Lingshu Xue, Ruofei Yin, Evan S Cole, Wei-Hsuan Lo-Ciganic, Walid F Gellad, Julie Donohue, Lu Tang
{"title":"开发和评估机器学习模型,以预测参与社区治疗计划的医疗补助登登者中阿片类药物使用障碍的急性护理。","authors":"Lingshu Xue, Ruofei Yin, Evan S Cole, Wei-Hsuan Lo-Ciganic, Walid F Gellad, Julie Donohue, Lu Tang","doi":"10.1111/add.70079","DOIUrl":null,"url":null,"abstract":"<p><strong>Aims: </strong>To develop machine-learning algorithms for predicting the risk of a hospitalization or emergency department (ED) visit for opioid use disorder (OUD) (i.e. OUD acute events) in Pennsylvania Medicaid enrollees in the Opioid Use Disorder Centers of Excellence (COE) program and to evaluate the fairness of model performance across racial groups.</p><p><strong>Methods: </strong>We studied 20 983 United States Medicaid enrollees aged 18 years or older who had COE visits between April 2019 and March 2021. We applied multivariate logistic regression, least absolute shrinkage and selection operator models, random forests, and eXtreme Gradient Boosting (XGB), to predict OUD acute events following the initial COE visit. Our models included predictors at the system, patient, and regional levels. We assessed model performance using multiple metrics by racial groups. Individuals were divided into a low, medium and high-risk group based on predicted risk scores.</p><p><strong>Results: </strong>The training (n = 13 990) and testing (n = 6993) samples displayed similar characteristics (mean age 38.1 ± 9.3 years, 58% male, 80% White enrollees) with 4% experiencing OUD acute events at baseline. XGB demonstrated the best prediction performance (C-statistic = 76.6% [95% confidence interval = 75.6%-77.7%] vs. 72.8%-74.7% for other methods). At the balanced cutoff, XGB achieved a sensitivity of 68.2%, specificity of 70.0%, and positive predictive value of 8.3%. The XGB model classified the testing sample into high-risk (6%), medium-risk (30%), and low-risk (63%) groups. In the high-risk group, 40.7% had OUD acute events vs. 16.5% and 5.0% in the medium- and low-risk groups. The high- and medium-risk groups captured 44% and 26% of individuals with OUD events. The XGB model exhibited lower false negative rates and higher false positive rates in racial/ethnic minority groups than White enrollees.</p><p><strong>Conclusions: </strong>New machine-learning algorithms perform well to predict risks of opioid use disorder (OUD) acute care use among United States Medicaid enrollees and improve fairness of prediction across racial and ethnic groups compared with previous OUD-related models.</p>","PeriodicalId":109,"journal":{"name":"Addiction","volume":" ","pages":""},"PeriodicalIF":5.2000,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Development and evaluation of a machine learning model to predict acute care for opioid use disorder among Medicaid enrollees engaged in a community-based treatment program.\",\"authors\":\"Lingshu Xue, Ruofei Yin, Evan S Cole, Wei-Hsuan Lo-Ciganic, Walid F Gellad, Julie Donohue, Lu Tang\",\"doi\":\"10.1111/add.70079\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Aims: </strong>To develop machine-learning algorithms for predicting the risk of a hospitalization or emergency department (ED) visit for opioid use disorder (OUD) (i.e. OUD acute events) in Pennsylvania Medicaid enrollees in the Opioid Use Disorder Centers of Excellence (COE) program and to evaluate the fairness of model performance across racial groups.</p><p><strong>Methods: </strong>We studied 20 983 United States Medicaid enrollees aged 18 years or older who had COE visits between April 2019 and March 2021. We applied multivariate logistic regression, least absolute shrinkage and selection operator models, random forests, and eXtreme Gradient Boosting (XGB), to predict OUD acute events following the initial COE visit. Our models included predictors at the system, patient, and regional levels. We assessed model performance using multiple metrics by racial groups. Individuals were divided into a low, medium and high-risk group based on predicted risk scores.</p><p><strong>Results: </strong>The training (n = 13 990) and testing (n = 6993) samples displayed similar characteristics (mean age 38.1 ± 9.3 years, 58% male, 80% White enrollees) with 4% experiencing OUD acute events at baseline. XGB demonstrated the best prediction performance (C-statistic = 76.6% [95% confidence interval = 75.6%-77.7%] vs. 72.8%-74.7% for other methods). At the balanced cutoff, XGB achieved a sensitivity of 68.2%, specificity of 70.0%, and positive predictive value of 8.3%. The XGB model classified the testing sample into high-risk (6%), medium-risk (30%), and low-risk (63%) groups. In the high-risk group, 40.7% had OUD acute events vs. 16.5% and 5.0% in the medium- and low-risk groups. The high- and medium-risk groups captured 44% and 26% of individuals with OUD events. The XGB model exhibited lower false negative rates and higher false positive rates in racial/ethnic minority groups than White enrollees.