A comparative study of pre-trained language models for named entity recognition in clinical trial eligibility criteria from multiple corpora

Evaluating Medical Entity Recognition in Health Care: Entity Model Quantitative Study

BACKGROUND

Named entity recognition (NER) models are essential for extracting structured information from unstructured medical texts by identifying entities such as diseases, treatments, and conditions, enhancing clinical decision-making and research. Innovations in machine learning, particularly those involving Bidirectional Encoder Representations From Transformers (BERT)-based deep learning and large language models, have significantly advanced NER capabilities. However, their performance varies across medical datasets due to the complexity and diversity of medical terminology. Previous studies have often focused on overall performance, neglecting specific challenges in medical contexts and the impact of macrofactors like lexical composition on prediction accuracy. These gaps hinder the development of optimized NER models for medical applications.

OBJECTIVE

This study aims to meticulously evaluate the performance of various NER models in the context of medical text analysis, focusing on how complex medical terminology affects entity recognition accuracy. Additionally, we explored the influence of macrofactors on model performance, seeking to provide insights for refining NER models and enhancing their reliability for medical applications.

METHODS

This study comprehensively evaluated 7 NER models-hidden Markov models, conditional random fields, BERT for Biomedical Text Mining, Big Transformer Models for Efficient Long-Sequence Attention, Decoding-enhanced BERT with Disentangled Attention, Robustly Optimized BERT Pretraining Approach, and Gemma-across 3 medical datasets: Revised Joint Workshop on Natural Language Processing in Biomedicine and its Applications (JNLPBA), BioCreative V CDR, and Anatomical Entity Mention (AnatEM). The evaluation focused on prediction accuracy, resource use (eg, central processing unit and graphics processing unit use), and the impact of fine-tuning hyperparameters. The macrofactors affecting model performance were also screened using the multilevel factor elimination algorithm.

RESULTS

The fine-tuned BERT for Biomedical Text Mining, with balanced resource use, generally achieved the highest prediction accuracy across the Revised JNLPBA and AnatEM datasets, with microaverage (AVG_MICRO) scores of 0.932 and 0.8494, respectively, highlighting its superior proficiency in identifying medical entities. Gemma, fine-tuned using the low-rank adaptation technique, achieved the highest accuracy on the BioCreative V CDR dataset with an AVG_MICRO score of 0.9962 but exhibited variability across the other datasets (AVG_MICRO scores of 0.9088 on the Revised JNLPBA and 0.8029 on AnatEM), indicating a need for further optimization. In addition, our analysis revealed that 2 macrofactors, entity phrase length and the number of entity words in each entity phrase, significantly influenced model performance.

CONCLUSIONS

This study highlights the essential role of NER models in medical informatics, emphasizing the imperative for model optimization via precise data targeting and fine-tuning. The insights from this study will notably improve clinical decision-making and facilitate the creation of more sophisticated and effective medical NER models.

Advancing entity recognition in biomedicine via instruction tuning of large language models

MOTIVATION

Large Language Models (LLMs) have the potential to revolutionize the field of Natural Language Processing, excelling not only in text generation and reasoning tasks but also in their ability for zero/few-shot learning, swiftly adapting to new tasks with minimal fine-tuning. LLMs have also demonstrated great promise in biomedical and healthcare applications. However, when it comes to Named Entity Recognition (NER), particularly within the biomedical domain, LLMs fall short of the effectiveness exhibited by fine-tuned domain-specific models. One key reason is that NER is typically conceptualized as a sequence labeling task, whereas LLMs are optimized for text generation and reasoning tasks.

RESULTS

We developed an instruction-based learning paradigm that transforms biomedical NER from a sequence labeling task into a generation task. This paradigm is end-to-end and streamlines the training and evaluation process by automatically repurposing pre-existing biomedical NER datasets. We further developed BioNER-LLaMA using the proposed paradigm with LLaMA-7B as the foundational LLM. We conducted extensive testing on BioNER-LLaMA across three widely recognized biomedical NER datasets, consisting of entities related to diseases, chemicals, and genes. The results revealed that BioNER-LLaMA consistently achieved higher F1-scores ranging from 5% to 30% compared to the few-shot learning capabilities of GPT-4 on datasets with different biomedical entities. We show that a general-domain LLM can match the performance of rigorously fine-tuned PubMedBERT models and PMC-LLaMA, biomedical-specific language model. Our findings underscore the potential of our proposed paradigm in developing general-domain LLMs that can rival SOTA performances in multi-task, multi-domain scenarios in biomedical and health applications.

AVAILABILITY AND IMPLEMENTATION

Datasets and other resources are available at https://github.com/BIDS-Xu-Lab/BioNER-LLaMA.

AutoCriteria: a generalizable clinical trial eligibility criteria extraction system powered by large language models

OBJECTIVES

We aim to build a generalizable information extraction system leveraging large language models to extract granular eligibility criteria information for diverse diseases from free text clinical trial protocol documents. We investigate the model's capability to extract criteria entities along with contextual attributes including values, temporality, and modifiers and present the strengths and limitations of this system.

