External validation of an opioid misuse machine learning classifier in hospitalized adult patients.
External validation of an opioid misuse machine learning classifier in hospitalized adult patients.
复制标题
DOI：
10.1186/s13722-021-00229-7
复制
发表时间：
2021-03-17
影响因子：
3.7
通讯作者：
Karnik NS
中科院分区：
文献类型：
--
作者：
Afshar M;Sharma B;Bhalla S;Thompson HM;Dligach D;Boley RA;Kishen E;Simmons A;Perticone K;Karnik NS
医院中的阿片类药物滥用筛查需要大量资源，而且很少进行。许多住院患者从未接受过阿片类药物治疗。对于医院来说，利用定期捕获的电子健康记录 (EHR) 数据的自动化方法可能更容易实施。我们之前在一个单独的医院环境中导出并内部验证了阿片类药物分类器。目的是在外部验证我们之前在另一家医院发布的开源机器学习分类器，以识别阿片类药物滥用案例。 2017 年 10 月至 2019 年 12 月期间，在全医院范围内的物质使用筛查项目中，通过人工筛查对 56,227 名住院成人进行了观察队列检查。手动完成的药物滥用筛查测试作为参考标准，用于验证具有来自 EHR 临床记录的编码字嵌入特征的卷积神经网络 (CNN) 分类器。阿片类药物分类器利用了 EHR 中的所有注释，并且还对前 24 小时的注释进行了敏感性分析。进行校准是为了说明患病率低于原始队列。 67.8% (n = 56,227) 完成了药物滥用的手动筛查，其中 1.1% (n = 628) 被确定为阿片类药物滥用。外部验证的数据包括 2,482,900 个注释，其中包含 67,969 个独特的临床概念特征。阿片类药物分类器在整个遭遇过程中的 AUC 为 0.99 (95% CI 0.99–0.99)，仅使用前 24 小时的笔记时为 0.98 (95% CI 0.98–0.99)。在校准分类器中，敏感性和阳性预测值为 0.81 (95% CI 0.77–0.84) 和 0.72 (95% CI 0.68–0.75)。在前 24 小时，它们分别为 0.75 (95% CI 0.71–0.78) 和 0.61 (95% CI 0.57–0.64)。我们的阿片类药物滥用分类器在外部验证期间具有良好的辨别力。我们的模型可以提供一种全面且自动化的方法来识别阿片类药物滥用，从而增强当前的工作流程并克服手动筛查障碍。在线版本包含可在 10.1186/s13722-021-00229-7 获取的补充材料。
Opioid misuse screening in hospitals is resource-intensive and rarely done. Many hospitalized patients are never offered opioid treatment. An automated approach leveraging routinely captured electronic health record (EHR) data may be easier for hospitals to institute. We previously derived and internally validated an opioid classifier in a separate hospital setting. The aim is to externally validate our previously published and open-source machine-learning classifier at a different hospital for identifying cases of opioid misuse. An observational cohort of 56,227 adult hospitalizations was examined between October 2017 and December 2019 during a hospital-wide substance use screening program with manual screening. Manually completed Drug Abuse Screening Test served as the reference standard to validate a convolutional neural network (CNN) classifier with coded word embedding features from the clinical notes of the EHR. The opioid classifier utilized all notes in the EHR and sensitivity analysis was also performed on the first 24 h of notes. Calibration was performed to account for the lower prevalence than in the original cohort. Manual screening for substance misuse was completed in 67.8% (n = 56,227) with 1.1% (n = 628) identified with opioid misuse. The data for external validation included 2,482,900 notes with 67,969 unique clinical concept features. The opioid classifier had an AUC of 0.99 (95% CI 0.99–0.99) across the encounter and 0.98 (95% CI 0.98–0.99) using only the first 24 h of notes. In the calibrated classifier, the sensitivity and positive predictive value were 0.81 (95% CI 0.77–0.84) and 0.72 (95% CI 0.68–0.75). For the first 24 h, they were 0.75 (95% CI 0.71–0.78) and 0.61 (95% CI 0.57–0.64). Our opioid misuse classifier had good discrimination during external validation. Our model may provide a comprehensive and automated approach to opioid misuse identification that augments current workflows and overcomes manual screening barriers. The online version contains supplementary material available at 10.1186/s13722-021-00229-7.
登录
查看更多内容
DOI：
10.1093/jamia/ocz068
发表时间：
2019-11-01
影响因子：
6.4
作者：
Afshar, Majid;Dligach, Dmitriy;Price, Ron
通讯作者：
Price, Ron
影响因子：
3.9
作者：
Barbosa, Carolina;Cowell, Alexander J.;Bray, Jeremy W.
通讯作者：
Bray, Jeremy W.
影响因子：
3
作者：
Elixhauser, A;Steiner, C;Coffey, RN
通讯作者：
Coffey, RN
CDC规定慢性疼痛的阿片类药物的指南 - 美国，2016年。
DOI：
10.1001/jama.2016.1464
发表时间：
2016-04-19
期刊：
JAMA
影响因子：
--
作者：
Dowell D;Haegerich TM;Chou R
通讯作者：
Chou R
影响因子：
25.8
作者：
Grant, Bridget F.;Saha, Tulshi D.;Ruan, W. June;Goldstein, Rise B.;Chou, S. Patricia;Jung, Jeesun;Zhang, Haitao;Smith, Sharon M.;Pickering, Roger P.;Huang, Boji;Hasin, Deborah S.
通讯作者：
Hasin, Deborah S.