检索结果-内蒙古大学图书馆

Developing an ICD-10 Coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description- Based Code Selection

引用

JMIR FORMATIVE RESEARCH 2025年 9卷 e60095页

作者： Puts, Sander Zegers, Catharina M. L. Dekker, Andre Bermejo, Inigo Maastricht Univ GROW Res Inst Oncol & Reprod Med Ctr Dept Radiat Oncol Maastro POB 616 NL-6200 MD Maastricht Netherlands Hasselt Univ Data Sci Inst DSI Hasselt Belgium

Background: The International Classification of Diseases (ICD), developed by the World Health Organization, standardizes health condition coding to support health care policy, research, and billing, but artificial intelligence automation, while promising, still underperforms compared with human accuracy and lacks the explainability needed for adoption in medical settings. Objective: The potential of large language models for assisting medical coders in the ICD-10 coding was explored through the development of a computer-assisted coding system. This study aimed to augment human coding by initially identifying lead terms and using retrieval-augmented generation (RAG)-based methods for computer-assisted coding enhancement. Methods: The explainability dataset from the CodiEsp challenge (CodiEsp-X) was used, featuring 1000 Spanish clinical cases annotated with ICD-10 codes. A new dataset, CodiEsp-X-lead, was generated using GPT-4 to replace full-textual evidence annotations with lead term annotations. A Robustly Optimized BERT (bidirectional encoder representations from transformers) Pretraining Approach transformer model was fine-tuned for named entity recognition to extract lead terms. GPT-4 was subsequently employed to generate code descriptions from the extracted textual evidence. Using a RAG approach, ICD codes were assigned to the lead terms by querying a vector database of ICD code descriptions with OpenAI's text-embedding-ada-002 model. Results: The fine-tuned Robustly Optimized BERT Pretraining Approach achieved an overall F1-score of 0.80 for ICD lead term extraction on the new CodiEsp-X-lead dataset. GPT-4-generated code descriptions reduced retrieval failures in the RAG approach by approximately 5% for both diagnoses and procedures. However, the overall explainability F1-score for the CodiEsp-X task was limited to 0.305, significantly lower than the state-of-the-art F1-score of 0.633. The diminished performance was partly due to the reliance on code descripti

关键词： International Classification of Diseases ICD-10 computer-assisted-coding GPT-4 coding term extraction code analysis computer assisted coding transformer model artificial intelligence AI automation retrieval-augmented generation RAG large language model LLM bidirectional encoder representations from transformers Robustly Optimized BERT Pretraining Approach RoBERTa named entity recognition NER

来源：评论

学校读者我要写书评

暂无评论

A comprehensive strategy for identifying plagiarism in academic submissions

引用

Journal of Umm Al-Qura University for Engineering and Architecture 2025年 1-16页

作者： Setu, Deblina Mazumder Islam, Tania Erfan, Md. Dey, Samrat Kumar Asif, Md. Rashid Al Samsuddoha, Md. Department of Computer Science and Engineering University of Barishal Barishal 8200 Bangladesh School of Science and Technology (SST) Bangladesh Open University (BOU) Gazipur 1705 Bangladesh

Plagiarism is a major problem in education, especially in higher education environments. To address this problem, a comprehensive detection method is proposed, utilizing cutting-edge models like bidirectional encoder representations from transformers (BERT) and cosine similarity for detecting direct copy and semantic changes. The methodology involves evaluating the BERT model and cosine similarity first, then performing pairwise comparisons to determine how similar a student’s work is to a reference text. If the semantic changes are higher, the content is classified as paraphrased;otherwise, it is considered direct copy in cases where the similarity threshold is greater than 30%. When the similarity threshold is less than or equal to 30%, the method moves to online plagiarism detection. This includes web scraping, generating search queries, and employing Term Frequency-Inverse Document Frequency (TF-IDF) vectorization with cosine similarity to assess the similarities between students’ content and online content. As a result, the study detects online plagiarism and distinguishes between plagiarizing and authentic content. The purpose is to provide an effective method to maintain academic integrity and enhance originality in student work. In similarity testing on MIT plagiarism detection datasets, this study demonstrated an average recall of 80%, precision of 68%, accuracy of 71%, and f1-score of 74%. With a threshold of 0.2, the average precision for online plagiarism detection reached 65%, accompanied by a 56% recall, an accuracy of 60%, and an f1-score of 60%. The results of the study demonstrate the efficiency of the strategy in enhancing plagiarism detection accuracy while reducing false positives. © The Author(s) 2025.