</p><p><strong>Conclusions: </strong>New machine-learning algorithms perform well to predict risks of opioid use disorder (OUD) acute care use among United States Medicaid enrollees and improve fairness of prediction across racial and ethnic groups compared with previous OUD-related models.</p>\",\"PeriodicalId\":109,\"journal\":{\"name\":\"Addiction\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":5.2000,\"publicationDate\":\"2025-04-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Addiction\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1111/add.70079\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PSYCHIATRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Addiction","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/add.70079","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHIATRY","Score":null,"Total":0}
Development and evaluation of a machine learning model to predict acute care for opioid use disorder among Medicaid enrollees engaged in a community-based treatment program.
Aims: To develop machine-learning algorithms for predicting the risk of a hospitalization or emergency department (ED) visit for opioid use disorder (OUD) (i.e. OUD acute events) in Pennsylvania Medicaid enrollees in the Opioid Use Disorder Centers of Excellence (COE) program and to evaluate the fairness of model performance across racial groups.
Methods: We studied 20 983 United States Medicaid enrollees aged 18 years or older who had COE visits between April 2019 and March 2021. We applied multivariate logistic regression, least absolute shrinkage and selection operator models, random forests, and eXtreme Gradient Boosting (XGB), to predict OUD acute events following the initial COE visit. Our models included predictors at the system, patient, and regional levels. We assessed model performance using multiple metrics by racial groups. Individuals were divided into a low, medium and high-risk group based on predicted risk scores.
Results: The training (n = 13 990) and testing (n = 6993) samples displayed similar characteristics (mean age 38.1 ± 9.3 years, 58% male, 80% White enrollees) with 4% experiencing OUD acute events at baseline. XGB demonstrated the best prediction performance (C-statistic = 76.6% [95% confidence interval = 75.6%-77.7%] vs. 72.8%-74.7% for other methods). At the balanced cutoff, XGB achieved a sensitivity of 68.2%, specificity of 70.0%, and positive predictive value of 8.3%. The XGB model classified the testing sample into high-risk (6%), medium-risk (30%), and low-risk (63%) groups. In the high-risk group, 40.7% had OUD acute events vs. 16.5% and 5.0% in the medium- and low-risk groups. The high- and medium-risk groups captured 44% and 26% of individuals with OUD events. The XGB model exhibited lower false negative rates and higher false positive rates in racial/ethnic minority groups than White enrollees.
Conclusions: New machine-learning algorithms perform well to predict risks of opioid use disorder (OUD) acute care use among United States Medicaid enrollees and improve fairness of prediction across racial and ethnic groups compared with previous OUD-related models.
期刊介绍:
Addiction publishes peer-reviewed research reports on pharmacological and behavioural addictions, bringing together research conducted within many different disciplines.
Its goal is to serve international and interdisciplinary scientific and clinical communication, to strengthen links between science and policy, and to stimulate and enhance the quality of debate. We seek submissions that are not only technically competent but are also original and contain information or ideas of fresh interest to our international readership. We seek to serve low- and middle-income (LAMI) countries as well as more economically developed countries.
Addiction’s scope spans human experimental, epidemiological, social science, historical, clinical and policy research relating to addiction, primarily but not exclusively in the areas of psychoactive substance use and/or gambling. In addition to original research, the journal features editorials, commentaries, reviews, letters, and book reviews.