Ward Ralph, Weeda Erin, Taber David J, Axon Robert Neal, Gebregziabher Mulugeta
Health Equity and Rural Outreach Innovation Center, Ralph H. Johnson Veterans Affairs Medical Center, Charleston, SC USA.
Department of Public Health Science, Medical University of South Carolina, Charleston, SC USA.
Health Serv Outcomes Res Methodol. 2022;22(2):275-295. doi: 10.1007/s10742-021-00263-7. Epub 2021 Nov 2.
Veterans suffer disproportionate health impacts from the opioid epidemic, including overdose, suicide, and death. Prediction models based on electronic medical record data can be powerful tools for identifying patients at greatest risk of such outcomes. The Veterans Health Administration implemented the Stratification Tool for Opioid Risk Mitigation (STORM) in 2018. In this study we propose changes to the original STORM model and propose alternative models that improve risk prediction performance. The best of these proposed models uses a multivariate generalized linear mixed modeling (mGLMM) approach to produce separate predictions for overdose and suicide-related events (SRE) rather than a single prediction for combined outcomes. Further improvements include incorporation of additional data sources and new predictor variables in a longitudinal setting. Compared to a modified version of the STORM model with the same outcome, predictor and interaction terms, our proposed model has a significantly better prediction performance in terms of AUC (84% vs. 77%) and sensitivity (71% vs. 66%). The mGLMM performed particularly well in identifying patients at risk for SREs, where 72% of actual events were accurately predicted among patients with the 100,000 highest risk scores compared with 49.7% for the modified STORM model. The mGLMM's strong performance in identifying true cases (sensitivity) among this highest risk group was the most important improvement given the model's primary purpose for accurately identifying patients at most risk for adverse outcomes such that they are prioritized to receive risk mitigation interventions. Some predictors in the proposed model have markedly different associations with overdose and suicide risks, which will allow clinicians to better target interventions to the most relevant risks.
The online version contains supplementary material available at 10.1007/s10742-021-00263-7.
退伍军人受到阿片类药物流行的健康影响尤为严重，包括过量用药、自杀和死亡。基于电子病历数据的预测模型可以成为识别此类结果风险最高患者的有力工具。退伍军人健康管理局于2018年实施了阿片类药物风险缓解分层工具（STORM）。在本研究中，我们提议对原始STORM模型进行更改，并提出可提高风险预测性能的替代模型。这些提议模型中最佳的模型采用多元广义线性混合建模（mGLMM）方法，对过量用药和自杀相关事件（SRE）分别进行预测，而不是对综合结果进行单一预测。进一步的改进包括在纵向环境中纳入额外的数据源和新的预测变量。与具有相同结果、预测变量和交互项的STORM模型修改版本相比，我们提议的模型在AUC（84%对77%）和敏感性（71%对66%）方面具有显著更好的预测性能。mGLMM在识别SRE风险患者方面表现特别出色，在风险评分最高的100,000名患者中，72%的实际事件被准确预测，而修改后的STORM模型为49.7%。鉴于该模型的主要目的是准确识别不良后果风险最高的患者，以便他们被优先安排接受风险缓解干预措施，mGLMM在这个最高风险组中识别真正病例（敏感性）的强大性能是最重要的改进。提议模型中的一些预测变量与过量用药和自杀风险的关联明显不同，这将使临床医生能够更好地针对最相关的风险进行干预。
在线版本包含可在10.1007/s10742-021-00263-7获取的补充材料。
