Two data-driven approaches to identifying the spectrum of problematic opioid use: A pilot study within a chronic pain cohort.
Two data-driven approaches to identifying the spectrum of problematic opioid use: A pilot study within a chronic pain cohort.
复制标题
DOI：
10.1016/j.ijmedinf.2021.104621
复制
发表时间：
2021-12
影响因子：
4.9
通讯作者：
Samuels DC
中科院分区：
文献类型：
--
作者：
Schirle L;Jeffery A;Yaqoob A;Sanchez-Roige S;Samuels DC
虽然电子健康记录（EHR）在阿片类药物使用障碍（OUD）研究中具有重要潜力，但在临床数据中检测OUD具有挑战性。使用EHR数据预测OUD的模型通常依赖于专注于极端阿片类药物使用的病例/对照分类。有必要扩大这项工作，以确定类阿片使用问题的范围。使用大型学术医学中心数据库，我们开发了2种数据驱动的OUD检测方法：（1）从与OUD相关的表型的全表型关联研究开发的Comorgan评分和（2）使用自然语言处理的基于文本的评分，以识别临床笔记中的OUD相关概念。我们通过相关系数、Wilcoxon秩和检验和受试者工作特征曲线下面积对两种评分的性能进行了评估。通过人工审查重新评估具有最高Comorbian和基于文本的评分的记录，以探索差异。与无证据的患者相比，在手动审查中被判定为OUD高证据的患者中，合并症和基于文本的OUD风险评分均显著升高（分别为p = 1.3E-5和1.3E-6）。风险评分彼此呈正相关（rho = 0.52，p < 0.001）。科摩罗和文本评分的AUC较高（分别为0.79和0.76）。对不一致结果的后续手动审查显示了数据驱动方法优于手动审查的优势，以及风险评估的改进机会。包括合并症和文本的风险评分提供了不同但协同的见解，以表征有问题的阿片类药物使用。这一试点项目为今后开展更有力的工作奠定了基础。
Although electronic health records (EHR) have significant potential for the study of opioid use disorders (OUD), detecting OUD in clinical data is challenging. Models using EHR data to predict OUD often rely on case/control classifications focused on extreme opioid use. There is a need to expand this work to characterize the spectrum of problematic opioid use. Using a large academic medical center database, we developed 2 data-driven methods of OUD detection: (1) a Comorbidity Score developed from a Phenome-Wide Association Study of phenotypes associated with OUD and (2) a Text-based Score using natural language processing to identify OUD-related concepts in clinical notes. We evaluated the performance of both scores against a manual review with correlation coefficients, Wilcoxon rank sum tests, and area-under the receiver operating characteristic curves. Records with the highest Comorbidity and Text-based scores were re-evaluated by manual review to explore discrepancies. Both the Comorbidity and Text-based OUD risk scores were significantly elevated in the patients judged as High Evidence for OUD in the manual review compared to those with No Evidence (p = 1.3E-5 and 1.3E-6, respectively). The risk scores were positively correlated with each other (rho = 0.52, p < 0.001). AUCs for the Comorbidity and Text-based scores were high (0.79 and 0.76, respectively). Follow-up manual review of discrepant findings revealed strengths of data-driven methods over manual review, and opportunities for improvement in risk assessment. Risk scores comprising comorbidities and text offer differing but synergistic insights into characterizing problematic opioid use. This pilot project establishes a foundation for more robust work in the future.
登录
查看更多内容
使用带时间戳的电子健康记录数据进行胰腺癌表型风险评分 (PheRS)：在两个大型生物库中的发现和验证。
影响因子：
4.5
作者：
Salvatore M;Beesley LJ;Fritsche LG;Hanauer D;Shi X;Mondul AM;Pearce CL;Mukherjee B
通讯作者：
Mukherjee B
DOI：
10.1126/science.aal4043
发表时间：
2018-03-16
期刊：
Science (New York, N.Y.)
影响因子：
--
作者：
Bastarache L;Hughey JJ;Hebbring S;Marlo J;Zhao W;Ho WT;Van Driest SL;McGregor TL;Mosley JD;Wells QS;Temple M;Ramirez AH;Carroll R;Osterman T;Edwards T;Ruderfer D;Velez Edwards DR;Hamid R;Cogan J;Glazer A;Wei WQ;Feng Q;Brilliant M;Zhao ZJ;Cox NJ;Roden DM;Denny JC
通讯作者：
Denny JC
影响因子：
3.1
作者：
Kovatch, Merav;Feingold, Daniel;Lev-Ran, Shaul
通讯作者：
Lev-Ran, Shaul
影响因子：
3.7
作者：
Lo-Ciganic, Wei-Hsuan;Huang, James L.;Gellad, Walid F.
通讯作者：
Gellad, Walid F.
影响因子：
4.7
作者：
Barnado A;Carroll RJ;Casey C;Wheless L;Denny JC;Crofford LJ
通讯作者：
Crofford LJ