Biomedical Natural Language Processing Research Articles

BiomedRAG: A retrieval augmented large language model for biomedicine.

Retrieval-augmented generation (RAG) involves a solution by retrieving knowledge from an established database to enhance the performance of large language models (LLM). , these models retrieve information at the sentence or paragraph level, potentially introducing noise and affecting the generation quality. To address these issues, we propose a novel BiomedRAG framework that directly feeds automatically retrieved chunk-based documents into the LLM. Our evaluation of BiomedRAG across four biomedical natural language processing tasks using eight datasets demonstrates that our proposed framework not only improves the performance by 9.95% on average, but also achieves state-of-the-art results, surpassing various baselines by 4.97%. BiomedRAG paves the way for more accurate and adaptable LLM applications in the biomedical domain.

Clinical analogy resolution performance for foundation language models

Using extensive data sources to create foundation language models has revolutionized the performance of deep learning-based architectures. This remarkable improvement has led to state-of-the-art results for various downstream NLP tasks, including clinical tasks. However, more research is needed to measure model performance intrinsically, especially in the clinical domain. We revisit the use of analogy questions as an effective method to measure the intrinsic performance of language models for the clinical domain in English. We tested multiple Transformers-based language models over analogy questions constructed from the Unified Medical Language System (UMLS), a massive knowledge graph of clinical concepts. Our results show that large language models are significantly more performant for analogy resolution than small language models. Similarly, domain-specific language models perform better than general domain language models. We also found a correlation between intrinsic and extrinsic performance, validated through PubMedQA extrinsic task. Creating clinical-specific and language-specific language models is essential for advancing biomedical and clinical NLP and will ensure a valid application in clinical practice. Finally, given that our proposed intrinsic test is based on a term graph available in multiple languages, the dataset can be built to measure the performance of models in languages other than English.

JTIS: enhancing biomedical document-level relation extraction through joint training with intermediate steps.

Biomedical Relation Extraction (RE) is central to Biomedical Natural Language Processing and is crucial for various downstream applications. Existing RE challenges in the field of biology have primarily focused on intra-sentential analysis. However, with the rapid increase in the volume of literature and the complexity of relationships between biomedical entities, it often becomes necessary to consider multiple sentences to fully extract the relationship between a pair of entities. Current methods often fail to fully capture the complex semantic structures of information in documents, thereby affecting extraction accuracy. Therefore, unlike traditional RE methods that rely on sentence-level analysis and heuristic rules, our method focuses on extracting entity relationships from biomedical literature titles and abstracts and classifying relations that are novel findings. In our method, a multitask training approach is employed for fine-tuning a Pre-trained Language Model in the field of biology. Based on a broad spectrum of carefully designed tasks, our multitask method not only extracts relations of better quality due to more effective supervision but also achieves a more accurate classification of whether the entity pairs are novel findings. Moreover, by applying a model ensemble method, we further enhance our model's performance. The extensive experiments demonstrate that our method achieves significant performance improvements, i.e. surpassing the existing baseline by 3.94% in RE and 3.27% in Triplet Novel Typing in F1 score on BioRED, confirming its effectiveness in handling complex biomedical literature RE tasks. Database URL: https://codalab.lisn.upsaclay.fr/competitions/13377#learn_the_details-dataset.

Relational Extraction from Biomedical Texts with Capsule Network and Hybrid Knowledge Graph Embeddings

