Prompt engineering for healthcare: Methodologies and applications

J Wang, E Shi, S Yu, Z Wu, C Ma, H Dai, Q Yang… - ar** of postpartum hemorrhage using large language models
E Alsentzer, MJ Rasmussen, R Fontoura, AL Cull… - NPJ Digital …, 2023 - nature.com
Many areas of medicine would benefit from deeper, more accurate phenoty**, but there
are limited approaches for phenoty** using clinical notes without substantial annotated …

[HTML][HTML] Knowledge injected prompt based fine-tuning for multi-label few-shot icd coding

Z Yang, S Wang, BPS Rawat, A Mitra… - Proceedings of the …, 2022 - ncbi.nlm.nih.gov
Abstract Automatic International Classification of Diseases (ICD) coding aims to assign
multiple ICD codes to a medical note with average length of 3,000+ tokens. This task is …

Knowledge graphs for the life sciences: Recent developments, challenges and opportunities

J Chen, H Dong, J Hastings, E Jiménez-Ruiz… - arxiv preprint arxiv …, 2023 - arxiv.org
The term life sciences refers to the disciplines that study living organisms and life processes,
and include chemistry, biology, medicine, and a range of other related disciplines. Research …

Paniniqa: Enhancing patient education through interactive question answering

P Cai, Z Yao, F Liu, D Wang, M Reilly… - Transactions of the …, 2023 - direct.mit.edu
A patient portal allows discharged patients to access their personalized discharge
instructions in electronic health records (EHRs). However, many patients have difficulty …

Keblm: Knowledge-enhanced biomedical language models

TM Lai, CX Zhai, H Ji - Journal of Biomedical Informatics, 2023 - Elsevier
Pretrained language models (PLMs) have demonstrated strong performance on many
natural language processing (NLP) tasks. Despite their great success, these PLMs are …

Improving summarization with human edits

Z Yao, BJ Schloss, SP Selvaraj - arxiv preprint arxiv:2310.05857, 2023 - arxiv.org
Recent work has shown the promise of learning with human feedback paradigms to produce
human-determined high-quality text. Existing works use human feedback to train large …

[HTML][HTML] Context variance evaluation of pretrained language models for prompt-based biomedical knowledge probing

Z Yao, Y Cao, Z Yang, H Yu - AMIA Summits on Translational …, 2023 - ncbi.nlm.nih.gov
Pretrained language models (PLMs) have motivated research on what kinds of knowledge
these models learn. Fill-in-the-blanks problem (eg, cloze tests) is a natural approach for …

Leveraging GPT-4 for identifying cancer phenotypes in electronic health records: a performance comparison between GPT-4, GPT-3.5-turbo, Flan-T5, Llama-3-8B …

K Bhattarai, IY Oh, JM Sierra, J Tang, PRO Payne… - JAMIA …, 2024 - academic.oup.com
Objective Accurately identifying clinical phenotypes from Electronic Health Records (EHRs)
provides additional insights into patients' health, especially when such information is …

NoteChat: a dataset of synthetic doctor-patient conversations conditioned on clinical notes

J Wang, Z Yao, Z Yang, H Zhou, R Li, X Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
The detailed clinical records drafted by doctors after each patient's visit are crucial for
medical practitioners and researchers. Automating the creation of these notes with language …