School of Information Technology and Mathematical Sciences, University of South Australia, Mawson Lakes Boulevard, South Australia 5095, Australia.
School of Information Technology and Mathematical Sciences, University of South Australia, Mawson Lakes Boulevard, South Australia 5095, Australia.
Comput Methods Programs Biomed. 2018 Jul;161:25-38. doi: 10.1016/j.cmpb.2018.03.021. Epub 2018 Apr 14.
Adverse drug reactions (ADRs) are one of the leading causes of morbidity and mortality and thus should be detected early to reduce consequences on health outcomes. Medication dispensing data are comprehensive sources of information about medicine uses that can be utilized for the signal detection of ADRs. Sequence symmetry analysis (SSA) has been employed in previous studies to detect signals of ADRs from medication dispensing data, but it has a moderate sensitivity and tends to miss some ADR signals. With successful applications in various areas, supervised machine learning (SML) methods are promising in detecting ADR signals. Gold standards of known ADRs and non- ADRs from previous studies create opportunities to take into account additional domain knowledge to improve ADR signal detection with SML.
We assess the utility of SML as a signal detection tool for ADRs in medication dispensing data with the consideration of domain knowledge from DrugBank and MedDRA. We compare the best performing SML method with SSA.
We model the ADR signal detection problem as a supervised machine learning problem by linking medication dispensing data with domain knowledge bases. Suspected ADR signals are extracted from the Australian Pharmaceutical Benefit Scheme (PBS) medication dispensing data from 2013 to 2016. We construct predictive features for each signal candidate based on its occurrences in medication dispensing data as well as its pharmacological properties. Pharmaceutical knowledge bases including DrugBank and MedDRA are employed to provide pharmacological features for a signal candidate. Given a gold standard of known ADRs and non-ADRs, SML learns to differentiate between known ADRs and non-ADRs based on their combined predictive features from linked sources, and then predicts whether a new case is a potential ADR signal.
We evaluate the performance of six widely used SML methods with two gold standards of known ADRs and non-ADRs from previous studies. On average, gradient boosting classifier achieves the sensitivity of 77%, specificity of 81%, positive predictive value of 76%, negative predictive value of 82%, area under precision-recall curve of 81%, and area under receiver operating characteristic curve of 82%, most of which are higher than in other SML methods. In particular, gradient boosting classifier has 21% higher sensitivity than and comparable specificity with SSA. Furthermore, gradient boosting classifier detects 10% more unknown potential ADR signals than SSA.
Our study demonstrates that gradient boosting classifier is a promising supervised signal detection tool for ADRs in medication dispensing data to complement SSA.
药物不良反应（ADR）是导致发病率和死亡率的主要原因之一，因此应尽早发现以降低对健康结果的影响。药物配药数据是关于药物使用的综合信息来源，可用于检测 ADR 信号。序列对称分析（SSA）已在前些研究中用于从药物配药数据中检测 ADR 信号，但它的灵敏度适中，往往会错过一些 ADR 信号。监督机器学习（SML）方法在各个领域的成功应用表明，它在检测 ADR 信号方面具有很大的潜力。来自先前研究的已知 ADR 和非 ADR 的黄金标准为考虑 DrugBank 和 MedDRA 中的附加领域知识以提高使用 SML 检测 ADR 信号提供了机会。
我们评估了 SML 作为一种药物配药数据中 ADR 信号检测工具的效用，同时考虑了来自 DrugBank 和 MedDRA 的领域知识。我们将表现最佳的 SML 方法与 SSA 进行了比较。
我们通过将药物配药数据与知识库链接，将 ADR 信号检测问题建模为监督机器学习问题。从 2013 年至 2016 年澳大利亚药品福利计划（PBS）药物配药数据中提取可疑 ADR 信号。我们根据信号在药物配药数据中的出现情况及其药理学特性为每个信号候选构建预测特征。使用 DrugBank 和 MedDRA 等药物知识库为信号候选物提供药理学特征。给定已知 ADR 和非 ADR 的黄金标准，SML 可以根据来自链接源的组合预测特征来区分已知 ADR 和非 ADR，然后预测新病例是否为潜在的 ADR 信号。
我们使用来自先前研究的两个已知 ADR 和非 ADR 的黄金标准评估了六种常用 SML 方法的性能。平均而言，梯度提升分类器的灵敏度为 77%，特异性为 81%，阳性预测值为 76%，阴性预测值为 82%，精度-召回曲线下面积为 81%，接收者操作特征曲线下面积为 82%，其中大多数都高于其他 SML 方法。特别是，梯度提升分类器的灵敏度比 SSA 高 21%，特异性相当。此外，梯度提升分类器比 SSA 检测到 10%更多未知的潜在 ADR 信号。
我们的研究表明，梯度提升分类器是一种有前途的药物配药数据中 ADR 监督信号检测工具，可以补充 SSA。