In the expanding landscape of biomedical literature, numerous latent associations outlined in scholarly papers await discovery and integration into biomedical databases. Biomedical Natural Language Processing (NLP) research focuses on automating knowledge extraction and mining from this literature, particularly emphasizing the essential task of Relation Extraction (RE). However, existing models have limitations, mainly in their applicability to partial datasets for RE tasks. Moreover, conventional models often treat RE as a binary classification challenge, which proves suboptimal given the diverse relationships, including intricate ones like similarity and hierarchy, present in the RE dataset. These limitations are exacerbated by the models’ inability to capture word-level positional nuances and sentence-level language features. In response to these challenges, we present a novel RE model called BicapBert. This model integrates neural networks and capsule networks, enhancing them with hybrid knowledge graph embeddings to extract relevant features. BicapBert utilizes PubMedBERT and capsule networks to extract word-level positional and sentence-level language features. It further captures knowledge features from a biomedical knowledge graph, integrating them with the aforementioned linguistic features. The amalgamated information is then input into a multi-layer perceptron, culminating in results derived through a softmax classifier. Experimental evaluations on three extensive RE task datasets showcase the state-of-the-art performance of our proposed model. Additionally, we validate the model’s efficacy on three randomly selected biomedical datasets for various tasks, further affirming its superiority.

Exploring the effectiveness of instruction tuning in biomedical language processing

Large Language Models (LLMs), particularly those similar to ChatGPT, have significantly influenced the field of Natural Language Processing (NLP). While these models excel in general language tasks, their performance in domain-specific downstream tasks such as biomedical and clinical Named Entity Recognition (NER), Relation Extraction (RE), and Medical Natural Language Inference (NLI) is still evolving. In this context, our study investigates the potential of instruction tuning for biomedical language processing, applying this technique to two general LLMs of substantial scale. We present a comprehensive, instruction-based model trained on a dataset that consists of approximately 200,000 instruction-focused samples. This dataset represents a carefully curated compilation of existing data, meticulously adapted and reformatted to align with the specific requirements of our instruction-based tasks. This initiative represents an important step in utilising such models to achieve results on par with specialised encoder-only models like BioBERT and BioClinicalBERT for various classical biomedical NLP tasks. Our work includes an analysis of the dataset’s composition and its impact on model performance, providing insights into the intricacies of instruction tuning. By sharing our codes, models, and the distinctively assembled instruction-based dataset, we seek to encourage ongoing research and development in this area.22Our code repository is available at https://github.com/nlpie-research/BioInstTune-LLM.

Use of SNOMED CT in Large Language Models: Scoping Review.

Large language models (LLMs) have substantially advanced natural language processing (NLP) capabilities but often struggle with knowledge-driven tasks in specialized domains such as biomedicine. Integrating biomedical knowledge sources such as SNOMED CT into LLMs may enhance their performance on biomedical tasks. However, the methodologies and effectiveness of incorporating SNOMED CT into LLMs have not been systematically reviewed. This scoping review aims to examine how SNOMED CT is integrated into LLMs, focusing on (1) the types and components of LLMs being integrated with SNOMED CT, (2) which contents of SNOMED CT are being integrated, and (3) whether this integration improves LLM performance on NLP tasks. Following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, we searched ACM Digital Library, ACL Anthology, IEEE Xplore, PubMed, and Embase for relevant studies published from 2018 to 2023. Studies were included if they incorporated SNOMED CT into LLM pipelines for natural language understanding or generation tasks. Data on LLM types, SNOMED CT integration methods, end tasks, and performance metrics were extracted and synthesized. The review included 37 studies. Bidirectional Encoder Representations from Transformers and its biomedical variants were the most commonly used LLMs. Three main approaches for integrating SNOMED CT were identified: (1) incorporating SNOMED CT into LLM inputs (28/37, 76%), primarily using concept descriptions to expand training corpora; (2) integrating SNOMED CT into additional fusion modules (5/37, 14%); and (3) using SNOMED CT as an external knowledge retriever during inference (5/37, 14%). The most frequent end task was medical concept normalization (15/37, 41%), followed by entity extraction or typing and classification. While most studies (17/19, 89%) reported performance improvements after SNOMED CT integration, only a small fraction (19/37, 51%) provided direct comparisons. The reported gains varied widely across different metrics and tasks, ranging from 0.87% to 131.66%. However, some studies showed either no improvement or a decline in certain performance metrics. This review demonstrates diverse approaches for integrating SNOMED CT into LLMs, with a focus on using concept descriptions to enhance biomedical language understanding and generation. While the results suggest potential benefits of SNOMED CT integration, the lack of standardized evaluation methods and comprehensive performance reporting hinders definitive conclusions about its effectiveness. Future research should prioritize consistent reporting of performance comparisons and explore more sophisticated methods for incorporating SNOMED CT's relational structure into LLMs. In addition, the biomedical NLP community should develop standardized evaluation frameworks to better assess the impact of ontology integration on LLM performance.

