We propose machine learning algorithms to automatically detect and predict
clopidogrel treatment failure using longitudinal structured electronic health
records (EHR). By drawing analogies between natural language and structured
EHR, we introduce various machine learning algorithms used in natural language
processing (NLP) applications to build models for treatment failure detection
and prediction. In this regard, we generated a cohort of patients with
clopidogrel prescriptions from UK Biobank and annotated if the patients had
treatment failure events within one year of the first clopidogrel prescription;
out of 502,527 patients, 1,824 patients were identified as treatment failure
cases, and 6,859 patients were considered as control cases. From the dataset,
we gathered diagnoses, prescriptions, and procedure records together per
patient and organized them into visits with the same date to build models. The
models were built for two different tasks, i.e., detection and prediction, and
the experimental results showed that time series models outperform bag-of-words
approaches in both tasks. In particular, a Transformer-based model, namely
BERT, could reach 0.928 AUC in detection tasks and 0.729 AUC in prediction
tasks. BERT also showed competence over other time series models when there is
not enough training data, because it leverages the pre-training procedure using
large unlabeled data.

我们提出机器学习算法，利用纵向结构化的电子健康记录（EHR）自动检测和预测氯吡格雷治疗的失败。通过将自然语言和结构化 EHR 进行类比，我们引入了自然语言处理（NLP）应用中使用的各种机器学习算法来构建处理失败检测和预测的模型。在此方面，我们从英国生物库中生成了一个患有氯吡格雷处方的患者队列，并注释了患者在首次氯吡格雷处方的一年内是否发生处理失败事件；在 502,527 名患者中，1,824 名患者被确定为处理失败病例，6,859 名患者被视为对照病例。从数据集中，我们将患者的诊断、处方和程序记录整合到相同日期的访问中来构建模型。模型为两个不同的任务，即检测和预测构建，实验结果显示在这两个任务中，时间序列模型优于词袋方法。特别是，一种基于 Transformer 的模型，即 BERT，在检测任务中可达到 0.928 的 AUC，而在预测任务中可达到 0.729 的 AUC。当没有足够的训练数据时，BERT 还显示出优势，因为它利用使用大量未标记数据的预训练过程。