关键词： bidirectional encoder representations from transformers Cosine similarity Paraphrasing Plagiarism Term frequency-inverse document frequency Web scraping

来源：评论

学校读者我要写书评

暂无评论

Contextual Embeddings in Sociological Research: Expanding the Analysis of Sentiment and Social Dynamics

引用

SOCIOLOGICAL METHODOLOGY 2025年第1期55卷 25-58页

作者： Mostafavi, Moeen Porter, Michael D. Robinson, Dawn T. Univ Virginia Dept Syst & Informat Engn 351 McCormick Rd Thornton Hall Room D221 Charlottesville VA 22901 USA Univ Virginia Syst & Informat Engn & Data Sci Charlottesville VA USA Univ Georgia Dept Sociol Athens GA USA

The authors introduce BERTNN (bidirectional encoder representations from transformers Neural Network), a novel methodology designed to expand affective lexicons, a critical component in sociological research. BERTNN estimates the affective meanings and their distribution for new concepts, bypassing the need for extensive surveys by leveraging their contextual usage in language. The cornerstone of BERTNN is the use of nuanced word embeddings from bidirectional encoder representations from transformers. BERTNN uniquely encodes words within the framework of synthesized social event sentences, preserving their meaning across actor-behavior-object positions. The model is fine-tuned on the basis of the implied sentiment changes, providing a more refined estimation of affective meanings. BERTNN outperforms previous approaches, setting a new standard in deriving multidimensional affective meanings for novel concepts. It efficiently replicates sentiment ratings that traditionally require extensive survey hours, demonstrating the power of automated modeling in sociological research. The expanded affective lexicons that can be produced with BERTNN cater to shifting cultural meanings and diverse subgroups, demonstrating the potential of computational linguistics to enrich the measurement tools in sociological research. This article underscores the novelty and significance of BERTNN in the broader context of sociological methodology.

关键词： affect control theory sentiment mining sentence embedding computational social science affective lexicon bidirectional encoder representations from transformers BERT contextual word embeddings

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model Integrating LDA, BERT, and Clustering for Enhanced Topic Modeling

引用

Quality and Quantity 2025年 1-28页

作者： Yadav, Arun Kumar Gupta, Tushar Kumar, Mohit Yadav, Divakar Department of CSE NIT Hamirpur (HP) Hamirpur India SOCIS IGNOU New Delhi India

Topic modeling is a popular machine learning technique in natural language processing for identifying themes within unstructured text. One of the most prominent methods for this purpose is Latent Dirichlet Allocation (LDA), which can automatically uncover topics from large text corpora. However, LDA alone may not always provide the best results. Using bidirectional encoder representations from transformers (BERT) embeddings in topic modeling, significantly enhances the quality and coherence of discovered topics by leveraging deep contextual representations of words. Clustering is another powerful unsupervised machine learning technique frequently used for topic modeling and information extraction from unstructured text. This study introduces a hybrid approach that combines LDA with BERT for enhanced topic modeling, incorporating dimensionality reduction-based clustering. To manage the increasing complexity and computational load of clustering with many features, Uniform Manifold Approximation and Projection is utilized for dimensionality reduction. Experiments conducted on benchmark datasets, specifically Reuters-21578 and 20newsgroups, illustrate the effectiveness of this cluster-informed topic modeling framework. The empirical results suggest that integrating clustering with BERT-LDA for topic modeling can be highly effective, as dimensionality reduction via clustering helps derive more cohesive topics. The study evaluates coherence scores using the BERT-LDA model on the 20newsgroups and Reuters datasets. For the 20newsgroups dataset, BERT-LDA shows a significant improvement in coherence scores: nearly 59% for 10 topics, 42% for 20 topics, 11% for 50 topics, and 16% for 98 topics. Similarly, for the Reuters dataset, coherence scores improved by about 85% for 10 topics, 63% for 20 topics, 43% for 50 topics, and 41% for 98 topics. These results highlight how BERT-LDA enhances topic coherence compared to traditional models. © The Author(s), under exclusive licence to

关键词： bidirectional encoder representations from transformers Dimensionality reduction k-means clustering Latent dirichlet allocation

