Jinghui Liu

Brisbane, Australia

jinghui.liu(at)csiro.au

I am a Research Scientist at the Australian e-Health Research Centre, CSIRO. My research focuses on applying natural language processing and language models in healthcare to improve care quality, increase health system efficiency, and support population health. I am particularly interested in applications that analyze clinical data from electronic health records, including clinical documentation generation, assisted medical coding, and predictive analytics for clinical decision support.

Before my current role, I was a Postdoctoral Research Fellow at CSIRO, where I contributed to CSIRO initiatives in clinical AI and antimicrobial resistance. I completed my PhD at the University of Melbourne in 2023, supervised by Prof. Karin Verspoor, Prof. Daniel Capurro, and Dr Anthony Nguyen. I also hold a Master of Health Informatics from the University of Michigan, Ann Arbor.

Research Interests

Clinical documentation improvement — clinical documentation generation and summarisation using LLMs.
Generative information extraction for health — extracting and structuring information from clinical reports.
Synthetic clinical text — supporting privacy-preserving model development in medical scenarios.
Predictive analytics on EHRs — multimodal modeling and predictive analytics using clinical records.
Medical coding — version-independent models for ICD and related terminologies.

Selected Publications

BioNLP

Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale

Jinghui Liu, Sarvesh Soni, and Anthony Nguyen

In Proceedings of the 25th Workshop on Biomedical Natural Language Processing, Jul 2026

Bib Link

@inproceedings{liu-etal-2026-systematic-evaluation,
  title = {Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by {LLM}s at Million-Note Scale},
  author = {Liu, Jinghui and Soni, Sarvesh and Nguyen, Anthony},
  editor = {Demner-Fushman, Dina and Ananiadou, Sophia and Roberts, Kirk and Tsujii, Junichi},
  booktitle = {Proceedings of the 25th Workshop on Biomedical Natural Language Processing},
  month = jul,
  year = {2026},
  address = {San Diego, California},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2026.bionlp-1.28/},
  pages = {353--371},
  isbn = {979-8-89176-434-7},
}

BioNLP

Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes

Jinghui Liu and Anthony Nguyen

In Proceedings of the 25th Workshop on Biomedical Natural Language Processing, Jul 2026

Bib Link

@inproceedings{liu-nguyen-2026-bridging,
  title = {Bridging the Version Gap: Multi-version Training Improves {ICD} Code Prediction, Especially for Rare Codes},
  author = {Liu, Jinghui and Nguyen, Anthony},
  editor = {Demner-Fushman, Dina and Ananiadou, Sophia and Roberts, Kirk and Tsujii, Junichi},
  booktitle = {Proceedings of the 25th Workshop on Biomedical Natural Language Processing},
  month = jul,
  year = {2026},
  address = {San Diego, California},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2026.bionlp-1.29/},
  pages = {372--381},
  isbn = {979-8-89176-434-7},
}

IEEE JBHI

Comparing text-based clinical risk prediction in critical care: A note-specific hierarchical network and Large Language Models

Jinghui Liu, Anthony Nguyen, Daniel Capurro, and Karin Verspoor

IEEE Journal of Biomedical and Health Informatics, 2025

Bib Link

@article{liu2025hierarchical,
  title = {Comparing text-based clinical risk prediction in critical care: A note-specific hierarchical network and Large Language Models},
  author = {Liu, Jinghui and Nguyen, Anthony and Capurro, Daniel and Verspoor, Karin},
  journal = {IEEE Journal of Biomedical and Health Informatics},
  year = {2025},
  volume = {PP},
  number = {99},
  pages = {1--12},
  publisher = {IEEE},
  url = {https://ieeexplore.ieee.org/document/11016178},
}

AIIM

Generating synthetic clinical text with local large language models to identify misdiagnosed limb fractures in radiology reports

Jinghui Liu, Bevan Koopman, Nathan J. Brown, Kevin Chu, and Anthony Nguyen

Artificial Intelligence in Medicine, 2025

Bib Link

@article{liu2025synthetic,
  title = {Generating synthetic clinical text with local large language models to identify misdiagnosed limb fractures in radiology reports},
  author = {Liu, Jinghui and Koopman, Bevan and Brown, Nathan J. and Chu, Kevin and Nguyen, Anthony},
  journal = {Artificial Intelligence in Medicine},
  year = {2025},
  volume = {159},
  pages = {103027},
  publisher = {Elsevier},
  url = {https://www.sciencedirect.com/science/article/pii/S0933365724002690},
}

ALTA

Rephrasing Electronic Health Records for Pretraining Clinical Language Models

Jinghui Liu and Anthony Nguyen

In Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association, 2024

Bib Link

@inproceedings{liu2024rephrasing,
  title = {Rephrasing Electronic Health Records for Pretraining Clinical Language Models},
  author = {Liu, Jinghui and Nguyen, Anthony},
  booktitle = {Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association},
  year = {2024},
  pages = {164--172},
  url = {https://aclanthology.org/2024.alta-1.13/},
}

ALTA

Enhancing Bacterial Infection Prediction in Critically Ill Patients by Integrating Clinical Text

Jinghui Liu and Anthony Nguyen

In Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association, 2023

Best Paper Bib Link

Best Paper Award

@inproceedings{liu2023bacterial,
  title = {Enhancing Bacterial Infection Prediction in Critically Ill Patients by Integrating Clinical Text},
  author = {Liu, Jinghui and Nguyen, Anthony},
  booktitle = {Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association},
  year = {2023},
  pages = {118--124},
  url = {https://aclanthology.org/2023.alta-1.13/},
}

JBI

Attention-based multimodal fusion with contrast for robust clinical prediction in the face of missing modalities

Jinghui Liu, Daniel Capurro, Anthony Nguyen, and Karin Verspoor

Journal of Biomedical Informatics, 2023

Bib Link

@article{liu2023multimodal,
  title = {Attention-based multimodal fusion with contrast for robust clinical prediction in the face of missing modalities},
  author = {Liu, Jinghui and Capurro, Daniel and Nguyen, Anthony and Verspoor, Karin},
  journal = {Journal of Biomedical Informatics},
  year = {2023},
  volume = {145},
  pages = {104466},
  publisher = {Elsevier},
  url = {https://www.sciencedirect.com/science/article/pii/S1532046423001879},
}

JBI

“Note Bloat” impacts deep learning-based NLP models for clinical prediction tasks

Jinghui Liu, Daniel Capurro, Anthony Nguyen, and Karin Verspoor

Journal of Biomedical Informatics, 2022

Bib Link

@article{liu2022notebloat,
  title = {``Note Bloat'' impacts deep learning-based {NLP} models for clinical prediction tasks},
  author = {Liu, Jinghui and Capurro, Daniel and Nguyen, Anthony and Verspoor, Karin},
  journal = {Journal of Biomedical Informatics},
  year = {2022},
  volume = {133},
  pages = {104149},
  publisher = {Elsevier},
  url = {https://www.sciencedirect.com/science/article/pii/S1532046422001617},
}

npj Digit. Med.

Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes

Jinghui Liu, Daniel Capurro, Anthony Nguyen, and Karin Verspoor

NPJ Digital Medicine, 2021

Bib Link

@article{liu2021drg,
  title = {Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes},
  author = {Liu, Jinghui and Capurro, Daniel and Nguyen, Anthony and Verspoor, Karin},
  journal = {NPJ Digital Medicine},
  year = {2021},
  volume = {4},
  pages = {103},
  publisher = {Nature Publishing Group},
  url = {https://www.nature.com/articles/s41746-021-00474-9},
}