Learning to explain is a good biomedical few-shot learner.

Significant progress has been achieved in biomedical text mining using deep learning methods, which rely heavily on large amounts of high-quality data annotated by human experts. However, the reality is that obtaining high-quality annotated data is extremely challenging due to data scarcity (e.g. rare or new diseases), data privacy and security concerns, and the high cost of data annotation. Additionally, nearly all researches focus on predicting labels without providing corresponding explanations. Therefore, in this paper, we investigate a more realistic scenario, biomedical few-shot learning, and explore the impact of interpretability on biomedical few-shot learning. We present LetEx-Learning to explain-a novel multi-task generative approach that leverages reasoning explanations from large language models (LLMs) to enhance the inductive reasoning ability of few-shot learning. Our approach includes (1) collecting high-quality explanations by devising a suite of complete workflow based on LLMs through CoT prompting and self-training strategies, (2) converting various biomedical NLP tasks into a text-to-text generation task in a unified manner, where collected explanations serve as additional supervision between text-label pairs by multi-task training. Experiments are conducted on three few-shot settings across six biomedical benchmark datasets. The results show that learning to explain improves the performances of diverse biomedical NLP tasks in low-resource scenario, outperforming strong baseline models significantly by up to 6.41%. Notably, the proposed method makes the 220M LetEx perform superior reasoning explanation ability against LLMs. Our source code and data are available at https://github.com/cpmss521/LetEx.

Enhancing Radiological Biomedical Natural Language Processing Tasks with Radiology-Specific Word Encodings: A Comparative Analysis of Word Embeddings Sources

Background: Machine Learning (ML)-based Biomedical Natural Language Processing (BNLP) techniques have garnered attention in radiology. However, these models typically depend on Word Encodings (WE) trained on generic datasets, as radiology-specific word libraries are limited. Objective: This study aimed to investigate the potential of radiography as a comprehensive database for generating Radiology-Specific Word Encodings (RSWE), enhancing the efficiency of BNLP tasks, especially in processing radiological texts. Methods: A systematic evaluation was conducted using WE derived from four databases: medical records, biomedical journals, Wikipedia, and news sources. Unstructured Electronic Medical Record (EMR) data from the Mayo Clinic and PubMed Central publications were used to train WE for medical-specific sources, while GloVe and Google News represented publicly available pre-trained WE for generic sources. Analytical evaluation employed medical keywords in three categories (illness, symptoms, drugs), and a 2-D graphical plot was created for 380 medical words. Numerical evaluation consisted of internal and external assessments. Results: Findings revealed that RSWE derived from EMR and PubMed Central outperformed generic WE, better capturing medical word meanings and identifying medically essential terms, aligning more closely with expert assessments. Conclusion: The study demonstrates the value of radiography as a radiology-specific resource for generating RSWE, with promising implications for improving BNLP in radiology.

Integrating deep learning architectures for enhanced biomedical relation extraction: a pipeline approach.

