Adverse drug event and medication extraction in electronic health records via a cascading architecture with different sequence labeling models and word embeddings

Abstract

Objective An adverse drug event (ADE) refers to an injury resulting from medical intervention related to a drug including harm caused by drugs or from the usage of drugs. Extracting ADEs from clinical records can help physicians associate adverse events to targeted drugs. Materials and Methods We proposed a cascading architecture to recognize medical concepts including ADEs, drug names, and entities related to drugs. The architecture includes a preprocessing method and an ensemble of conditional random fields (CRFs) and neural network–based models to respectively address the challenges of surrogate string and overlapping annotation boundaries observed in the employed ADEs and medication extraction (ADME) corpus. The effectiveness of applying different pretrained and postprocessed word embeddings for the ADME task was also studied. Results The empirical results showed that both CRFs and neural network–based models provide promising solution for the ADME task. The neural network–based models particularly outperformed CRFs in concept types involving narrative descriptions. Our best run achieved an overall micro F-score of 0.919 on the employed corpus. Our results also suggested that the Global Vectors for word representation embedding in general domain provides a very strong baseline, which can be further improved by applying the principal component analysis to generate more isotropic vectors. Conclusions We have demonstrated that the proposed cascading architecture can handle the problem of overlapped annotations and further improve the overall recall and F-scores because the architecture enables the developed models to exploit more context information and forms an ensemble for creating a stronger recognizer.

Deep Learning-Based Natural Language Processing for Screening Psychiatric Patients

“…The hyper-parameters set for the networks are listed in Table 3 . For the pre-trained models, we used GloVe 6B-300d, which was trained on Wikipedia and Gigaword and empirically outperformed other word embedding methods on several medical NLP tasks ( 20 , 30 ). The same BERT BASE uncased model used for fine-tuning was chosen to generate the contextual embeddings.…”

Evaluation of Transfer Learning for Adverse Drug Event (ADE) and Medication Entity Extraction

“…Chen et al (2020) also used a joint-architecture supplemented by UMLS (Bodenreider, 2004) concept lookups and unique modeling of temporal entities. Dai et al (2020) cascaded classifiers sequentially to widen the contextual information available for ADE identification. This model also facilitates improved identification when spans overlap.…”

Hybrid Deep Learning for Medication-Related Information Extraction From Clinical Texts in French: MedExt Algorithm Development Study

“…This data set contained 16,225 drug mentions in the training set and a total of 50,951 entity annotations again in the training set. Among the best-performing algorithms, bidirectional long short term memory and bidirectional long short term memory with conditional random field architectures were popular [24][25][26][27]. Some systems combined attention mechanisms [28] or convolutional neural networks [27].…”

“…Others combined classic entity extraction systems such as cTakes with classifiers such as support vector machines [29]. Ensemble approaches, combining multiple classifiers were also proposed [24][25][26]30].…”