A clinical specific BERT developed using a huge Japanese clinical text corpus
Ontology highlight
ABSTRACT:
SUBMITTER: Kawazoe Y
PROVIDER: S-EPMC8577751 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundSemantic textual similarity (STS) captures the degree of semantic similarity between texts. It plays an important role in many natural language processing applications such as text summarization, question answering, machine translation, information retrieval, dialog systems, plagiarism detection, and query ranking. STS has been widely studied in the general English domain. However, there exists few resources for STS tasks in the clinical domain and in languages other than English, such as Japanese.ObjectiveThe objective of this study is to capture semantic similarity between Japanese clinical texts (Japanese clinical STS) by creating a Japanese dataset that is publicly available.MaterialsWe created two datasets for Japanese clinical STS: (1) Japanese case reports (CR dataset) and (2) Japanese electronic medical records (EMR dataset). The CR dataset was created from publicly available case reports extracted from the CiNii database. The EMR dataset was created from Japanese electronic medical records.MethodsWe used an approach based on bidirectional encoder representations from transformers (BERT) to capture the semantic similarity between the clinical domain texts. BERT is a popular approach for transfer learning and has been proven to be effective in achieving high accuracy for small datasets. We implemented two Japanese pretrained BERT models: a general Japanese BERT and a clinical Japanese BERT. The general Japanese BERT is pretrained on Japanese Wikipedia texts while the clinical Japanese BERT is pretrained on Japanese clinical texts.ResultsThe BERT models performed well in capturing semantic similarity in our datasets. The general Japanese BERT outperformed the clinical Japanese BERT and achieved a high correlation with human score (0.904 in the CR dataset and 0.875 in the EMR dataset). It was unexpected that the general Japanese BERT outperformed the clinical Japanese BERT on clinical domain dataset. This could be due to the fact that the general Japanese BERT is pretrained on a wide range of texts compared with the clinical Japanese BERT.
| S-EPMC8294940 | biostudies-literature
Project description: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.
| S-EPMC9265758 | biostudies-literature
Project description:Extraction of associations of singular nucleotide polymorphism (SNP) and phenotypes from biomedical literature is a vital task in BioNLP. Recently, some methods have been developed to extract mutation-diseases affiliations. However, no accessible method of extracting associations of SNP-phenotype from content considers their degree of certainty. In this paper, several machine learning methods were developed to extract ranked SNP-phenotype associations from biomedical abstracts and then were compared to each other. In addition, shallow machine learning methods, including random forest, logistic regression, and decision tree and two kernel-based methods like subtree and local context, a rule-based and a deep CNN-LSTM-based and two BERT-based methods were developed in this study to extract associations. Furthermore, the experiments indicated that although the used linguist features could be employed to implement a superior association extraction method outperforming the kernel-based counterparts, the used deep learning and BERT-based methods exhibited the best performance. However, the used PubMedBERT-LSTM outperformed the other developed methods among the used methods. Moreover, similar experiments were conducted to estimate the degree of certainty of the extracted association, which can be used to assess the strength of the reported association. The experiments revealed that our proposed PubMedBERT-CNN-LSTM method outperformed the sophisticated methods on the task.
| S-EPMC10099837 | biostudies-literature
Project description:Due to the massive growth of scientific publications, literature mining is becoming increasingly popular for researchers to thoroughly explore scientific text and extract such data to create new databases or augment existing databases. Efforts in literature-mining software design and implementation have improved text-mining productivity, but most of the toolkits that mine text are based on traditional machine-learning-algorithms which hinder the performance of downstream text-mining tasks. Natural-language processing (NLP) and text-mining technologies have seen a rapid development since the release of transformer models, such as bidirectional encoder representations from transformers (BERT). Upgrading rule-based or machine-learning-based literature-mining toolkits by embedding transformer models into the software is therefore likely to improve their text-mining performance. To this end, we release a Python-based literature-mining toolkit for the field of battery materials, BatteryDataExtractor, which involves the embedding of BatteryBERT models in its automated data-extraction pipeline. This pipeline employs BERT models for token-classification tasks, such as abbreviation detection, part-of-speech tagging, and chemical-named-entity recognition, as well as new double-turn question-answering data-extraction models for auto-generating repositories of inter-related material and property data as well as general information. We demonstrate that BatteryDataExtractor exhibits state-of-the-art performance on the evaluation data sets for both token classification and automated data extraction. To aid the use of BatteryDataExtractor, its code is provided as open-source software, with associated documentation to serve as a user guide.