MATERIALS AND METHODS

The clinical trial data were acquired from https://ClinicalTrials.gov/. We developed a system, AutoCriteria, which comprises the following modules: preprocessing, knowledge ingestion, prompt modeling based on GPT, postprocessing, and interim evaluation. The final system evaluation was performed, both quantitatively and qualitatively, on 180 manually annotated trials encompassing 9 diseases.

RESULTS

AutoCriteria achieves an overall F1 score of 89.42 across all 9 diseases in extracting the criteria entities, with the highest being 95.44 for nonalcoholic steatohepatitis and the lowest of 84.10 for breast cancer. Its overall accuracy is 78.95% in identifying all contextual information across all diseases. Our thematic analysis indicated accurate logic interpretation of criteria as one of the strengths and overlooking/neglecting the main criteria as one of the weaknesses of AutoCriteria.

DISCUSSION

AutoCriteria demonstrates strong potential to extract granular eligibility criteria information from trial documents without requiring manual annotations. The prompts developed for AutoCriteria generalize well across different disease areas. Our evaluation suggests that the system handles complex scenarios including multiple arm conditions and logics.

CONCLUSION

AutoCriteria currently encompasses a diverse range of diseases and holds potential to extend to more in the future. This signifies a generalizable and scalable solution, poised to address the complexities of clinical trial application in real-world settings.

Advancing Italian biomedical information extraction with transformers-based models: Methodological insights and multicenter practical application

The introduction of computerized medical records in hospitals has reduced burdensome activities like manual writing and information fetching. However, the data contained in medical records are still far underutilized, primarily because extracting data from unstructured textual medical records takes time and effort. Information Extraction, a subfield of Natural Language Processing, can help clinical practitioners overcome this limitation by using automated text-mining pipelines. In this work, we created the first Italian neuropsychiatric Named Entity Recognition dataset, PsyNIT, and used it to develop a Transformers-based model. Moreover, we collected and leveraged three external independent datasets to implement an effective multicenter model, with overall F1-score 84.77 %, Precision 83.16 %, Recall 86.44 %. The lessons learned are: (i) the crucial role of a consistent annotation process and (ii) a fine-tuning strategy that combines classical methods with a "low-resource" approach. This allowed us to establish methodological guidelines that pave the way for Natural Language Processing studies in less-resourced languages.

Named Entity Recognition and Normalization for Alzheimer's Disease Eligibility Criteria

Alzheimer's Disease (AD) is a complex neurodegenerative disorder that affects millions of people worldwide. Finding effective treatments for this disease is crucial. Clinical trials play an essential role in developing and testing new treatments for AD. However, identifying eligible participants can be challenging, time-consuming, and costly. In recent years, the development of natural language processing (NLP) techniques, specifically named entity recognition (NER) and named entity normalization (NEN), have helped to automate the identification and extraction of relevant information from the eligibility criteria (EC) more efficiently, in order to facilitate semi-automatic patient recruitment and enable data FAIRness for clinical trial data. Nevertheless, most current biomedical NER models only provide annotations for a restricted set of entity types that may not be applicable to the clinical trial data. Additionally, accurately performing NEN on entities that are negated using a negative prefix currently lacks established techniques. In this paper, we introduce a pipeline designed for information extraction from AD clinical trial EC, which involves preprocessing of the EC data, clinical NER, and biomedical NEN to Unified Medical Language System (UMLS). Our NER model can identify named entities in seven pre-defined categories, while our NEN model employs a combination of exact match and partial match search strategies, as well as customized rules to accurately normalize entities with negative prefixes. To evaluate the performance of our pipeline, we measured the precision, recall, and F1 score for the NER component, and we manually reviewed the top five mapping results produced by the NEN component. Our evaluation of the pipeline's performance revealed that it can successfully normalize named entities in clinical trial ECs with optimal accuracies. The NER component achieved a overall F1 of 0.816, demonstrating its ability to accurately identify seven types of named entities in clinical text. The NEN component of the pipeline also demonstrated impressive performance, with customized rules and a combination of exact and partial match strategies leading to an accuracy of 0.940 for normalized entities.

The New Version of the ANDDigest Tool with Improved AI-Based Short Names Recognition

The body of scientific literature continues to grow annually. Over 1.5 million abstracts of biomedical publications were added to the PubMed database in 2021. Therefore, developing cognitive systems that provide a specialized search for information in scientific publications based on subject area ontology and modern artificial intelligence methods is urgently needed. We previously developed a web-based information retrieval system, ANDDigest, designed to search and analyze information in the PubMed database using a customized domain ontology. This paper presents an improved ANDDigest version that uses fine-tuned PubMedBERT classifiers to enhance the quality of short name recognition for molecular-genetics entities in PubMed abstracts on eight biological object types: cell components, diseases, side effects, genes, proteins, pathways, drugs, and metabolites. This approach increased average short name recognition accuracy by 13%.