Bédard Mélanie, Moodie Erica Em, Cox Joseph, Gill John, Walmsley Sharon, Martel-Laferrière Valérie, Cooper Curtis, Klein Marina B
Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, Quebec, Canada.
Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, Quebec, Canada.
Can Liver J. 2025 Mar 12;8(2):295-308. doi: 10.3138/canlivj-2024-0060. eCollection 2025 May.
Drug poisoning (overdose) is a public health crisis, particularly among people living with HIV and hepatitis C (HCV) co-infection. Identifying potential predictors of drug poisoning could help decrease drug-related deaths.
Data from the Canadian Co-infection Cohort were used to predict death due to drug poisoning within 6 months of a cohort visit. Participants were eligible for analysis if they ever reported drug use. Supervised machine learning (stratified random forest with undersampling to account for imbalanced data) was used to develop a classification algorithm using 40 sociodemographic, behavioural, and clinical variables. Predictors were ranked in order of importance, and odds ratios and 95% confidence intervals (CIs) were generated using a generalized estimating equation regression.
Of 2,175 study participants, 1,998 met the eligibility criteria. There were 94 drug poisoning deaths, 53 within 6 months of a last visit. When applied to the entire sample, the model had an area under the curve (AUC) of 0.9965 (95% CI, 0.9941-0.9988). However, the false-positive rate was high, resulting in a poor positive predictive value (1.5%). Our model did not generalize well out of sample (AUC 0.6, 95% CI 0.54-0.68). The top important variables were addiction therapy (6 months), history of sexually transmitted infection, smoking (6 months), ever being on prescription opioids, and non-injection opioid use (6 months). However, no predictor was strong.
Despite rich data, our model was not able to accurately predict drug poisoning deaths. Larger datasets and information about changing drug markets could help improve future prediction efforts.
药物中毒（过量用药）是一场公共卫生危机，在同时感染艾滋病毒和丙型肝炎病毒（HCV）的人群中尤为突出。识别药物中毒的潜在预测因素有助于减少与药物相关的死亡。
利用加拿大合并感染队列的数据预测队列访视后6个月内药物中毒导致的死亡。曾报告使用过药物的参与者符合分析条件。使用监督机器学习（带欠采样的分层随机森林以处理数据不平衡问题），利用40个社会人口统计学、行为和临床变量开发分类算法。预测因素按重要性排序，并使用广义估计方程回归生成比值比和95%置信区间（CI）。
在2175名研究参与者中，1998名符合纳入标准。有94例药物中毒死亡，其中53例发生在最后一次访视后的6个月内。应用于整个样本时，该模型的曲线下面积（AUC）为0.9965（95%CI，0.9941 - 0.9988）。然而，假阳性率很高，导致阳性预测值较低（1.5%）。我们的模型在样本外的泛化能力不佳（AUC为0.6，95%CI为0.54 - 0.68）。最重要的变量是成瘾治疗（6个月）、性传播感染史、吸烟（6个月）、曾使用处方阿片类药物以及非注射用阿片类药物使用（6个月）。然而，没有一个预测因素的预测能力很强。
尽管数据丰富，但我们的模型无法准确预测药物中毒死亡。更大的数据集以及有关不断变化的药物市场信息可能有助于改进未来的预测工作。