| S-EPMC9627715 | biostudies-literature
Project description:BackgroundPhenotypic information locked away in unstructured narrative text presents significant barriers to information accessibility, both for clinical practitioners and for computerised applications used for clinical research purposes. Text mining (TM) techniques have previously been applied successfully to extract different types of information from text in the biomedical domain. They have the potential to be extended to allow the extraction of information relating to phenotypes from free text.MethodsTo stimulate the development of TM systems that are able to extract phenotypic information from text, we have created a new corpus (PhenoCHF) that is annotated by domain experts with several types of phenotypic information relating to congestive heart failure. To ensure that systems developed using the corpus are robust to multiple text types, it integrates text from heterogeneous sources, i.e., electronic health records (EHRs) and scientific articles from the literature. We have developed several different phenotype extraction methods to demonstrate the utility of the corpus, and tested these methods on a further corpus, i.e., ShARe/CLEF 2013.ResultsEvaluation of our automated methods showed that PhenoCHF can facilitate the training of reliable phenotype extraction systems, which are robust to variations in text type. These results have been reinforced by evaluating our trained systems on the ShARe/CLEF corpus, which contains clinical records of various types. Like other studies within the biomedical domain, we found that solutions based on conditional random fields produced the best results, when coupled with a rich feature set.ConclusionsPhenoCHF is the first annotated corpus aimed at encoding detailed phenotypic information. The unique heterogeneous composition of the corpus has been shown to be advantageous in the training of systems that can accurately extract phenotypic information from a range of different text types. Although the scope of our annotation is currently limited to a single disease, the promising results achieved can stimulate further work into the extraction of phenotypic information for other diseases. The PhenoCHF annotation guidelines and annotations are publicly available at https://code.google.com/p/phenochf-corpus.
| S-EPMC4474585 | biostudies-literature
Project description:We consider the incidence of text "reuse" by researchers via a systematic pairwise comparison of the text content of all articles deposited to arXiv.org from 1991 to 2012. We measure the global frequencies of three classes of text reuse and measure how chronic text reuse is distributed among authors in the dataset. We infer a baseline for accepted practice, perhaps surprisingly permissive compared with other societal contexts, and a clearly delineated set of aberrant authors. We find a negative correlation between the amount of reused text in an article and its influence, as measured by subsequent citations. Finally, we consider the distribution of countries of origin of articles containing large amounts of reused text.
| S-EPMC4291616 | biostudies-literature
Project description:BackgroundDrug pharmacokinetics parameters, drug interaction parameters, and pharmacogenetics data have been unevenly collected in different databases and published extensively in the literature. Without appropriate pharmacokinetics ontology and a well annotated pharmacokinetics corpus, it will be difficult to develop text mining tools for pharmacokinetics data collection from the literature and pharmacokinetics data integration from multiple databases.DescriptionA comprehensive pharmacokinetics ontology was constructed. It can annotate all aspects of in vitro pharmacokinetics experiments and in vivo pharmacokinetics studies. It covers all drug metabolism and transportation enzymes. Using our pharmacokinetics ontology, a PK-corpus was constructed to present four classes of pharmacokinetics abstracts: in vivo pharmacokinetics studies, in vivo pharmacogenetic studies, in vivo drug interaction studies, and in vitro drug interaction studies. A novel hierarchical three level annotation scheme was proposed and implemented to tag key terms, drug interaction sentences, and drug interaction pairs. The utility of the pharmacokinetics ontology was demonstrated by annotating three pharmacokinetics studies; and the utility of the PK-corpus was demonstrated by a drug interaction extraction text mining analysis.ConclusionsThe pharmacokinetics ontology annotates both in vitro pharmacokinetics experiments and in vivo pharmacokinetics studies. The PK-corpus is a highly valuable resource for the text mining of pharmacokinetics parameters and drug interactions.
| S-EPMC3571923 | biostudies-literature
Project description:In cancer research, pathology report text is a largely un-tapped data source. Pathology reports are routinely generated, more nuanced than structured data, and contain added insight from pathologists. However, there are no publicly-available datasets for benchmarking report-based models. Two recent advances suggest the urgent need for a benchmark dataset. First, improved optical character recognition (OCR) techniques will make it possible to access older pathology reports in an automated way, increasing data available for analysis. Second, recent improvements in natural language processing (NLP) techniques using AI allow more accurate prediction of clinical targets from text. We apply state-of-the-art OCR and customized post- processing to publicly available report PDFs from The Cancer Genome Atlas, generating a machine-readable corpus of 9,523 reports. We perform a proof-of-principle cancer-type classification across 32 tissues, achieving 0.992 average AU-ROC. This dataset will be useful to researchers across specialties, including research clinicians, clinical trial investigators, and clinical NLP researchers.
