Identifying emergency department patients at high risk for opioid overdose using natural language processing and machine learning

0 PSYCHOLOGY, CLINICAL
Amanda Sharp , Gareth J. Parry , Gabriel Ríos Pérez , Brian O. Mullin , Xinyu Yang , Anika Kumar , Timothy Creedon , Michael Flores , Christopher M. Fischer , Zev Schuman-Olivier , Margo Moyer , Nathaniel M. Tran , Benjamin L. Cook
{"title":"Identifying emergency department patients at high risk for opioid overdose using natural language processing and machine learning","authors":"Amanda Sharp ,&nbsp;Gareth J. Parry ,&nbsp;Gabriel Ríos Pérez ,&nbsp;Brian O. Mullin ,&nbsp;Xinyu Yang ,&nbsp;Anika Kumar ,&nbsp;Timothy Creedon ,&nbsp;Michael Flores ,&nbsp;Christopher M. Fischer ,&nbsp;Zev Schuman-Olivier ,&nbsp;Margo Moyer ,&nbsp;Nathaniel M. Tran ,&nbsp;Benjamin L. Cook","doi":"10.1016/j.josat.2025.209718","DOIUrl":null,"url":null,"abstract":"<div><h3>Introduction</h3><div>Emergency departments (ED) are potential sites for identifying and treating individuals at high risk for opioid overdose. This study used machine learning (ML)-based models to predict opioid overdose death in the 12 months after an ED visit.</div></div><div><h3>Methods</h3><div>The study merged electronic health records (EHR), including clinical notes, of adult patients admitted to an urban safety net ED from 2011 to 2018 with opioid overdose-related mortality tables from 2012 to 2019. The sample includes all patients who experienced an opioid overdose related death (<em>n</em> = 729) and a subset of ED patients that did not (<em>n</em> = 4927). A mutual information classification algorithm was employed for feature selection. Predictive XGBoost, random forest, and regression models trained on 70 % of the sample with the reduced feature matrix and validated on a test set (30 % of sample).</div></div><div><h3>Results</h3><div>Feature selection reduced the feature matrix from 1336 to 50 features, with 37 originating from EHR clinical notes. Using a probability of &gt;0.5 as a predictor of opioid overdose death, all models demonstrated satisfactory calibration and excellent accuracy, precision, and recall across all models (averaging 92 % accuracy, 75 % precision and 57 % recall).</div></div><div><h3>Conclusion</h3><div>ML algorithms based on structured and unstructured EHR can successfully classify patients at risk of fatal opioid overdose. Prospectively, these tools can be used to identify patients that may benefit from interventions to reduce their risk of opioid overdose death. The development of these predictive models may improve the timeliness and efficacy of clinical decision making and ED-initiated services for opioid use disorders.</div></div>","PeriodicalId":73960,"journal":{"name":"Journal of substance use and addiction treatment","volume":"175 ","pages":"Article 209718"},"PeriodicalIF":0.0000,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of substance use and addiction treatment","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2949875925000979","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"PSYCHOLOGY, CLINICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction

Emergency departments (ED) are potential sites for identifying and treating individuals at high risk for opioid overdose. This study used machine learning (ML)-based models to predict opioid overdose death in the 12 months after an ED visit.

Methods

The study merged electronic health records (EHR), including clinical notes, of adult patients admitted to an urban safety net ED from 2011 to 2018 with opioid overdose-related mortality tables from 2012 to 2019. The sample includes all patients who experienced an opioid overdose related death (n = 729) and a subset of ED patients that did not (n = 4927). A mutual information classification algorithm was employed for feature selection. Predictive XGBoost, random forest, and regression models trained on 70 % of the sample with the reduced feature matrix and validated on a test set (30 % of sample).

Results

Feature selection reduced the feature matrix from 1336 to 50 features, with 37 originating from EHR clinical notes. Using a probability of >0.5 as a predictor of opioid overdose death, all models demonstrated satisfactory calibration and excellent accuracy, precision, and recall across all models (averaging 92 % accuracy, 75 % precision and 57 % recall).

Conclusion

ML algorithms based on structured and unstructured EHR can successfully classify patients at risk of fatal opioid overdose. Prospectively, these tools can be used to identify patients that may benefit from interventions to reduce their risk of opioid overdose death. The development of these predictive models may improve the timeliness and efficacy of clinical decision making and ED-initiated services for opioid use disorders.
使用自然语言处理和机器学习识别阿片类药物过量高风险的急诊科患者
急诊科(ED)是识别和治疗阿片类药物过量高风险个体的潜在场所。本研究使用基于机器学习(ML)的模型来预测急诊科就诊后12个月内阿片类药物过量死亡。方法将2011年至2018年城市安全网急诊科收治的成年患者的电子健康记录(包括临床记录)与2012年至2019年阿片类药物过量相关的死亡率表合并。样本包括所有经历阿片类药物过量相关死亡的患者(n = 729)和一部分未经历阿片类药物过量相关死亡的ED患者(n = 4927)。采用互信息分类算法进行特征选择。预测XGBoost、随机森林和回归模型在70%的样本上使用简化的特征矩阵进行训练,并在测试集(30%样本)上进行验证。结果特征选择将特征矩阵从1336个减少到50个,其中37个来自EHR临床记录。使用>;0.5的概率作为阿片类药物过量死亡的预测因子,所有模型都表现出令人满意的校准和出色的准确性、精密度和召回率(平均准确率为92%,精确度为75%,召回率为57%)。结论基于结构化和非结构化电子病历的ml算法可以成功地对阿片类药物过量致死风险患者进行分类。展望未来,这些工具可用于识别可能受益于干预措施以降低阿片类药物过量死亡风险的患者。这些预测模型的发展可能会提高阿片类药物使用障碍的临床决策和ed启动服务的及时性和有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of substance use and addiction treatment
Journal of substance use and addiction treatment Biological Psychiatry, Neuroscience (General), Psychiatry and Mental Health, Psychology (General)
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信