Biomedical relation extraction from scientific publications is a key task in biomedical natural language processing (NLP) and can facilitate the creation of large knowledge bases, enable more efficient knowledge discovery, and accelerate evidence synthesis. In this paper, building upon our previous effort in the BioCreative VIII BioRED Track, we propose an enhanced end-to-end pipeline approach for biomedical relation extraction (RE) and novelty detection (ND) that effectively leverages existing datasets and integrates state-of-the-art deep learning methods. Our pipeline consists of four tasks performed sequentially: named entity recognition (NER), entity linking (EL), RE, and ND. We trained models using the BioRED benchmark corpus that was the basis of the shared task. We explored several methods for each task and combinations thereof: for NER, we compared a BERT-based sequence labeling model that uses the BIO scheme with a span classification model. For EL, we trained a convolutional neural network model for diseases and chemicals and used an existing tool, PubTator 3.0, for mapping other entity types. For RE and ND, we adapted the BERT-based, sentence-bound PURE model to bidirectional and document-level extraction. We also performed extensive hyperparameter tuning to improve model performance. We obtained our best performance using BERT-based models for NER, RE, and ND, and the hybrid approach for EL. Our enhanced and optimized pipeline showed substantial improvement compared to our shared task submission, NER: 93.53 (+3.09), EL: 83.87 (+9.73), RE: 46.18 (+15.67), and ND: 38.86 (+14.9). While the performances of the NER and EL models are reasonably high, RE and ND tasks remain challenging at the document level. Further enhancements to the dataset could enable more accurate and useful models for practical use. We provide our models and code at https://github.com/janinaj/e2eBioMedRE/. Database URL: https://github.com/janinaj/e2eBioMedRE/.

The overview of the BioRED (Biomedical Relation Extraction Dataset) track at BioCreative VIII.

The BioRED track at BioCreative VIII calls for a community effort to identify, semantically categorize, and highlight the novelty factor of the relationships between biomedical entities in unstructured text. Relation extraction is crucial for many biomedical natural language processing (NLP) applications, from drug discovery to custom medical solutions. The BioRED track simulates a real-world application of biomedical relationship extraction, and as such, considers multiple biomedical entity types, normalized to their specific corresponding database identifiers, as well as defines relationships between them in the documents. The challenge consisted of two subtasks: (i) in Subtask 1, participants were given the article text and human expert annotated entities, and were asked to extract the relation pairs, identify their semantic type and the novelty factor, and (ii) in Subtask 2, participants were given only the article text, and were asked to build an end-to-end system that could identify and categorize the relationships and their novelty. We received a total of 94 submissions from 14 teams worldwide. The highest F-score performances achieved for the Subtask 1 were: 77.17% for relation pair identification, 58.95% for relation type identification, 59.22% for novelty identification, and 44.55% when evaluating all of the above aspects of the comprehensive relation extraction. The highest F-score performances achieved for the Subtask 2 were: 55.84% for relation pair, 43.03% for relation type, 42.74% for novelty, and 32.75% for comprehensive relation extraction. The entire BioRED track dataset and other challenge materials are available at https://ftp.ncbi.nlm.nih.gov/pub/lu/BC8-BioRED-track/ and https://codalab.lisn.upsaclay.fr/competitions/13377 and https://codalab.lisn.upsaclay.fr/competitions/13378. Database URL: https://ftp.ncbi.nlm.nih.gov/pub/lu/BC8-BioRED-track/https://codalab.lisn.upsaclay.fr/competitions/13377https://codalab.lisn.upsaclay.fr/competitions/13378.

Improving biomedical entity linking for complex entity mentions with LLM-based text simplification.

Large amounts of important medical information are captured in free-text documents in biomedical research and within healthcare systems, which can be made accessible through natural language processing (NLP). A key component in most biomedical NLP pipelines is entity linking, i.e. grounding textual mentions of named entities to a reference of medical concepts, usually derived from a terminology system, such as the Systematized Nomenclature of Medicine Clinical Terms. However, complex entity mentions, spanning multiple tokens, are notoriously hard to normalize due to the difficulty of finding appropriate candidate concepts. In this work, we propose an approach to preprocess such mentions for candidate generation, building upon recent advances in text simplification with generative large language models. We evaluate the feasibility of our method in the context of the entity linking track of the BioCreative VIII SympTEMIST shared task. We find that instructing the latest Generative Pre-trained Transformer model with a few-shot prompt for text simplification results in mention spans that are easier to normalize. Thus, we can improve recall during candidate generation by 2.9percentage points compared to our baseline system, which achieved the best score in the original shared task evaluation. Furthermore, we show that this improvement in recall can be fully translated into top-1 accuracy through careful initialization of a subsequent reranking model. Our best system achieves an accuracy of 63.6% on the SympTEMIST test set. The proposed approach has been integrated into the open-source xMEN toolkit, which is available online via https://github.com/hpi-dhc/xmen.

