McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA.
Department of Biostatistics & Data Science, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA.
J Biomed Inform. 2024 Apr;152:104621. doi: 10.1016/j.jbi.2024.104621. Epub 2024 Mar 5.
The primary objective of this review is to investigate the effectiveness of machine learning and deep learning methodologies in the context of extracting adverse drug events (ADEs) from clinical benchmark datasets. We conduct an in-depth analysis, aiming to compare the merits and drawbacks of both machine learning and deep learning techniques, particularly within the framework of named-entity recognition (NER) and relation classification (RC) tasks related to ADE extraction. Additionally, our focus extends to the examination of specific features and their impact on the overall performance of these methodologies. In a broader perspective, our research extends to ADE extraction from various sources, including biomedical literature, social media data, and drug labels, removing the limitation to exclusively machine learning or deep learning methods.
We conducted an extensive literature review on PubMed using the query "(((machine learning [Medical Subject Headings (MeSH) Terms]) OR (deep learning [MeSH Terms])) AND (adverse drug event [MeSH Terms])) AND (extraction)", and supplemented this with a snowballing approach to review 275 references sourced from retrieved articles.
In our analysis, we included twelve articles for review. For the NER task, deep learning models outperformed machine learning models. In the RC task, gradient Boosting, multilayer perceptron and random forest models excelled. The Bidirectional Encoder Representations from Transformers (BERT) model consistently achieved the best performance in the end-to-end task. Future efforts in the end-to-end task should prioritize improving NER accuracy, especially for 'ADE' and 'Reason'.
These findings hold significant implications for advancing the field of ADE extraction and pharmacovigilance, ultimately contributing to improved drug safety monitoring and healthcare outcomes.
本综述的主要目的是研究机器学习和深度学习方法在从临床基准数据集提取不良药物事件（ADE）方面的有效性。我们进行了深入分析，旨在比较机器学习和深度学习技术的优缺点，特别是在命名实体识别（NER）和关系分类（RC）任务方面，这些任务与 ADE 提取相关。此外，我们还关注特定特征及其对这些方法整体性能的影响。从更广泛的角度来看，我们的研究还扩展到从各种来源（包括生物医学文献、社交媒体数据和药物标签）提取 ADE，不再仅限于使用机器学习或深度学习方法。
我们在 PubMed 上使用查询“(((machine learning [Medical Subject Headings (MeSH) Terms]) OR (deep learning [MeSH Terms])) AND (adverse drug event [MeSH Terms])) AND (extraction)”进行了广泛的文献综述，并通过滚雪球的方法补充了从检索到的文章中获取的 275 篇参考文献。
在我们的分析中，我们纳入了十二篇文章进行综述。在 NER 任务中，深度学习模型优于机器学习模型。在 RC 任务中，梯度提升、多层感知机和随机森林模型表现出色。基于转换器的双向编码器表示（BERT）模型在端到端任务中始终表现出最佳性能。未来在端到端任务中的努力应优先提高 NER 准确性，特别是对于“ADE”和“Reason”。
这些发现对推进 ADE 提取和药物警戒领域具有重要意义，最终有助于改善药物安全性监测和医疗保健结果。
