A generalist vision–language foundation model for diverse biomedical tasks

K Zhang, R Zhou, E Adhikarla, Z Yan, Y Liu, J Yu… - Nature Medicine, 2024 - nature.com
Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or
modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize …

Fine-tuning aligned language models compromises safety, even when users do not intend to!

X Qi, Y Zeng, T **e, PY Chen, R Jia, P Mittal… - arxiv preprint arxiv …, 2023 - arxiv.org
Optimizing large language models (LLMs) for downstream use cases often involves the
customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama …

Pre-training in medical data: A survey

Y Qiu, F Lin, W Chen, M Xu - Machine Intelligence Research, 2023 - Springer
Medical data refers to health-related information associated with regular patient care or as
part of a clinical trial program. There are many categories of such data, such as clinical …

Biomedgpt: A unified and generalist biomedical generative pre-trained transformer for vision, language, and multimodal tasks

K Zhang, J Yu, E Adhikarla, R Zhou, Z Yan… - arxiv e …, 2023 - ui.adsabs.harvard.edu
Conventional task-and modality-specific artificial intelligence (AI) models are inflexible in
real-world deployment and maintenance for biomedicine. At the same time, the growing …

[HTML][HTML] Integrating domain knowledge for biomedical text analysis into deep learning: A survey

L Cai, J Li, H Lv, W Liu, H Niu, Z Wang - Journal of Biomedical Informatics, 2023 - Elsevier
The past decade has witnessed an explosion of textual information in the biomedical field.
Biomedical texts provide a basis for healthcare delivery, knowledge discovery, and decision …

BioInstruct: instruction tuning of large language models for biomedical natural language processing

H Tran, Z Yang, Z Yao, H Yu - Journal of the American Medical …, 2024 - academic.oup.com
Objectives To enhance the performance of large language models (LLMs) in biomedical
natural language processing (BioNLP) by introducing a domain-specific instruction dataset …

Parameter-efficient fine-tuning of llama for the clinical domain

AP Gema, P Minervini, L Daines, T Hope… - arxiv preprint arxiv …, 2023 - arxiv.org
Adapting pretrained language models to novel domains, such as clinical applications,
traditionally involves retraining their entire set of parameters. Parameter-Efficient Fine …

Clinical prompt learning with frozen language models

N Taylor, Y Zhang, DW Joyce, Z Gao… - … on Neural Networks …, 2023 - ieeexplore.ieee.org
When the first transformer-based language models were published in the late 2010s,
pretraining with general text and then fine-tuning the model on a task-specific dataset often …

[HTML][HTML] Learning to make rare and complex diagnoses with generative AI assistance: qualitative study of popular large language models

T Abdullahi, R Singh, C Eickhoff - JMIR Medical Education, 2024 - mededu.jmir.org
Background: Patients with rare and complex diseases often experience delayed diagnoses
and misdiagnoses because comprehensive knowledge about these diseases is limited to …

Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients

M Mahbub, S Srinivasan, I Danciu, A Peluso, E Begoli… - Plos one, 2022 - journals.plos.org
Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes
and efficient utilization of resources. Accessibility of electronic health records (EHR) has …