BioInstruct: instruction tuning of large language models for biomedical natural language processing.

To enhance the performance of large language models (LLMs) in biomedical natural language processing (BioNLP) by introducing a domain-specific instruction dataset and examining its impact when combined with multi-task learning principles. We created the BioInstruct, comprising 25005 instructions to instruction-tune LLMs (LLaMA 1 and 2, 7B and 13B version). The instructions were created by prompting the GPT-4 language model with 3-seed samples randomly drawn from an 80 human curated instructions. We employed Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. We then evaluated these instruction-tuned LLMs on several BioNLP tasks, which can be grouped into 3 major categories: question answering (QA), information extraction (IE), and text generation (GEN). We also examined whether categories (eg, QA, IE, and generation) of instructions impact model performance. Comparing with LLMs without instruction-tuned, our instruction-tuned LLMs demonstrated marked performance gains: 17.3% in QA on average accuracy metric, 5.7% in IE on average F1 metric, and 96% in Generation tasks on average GPT-4 score metric. Our 7B-parameter instruction-tuned LLaMA 1 model was competitive or even surpassed other LLMs in the biomedical domain that were also fine-tuned from LLaMA 1 with vast domain-specific data or a variety of tasks. Our results also show that the performance gain is significantly higher when instruction fine-tuning is conducted with closely related tasks. Our findings align with the observations of multi-task learning, suggesting the synergies between 2 tasks. The BioInstruct dataset serves as a valuable resource and instruction tuned LLMs lead to the best performing BioNLP applications.

An in-depth evaluation of federated learning on biomedical natural language processing for information extraction

Language models (LMs) such as BERT and GPT have revolutionized natural language processing (NLP). However, the medical field faces challenges in training LMs due to limited data access and privacy constraints imposed by regulations like the Health Insurance Portability and Accountability Act (HIPPA) and the General Data Protection Regulation (GDPR). Federated learning (FL) offers a decentralized solution that enables collaborative learning while ensuring data privacy. In this study, we evaluated FL on 2 biomedical NLP tasks encompassing 8 corpora using 6 LMs. Our results show that: (1) FL models consistently outperformed models trained on individual clients’ data and sometimes performed comparably with models trained with polled data; (2) with the fixed number of total data, FL models training with more clients produced inferior performance but pre-trained transformer-based models exhibited great resilience. (3) FL models significantly outperformed pre-trained LLMs with few-shot prompting.

Large language models for biomedicine: foundations, opportunities, challenges, and best practices.

Generative large language models (LLMs) are a subset of transformers-based neural network architecture models. LLMs have successfully leveraged a combination of an increased number of parameters, improvements in computational efficiency, and large pre-training datasets to perform a wide spectrum of natural language processing (NLP) tasks. Using a few examples (few-shot) or no examples (zero-shot) for prompt-tuning has enabled LLMs to achieve state-of-the-art performance in a broad range of NLP applications. This article by the American Medical Informatics Association (AMIA) NLP Working Group characterizes the opportunities, challenges, and best practices for our community to leverage and advance the integration of LLMs in downstream NLP applications effectively. This can be accomplished through a variety of approaches, including augmented prompting, instruction prompt tuning, and reinforcement learning from human feedback (RLHF). Our focus is on making LLMs accessible to the broader biomedical informatics community, including clinicians and researchers who may be unfamiliar with NLP. Additionally, NLP practitioners may gain insight from the described best practices. We focus on 3 broad categories of NLP tasks, namely natural language understanding, natural language inferencing, and natural language generation. We review the emerging trends in prompt tuning, instruction fine-tuning, and evaluation metrics used for LLMs while drawing attention to several issues that impact biomedical NLP applications, including falsehoods in generated text (confabulation/hallucinations), toxicity, and dataset contamination leading to overfitting. We also review potential approaches to address some of these current challenges in LLMs, such as chain of thought prompting, and the phenomena of emergent capabilities observed in LLMs that can be leveraged to address complex NLP challenge in biomedical applications.