来源：评论

学校读者我要写书评

暂无评论

Impact of a Virtual Reality Video ( "A Walk-Through Dementia" ) on YouTube Users: Topic Modeling Analysis

引用

JMIR Formative Research 2025年 9卷 e67755页

作者： Li, Xiaoli Liu, Xiaoyu Yin, Cheng Collins, Sandra Alanazi, Eman School of Health Sciences Southern Illinois University Carbondale Carbondale IL United States College for Public Health & Social Justice Saint Louis University Saint Louis MO United States Department of Rehabilitation and Health Services University of North Texas Denton TX United States Health Informatics Department College of Health Sciences Saudi Electronic University Riyadh Saudi Arabia

Background: Emerging research has highlighted the potential of virtual reality (VR) as a tool for training health care students and professionals in care skills for individuals with Alzheimer disease and related dementias (ADRD). However, there is limited research on the use of VR to engage the general public in raising awareness about ADRD. Objective: This research aimed to examine the impact of the VR video “A Walk-Through Dementia” on YouTube users by analyzing their posts. Methods: We collected 12, 754 comments from the VR video series “A Walk-Through Dementia, ” which simulates the everyday challenges faced by individuals with ADRD, providing viewers with an immersive experience of the condition. Topic modeling was conducted to gauge viewer opinions and reactions to the videos. A pretrained bidirectional encoder representations from transformers (BERT) model was used to transform the YouTube comments into high-dimensional vector embeddings, allowing for systematic identification and detailed analysis of the principal topics and their thematic structures within the dataset. Results: We identified the top 300 most frequent words in the dataset and categorized them into nouns, verbs, and adjectives or adverbs using a part-of-speech tagging model, fine-tuned for accurate tagging tasks. The topic modeling process identified eight8 initial topics based on the most frequent words. After manually reviewing the 8 topics and the content of the comments, we synthesized them into 5 themes. The predominant theme, represented in 2917 comments, centered on users’ personal experiences with the impact of ADRD on patients and caregivers. The remaining themes were categorized into 4 main areas: positive reactions to the VR videos, challenges faced by individuals with ADRD, the role of caregivers, and learning from the VR videos. Conclusions: Using topic modeling, this study demonstrated that VR applications serve as engaging and experiential learning tools, offering the public a

关键词： ADRD Alzheimer disease Alzheimer disease and related dementias BERT bidirectional encoder representations from transformers dementia digital world experiential learning tool health care professional health care student older adult public awareness simulation social media comments text mining topic modeling training virtual environment virtual reality virtual tour VR VR application VR video walk-through dementia YouTube

来源：评论

学校读者我要写书评

暂无评论

Automating Endoscopic Scoring Through Artificial Intelligence

Gastro Hep Advances

引用

Gastro Hep Advances 2025年第7期4卷

作者： Nicholas Denson James Reigle Julia Smith David H. Bruining Yizhao Ni Jasbir Dhaliwal Division of Gastroenterology Hepatology and Nutrition Cincinnati Children's Hospital Medical Center Cincinnati Ohio Division of Gastroenterology and Hepatology Mayo Clinic Rochester Minnesota Kaiser Permanente Oakland California Department of Pediatrics University of Cincinnati Cincinnati Ohio Division of Biomedical Informatics Cincinnati Children's Hospital Medical Center Cincinnati Ohio James M Anderson Center for Health Systems Excellence Cincinnati Children's Hospital Medical Center Cincinnati Ohio

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing for Chest X-Ray Reports in the Transformer Era: BERT-Like encoders for Comprehension and GPT-Like Decoders for Generation

iRADIOLOGY

引用

iRADIOLOGY 2025年

作者： Han Yuan Duke-NUS Medical School National University of Singapore Singapore

来源：评论

学校读者我要写书评

暂无评论

Comparing deep learning architectures for sentiment analysis on drug reviews

引用

JOURNAL OF BIOMEDICAL INFORMATICS 2020年 110卷 103539-103539页

作者： Colon-Ruiz, Cristobal Segura-Bedmar, Isabel Univ Carlos III Madrid Comp Sci Dept Ave Univ 30 Madrid 28911 Spain

