Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
J Am Med Inform Assoc. 2021 Dec 28;29(1):22-32. doi: 10.1093/jamia/ocab218.
To develop and validate algorithms for predicting 30-day fatal and nonfatal opioid-related overdose using statewide data sources including prescription drug monitoring program data, Hospital Discharge Data System data, and Tennessee (TN) vital records. Current overdose prevention efforts in TN rely on descriptive and retrospective analyses without prognostication.
Study data included 3 041 668 TN patients with 71 479 191 controlled substance prescriptions from 2012 to 2017. Statewide data and socioeconomic indicators were used to train, ensemble, and calibrate 10 nonparametric "weak learner" models. Validation was performed using area under the receiver operating curve (AUROC), area under the precision recall curve, risk concentration, and Spiegelhalter z-test statistic.
Within 30 days, 2574 fatal overdoses occurred after 4912 prescriptions (0.0069%) and 8455 nonfatal overdoses occurred after 19 460 prescriptions (0.027%). Discrimination and calibration improved after ensembling (AUROC: 0.79-0.83; Spiegelhalter P value: 0-.12). Risk concentration captured 47-52% of cases in the top quantiles of predicted probabilities.
Partitioning and ensembling enabled all study data to be used given computational limits and helped mediate case imbalance. Predicting risk at the prescription level can aggregate risk to the patient, provider, pharmacy, county, and regional levels. Implementing these models into Tennessee Department of Health systems might enable more granular risk quantification. Prospective validation with more recent data is needed.
Predicting opioid-related overdose risk at statewide scales remains difficult and models like these, which required a partnership between an academic institution and state health agency to develop, may complement traditional epidemiological methods of risk identification and inform public health decisions.
利用包括处方药物监测计划数据、医院出院数据系统数据和田纳西州（TN）生命记录在内的全州数据源，开发和验证预测 30 天致命和非致命阿片类药物相关过量的算法。目前，TN 的过量预防工作依赖于描述性和回顾性分析，而没有预测。
研究数据包括 2012 年至 2017 年期间的 3041668 名 TN 患者和 71479191 份受控物质处方。全州数据和社会经济指标用于训练、集成和校准 10 个非参数“弱学习者”模型。使用接收者操作特征曲线下面积（AUROC）、精度召回曲线下面积、风险集中和 Spiegelhalter z 检验统计量进行验证。
在 30 天内，4912 份处方后发生了 2574 例致命过量，19460 份处方后发生了 8455 例非致命过量（0.0069%和 0.027%）。集成后，区分度和校准得到了改善（AUROC：0.79-0.83；Spiegelhalter P 值：0-.12）。风险集中在预测概率最高的前几个分位数中捕获了 47-52%的病例。
分区和集成使得在计算限制下可以使用所有研究数据，并有助于缓解病例不平衡。在处方级别预测风险可以将风险汇总到患者、提供者、药房、县和地区级别。将这些模型实施到田纳西州卫生系统中可能会实现更细粒度的风险量化。需要使用更近期的数据进行前瞻性验证。
在全州范围内预测阿片类药物相关过量风险仍然具有挑战性，像这样的模型需要学术机构和州卫生机构之间的合作来开发，可以补充传统的风险识别流行病学方法，并为公共卫生决策提供信息。
