Developing and validating a machine-learning algorithm to predict opioid overdose in Medicaid beneficiaries in two US states: a prognostic modelling study.
Developing and validating a machine-learning algorithm to predict opioid overdose in Medicaid beneficiaries in two US states: a prognostic modelling study.
复制标题
DOI：
10.1016/s2589-7500(22)00062-0
复制
发表时间：
2022-06
影响因子：
30.8
通讯作者：
Gellad, Walid F.
中科院分区：
文献类型：
--
作者：
Lo-Ciganic, Wei-Hsuan;Donohue, Julie M.;Yang, Qingnan;Huang, James L.;Chang, Ching-Yuan;Weiss, Jeremy C.;Guo, Jingchuan;Zhang, Hao H.;Cochran, Gerald;Gordon, Adam J.;Malone, Daniel C.;Kwoh, Chian K.;Wilson, Debbie L.;Kuza, Courtney C.;Gellad, Walid F.
目前还不清楚，用于预测阿片类药物过量的机器学习算法在应用于其他人群时，是否也会表现良好。我们的目标是开发一种机器学习算法，使用宾夕法尼亚州医疗补助数据预测阿片类药物过量的3个月风险，并在两个数据源（即宾夕法尼亚州医疗补助数据和来自不同州的数据）中进行外部验证。这项预测建模研究开发并验证了一种机器学习算法，用于预测美国宾夕法尼亚州和亚利桑那州一种或多种阿片类药物处方的医疗补助受益人的过量用药。为了预测随后3个月内因过量而就诊的医院或急诊室风险，我们在3个月内从药物和医疗保健遭遇索赔数据中测量了284个潜在预测因素，从首次阿片类药物处方前3个月开始，一直持续到失访或研究结束。我们开发并内部验证了一种梯度提升机器算法，使用2013-16年宾夕法尼亚州医疗补助数据（n=639 693）预测过量。我们使用（1）2017-18年宾夕法尼亚州医疗补助数据（n=318 585）和（2）2015-17年亚利桑那州医疗补助数据（n=391 959）对模型进行了外部验证。我们报告了几个预测性能指标（例如，C统计量，阳性预测值）。受益者被分层为风险评分亚组，以支持临床使用。共有8641（1.35%）2013-16宾夕法尼亚州医疗补助受益人，2705（0.85%）2017-18宾夕法尼亚州医疗补助受益人和2410（0.61%）2015-17亚利桑那州受益人在研究期间有一次或多次用药过量。根据2013 -16年宾夕法尼亚州训练数据集开发并在2013 - 16年宾夕法尼亚州内部验证数据集、2017-18年宾夕法尼亚州外部验证数据集和2015-17年亚利桑那州外部验证数据集上验证的预测3个月用药过量的算法的C统计量为0·841（95%CI 0.835 ~ 0.847）、0.828（0.822 ~ 0.834）、0.817（0.807 ~ 0.826）。在外部验证数据集中，2017-18年宾夕法尼亚州318585名受益人中有71361人（22.4%）属于高风险亚组阳性预测值为0.38 ~ 4.08%;在随后的3个月内捕获73%的过量用药），391 959 2015-17亚利桑那州受益人中有40 041人（10%）属于高风险亚组（阳性预测值为0.19 - 1.97%;捕获55%的过量）。两个验证数据集中的低风险亚组中，用药过量的个体数很少（≤ 0.2%）。一种预测来自宾夕法尼亚州医疗补助数据的阿片类药物过量的机器学习算法在最近的宾夕法尼亚州数据和亚利桑那州医疗补助数据的外部验证中表现良好。该算法可能是有价值的过量的风险预测和医疗补助受益人的分层。国家卫生研究所，国家药物滥用研究所，国家老龄化研究所。
Little is known about whether machine-learning algorithms developed to predict opioid overdose using earlier years and from a single state will perform as well when applied to other populations. We aimed to develop a machine-learning algorithm to predict 3-month risk of opioid overdose using Pennsylvania Medicaid data and externally validated it in two data sources (ie, later years of Pennsylvania Medicaid data and data from a different state). This prognostic modelling study developed and validated a machine-learning algorithm to predict overdose in Medicaid beneficiaries with one or more opioid prescription in Pennsylvania and Arizona, USA. To predict risk of hospital or emergency department visits for overdose in the subsequent 3 months, we measured 284 potential predictors from pharmaceutical and health-care encounter claims data in 3-month periods, starting 3 months before the first opioid prescription and continuing until loss to follow-up or study end. We developed and internally validated a gradient-boosting machine algorithm to predict overdose using 2013–16 Pennsylvania Medicaid data (n=639 693). We externally validated the model using (1) 2017–18 Pennsylvania Medicaid data (n=318 585) and (2) 2015–17 Arizona Medicaid data (n=391 959). We reported several prediction performance metrics (eg, C-statistic, positive predictive value). Beneficiaries were stratified into risk-score subgroups to support clinical use. A total of 8641 (1·35%) 2013–16 Pennsylvania Medicaid beneficiaries, 2705 (0·85%) 2017–18 Pennsylvania Medicaid beneficiaries, and 2410 (0·61%) 2015–17 Arizona beneficiaries had one or more overdose during the study period. C-statistics for the algorithm predicting 3-month overdoses developed from the 2013–16 Pennsylvania training dataset and validated on the 2013–16 Pennsylvania internal validation dataset, 2017–18 Pennsylvania external validation dataset, and 2015–17 Arizona external validation dataset were 0·841 (95% CI 0·835–0·847), 0·828 (0·822–0·834), and 0·817 (0·807–0·826), respectively. In external validation datasets, 71 361 (22·4%) of 318 585 2017–18 Pennsylvania beneficiaries were in high-risk subgroups (positive predictive value of 0·38–4·08%; capturing 73% of overdoses in the subsequent 3 months) and 40 041 (10%) of 391 959 2015–17 Arizona beneficiaries were in high-risk subgroups (positive predictive value of 0·19–1·97%; capturing 55% of overdoses). Lower risk subgroups in both validation datasets had few individuals (≤0·2%) with an overdose. A machine-learning algorithm predicting opioid overdose derived from Pennsylvania Medicaid data performed well in external validation with more recent Pennsylvania data and with Arizona Medicaid data. The algorithm might be valuable for overdose risk prediction and stratification in Medicaid beneficiaries. National Institute of Health, National Institute on Drug Abuse, National Institute on Aging.