Using machine learning to predict risk of incident opioid use disorder among fee-for-service Medicare beneficiaries: A prognostic study
Using machine learning to predict risk of incident opioid use disorder among fee-for-service Medicare beneficiaries: A prognostic study
复制标题
DOI：
10.1371/journal.pone.0235981
复制
发表时间：
2020-07-17
期刊：
影响因子：
3.7
通讯作者：
Gellad, Walid F.
中科院分区：
文献类型：
--
作者：
Lo-Ciganic, Wei-Hsuan;Huang, James L.;Gellad, Walid F.
目的开发并验证一种机器学习算法，以提高>= 1阿片类药物处方的医疗保险受益人发生OUD诊断的预测。方法：本预后研究纳入了2011-2016年期间361,527名按服务收费的医疗保险受益人，无癌症，服用>= 1阿片类药物处方。我们将受益人随机分为培训样本、测试样本和验证样本。我们测量了269个潜在的预测因素，包括社会人口统计学、健康状况、阿片类药物使用模式、提供者层面和区域层面的因素，从开始使用阿片类药物前的三个月开始，直到出现OUD、失去随访或2016年底。主要结局是记录的OUD诊断或开始使用美沙酮或丁丙诺啡治疗OUD作为事件OUD的替代。我们使用弹性网、随机森林、梯度增强机和深度神经网络来预测接下来三个月的OUD。我们使用c统计和其他指标（例如，需要评估的数量来识别患有OUD的个体[NNE]）来评估预测性能。受益人按风险评分十分位数分成亚组。结果训练样本（n = 120,474）、测试样本（n = 120,556）和验证样本（n = 120,497）具有相似的特征（年龄>= 65岁= 81.1%，女性= 61.3%，白人= 83.5%，残疾资格= 25.5%，发生OUD的1.5%）。在验证样本中，4种方法的预测性能相近（c统计量范围为0.874 ~ 0.882）；弹性网所需的预测因子最少（n = 48）。采用弹性网络算法，验证队列中风险前十分位个体（15.8% [n = 19047]）的阳性预测值为0.96%，阴性预测值为99.7%，NNE为104。近70%发生OUD的个体位于前两个十分位数（n = 37,078），发生率最高（每10,000名受益人中有36至301人）。在最低的8个十分位数（n = 83,419）的个体中，OUD的发生率最低（每10,000人中有3至28人）。结论机器学习算法提高了医疗保险受益人发生OUD事件的风险预测和风险分层。
Objective To develop and validate a machine-learning algorithm to improve prediction of incident OUD diagnosis among Medicare beneficiaries with >= 1 opioid prescriptions. Methods This prognostic study included 361,527 fee-for-service Medicare beneficiaries, without cancer, filling >= 1 opioid prescriptions from 2011-2016. We randomly divided beneficiaries into training, testing, and validation samples. We measured 269 potential predictors including socio-demographics, health status, patterns of opioid use, and provider-level and regional-level factors in 3-month periods, starting from three months before initiating opioids until development of OUD, loss of follow-up or end of 2016. The primary outcome was a recorded OUD diagnosis or initiating methadone or buprenorphine for OUD as proxy of incident OUD. We applied elastic net, random forests, gradient boosting machine, and deep neural network to predict OUD in the subsequent three months. We assessed prediction performance using C-statistics and other metrics (e.g., number needed to evaluate to identify an individual with OUD [NNE]). Beneficiaries were stratified into subgroups by risk-score decile. Results The training (n = 120,474), testing (n = 120,556), and validation (n = 120,497) samples had similar characteristics (age >= 65 years = 81.1%; female = 61.3%; white = 83.5%; with disability eligibility = 25.5%; 1.5% had incident OUD). In the validation sample, the four approaches had similar prediction performances (C-statistic ranged from 0.874 to 0.882); elastic net required the fewest predictors (n = 48). Using the elastic net algorithm, individuals in the top decile of risk (15.8% [n = 19,047] of validation cohort) had a positive predictive value of 0.96%, negative predictive value of 99.7%, and NNE of 104. Nearly 70% of individuals with incident OUD were in the top two deciles (n = 37,078), having highest incident OUD (36 to 301 per 10,000 beneficiaries). Individuals in the bottom eight deciles (n = 83,419) had minimal incident OUD (3 to 28 per 10,000). Conclusions Machine-learning algorithms improve risk prediction and risk stratification of incident OUD in Medicare beneficiaries.