Developing a deep learning natural language processing algorithm for automated reporting of adverse drug reactions

McMaster, Christopher; Chan, Julia; Liew, David; Su, Elizabeth; Frauman, Albert G; Chapman, Wendy W.; Pires, Douglas E V

doi:10.1016/j.jbi.2022.104265

Cited by 15 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the use of deep learning facilitates the prediction of drug side effects that may not have been identified during clinical trials and the development of different architectures to predict potential side effects for drugs in the clinical development stage. Different ensemble deep learning networks can be improved for the predictive performance of ADRs that help in supporting medical decisions and drug development [26][27][28].…”

Section: Proposed Model Architecturementioning

confidence: 99%

Layer-Weighted Attention and Ascending Feature Selection: An Approach for Seriousness Level Prediction Using the FDA Adverse Event Reporting System

Aldughayfiq,

Allahem,

Mostafa

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In this study, we introduce a novel combination of layer-static-weighted attention and ascending feature selection techniques to predict the seriousness level of adverse drug events using the Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS). We utilized natural language processing (NLP) to analyze the terms in the active substance field, in addition to considering demographic and event information such as patient sex, healthcare provider qualification, and drug characterization. Our ascending feature selection method, which progressively incorporates additional features based on their importance, demonstrated continuous enhancements in prediction performance. Simultaneously, we employed a layer-static-weighted attention technique, which dynamically adjusts the model’s focus between natural language processing (NLP) and demographic features. This technique achieved its best performance at a balanced weight of 50%, yielding an average test accuracy of 74.56% and CV ROC score of 0.83 when 4000 features were included, indicating a compelling advantage to include a larger volume of meaningful features. By integrating these methodologies, we constructed a robust model capable of effectively predicting seriousness levels, offering significant potential for improving pharmacovigilance and enhancing drug safety monitoring. The results underscore the value of NLP and demographic data in predicting drug event seriousness and demonstrate the effectiveness of our combined techniques. We encourage further research to refine these methods and evaluate their application to other clinical datasets.

show abstract

Section: Proposed Model Architecturementioning

confidence: 99%

Layer-Weighted Attention and Ascending Feature Selection: An Approach for Seriousness Level Prediction Using the FDA Adverse Event Reporting System

Aldughayfiq,

Allahem,

Mostafa

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…They proved that the contextualized language model-based approach outperformed other models overall ( Mahendran and McInnes, 2021 ). Christopher et al developed a deep learning natural language processing algorithm to identify ADRs in discharge summaries at a single academic hospital centre ( McMaster et al, 2023 ).…”

Section: Related Workmentioning

confidence: 99%

Research on named entity recognition of adverse drug reactions based on NLP and deep learning

Wei

Dai

et al. 2023

Front. Pharmacol.

View full text Add to dashboard Cite

Introduction: Adverse drug reactions (ADR) are directly related to public health and become the focus of public and media attention. At present, a large number of ADR events have been reported on the Internet, but the mining and utilization of such information resources is insufficient. Named entity recognition (NER) is the basic work of many natural language processing (NLP) tasks, which aims to identify entities with specific meanings from natural language texts.Methods: In order to identify entities from ADR event data resources more effectively, so as to provide valuable health knowledge for people, this paper introduces ALBERT in the input presentation layer on the basis of the classic BiLSTM-CRF model, and proposes a method of ADR named entity recognition based on the ALBERT-BiLSTM-CRF model. The textual information about ADR on the website “Chinese medical information query platform” (https://www.dayi.org.cn) was collected by the crawler and used as research data, and the BIO method was used to label three types of entities: drug name (DRN), drug component (COM), and adverse drug reactions (ADR) to build a corpus. Then, the words were mapped to the word vector by using the ALBERT module to obtain the character level semantic information, the context coding was performed by the BiLSTM module, and the label decoding was using the CRF module to predict the real label.Results: Based on the constructed corpus, experimental comparisons were made with two classical models, namely, BiLSTM-CRF and BERT-BiLSTM-CRF. The experimental results show that the F1 of our method is 91.19% on the whole, which is 1.5% and 1.37% higher than the other two models respectively, and the performance of recognition of three types of entities is significantly improved, which proves the superiority of this method.Discussion: The method proposed can be used effectively in NER from ADR information on the Internet, which provides a basis for the extraction of drug-related entity relationships and the construction of knowledge graph, thus playing a role in practical health systems such as intelligent diagnosis, risk reasoning and automatic question answering.

show abstract

“…In addition, traditional design methods of the metasurfaces require complex numerical calculations and quite timeconsuming. In recent years, we have witnessed the success of deep learning in a number of complex machine learning tasks, such as computer vision [38], natural language processing [39], and image processing [40]. Many breakthroughs have also been achieved in other fields unrelated to computers, including many fundamental disciplines such as life sciences [41], chemistry [42], and physics [43].…”

Section: Introductionmentioning

confidence: 99%

Performance analysis and prediction of tunable metasurface filter based on electrochemical metallization

Chen,

Wu,

et al. 2024

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

In this paper, a tunable metasurface filter based on electrochemical metallization is proposed. The finite element method (FEM) is used to simulate the formation and rupture of the conductive filament (CF). The geometric structure of the metasurfaces filter is reconstructed by CF to achieve the purpose of tuning the transmission characteristics of the metasurface. Due to the formation of CF in the gap of separated rectangular gold patches, the proposed metasurface simultaneously exhibits the resonance characteristics of two separated rectangular gold patches and unseparated rectangular gold patches. Numerical calculations show that when the radius of the CF increases from 5 nm to 25 nm, the metasurface shows good tunable filtering characteristics, and its quality factor gradually increases. Finally, in order to solve the problem of consuming a lot of time to design metasurface, a deep neural network (DNN) is used to predict the transmission curves corresponding to different metasurface structures. The results show that the Mean Square Error (MSE) of the training model is less than 1×10-3, which shows superior robustness and generalization, and greatly shortens the time required for design. This design paves a new way to develop optoelectronic devices, such as modulators, sensors and optical switches.

show abstract

Developing a deep learning natural language processing algorithm for automated reporting of adverse drug reactions

Cited by 15 publications

References 22 publications

Layer-Weighted Attention and Ascending Feature Selection: An Approach for Seriousness Level Prediction Using the FDA Adverse Event Reporting System

Layer-Weighted Attention and Ascending Feature Selection: An Approach for Seriousness Level Prediction Using the FDA Adverse Event Reporting System

Research on named entity recognition of adverse drug reactions based on NLP and deep learning

Performance analysis and prediction of tunable metasurface filter based on electrochemical metallization

Contact Info

Product

Resources

About