Hui Lin

Dr. Hui Lin

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 July 2025 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
MZMenglei Zhu
Menglei Zhu
HLHui Lin
Hui Lin
JJJue Jiang
Jue Jiang
AJAbbas J. Jinia
Abbas J. Jinia
JJJustin Jee
Justin Jee
ALAnyi Li
Anyi Li
Subspecialty knowledge barriers have limited the adoption of large language models (LLMs) in oncology. We introduce Woollie, an open-source, oncology-specific LLM trained on real-world data from Memorial Sloan Kettering Cancer Center (MSK) across lung, breast, prostate, pancreatic, and colorectal cancers, with external validation using University of California, San Francisco (UCSF) data. Woollie surpasses ChatGPT in medical benchmarks and excels in eight non-medical benchmarks. Analyzing 39,319 radiology impression notes from 4002 patients, it achieved an overall area under the receiver operating characteristic curve (AUROC) of 0.97 for cancer progression prediction on MSK data, including a notable 0.98 AUROC for pancreatic cancer. On UCSF data, it achieved an overall AUROC of 0.88, excelling in lung cancer detection with an AUROC of 0.95. As the first oncology specific LLM validated across institutions, Woollie demonstrates high accuracy and consistency across cancer types, underscoring its potential to enhance cancer progression analysis.

15 May 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
JBJorge Barrios
Jorge Barrios
EPEvan Porter
Evan Porter
DCDante P. I. Capaldi
Dante P. I. Capaldi
TUTaman Upadhaya
Taman Upadhaya
WCWilliam C. Chen
William C. Chen
OMOlivier Morin
Olivier Morin
Brain metastases are a frequent and debilitating manifestation of advanced cancer. Here, we collect and analyze neuroimaging of 3,065 cancer patients with 13,067 brain metastases, representing an extensive collection for research. We find that metastases predominantly localize to high perfusion areas near the grey-white matter junction, but also identify notable differences depending on the primary cancer histology as well as brain regions which do not conform to this relationship. Lung and breast cancers, in contrast to melanoma, frequently metastasize to the cerebellum, hinting at biological pathways of spread. Additionally, the deep brain structures are relatively spared from metastasis, regardless of primary cancer type. Leveraging this data, we propose a probabilistic brain metastasis risk model to enhance the therapeutic ratio of whole-brain radiotherapy by targeting high risk areas while preserving cortical and subcortical brain regions of functional significance and low metastasis risk, potentially reducing the cognitive side effects of therapy.

20 July 2023 in Research Square
Verified
Preprint
Open access
PDF file
HLHui Lin
Hui Lin
JGJorge Barrios Ginart
Jorge Barrios Ginart
WCWilliam Chen
William Chen
YIYannet Interian
Yannet Interian
HGHaotian Gong
Haotian Gong
OMOlivier Morin
Olivier Morin
Deep learning transformer models have exhibited exceptional performance in various clinical tasks, including cancer outcome prediction, when applied to electronic health records (EHR). Inspired by the success of bidirectional encoder representations from transformers (BERT) in natural language processing, we present OncoBERT, a deep transformer transfer learning framework tailored for cancer outcome prediction using unstructured clinical notes from diverse cancer sites including Glioma, Prostate, and Breast. OncoBERT adapts the BERT framework for unstructured EHR notes processing and employs a logistic regression model for binary survival prediction. Our framework analyzes aggregated EHR notes for each patient from the time of diagnosis to the initial outcome evaluation timepoint, progressively incorporating new notes for up to one year, which allows us to capture the evolving nature of cancer prognostication. In comparison to stage-based outcome models and a conventional NLP method, OncoBERT outperforms them in predicting cancer outcomes across three distinct cancer types. Furthermore, we introduce a novel interpretability pipeline that allows us to extract clinical note segments identified by the OncoBERT model as the most relevant indicators of prognosis. This pipeline enhances the interpretability of the predictive outcome, surpassing the limitations of attention weights. By providing clearer insights into the model's decision-making process, our approach improves the transparency and comprehensibility of the results, ultimately empowering clinicians and patients to make more informed decisions.

22 September 2026 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
SAShreyas Anil
Shreyas Anil
BSBhumika Srinivas
Bhumika Srinivas
BLBo Liu
Bo Liu
ALAnyi Li
Anyi Li
YIYannet Interian
Yannet Interian
HLHui Lin
Hui Lin
Outcome prediction from unstructured EHR notes remains challenging, especially for rare cancers with limited representation in large language model (LLM) pre-training data. We present a dynamic prompting framework that retrieves semantically similar patient examples, constructs tailored few-shot prompts and integrates note summaries to enhance outcome predictions. We evaluated this approach on a retrospective cohort of 503 breast cancer and 475 glioma patients using EHR notes from the first 180 days post-diagnosis. Dynamic prompting substantially improved glioma prediction while producing modest improvements for breast cancer, consistent with our hypothesis that dynamic prompting benefits rare cancers more. The combined summarization-driven dynamic-prompting approach achieved the highest performance while maintaining stability. Embedding visualizations suggested alignment with established prognostic markers in both cohorts. In this proof-of-concept, dynamic prompting improved outcome prediction for a lower-incidence cancer (glioma) in a single cohort while maintaining performance for a common cancer (breast), establishing it as a promising approach for LLM-based outcome prediction from unstructured EHR notes. Validation across additional low-incidence tumor types and institutions is required before these findings can be generalized.

2 June 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
JBJorge Barrios
Jorge Barrios
EPEvan Porter
Evan Porter
DCDante P. I. Capaldi
Dante P. I. Capaldi
TUTaman Upadhaya
Taman Upadhaya
WCWilliam C. Chen
William C. Chen
OMOlivier Morin
Olivier Morin