| S-EPMC10441484 | biostudies-literature
Project description:BackgroundChronic pain affects more than 20% of adults in the United States and is associated with substantial physical, mental, and social burden. Clinical text contains rich information about chronic pain, but no systematic appraisal has been performed to assess the electronic health record (EHR) narratives for these patients. A formal content analysis of the unstructured EHR data can inform clinical practice and research in chronic pain.ObjectiveWe characterized individual episodes of chronic pain by annotating and analyzing EHR notes for a stratified cohort of adults with known chronic pain.MethodsWe used the Rochester Epidemiology Project infrastructure to screen all residents of Olmsted County, Minnesota, for evidence of chronic pain, between January 1, 2005, and September 30, 2015. Diagnosis codes were used to assemble a cohort of 6586 chronic pain patients; people with cancer were excluded. The records of an age- and sex-stratified random sample of 62 patients from the cohort were annotated using an iteratively developed guideline. The annotated concepts included date, location, severity, causes, effects on quality of life, diagnostic procedures, medications, and other treatment modalities.ResultsA total of 94 chronic pain episodes from 62 distinct patients were identified by reviewing 3272 clinical notes. Documentation was written by clinicians across a wide spectrum of specialties. Most patients (40/62, 65%) had 1 pain episode during the study period. Interannotator agreement ranged from 0.78 to 1.00 across the annotated concepts. Some pain-related concepts (eg, body location) had 100% (94/94) coverage among all the episodes, while others had moderate coverage (eg, effects on quality of life) (55/94, 59%). Back pain and leg pain were the most common types of chronic pain in the annotated cohort. Musculoskeletal issues like arthritis were annotated as the most common causes. Opioids were the most commonly captured medication, while physical and occupational therapies were the most common nonpharmacological treatments.ConclusionsWe systematically annotated chronic pain episodes in clinical text. The rich content analysis results revealed complexity of the chronic pain episodes and of their management, as well as the challenges in extracting pertinent information, even for humans. Despite the pilot study nature of the work, the annotation guideline and corpus should be able to serve as informative references for other institutions with shared interest in chronic pain research using EHRs.
| S-EPMC7704279 | biostudies-literature
Project description:BackgroundGiven the increasing number of people suffering from tinnitus, the accurate categorization of patients with actionable reports is attractive in assisting clinical decision making. However, this process requires experienced physicians and significant human labor. Natural language processing (NLP) has shown great potential in big data analytics of medical texts; yet, its application to domain-specific analysis of radiology reports is limited.ObjectiveThe aim of this study is to propose a novel approach in classifying actionable radiology reports of tinnitus patients using bidirectional encoder representations from transformer BERT-based models and evaluate the benefits of in domain pre-training (IDPT) along with a sequence adaptation strategy.MethodsA total of 5864 temporal bone computed tomography(CT) reports are labeled by two experienced radiologists as follows: (1) normal findings without notable lesions; (2) notable lesions but uncorrelated to tinnitus; and (3) at least one lesion considered as potential cause of tinnitus. We then constructed a framework consisting of deep learning (DL) neural networks and self-supervised BERT models. A tinnitus domain-specific corpus is used to pre-train the BERT model to further improve its embedding weights. In addition, we conducted an experiment to evaluate multiple groups of max sequence length settings in BERT to reduce the excessive quantity of calculations. After a comprehensive comparison of all metrics, we determined the most promising approach through the performance comparison of F1-scores and AUC values.ResultsIn the first experiment, the BERT finetune model achieved a more promising result (AUC-0.868, F1-0.760) compared with that of the Word2Vec-based models(AUC-0.767, F1-0.733) on validation data. In the second experiment, the BERT in-domain pre-training model (AUC-0.948, F1-0.841) performed significantly better than the BERT based model(AUC-0.868, F1-0.760). Additionally, in the variants of BERT fine-tuning models, Mengzi achieved the highest AUC of 0.878 (F1-0.764). Finally, we found that the BERT max-sequence-length of 128 tokens achieved an AUC of 0.866 (F1-0.736), which is almost equal to the BERT max-sequence-length of 512 tokens (AUC-0.868,F1-0.760).ConclusionIn conclusion, we developed a reliable BERT-based framework for tinnitus diagnosis from Chinese radiology reports, along with a sequence adaptation strategy to reduce computational resources while maintaining accuracy. The findings could provide a reference for NLP development in Chinese radiology reports.
| S-EPMC9338483 | biostudies-literature