Biomedical text readability after hypernym substitution with fine-tuned large language models.

The advent of patient access to complex medical information online has highlighted the need for simplification of biomedical text to improve patient understanding and engagement in taking ownership of their health. However, comprehension of biomedical text remains a difficult task due to the need for domain-specific expertise. We aimed to study the simplification of biomedical text via large language models (LLMs) commonly used for general natural language processing tasks involve text comprehension, summarization, generation, and prediction of new text from prompts. Specifically, we finetuned three variants of large language models to perform substitutions of complex words and word phrases in biomedical text with a related hypernym. The output of the text substitution process using LLMs was evaluated by comparing the pre- and post-substitution texts using four readability metrics and two measures of sentence complexity. A sample of 1,000 biomedical definitions in the National Library of Medicine's Unified Medical Language System (UMLS) was processed with three LLM approaches, and each showed an improvement in readability and sentence complexity after hypernym substitution. Readability scores were translated from a pre-processed collegiate reading level to a post-processed US high-school level. Comparison between the three LLMs showed that the GPT-J-6b approach had the best improvement in measures of sentence complexity. This study demonstrates the merit of hypernym substitution to improve readability of complex biomedical text for the public and highlights the use case for fine-tuning open-access large language models for biomedical natural language processing.

Impact of Translation on Biomedical Information Extraction: Experiment on Real-Life Clinical Notes.

Biomedical natural language processing tasks are best performed with English models, and translation tools have undergone major improvements. On the other hand, building annotated biomedical data sets remains a challenge. The aim of our study is to determine whether the use of English tools to extract and normalize French medical concepts based on translations provides comparable performance to that of French models trained on a set of annotated French clinical notes. We compared 2 methods: 1 involving French-language models and 1 involving English-language models. For the native French method, the named entity recognition and normalization steps were performed separately. For the translated English method, after the first translation step, we compared a 2-step method and a terminology-oriented method that performs extraction and normalization at the same time. We used French, English, and bilingual annotated data sets to evaluate all stages (named entity recognition, normalization, and translation) of our algorithms. The native French method outperformed the translated English method, with an overall F1-score of 0.51 (95% CI 0.47-0.55), compared with 0.39 (95% CI 0.34-0.44) and 0.38 (95% CI 0.36-0.40) for the 2 English methods tested. Despite recent improvements in translation models, there is a significant difference in performance between the 2 approaches in favor of the native French method, which is more effective on French medical texts, even with few annotated documents.

Taiyi: a bilingual fine-tuned large language model for diverse biomedical tasks.

Most existing fine-tuned biomedical large language models (LLMs) focus on enhancing performance in monolingual biomedical question answering and conversation tasks. To investigate the effectiveness of the fine-tuned LLMs on diverse biomedical natural language processing (NLP) tasks in different languages, we present Taiyi, a bilingual fine-tuned LLM for diverse biomedical NLP tasks. We first curated a comprehensive collection of 140 existing biomedical text mining datasets (102 English and 38 Chinese datasets) across over 10 task types. Subsequently, these corpora were converted to the instruction data used to fine-tune the general LLM. During the supervised fine-tuning phase, a 2-stage strategy is proposed to optimize the model performance across various tasks. Experimental results on 13 test sets, which include named entity recognition, relation extraction, text classification, and question answering tasks, demonstrate that Taiyi achieves superior performance compared to general LLMs. The case study involving additional biomedical NLP tasks further shows Taiyi's considerable potential for bilingual biomedical multitasking. Leveraging rich high-quality biomedical corpora and developing effective fine-tuning strategies can significantly improve the performance of LLMs within the biomedical domain. Taiyi shows the bilingual multitasking capability through supervised fine-tuning. However, those tasks such as information extraction that are not generation tasks in nature remain challenging for LLM-based generative approaches, and they still underperform the conventional discriminative approaches using smaller language models.

Evaluating the ChatGPT family of models for biomedical reasoning and classification.

