.png){kind=icon}
返回
Ascle-A Python Natural Language Processing Toolkit for MedicalText Generation:Development and Evaluation Study
.png){kind=icon}
OA
AI
DOI：10.2196/60601.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Background: Medical texts present significant domain-specific challenges, and manually curating these texts is a time-consumingand labor-intensive process. To address this, natural language processing (NLP) algorithms have been developed to automatetext processing. In the biomedical field, various toolkits for text processing exist, which have greatly improved the efficiency ofhandling unstructured text. However, these existing toolkits tend to emphasize different perspectives, and none of them offergeneration capabilities, leaving a significant gap in the current offerings.Objective: This study aims to describe the development and preliminary evaluation of Ascle. Ascle is tailored for biomedicalresearchers and clinical staff with an easy-to-use, all-in-one solution that requires minimal programming expertise. For the firsttime, Ascle provides 4 advanced and challenging generative functions: question-answering, text summarization, text simplification,and machine translation. In addition, Ascle integrates 12 essential NLP functions, along with query and search capabilities forclinical databases.Methods: We fine-tuned 32 domain-specific language models and evaluated them thoroughly on 27 established benchmarks.In addition, for the question-answering task, we developed a retrieval-augmented generation (RAG) framework for large language models that incorporated a medical knowledge graph with ranking techniques to enhance the reliability of generated answers.Additionally, we conducted a physician validation to assess the quality of generated content beyond automated metrics.Results: The fine-tuned models and RAG framework consistently enhanced text generation tasks. For example, the fine-tunedmodels improved the machine translation task by 20.27 in terms of BLEU score. In the question-answering task, the RAGframework raised the ROUGE-L score by 18% over the vanilla models. Physician validation of generated answers showed highscores for readability (4.95/5) and relevancy (4.43/5), with a lower score for accuracy (3.90/5) and completeness (3.31/5).Conclusions: This study introduces the development and evaluation of Ascle, a user-friendly NLP toolkit designed for medicaltext generation. All code is publicly available through the Ascle GitHub repository. All fine-tuned language models can beaccessed through Hugging Face
Keyword:
natural language processing
machine learning
deep learning
generative artificial intelligence
large language models
retrieval-augmented generation
healthcare
期刊
IF:
6
论文数:
9.7K
被引数:
5.0W
机构
引用论文
分享收藏Gender-related differences in concomitant articular injuries after acute lateral patellar dislocation.png)
Injury
InjuryIF0
PREAI
分享收藏Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis深度EHR: 用于电子健康记录 (EHR) 分析的深度学习技术的最新进展综述
OAAI
OAAI分享收藏1,2,4,5‐Benzenetetracarboxylic Acid and 4,4′‐Bipyridine as Ligands in Designing Low‐Dimensional Coordination Polymers1,2，4,5-苯四甲酸和4,4-联吡啶作为低维配位聚合物设计中的配体
PREAI
分享收藏分享收藏Bile Acid-Induced Arrhythmia Is Mediated by Muscarinic M2 Receptors in Neonatal Rat CardiomyocytesPLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容