A deep learning analysis for dual healthcare system users and risk of opioid use disorder

Abstract The opioid crisis has disproportionately affected U.S. veterans, leading the Veterans Health Administration to implement opioid prescribing guidelines. Veterans who receive care from both VA and non-VA providers—known as dual-system users—have an increased risk of Opioid Use Disorder (OUD)....

Full description

Saved in:
Bibliographic Details
Main Authors: Ying Yin, Elizabeth Workman, Phillip Ma, Yan Cheng, Yijun Shao, Joseph L. Goulet, Friedhelm Sandbrink, Cynthia Brandt, Christopher Spevak, Jacob T. Kean, William Becker, Alexander Libin, Nawar Shara, Helen M. Sheriff, Jorie Butler, Rajeev M. Agrawal, Joel Kupersmith, Qing Zeng-Trietler
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-77602-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832571783863074816
author Ying Yin
Elizabeth Workman
Phillip Ma
Yan Cheng
Yijun Shao
Joseph L. Goulet
Friedhelm Sandbrink
Cynthia Brandt
Christopher Spevak
Jacob T. Kean
William Becker
Alexander Libin
Nawar Shara
Helen M. Sheriff
Jorie Butler
Rajeev M. Agrawal
Joel Kupersmith
Qing Zeng-Trietler
author_facet Ying Yin
Elizabeth Workman
Phillip Ma
Yan Cheng
Yijun Shao
Joseph L. Goulet
Friedhelm Sandbrink
Cynthia Brandt
Christopher Spevak
Jacob T. Kean
William Becker
Alexander Libin
Nawar Shara
Helen M. Sheriff
Jorie Butler
Rajeev M. Agrawal
Joel Kupersmith
Qing Zeng-Trietler
author_sort Ying Yin
collection DOAJ
description Abstract The opioid crisis has disproportionately affected U.S. veterans, leading the Veterans Health Administration to implement opioid prescribing guidelines. Veterans who receive care from both VA and non-VA providers—known as dual-system users—have an increased risk of Opioid Use Disorder (OUD). The interaction between dual-system use and demographic and clinical factors, however, has not been previously explored. We conducted a retrospective study of 856,299 patient instances from the Washington DC and Baltimore VA Medical Centers (2012–2019), using a deep neural network (DNN) and explainable Artificial Intelligence to examine the impact of dual-system use on OUD and how demographic and clinical factors interact with it. Of the cohort, 146,688(17%) had OUD, determined through Natural Language Processing of clinical notes and ICD-9/10 diagnoses. The DNN model, with a 78% area under the curve, confirmed that dual-system use is a risk factor for OUD, along with prior opioid use or other substance use. Interestingly, a history of other drug use interacted negatively with dual-system use regarding OUD risk. In contrast, older age was associated with a lower risk of OUD but interacted positively with dual-system use. These findings suggest that within the dual-system users, patients with certain risk profiles warrant special attention.
format Article
id doaj-art-43de9d3be4f6459e957a73cb9bf29d3d
institution Kabale University
issn 2045-2322
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-43de9d3be4f6459e957a73cb9bf29d3d2025-02-02T12:19:42ZengNature PortfolioScientific Reports2045-23222025-01-011511910.1038/s41598-024-77602-4A deep learning analysis for dual healthcare system users and risk of opioid use disorderYing Yin0Elizabeth Workman1Phillip Ma2Yan Cheng3Yijun Shao4Joseph L. Goulet5Friedhelm Sandbrink6Cynthia Brandt7Christopher Spevak8Jacob T. Kean9William Becker10Alexander Libin11Nawar Shara12Helen M. Sheriff13Jorie Butler14Rajeev M. Agrawal15Joel Kupersmith16Qing Zeng-Trietler17Washington DC VA Medical CenterWashington DC VA Medical CenterWashington DC VA Medical CenterWashington DC VA Medical CenterWashington DC VA Medical CenterVA Connecticut Healthcare SystemWashington DC VA Medical CenterVA Connecticut Healthcare SystemGeorgetown University School of MedicineThe University of UtahVA Connecticut Healthcare SystemGeorgetown University School of MedicineGeorgetown University School of MedicineWashington DC VA Medical CenterThe University of UtahMedStar HealthGeorgetown University School of MedicineWashington DC VA Medical CenterAbstract The opioid crisis has disproportionately affected U.S. veterans, leading the Veterans Health Administration to implement opioid prescribing guidelines. Veterans who receive care from both VA and non-VA providers—known as dual-system users—have an increased risk of Opioid Use Disorder (OUD). The interaction between dual-system use and demographic and clinical factors, however, has not been previously explored. We conducted a retrospective study of 856,299 patient instances from the Washington DC and Baltimore VA Medical Centers (2012–2019), using a deep neural network (DNN) and explainable