开发并评估一种机器学习模型，以预测参与社区治疗项目的医疗补助计划参保者中阿片类药物使用障碍的急性护理情况。

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.

作者信息

Xue Lingshu, Yin Ruofei, Cole Evan S, Lo-Ciganic Wei-Hsuan, Gellad Walid F, Donohue Julie, Tang Lu

机构信息

Department of Health Policy and Management, University of Pittsburgh, Pittsburgh, PA, USA.

Department of Biostatistics and Health Data Science, University of Pittsburgh, Pittsburgh, PA, USA.

出版信息

Addiction. 2025 Sep;120(9):1780-1789. doi: 10.1111/add.70079. Epub 2025 Apr 29.

DOI:10.1111/add.70079

PMID:40302110

Abstract

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.

摘要

目的

开发机器学习算法，以预测宾夕法尼亚州医疗补助计划中参与阿片类药物使用障碍卓越中心（COE）项目的参保者因阿片类药物使用障碍（OUD）而住院或前往急诊科就诊（即OUD急性事件）的风险，并评估模型在不同种族群体中表现的公平性。

方法

我们研究了20983名年龄在18岁及以上的美国医疗补助计划参保者，他们在2019年4月至2021年3月期间接受了COE诊疗。我们应用多变量逻辑回归、最小绝对收缩和选择算子模型、随机森林以及极端梯度提升（XGB）来预测初次COE诊疗后的OUD急性事件。我们的模型包括系统、患者和地区层面的预测因子。我们按种族群体使用多种指标评估模型表现。根据预测风险分数将个体分为低、中、高风险组。

结果

训练样本（n = 13990）和测试样本（n = 6993）具有相似特征（平均年龄38.1±9.3岁，58%为男性，80%为白人参保者），基线时4%的人经历过OUD急性事件。XGB表现出最佳预测性能（C统计量 = 76.6% [95%置信区间 = 75.6% - 77.7%]，而其他方法为72.8% - 74.7%）。在平衡截断点时，XGB的灵敏度为68.2%，特异度为70.0%，阳性预测值为8.3%。XGB模型将测试样本分为高风险（6%）、中风险（30%）和低风险（63%）组。在高风险组中，40.7%的人发生了OUD急性事件，而中风险组和低风险组分别为16.5%和5.0%。高风险组和中风险组分别涵盖了44%和26%发生OUD事件的个体。与白人参保者相比，XGB模型在少数种族/族裔群体中的假阴性率较低，假阳性率较高。