Kinney Kerry L, Zheng Yufeng, Morris Matthew C, Schumacher Julie A, Bhardwaj Saurabh B, Rowlett James K
Department of Psychiatry and Human Behavior, University of Mississippi Medical Center, Jackson, MS, United States.
Center for Innovation and Discovery in Addictions, University of Mississippi Medical Center, Jackson, MS, United States.
Front Psychiatry. 2023 Mar 10;14:1087879. doi: 10.3389/fpsyt.2023.1087879. eCollection 2023.
Benzodiazepines are the most commonly prescribed psychotropic medications, but they may place users at risk of serious adverse effects. Developing a method to predict benzodiazepine prescriptions could assist in prevention efforts.
The present study applies machine learning methods to de-identified electronic health record data, in order to develop algorithms for predicting benzodiazepine prescription receipt (yes/no) and number of benzodiazepine prescriptions (0, 1, 2+) at a given encounter. Support-vector machine (SVM) and random forest (RF) approaches were applied to outpatient psychiatry, family medicine, and geriatric medicine data from a large academic medical center. The training sample comprised encounters taking place between January 2020 and December 2021 ( = 204,723 encounters); the testing sample comprised data from encounters taking place between January and March 2022 ( = 28,631 encounters). The following empirically-supported features were evaluated: anxiety and sleep disorders (primary anxiety diagnosis, any anxiety diagnosis, primary sleep diagnosis, any sleep diagnosis), demographic characteristics (age, gender, race), medications (opioid prescription, number of opioid prescriptions, antidepressant prescription, antipsychotic prescription), other clinical variables (mood disorder, psychotic disorder, neurocognitive disorder, prescriber specialty), and insurance status (any insurance, type of insurance). We took a step-wise approach to developing a prediction model, wherein Model 1 included only anxiety and sleep diagnoses, and each subsequent model included an additional group of features.
For predicting benzodiazepine prescription receipt (yes/no), all models showed good to excellent overall accuracy and area under the receiver operating characteristic curve (AUC) for both SVM (Accuracy = 0.868-0.883; AUC = 0.864-0.924) and RF (Accuracy = 0.860-0.887; AUC = 0.877-0.953). Overall accuracy was also high for predicting number of benzodiazepine prescriptions (0, 1, 2+) for both SVM (Accuracy = 0.861-0.877) and RF (Accuracy = 0.846-0.878).
Results suggest SVM and RF algorithms can accurately classify individuals who receive a benzodiazepine prescription and can separate patients by the number of benzodiazepine prescriptions received at a given encounter. If replicated, these predictive models could inform system-level interventions to reduce the public health burden of benzodiazepines.
苯二氮䓬类药物是最常开具的精神类药物，但它们可能会使使用者面临严重不良反应的风险。开发一种预测苯二氮䓬类药物处方的方法有助于预防工作。
本研究将机器学习方法应用于去识别化的电子健康记录数据，以开发用于预测在给定就诊时是否收到苯二氮䓬类药物处方（是/否）以及苯二氮䓬类药物处方数量（0、1、2种及以上）的算法。支持向量机（SVM）和随机森林（RF）方法被应用于来自大型学术医疗中心的门诊精神病学、家庭医学和老年医学数据。训练样本包括2020年1月至2021年12月期间发生的就诊（=204,723次就诊）；测试样本包括2022年1月至3月期间发生的就诊数据（=28,631次就诊）。对以下经实证支持的特征进行了评估：焦虑和睡眠障碍（原发性焦虑诊断、任何焦虑诊断、原发性睡眠诊断、任何睡眠诊断）、人口统计学特征（年龄、性别、种族）、药物（阿片类药物处方、阿片类药物处方数量、抗抑郁药处方、抗精神病药处方）、其他临床变量（情绪障碍、精神障碍、神经认知障碍、开处方医生专业）以及保险状况（任何保险、保险类型）。我们采用逐步方法来开发预测模型，其中模型1仅包括焦虑和睡眠诊断，每个后续模型包括一组额外的特征。
对于预测是否收到苯二氮䓬类药物处方（是/否），所有模型对于SVM（准确率=0.868 - 0.883；曲线下面积[AUC]=0.864 - 0.924）和RF（准确率=0.860 - 0.887；AUC = 0.877 - 0.953）均显示出良好到优异的总体准确率和受试者工作特征曲线下面积。对于预测苯二氮䓬类药物处方数量（0、1、2种及以上），SVM（准确率=0.861 - 0.877）和RF（准确率=0.846 - 0.878）的总体准确率也很高。
结果表明，SVM和RF算法可以准确地对接受苯二氮䓬类药物处方的个体进行分类，并可以根据在给定就诊时收到的苯二氮䓬类药物处方数量对患者进行区分。如果得到重复验证，这些预测模型可为系统层面的干预措施提供信息，以减轻苯二氮䓬类药物的公共卫生负担。
