Department of Public Health Sciences, School of Medicine and Dentistry, University of Rochester, Rochester, NY, USA.
Rochester Data Science Consortium, Rochester, NY, USA.
Addiction. 2020 Jul;115(7):1308-1317. doi: 10.1111/add.14943. Epub 2020 Feb 27.
A substantial share of fatal drug overdoses is missing information on specific drug involvement, leading to under-reporting of opioid-related death rates and a misrepresentation of the extent of the opioid epidemic. We aimed to compare methodological approaches to predicting opioid involvement in unclassified drug overdoses in US death records and to estimate the number of fatal opioid overdoses from 1999 to 2016 using the best-performing method.
This was a secondary data analysis of the universe of drug overdoses in 1999-2016 obtained from the National Center for Health Statistics Detailed Multiple Cause of Death records.
United States.
A total of 632 331 drug overdose decedents. Drug overdoses with known drug classification comprised 78.2% of the cases (n = 494 316) and unclassified drug overdoses (ICD-10 T50.9) comprised 21.8% (n = 138 015).
Known opioid involvement was defined using ICD-10 codes T40.0-40.4 and T40.6, recorded in the set of contributing causes. Opioid involvement in unclassified drug overdoses was predicted using multiple methodological approaches: logistic regression and machine learning techniques, inclusion/exclusion of contributing causes of death and inclusion/exclusion of county-level characteristics. Having selected the model with the highest predictive ability, we calculated corrected estimates of opioid-related mortality.
Logistic regression and random forest models performed similarly. Including contributing causes substantially improved predictive accuracy, while including county characteristics did not. Using a superior prediction model, we found that 71.8% of unclassified drug overdoses in 1999-2016 involved opioids, translating into 99 160 additional opioid-related deaths, or approximately 28% more than reported. Importantly, there was a striking geographic variation in undercounting of opioid overdoses.
In modeling opioid involvement in unclassified drug overdoses, highest predictive accuracy is achieved using a statistical model-either logistic regression or a random forest ensemble-with decedent characteristics and contributing causes of death as predictors.
大量致命药物过量的信息缺失，无法明确具体药物的使用情况，这导致了阿片类药物相关死亡率的漏报，并对阿片类药物泛滥的严重程度造成了错误的描述。我们旨在比较美国死亡记录中未分类药物过量中阿片类药物使用情况的预测方法，并使用表现最佳的方法来估算 1999 年至 2016 年期间致命阿片类药物过量的数量。
这是对 1999 年至 2016 年来自国家卫生统计中心详细多原因死亡记录的药物过量的全宇宙的二次数据分析。
美国。
共有 632331 名药物过量死亡者。已知药物分类的药物过量占病例的 78.2%（n=494316），未分类的药物过量（ICD-10 T50.9）占 21.8%（n=138015）。
已知的阿片类药物使用情况使用 ICD-10 代码 T40.0-40.4 和 T40.6 来定义，这些代码记录在促成原因中。使用多种方法预测未分类药物过量中的阿片类药物使用情况：逻辑回归和机器学习技术、纳入/排除死亡的促成原因以及纳入/排除县一级的特征。在选择了具有最高预测能力的模型后，我们计算了校正后的阿片类药物相关死亡率估计值。
逻辑回归和随机森林模型的表现相似。纳入促成原因大大提高了预测准确性，而纳入县一级的特征则没有。使用一个优越的预测模型，我们发现 1999 年至 2016 年期间，71.8%的未分类药物过量涉及阿片类药物，这意味着有 99160 例额外的阿片类药物相关死亡，比报告的数字多了约 28%。重要的是，阿片类药物过量的漏报情况在地理上存在显著差异。
在对未分类药物过量中阿片类药物使用情况进行建模时，使用统计模型（逻辑回归或随机森林集成），结合死亡者特征和死亡的促成原因作为预测因素，可获得最高的预测准确性。
