Test was administered to all providers. Natural language processing screened human annotation using validated regex ontologies evaluated each provider's care on four prostate cancer quality indicators: (1) active surveillance utilization; (2) molecular biomarker discussion; (3) urinary function evaluation; and (4) sexual function evaluation. The chi-squared test and phi coefficient were utilized to respectively measure the statistical significance and the strength of association between race and four quality indicators. 1,094 patients were included. While Providers A and B demonstrated no preference on the race Implicit Association Test, Provider C showed preference for White patients. Provider C recommended active surveillance (p<0.01, φ = 0.175) and considered biomarkers (p = 0.047, φ = 0.127) more often in White men than expected, suggestive of treatment imparity. Provider A considered biomarkers (p<0.01, φ = 0.179) more often in White men than expected. Provider B demonstrated treatment parity in all evaluated quality indicators (p>0.05).<h4>Conclusions</h4>In this pilot study, providers' practice patterns were associated with both patient race and implicit racial preferences in prostate cancer. Alerting providers of existing implicit bias may restore parity, however future assessments are needed to validate this concept.
format Article
id doaj-art-16f3a3d0d3434966a43dbc0e3e786988
institution Kabale University
issn 1932-6203
language English
publishDate 2024-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-16f3a3d0d3434966a43dbc0e3e7869882025-01-17T05:31:56ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011912e031498910.1371/journal.pone.0314989Ascertaining provider-level implicit bias in electronic health records with rules-based natural language processing: A pilot study in the case of prostate cancer.Ashwin RamaswamyMichael HungJoe PeltParsa IranmahboubLina P CalderonIan S ScherrGerald WangDavid GreenNeal PatelTimothy D McClureChristopher BarbieriJim C HuCharlotta LindvallDouglas S Scherr<h4>Purpose</h4>Implicit, unconscious biases in medicine are personal attitudes about race, ethnicity, gender, and other characteristics that may lead to discriminatory patterns of care. However, there is no consensus on whether implicit bias represents a true predictor of differential care given an absence of real-world studies. We conducted the first real-world pilot study of provider implicit bias by evaluating treatment parity in prostate cancer using unstructured data-the most common way providers document granular details of the patient encounter.<h4>Methods and findings</h4>Patients ≥18 years with a diagnosis of very-low to favorable intermediate-risk prostate cancer followed by 3 urologic oncologists from 2010 through 2021. The race Implicit Association Test was administered to all providers. Natural language processing screened human annotation using validated regex ontologies evaluated each provider's care on four prostate cancer quality indicators: (1) active surveillance utilization; (2) molecular biomarker discussion; (3) urinary function evaluation; and (4) sexual function evaluation. The chi-squared test and phi coefficient were utilized to respectively measure the statistical significance and the strength of association between race and four quality indicators. 1,094 patients were included. While Providers A and B demonstrated no preference on the race Implicit Association Test, Provider C showed preference for White patients. Provider C recommended active surveillance (p<0.01, φ = 0.175) and considered biomarkers (p = 0.047, φ = 0.127) more often in White men than expected, suggestive of treatment imparity. Provider A considered biomarkers (p<0.01, φ = 0.179) more often in White men than expected. Provider B demonstrated treatment parity in all evaluated quality indicators (p>0.05).<h4>Conclusions</h4>In this pilot study, providers' practice patterns were associated with both patient race and implicit racial preferences in prostate cancer. Alerting providers of existing implicit bias may restore parity, however future assessments are needed to validate this concept.https://doi.org/10.1371/journal.pone.0314989
spellingShingle Ashwin Ramaswamy
Michael Hung
Joe Pelt
Parsa Iranmahboub
Lina P Calderon
Ian S Scherr
Gerald Wang
David Green
Neal Patel
Timothy D McClure
Christopher Barbieri
Jim C Hu
Charlotta Lindvall
Douglas S Scherr
Ascertaining provider-level implicit bias in electronic health records with rules-based natural language processing: A pilot study in the case of prostate cancer.
PLoS ONE
title Ascertaining provider-level implicit bias in electronic health records with rules-based natural language processing: A pilot study in the case of prostate cancer.
title_full Ascertaining provider-level implicit bias in electronic health records with rules-based natural language processing: A pilot study in the case of prostate cancer.
title_fullStr Ascertaining provider-level implicit bias in electronic health records with rules-based natural language processing: A pilot study in the case of prostate cancer.
title_full_unstemmed Ascertaining provider-level implicit bias in electronic health records with rules-based natural language processing: A pilot study in the case of prostate cancer.
title_short Ascertaining provider-level implicit bias in electronic health records with rules-based natural language processing: A pilot study in the case of prostate cancer.
title_sort ascertaining provider level implicit bias in electronic health records with rules based natural language processing a pilot study in the case of prostate cancer
url https://doi.org/10.1371/journal.pone.0314989
work_keys_str_mv AT ashwinramaswamy ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT michaelhung ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT joepelt ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT parsairanmahboub ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT linapcalderon ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT iansscherr ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT geraldwang ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT davidgreen ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT nealpatel ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT timothydmcclure ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT christopherbarbieri ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT jimchu ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT charlottalindvall ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer
AT douglassscherr ascertainingproviderlevelimplicitbiasinelectronichealthrecordswithrulesbasednaturallanguageprocessingapilotstudyinthecaseofprostatecancer