BERT based clinical knowledge extraction for biomedical knowledge graph construction and analysis

Harnoune, Ayoub; Rhanoui, Maryem; Mikram, Mounia; Yousfi, Siham; Elkaimbillah, Zineb; Asri, Bouchra El

doi:10.1016/j.cmpbup.2021.100042

Cited by 43 publications

(22 citation statements)

References 56 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Harnoune et al [ 24 ] presented an end-to-end strategy for information extraction and analysis from biological, clinical notes using the Bidirectional Encoder Representations from Transformers (BERT) model and the Conditional Random Field (CRF) layer. They also constructed a named entity recognition model capable of recognizing entities such as drug, strength, duration, frequency, adverse drug responses, the rationale for taking medicine, method of administration, and form.…”

Section: Literature Surveymentioning

confidence: 99%

“…Security should be maintained in clinical data [ 20 ] as sensitive information needs more privacy [ 21 ] and data quality to improve the accessibility [ 22 ] of unstructured data. [ 23 ] requires efficient and accurate data extraction and in [ 24 ], there is a need to consider the security and authority in the clinical text data. Hence, it is understood that the existing techniques face problems in improving the quality of clinical text data; the accessibility of unstructured data is not provided, and it is difficult to maintain data security and authority.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

Clinical Text Data Categorization and Feature Extraction Using Medical-Fissure Algorithm and Neg-Seq Algorithm

Pagad

Pradeep²,

Almuzaini

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

A large amount of patient information has been gathered in Electronic Health Records (EHRs) concerning their conditions. An EHR, as an unstructured text document, serves to maintain health by identifying, treating, and curing illnesses. In this research, the technical complexities in extracting the clinical text data are removed by using machine learning and natural language processing techniques, in which an unstructured clinical text data with low data quality is recognized by Halve Progression, which uses Medical-Fissure Algorithm which provides better data quality and makes diagnosis easier by using a cross-validation approach. Moreover, to enhance the accuracy in extracting and mapping clinical text data, Clinical Data Progression uses Neg-Seq Algorithm in which the redundancy in clinical text data is removed. Finally, the extracted clinical text data is stored in the cloud with a secret key to enhance security. The proposed technique improves the data quality and provides an efficient data extraction with high accuracy of 99.6%.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

Clinical Text Data Categorization and Feature Extraction Using Medical-Fissure Algorithm and Neg-Seq Algorithm

Pagad

Pradeep²,

Almuzaini

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…At the end of 2018, Google has built one such model, named BERT, that outperforms nearly all existing deep learning models in several NLP tasks [23][24][25]. BERT has recently obtained state-of-the-art results for a wide variety of NLP tasks, such as extracting clinical information for breast cancer [26] and analysis for biomedical clinical data [27]. Fan et al [17] proposed using the BERT model for adverse drug events (ADEs) detection and extraction from online open data, since it allowed more drug side effects to be identified for doctors.…”

Section: Deep Learning In the Medical Domainmentioning

confidence: 99%

“…The use of text summarization in the medical field has been reported in the literature [30]. Medical documents summarization has received significant research attention in different fields such as bioinformatics [31], imaging informatics [32], clinical informatics [26,27], and public health informatics [33][34][35]. Gayathri and Jaisankar [33] developed and applied a semantic dynamic summarizing technique to extract important sentences from medical documents.…”

Section: Text Summarization In the Medical Domainmentioning

confidence: 99%

Increasing Women’s Knowledge about HPV Using BERT Text Summarization: An Online Randomized Study

Bitar

Babour

Nafa

et al. 2022

IJERPH

View full text Add to dashboard Cite

Despite the availability of online educational resources about human papillomavirus (HPV), many women around the world may be prevented from obtaining the necessary knowledge about HPV. One way to mitigate the lack of HPV knowledge is the use of auto-generated text summarization tools. This study compares the level of HPV knowledge between women who read an auto-generated summary of HPV made using the BERT deep learning model and women who read a long-form text of HPV. We randomly assigned 386 women to two conditions: half read an auto-generated summary text about HPV (n = 193) and half read an original text about HPV (n = 193). We administrated measures of HPV knowledge that consisted of 29 questions. As a result, women who read the original text were more likely to correctly answer two questions on the general HPV knowledge subscale than women who read the summarized text. For the HPV testing knowledge subscale, there was a statistically significant difference in favor of women who read the original text for only one question. The final subscale, HPV vaccination knowledge questions, did not significantly differ across groups. Using BERT for text summarization has shown promising effectiveness in increasing women’s knowledge and awareness about HPV while saving their time.

show abstract

“…Their findings along with others [15][16][17][18][19][20][21][22] have shown that BERT-based models outperform other techniques for extracting clinical UMLS concepts. Based on their findings and other work [23][24][25] which show optimum performance is obtained for NER and MEL when the context is taken into account, we decide to experiment with a BERT-based contextualized embedding approach. In order to compare the performance of NeighBERT with the latest high-performing BERT-based techniques, we experiment with the following approaches: BioBERT [20], UmlsBERT [17], and BlueBERT [22].…”

Section: Clinical Concept and Relation Extractionmentioning

confidence: 99%

NeighBERT: Medical Entity Linking Using Relation Induced Dense Retrieval

Singh¹,

Krishnamoorthy²,

Ortega³

2022

Preprint

View full text Add to dashboard Cite

One of the common tasks in clinical natural language processing is medical entity linking (MEL) which involves mention detection followed by linking the mention to an entity in a knowledge base. One reason that MEL has not been solved is due to a problem that occurs in language where ambiguous texts can be resolved to several named entities. This problem is exacerbated when processing text found in electronic health records. Recent work has shown that deep learning models based on transformers outperform previous methods on linking at higher rates of performance. We introduce NeighBERT, a custom pre-training technique which extends BERT \citep{devlin-etal-2019-bert} by encoding how entities are related within a knowledge graph. This technique adds relational context that has been traditionally missing in original BERT, helping resolve the ambiguity found in clinical text. In our experiments, NeighBERT improves the precision, recall and F1-score of the state of the art by 1--3 points for named entity recognition and 10--15 points for MEL on two widely known clinical datasets.

show abstract

BERT based clinical knowledge extraction for biomedical knowledge graph construction and analysis

Cited by 43 publications

References 56 publications

Clinical Text Data Categorization and Feature Extraction Using Medical-Fissure Algorithm and Neg-Seq Algorithm

Clinical Text Data Categorization and Feature Extraction Using Medical-Fissure Algorithm and Neg-Seq Algorithm

Increasing Women’s Knowledge about HPV Using BERT Text Summarization: An Online Randomized Study

NeighBERT: Medical Entity Linking Using Relation Induced Dense Retrieval

Contact Info

Product

Resources

About