Artificial Intelligence to examine the impact of dual-system use on OUD and how demographic and clinical factors interact with it. Of the cohort, 146,688(17%) had OUD, determined through Natural Language Processing of clinical notes and ICD-9/10 diagnoses. The DNN model, with a 78% area under the curve, confirmed that dual-system use is a risk factor for OUD, along with prior opioid use or other substance use. Interestingly, a history of other drug use interacted negatively with dual-system use regarding OUD risk. In contrast, older age was associated with a lower risk of OUD but interacted positively with dual-system use. These findings suggest that within the dual-system users, patients with certain risk profiles warrant special attention.https://doi.org/10.1038/s41598-024-77602-4Deep neural networkExplainable AIOpioid use disorderDual-system useInteraction
spellingShingle Ying Yin
Elizabeth Workman
Phillip Ma
Yan Cheng
Yijun Shao
Joseph L. Goulet
Friedhelm Sandbrink
Cynthia Brandt
Christopher Spevak
Jacob T. Kean
William Becker
Alexander Libin
Nawar Shara
Helen M. Sheriff
Jorie Butler
Rajeev M. Agrawal
Joel Kupersmith
Qing Zeng-Trietler
A deep learning analysis for dual healthcare system users and risk of opioid use disorder
Scientific Reports
Deep neural network
Explainable AI
Opioid use disorder
Dual-system use
Interaction
title A deep learning analysis for dual healthcare system users and risk of opioid use disorder
title_full A deep learning analysis for dual healthcare system users and risk of opioid use disorder
title_fullStr A deep learning analysis for dual healthcare system users and risk of opioid use disorder
title_full_unstemmed A deep learning analysis for dual healthcare system users and risk of opioid use disorder
title_short A deep learning analysis for dual healthcare system users and risk of opioid use disorder
title_sort deep learning analysis for dual healthcare system users and risk of opioid use disorder
topic Deep neural network
Explainable AI
Opioid use disorder
Dual-system use
Interaction
url https://doi.org/10.1038/s41598-024-77602-4
work_keys_str_mv AT yingyin adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT elizabethworkman adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT phillipma adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT yancheng adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT yijunshao adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT josephlgoulet adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT friedhelmsandbrink adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT cynthiabrandt adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT christopherspevak adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT jacobtkean adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT williambecker adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT alexanderlibin adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT nawarshara adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT helenmsheriff adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT joriebutler adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT rajeevmagrawal adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT joelkupersmith adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT qingzengtrietler adeeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT yingyin deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT elizabethworkman deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT phillipma deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT yancheng deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT yijunshao deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT josephlgoulet deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT friedhelmsandbrink deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT cynthiabrandt deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT christopherspevak deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT jacobtkean deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT williambecker deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT alexanderlibin deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT nawarshara deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT helenmsheriff deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT joriebutler deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT rajeevmagrawal deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT joelkupersmith deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder
AT qingzengtrietler deeplearninganalysisfordualhealthcaresystemusersandriskofopioidusedisorder