Carrell David S, Albertson-Junkans Ladia, Ramaprasan Arvind, Scull Grant, Mackwood Matt, Johnson Eric, Cronkite David J, Baer Andrew, Hansen Kris, Green Carla A, Hazlehurst Brian L, Janoff Shannon L, Coplan Paul M, DeVeaugh-Geiss Angela, Grijalva Carlos G, Liang Caihua, Enger Cheryl L, Lange Jane, Shortreed Susan M, Von Korff Michael
Kaiser Permanente Washington Health Research Institute, Seattle, WA, USA.
Kaiser Permanente Washington, Seattle, WA, USA.
J Drug Assess. 2020 Apr 28;9(1):97-105. doi: 10.1080/21556660.2020.1750419. eCollection 2020.
Opioid surveillance in response to the opioid epidemic will benefit from scalable, automated algorithms for identifying patients with clinically documented signs of problem prescription opioid use. Existing algorithms lack accuracy. We sought to develop a high-sensitivity, high-specificity classification algorithm based on widely available structured health data to identify patients receiving chronic extended-release/long-acting (ER/LA) therapy with evidence of problem use to support subsequent epidemiologic investigations. Outpatient medical records of a probability sample of 2,000 Kaiser Permanente Washington patients receiving ≥60 days' supply of ER/LA opioids in a 90-day period from 1 January 2006 to 30 June 2015 were manually reviewed to determine the presence of clinically documented signs of problem use and used as a reference standard for algorithm development. Using 1,400 patients as training data, we constructed candidate predictors from demographic, enrollment, encounter, diagnosis, procedure, and medication data extracted from medical claims records or the equivalent from electronic health record (EHR) systems, and we used adaptive least absolute shrinkage and selection operator (LASSO) regression to develop a model. We evaluated this model in a comparable 600-patient validation set. We compared this model to ICD-9 diagnostic codes for opioid abuse, dependence, and poisoning. This study was registered with ClinicalTrials.gov as study NCT02667262 on 28 January 2016. We operationalized 1,126 potential predictors characterizing patient demographics, procedures, diagnoses, timing, dose, and location of medication dispensing. The final model incorporating 53 predictors had a sensitivity of 0.582 at positive predictive value (PPV) of 0.572. ICD-9 codes for opioid abuse, dependence, and poisoning had a sensitivity of 0.390 at PPV of 0.599 in the same cohort. Scalable methods using widely available structured EHR/claims data to accurately identify problem opioid use among patients receiving long-term ER/LA therapy were unsuccessful. This approach may be useful for identifying patients needing clinical evaluation.
应对阿片类药物流行的阿片类药物监测将受益于可扩展的自动化算法，以识别有问题处方阿片类药物使用临床记录迹象的患者。现有算法缺乏准确性。我们试图基于广泛可用的结构化健康数据开发一种高灵敏度、高特异性的分类算法，以识别接受慢性缓释/长效（ER/LA）治疗且有问题使用证据的患者，以支持后续的流行病学调查。对2006年1月1日至2015年6月30日期间在90天内接受≥60天供应量ER/LA阿片类药物的2000名凯撒永久医疗华盛顿患者的概率样本的门诊病历进行人工审查，以确定是否存在问题使用的临床记录迹象，并将其用作算法开发的参考标准。我们使用1400名患者作为训练数据，从医疗理赔记录或电子健康记录（EHR）系统的等效数据中提取的人口统计学、登记、就诊、诊断、手术和用药数据构建候选预测因子，并使用自适应最小绝对收缩和选择算子（LASSO）回归来开发模型。我们在一个可比的600名患者验证集中评估了该模型。我们将该模型与阿片类药物滥用、依赖和中毒的ICD-9诊断代码进行了比较。这项研究于2016年1月28日在ClinicalTrials.gov注册为研究NCT02667262。我们实施了1126个潜在预测因子，这些因子表征了患者的人口统计学、手术、诊断、时间、剂量和药物配给地点。包含53个预测因子的最终模型在阳性预测值（PPV）为0.572时的灵敏度为0.582。在同一队列中，阿片类药物滥用、依赖和中毒的ICD-9代码在PPV为0.599时的灵敏度为0.390。使用广泛可用的结构化EHR/理赔数据来准确识别接受长期ER/LA治疗患者中问题阿片类药物使用的可扩展方法未成功。这种方法可能有助于识别需要临床评估的患者。
