• Ascle: A Python Natural Langua...

Treffer: Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation.

Title:
Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation.
Authors:
Yang R; Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore.; Department of Biomedical Informatics, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore., Zeng Q; Department of Linguistics, Northwestern University, Evanston, IL, USA., You K; Department of Computer Science, Yale University, New Haven, CT, USA., Qiao Y; Yale School of Public Health, Yale University, New Haven, CT, USA., Huang L; Department of Computer Science, Yale University, New Haven, CT, USA., Hsieh CC; Department of Computer Science, Yale University, New Haven, CT, USA., Rosand B; Department of Computer Science, Yale University, New Haven, CT, USA., Goldwasser J; Department of Computer Science, Yale University, New Haven, CT, USA., Dave AD; Yale New Haven Hospital, Yale School of Medicine, Yale University, New Haven, CT, USA., Keenan TDL; Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, MD, USA., Chew EY; Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, MD, USA., Radev D; Department of Computer Science, Yale University, New Haven, CT, USA., Lu Z; National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, USA., Xu H; Section of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, CT, USA., Chen Q; National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, USA.; Section of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, CT, USA., Li I; Information Technology Center, University of Tokyo, Tokyo, Japan.
Source:
ArXiv [ArXiv] 2023 Dec 09. Date of Electronic Publication: 2023 Dec 09.
Publication Type:
Journal Article; Preprint
Language:
English
Journal Info:
Country of Publication: United States NLM ID: 101759493 Publication Model: Electronic Cited Medium: Internet ISSN: 2331-8422 (Electronic) Linking ISSN: 23318422 NLM ISO Abbreviation: ArXiv Subsets: PubMed not MEDLINE
Comments:
Update in: J Med Internet Res. 2024 Oct 3;26:e60601. doi: 10.2196/60601.. (PMID: 39361955)
References:
NPJ Digit Med. 2023 Jan 3;6(1):1. (PMID: 36596833)
Proc Conf. 2021 Jun;2021:4972-4984. (PMID: 35663507)
Brief Bioinform. 2021 Nov 5;22(6):. (PMID: 34308472)
AMIA Annu Symp Proc. 2022 Feb 21;2021:438-447. (PMID: 35308962)
Adv Prev Med. 2017;2017:9780317. (PMID: 28656111)
Sci Data. 2019 Jan 15;6(1):1. (PMID: 30647409)
PLoS Biol. 2018 Apr 16;16(4):e2002846. (PMID: 29659566)
J Biomed Inform. 2014 Dec;52:457-67. (PMID: 25016293)
BMC Med Inform Decis Mak. 2021 Jan 2;21(1):1. (PMID: 33388057)
J Gen Intern Med. 2022 Apr;37(5):1275-1277. (PMID: 35132559)
J Am Med Inform Assoc. 2010 Sep-Oct;17(5):507-13. (PMID: 20819853)
BMC Bioinformatics. 2019 Jan 3;20(1):1. (PMID: 30606105)
Sci Data. 2020 Jan 2;7(1):1. (PMID: 31896794)
Nat Med. 2023 Aug;29(8):1930-1940. (PMID: 37460753)
J Am Med Inform Assoc. 2021 Aug 13;28(9):1892-1899. (PMID: 34157094)
Grant Information:
K99 LM014024 United States LM NLM NIH HHS
Contributed Indexing:
Keywords: generative artificial intelligence; healthcare; machine learning; natural language processing
Entry Date(s):
Date Created: 20251001 Date Completed: 20251010 Latest Revision: 20251011
Update Code:
20251011
PubMed Central ID:
PMC12478431
PMID:
41031083
Database:
MEDLINE

Weitere Informationen

Objective: This study introduces Ascle, a pioneering natural language processing (NLP) toolkit designed for medical text generation. Ascle is tailored for biomedical researchers and healthcare professionals with an easy-to-use, all-in-one solution that requires minimal programming expertise. For the first time, Ascle evaluates and provides interfaces for the latest pre-trained language models, encompassing four 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 for clinical databases.
Materials and Methods: We fine-tuned 32 domain-specific language models and evaluated them thoroughly on 24 established benchmarks. Additionally, for the question-answering task, we conducted manual reviews with clinicians, focusing on Readability, Relevancy, Accuracy, and Completeness, to provide users with a more reliable evaluation.
Results: The fine-tuned models consistently improved text generation tasks. For instance, it improved the machine translation task by 20.27 in terms of BLEU score. For the answer generation task, manual reviews showed the generated answers had average scores of 4.95 (out of 5), 4.43, 3.9, and 3.31 in Readability, Relevancy, Accuracy, and Completeness, respectively.
Conclusions: This study introduces the development and evaluation of Ascle, a user-friendly NLP toolkit designed for medical text generation. Ascle offers an all-in-one solution including four advanced generative functions: question-answering, text summarization, text simplification, and machine translation. The toolkit, its models, and associated data are publicly available via https://github.com/Yale-LILY/Ascle.

CONFLICT OF INTEREST STATEMENT The authors do not have conflicts of interest related to this study.