Peixing Wan, M.D., Ph.D.

Associate Researcher, Assistant Professor

Research Interest

Development and Clinical Application of Medical Large Language Models

Contact Information

peixing@bjmu.edu.cn

Education

Sept 2010 – July 2015	Wuhan University, School of Medicine – M.D.
Sept 2015 – July 2020	Sun Yat-sen University, School of Medicine –Ph.D.
Oct 2018 – Jan 2021	University of Michigan, Biomedical Sciences – Research assistant

Professional Experience

Jan 2021 – Feb 2025	National Institutes of Health (NIH), USA – Postdoctoral Fellow
Mar 2025 – Present	Department of Medical Bioinformatics, Peking University –Assistant Professor

Biography

Dr. Wan is an interdisciplinary researcher in medical artificial intelligence, combining a solid foundation in clinical medicine with advanced expertise in biomedical informatics and computational modeling. Her work has led to original contributions in the development and clinical validation of medical large language models (LLMs), addressing critical gaps in healthcare dialogue systems and decision-support applications.

Dr. Wan received systematic clinical training at Wuhan University and Sun Yat-sen University, followed by advanced research training at the University of Michigan and the U.S. National Institutes of Health (NIH). This trajectory fostered a multidisciplinary research portfolio that integrates clinical knowledge, artificial intelligence methodologies, and translational applications in healthcare.

She has consistently produced influential scholarship with first-author publications in leading journals including Nature Medicine, Cell Death & Differentiation, Molecular Therapy, and Cell Genomics (co-first). In addition, she has authored commentaries in The Lancet, The Lancet Planetary Health, and Clinical and Translational Medicine. Her study in Nature Medicine was highlighted in a contemporaneous feature article, and several of her high-impact works have each accrued over 200 citations, underscoring their international recognition and impact.

Research Directions

Although medical large language models hold transformative potential, they continue to face critical methodological and translational challenges, particularly in multimodal information integration and decision transparency.

• Multimodal signal integration: Existing systems are predominantly text-based and struggle to capture the full spectrum of communicative cues essential for clinical reasoning, such as prosody, facial expression, and nonverbal behaviors.

• Decision interpretability: Current inference mechanisms often lack transparency, limiting the ability to generate clear, evidence-based justifications for outputs. This reduces clinical trust and complicates risk management in real-world applications.

To address these limitations, Dr. Wan’s research program is organized around three interrelated directions:

1. Development of Multimodal Medical LLMs – advancing architectures that integrate text, speech, and nonverbal clinical signals.

2. Enhancing Interpretability of LLM Decision-Making – designing frameworks to improve transparency, explainability, and trustworthiness in clinical reasoning.

3. Clinical Validation and Deployment – conducting prospective clinical trials to rigorously evaluate the safety, efficacy, and utility of medical LLMs in real-world healthcare environments.

Representative Publications

1. Outpatient reception via collaboration between nurses and a large language model: a randomized controlled trial.

Wan P*, Huang Z*, Tang W, Nie Y, Pei D, Deng S, Chen J, Zhou Y, Duan H, Chen Q#, Long E#.

Nature Medicine. 2024 (Article, Highlighted by Nature Medicine, ‘Improving primary healthcare with generative AI’) (IF="87.2)

2. From function to translation: Decoding genetic susceptibility to human diseases via artificial intelligence.

Long E#*, Wan P*, Chen Q, Lu Z, Choi J#.

Cell Genomics. 2023 (IF="11.1)

3. LncRNA H19 initiates microglial pyroptosis and neuronal death in retinal ischemia/reperfusion injury.

Wan P*, Su W*, Zhang Y, Li Z, Deng C, Li J, Jiang N, Huang S, Long E, Zhuo Y#.

Cell Death & Differentiation. 2020 (Article) (IF="15.8," Citation="192)

4. TET-dependent GDF7 hypomethylation impairs aqueous humor outflow and serves as a potential therapeutic target in glaucoma.

Wan P*, Long E*, Li Z, Zhu Y, Su W, Zhuo Y#.

Molecular Therapy. 2021 (Article) (IF="12.9)

5. From General to Specific: Tailoring Large Language Models for Real-World Medical Communications.

Sun X*, Tang W*, …, Long E#, Wan P#.

Clinical and Translational Medicine. 2025 (Commentary) (IF="10.6)

6. Necroptosis and tumor progression.

Yan J, Wan P, Choksi S, Liu ZG#.

Trends in Cancer. 2021 (Opinion) (IF="14.2," Citation="208)

7. Examining MLKL phosphorylation to detect necroptosis in murine mammary tumors.

Baik JY*, Wan P*, …, Liu ZG#.

STAR Protocols. 2022 (Cell Press Journal matching Nature Protocols)

8. Trimetazidine protects retinal ganglion cells from acute glaucoma via the Nrf2/Ho-1 pathway.

Wan P, Su W, Zhang Y, Li Z, Deng C, Zhuo Y#.

Clinical Science. 2017 (Article, Cover Story) (IF="6.1," Citation="49)

9. Precise long non-coding RNA modulation in visual maintenance and impairment.

Wan P, Su W, Zhuo Y#.

Journal of Medical Genetics. 2017 (Review) (IF="6.3).

10. The Role of Long Noncoding RNAs in Neurodegenerative Diseases.

Wan P, Su W, Zhuo Y#.

Molecular Neurobiology. 2016 (Review) (IF="5.6," Citation="163)

11. Expectations of medical students in China.

Wan P, Long E#.

The Lancet. 2016 (Letter) (IF="79.3).

12. Pollution control for a healthier Chinese population.

Wan P, Long E#.

The Lancet Planetary Health. 2018 (Correspondence) (IF="19.2)

13. Methodological advances in necroptosis research: from challenges to solutions.

Wan P*#, Yan J, Liu ZG.

Journal of the National Cancer Center. 2022 (IF="7.6)

14. Use of a Neural Net to Model the Impact of Optical Coherence Tomography Abnormalities on Vision in Age-related Macular Degeneration.

Wan P, Long E#.

American Journal of Ophthalmology. 2018 (Correspondence) (IF="5.3)

15. Predicting Real-World Future of Glaucoma Patients? Cautions Are Required for Machine Learning.

Long E, Wan P#, Zhuo Y.

Translational Vision Science and Technology. 2017 (Letter) (IF="3.3)