Ellis Randall J, Wang Zichen, Genes Nicholas, Ma'ayan Avi
1Department of Pharmacological Sciences, Mount Sinai Center for Bioinformatics, Icahn School of Medicine at Mount Sinai, New York, NY 10029 USA.
2Department of Emergency Medicine, Mount Sinai Hospital, New York, NY 10029 USA.
BioData Min. 2019 Jan 29;12:3. doi: 10.1186/s13040-019-0193-0. eCollection 2019.
The opioid epidemic in the United States is averaging over 100 deaths per day due to overdose. The effectiveness of opioids as pain treatments, and the drug-seeking behavior of opioid addicts, leads physicians in the United States to issue over 200 million opioid prescriptions every year. To better understand the biomedical profile of opioid-dependent patients, we analyzed information from electronic health records (EHR) including lab tests, vital signs, medical procedures, prescriptions, and other data from millions of patients to predict opioid substance dependence.
We trained a machine learning model to classify patients by likelihood of having a diagnosis of substance dependence using EHR data from patients diagnosed with substance dependence, along with control patients with no history of substance-related conditions, matched by age, gender, and status of HIV, hepatitis C, and sickle cell disease. The top machine learning classifier using all features achieved a mean area under the receiver operating characteristic (AUROC) curve of ~ 92%, and analysis of the model uncovered associations between basic clinical factors and substance dependence. Additionally, diagnoses, prescriptions, and procedures prior to the diagnoses of substance dependence were analyzed to elucidate the clinical profile of substance-dependent patients, relative to controls.
The predictive model may hold utility for identifying patients at risk of developing dependence, risk of overdose, and opioid-seeking patients that report other symptoms in their visits to the emergency room.
美国的阿片类药物泛滥导致每天平均有超过100人因过量用药死亡。阿片类药物作为疼痛治疗手段的有效性以及阿片类药物成瘾者的觅药行为，使得美国医生每年开出超过2亿张阿片类药物处方。为了更好地了解阿片类药物依赖患者的生物医学特征，我们分析了电子健康记录（EHR）中的信息，包括实验室检查、生命体征、医疗程序、处方以及数百万患者的其他数据，以预测阿片类物质依赖情况。
我们训练了一个机器学习模型，使用来自被诊断为物质依赖的患者的电子健康记录数据，以及没有物质相关疾病史的对照患者（按年龄、性别以及艾滋病毒、丙型肝炎和镰状细胞病状况进行匹配），根据物质依赖诊断可能性对患者进行分类。使用所有特征的顶级机器学习分类器在受试者工作特征（AUROC）曲线下的平均面积约为92%，对该模型的分析揭示了基本临床因素与物质依赖之间的关联。此外，还分析了在物质依赖诊断之前的诊断、处方和程序，以阐明物质依赖患者相对于对照患者的临床特征。
该预测模型可能有助于识别有发展为依赖风险、过量用药风险的患者以及在急诊就诊时报告其他症状的觅阿片类药物患者。