Large language models (LLMs) have shown impressive ability in biomedical question-answering, but have not been adequately investigated for more specific biomedical applications. This study investigates ChatGPT family of models (GPT-3.5, GPT-4) in biomedical tasks beyond question-answering. We evaluated model performance with 11 122 samples for two fundamental tasks in the biomedical domain-classification (n = 8676) and reasoning (n = 2446). The first task involves classifying health advice in scientific literature, while the second task is detecting causal relations in biomedical literature. We used 20% of the dataset for prompt development, including zero- and few-shot settings with and without chain-of-thought (CoT). We then evaluated the best prompts from each setting on the remaining dataset, comparing them to models using simple features (BoW with logistic regression) and fine-tuned BioBERT models. Fine-tuning BioBERT produced the best classification (F1: 0.800-0.902) and reasoning (F1: 0.851) results. Among LLM approaches, few-shot CoT achieved the best classification (F1: 0.671-0.770) and reasoning (F1: 0.682) results, comparable to the BoW model (F1: 0.602-0.753 and 0.675 for classification and reasoning, respectively). It took 78 h to obtain the best LLM results, compared to 0.078 and 0.008 h for the top-performing BioBERT and BoW models, respectively. The simple BoW model performed similarly to the most complex LLM prompting. Prompt engineering required significant investment. Despite the excitement around viral ChatGPT, fine-tuning for two fundamental biomedical natural language processing tasks remained the best strategy.

CMBEE: A constraint-based multi-task learning framework for biomedical event extraction

Objective:Event extraction plays a crucial role in natural language processing. However, in the biomedical domain, the presence of nested events adds complexity to event extraction compared to single events, and these events usually have strong semantic relationships and constraints. Previous approaches ignored the binding connections between these complex nested events. This study aims to develop a unified framework based on event constraint information that jointly extract biomedical event triggers and arguments and enhance the performance of nested biomedical event extraction. Material and Methods:We propose a multi-task learning framework based on constraint information called CMBEE for the task of biomedical event extraction. The N-tuple form of event patterns is used to represent the constrained information, which is integrated into role detection and event type classification tasks. The framework use attention mechanism and gating mechanism to explore the fusion of multiple tuple information, as well as local and global constrained information fusion methods to dig further into the connections between events. Results:Experimental results demonstrate that our proposed method achieves the highest F1 score on a multilevel event extraction biomedical (MLEE) corpus and performs favorably on the biomedical natural language processing shared task 2013 Genia event corpus (GE 13). Conclusions:The experimental results indicate that modeling event patterns and constraints for multi-event extraction tasks is effective for complex biomedical event extraction. The fusion strategy proposed in this study, which incorporates different constraint information, helps to better express semantic information.

A study of generative large language model for medical research and healthcare

There are enormous enthusiasm and concerns in applying large language models (LLMs) to healthcare. Yet current assumptions are based on general-purpose LLMs such as ChatGPT, which are not developed for medical use. This study develops a generative clinical LLM, GatorTronGPT, using 277 billion words of text including (1) 82 billion words of clinical text from 126 clinical departments and approximately 2 million patients at the University of Florida Health and (2) 195 billion words of diverse general English text. We train GatorTronGPT using a GPT-3 architecture with up to 20 billion parameters and evaluate its utility for biomedical natural language processing (NLP) and healthcare text generation. GatorTronGPT improves biomedical natural language processing. We apply GatorTronGPT to generate 20 billion words of synthetic text. Synthetic NLP models trained using synthetic text generated by GatorTronGPT outperform models trained using real-world clinical text. Physicians’ Turing test using 1 (worst) to 9 (best) scale shows that there are no significant differences in linguistic readability (p = 0.22; 6.57 of GatorTronGPT compared with 6.93 of human) and clinical relevance (p = 0.91; 7.0 of GatorTronGPT compared with 6.97 of human) and that physicians cannot differentiate them (p < 0.001). This study provides insights into the opportunities and challenges of LLMs for medical research and healthcare.