Since the turn of the century, as millions of user's opinions are available on the web, sentiment analysis has become one of the most fruitful research fields in Natural Language Processing (NLP). Research on sentiment analysis has covered a wide range of domains such as economy, polity, and medicine, among others. In the pharmaceutical field, automatic analysis of online user reviews allows for the analysis of large amounts of user's opinions and to obtain relevant information about the effectiveness and side effects of drugs, which could be used to improve pharmacovigilance systems. Throughout the years, approaches for sentiment analysis have progressed from simple rules to advanced machine learning techniques such as deep learning, which has become an emerging technology in many NLP tasks. Sentiment analysis is not oblivious to this success, and several systems based on deep learning have recently demonstrated their superiority over former methods, achieving state-of-the-art results on standard sentiment analysis datasets. However, prior work shows that very few attempts have been made to apply deep learning to sentiment analysis of drug reviews. We present a benchmark comparison of various deep learning architectures such as Convolutional Neural Networks (CNN) and Long short-term memory (LSTM) recurrent neural networks. We propose several combinations of these models and also study the effect of different pre-trained word embedding models. As transformers have revolutionized the NLP field achieving state-of-art results for many NLP tasks, we also explore bidirectional encoder representations from transformers (BERT) with a Bi-LSTM for the sentiment analysis of drug reviews. Our experiments show that the usage of BERT obtains the best results, but with a very high training time. On the other hand, CNN achieves acceptable results while requiring less training time.

关键词： Sentiment analysis Multi-class text classification Deep learning Convolutional neural network Long short-term memory bidirectional encoder representations from transformers

来源：评论

学校读者我要写书评

暂无评论

Using of transformers Models for Text Classification to Mobile Educational Applications

引用

IEEE LATIN AMERICA TRANSACTIONS 2023年第6期21卷 730-736页

作者： Garrido, Anabel Pilicita Arias, Enrique Barra Univ Politecn Madrid Madrid Spain

In Q2 2022, educational apps were the second most popular category on the Google Play Store, accounting for 10.47% of the apps available worldwide. This work explores the application of five BERT-based pre-trained models with the transformers architecture to classify mobile educational applications. These five models are according to the knowledge field: bert-base-cased, bert-base-uncased, roberta-base, albert-base-v2 and distilbert-base-uncased. This study uses a dataset with educational apps of Google Play, this dataset was enriched with description and category because it lacked this information. In all models, a tokenizer and fine-tuning works were applied for training in the classification task. After training the data, the testing phase was performed in which the models had to go through four training epochs to obtain better results: roberta-base with 81% accuracy, bert-base-uncased with 79% accuracy, bert-base-cased obtained 80% accuracy, albert-base-v2 obtained 78% accuracy and distilbert-base-uncased obtained 76% accuracy.

关键词： Bit error rate transformers Internet Training Text categorization Recurrent neural networks IEEE transactions Natural Language Processing Multiclass Text Classification bidirectional encoder representations from transformers

来源：评论

学校读者我要写书评

暂无评论

A Novel Named Entity Recognition Scheme for Steel E-Commerce Platforms Using a Lite BERT

引用

Computer Modeling in Engineering & Sciences 2021年第10期129卷 47-63页

作者： Maojian Chen Xiong Luo Hailun Shen Ziyang Huang Qiaojuan Peng School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing100083China Shunde Graduate School University of Science and Technology BeijingFoshan528399China Ouyeel Co. Ltd.Shanghai201999China

In the era of big data,E-commerce plays an increasingly important role,and steel E-commerce certainly occupies a positive ***,it is very difficult to choose satisfactory steel raw materials from diverse steel commodities online on steel E-commerce platforms in the purchase of *** order to improve the efficiency of purchasers searching for commodities on the steel E-commerce platforms,we propose a novel deep learning-based loss function for named entity recognition(NER).Considering the impacts of small sample and imbalanced data,in our NER scheme,the focal loss,the label smoothing,and the cross entropy are incorporated into a lite bidirectional encoder representations from transformers(BERT)model to avoid the ***,through the analysis of different classic annotation techniques used to tag data,an ideal one is chosen for the training model in our proposed *** are conducted on Chinese steel E-commerce *** experimental results show that the training time of a lite BERT(ALBERT)-based method is much shorter than that of BERT-based models,while achieving the similar computational performance in terms of metrics precision,recall,and F1 with BERT-based ***,our proposed approach performs much better than that of combining Word2Vec,bidirectional long short-term memory(Bi-LSTM),and conditional random field(CRF)models,in consideration of training time and F1.

关键词： Named entity recognition bidirectional encoder representations from transformers steel E-commerce platform annotation technique

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：