A large language model for electronic health records

X Yang, A Chen, N PourNejatian, HC Shin… - NPJ digital …, 2022 - nature.com
medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large
clinical language model… -identified clinical text) and systematically evaluate it on five clinical

Gatortron: A large clinical language model to unlock patient information from unstructured electronic health records

X Yang, A Chen, N PourNejatian, HC Shin… - arXiv preprint arXiv …, 2022 - arxiv.org
medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large
clinical language model … de-identified clinical text) and systematically evaluate it on 5 clinical

The shaky foundations of large language models and foundation models for electronic health records

M Wornow, Y Xu, R Thapa, B Patel, E Steinberg… - npj Digital …, 2023 - nature.com
… ChatGPT is a large language model (LLM), a type of FM which ingests text and outputs text
in response. Though ChatGPT was trained to simply predict the next word in a sentence—it is …

Med7: A transferable clinical natural language processing model for electronic health records

A Kormilitzin, N Vaci, Q Liu… - Artificial Intelligence in …, 2021 - Elsevier
… , similar to the masked language model objectives introduced in … The pre-trained language
model was then used to initialise the … of hyperparameters of the language model, such as the …

MedRoBERTa. nl: a language model for Dutch electronic health records

S Verkijk, P Vossen - Computational Linguistics in the Netherlands, 2021 - research.vu.nl
large volumes of unstructured medical data. In this paper, we present MedRoBERTa.nl, the
first language model trained on Dutch hospital … takers in hospitals about an individual patient. …

CancerBERT: a cancer domain-specific language model for extracting breast cancer phenotypes from electronic health records

S Zhou, N Wang, L Wang, H Liu… - … of the American Medical …, 2022 - academic.oup.com
electronic health records of a local hospital. We annotated named entities in 200 pathology
reports and 50 clinical … We kept pretraining the BlueBERT model on the cancer corpus with …

Natural language generation for electronic health records

SH Lee - NPJ digital medicine, 2018 - nature.com
… Like BLEU and ROUGE, CIDEr is based on an n-gram language model, and so we modify
it to allow for variable-length n-grams to avoid producing harsh ratings for synthetic chief …

A scoping review of using Large Language Models (LLMs) to investigate Electronic Health Records (EHRs)

L Li, J Zhou, Z Gao, W Hua, L Fan, H Yu… - arXiv preprint arXiv …, 2024 - arxiv.org
… For LLM-related keywords, we used two general terms, “large language model” and “LLM,” …
two search terms, “Electronic Medical Record” and “Electronic Health Record.” We applied …

Large language models to identify social determinants of health in electronic health records

M Guevara, S Chen, S Thomas, TL Chaunzwa… - NPJ digital …, 2024 - nature.com
… missing or incomplete in the structured data of electronic health records (EHRs). Large language
models (LLMs) could … LLM large language model, SDoH Social determinants of health. …

… language model–based generative natural language processing framework fine‐tuned on clinical notes accurately extracts headache frequency from electronic health …

CC Chiang, M Luo, G Dumkrieger… - … : The Journal of …, 2024 - Wiley Online Library
… information extraction model based on a state-of-the-art large language model, a GPT-2
generative model that can extract headache frequency from EHR free-text clinical notes with …