BACKGROUND AND AIMS 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. DESIGN 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. SETTING United States. CASES 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). MEASUREMENTS 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. FINDINGS 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. CONCLUSIONS 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.

中文翻译：

---

利用死亡原因可以提高对美国死亡记录中未分类药物过量中阿片类药物参与的预测


背景和目标 致命药物过量的很大一部分缺乏有关特定药物参与的信息，导致阿片类药物相关死亡率的漏报和阿片类药物流行程度的误报。我们的目的是比较预测美国死亡记录中未分类药物过量中阿片类药物参与的方法，并使用表现最佳的方法估计 1999 年至 2016 年致命阿片类药物过量的数量。设计这是对 1999 年至 2016 年药物过量总体情况的二次数据分析，该数据来自国家卫生统计中心详细的多种死因记录。设置美国。案例 共有吸毒过量死者 632 331 名。已知药物分类的药物过量占病例的 78.2% (n = 494 316)，未分类的药物过量 (ICD-10 T50.9) 占 21.8% (n = 138 015)。测量 已知的阿片类药物参与是使用 ICD-10 代码 T40.0-40.4 和 T40.6 定义的，记录在成因组中。使用多种方法预测阿片类药物参与未分类药物过量的情况：逻辑回归和机器学习技术、纳入/排除死亡原因以及纳入/排除县级特征。选择具有最高预测能力的模型后，我们计算了阿片类药物相关死亡率的校正估计值。结果 逻辑回归和随机森林模型的表现类似。纳入贡献原因可显着提高预测准确性，而纳入县特征则没有。使用高级预测模型，我们发现 71。1999 年至 2016 年，8% 的未分类药物过量涉及阿片类药物，导致与阿片类药物相关的死亡人数增加 99 160 例，比报告的数量高出约 28%。重要的是，阿片类药物过量的低估存在显着的地理差异。结论 在对阿片类药物参与未分类药物过量进行建模时，使用统计模型（逻辑回归或随机森林集成）可以实现最高的预测准确性，并以死因特征和死因作为预测因子。