• Artificial intelligence
• Neuropsychiatric disorders
• Digital mental health
• Social Robots

Leo Fan’s specialized research area lies at the intersection of medical artificial intelligence, digital psychiatry, neuropsychiatric disorders, and human-centered AI systems. His work focuses on developing responsible AI methods that support mental health and neuropsychiatric care across clinical training, patient engagement, early screening, and decision support. He integrates large language models, multimodal learning, digital phenotyping, and AI agents to build clinically meaningful, trustworthy, and scalable systems. His research includes LLM-powered simulated patients for medical education, multimodal AI for neurological and psychiatric disease detection, and digital mental health tools that can interpret real-world behavioral, clinical, and social data. More broadly, Leo aims to bridge technical AI innovation with practical healthcare needs by improving early detection, personalized intervention, patient-centered communication, and responsible deployment of AI in psychiatry and related medical domains. This aligns with his stated research interests in artificial intelligence, neuropsychiatric disorders, digital mental health, and social robots.

Leo Fan is a Vice-Chancellor Assistant Professor in the Department of Psychiatry, Faculty of Medicine, The Chinese University of Hong Kong. He received his Ph.D. in Information from the University of Michigan and his B.S. in Statistics from the University of California, Los Angeles. Before joining CUHK, he was affiliated with the AI in Medicine Program at Mass General Brigham and Harvard Medical School, where his work bridged AI, digital health, and medical research.

Leo’s research focuses on developing clinically applicable and responsible artificial intelligence systems for psychiatry, neuropsychiatric disorders, digital mental health, social robots, and patient-centered care. His work integrates large language models, multimodal learning, digital phenotyping, AI agents, and human-centered system design to support clinical reasoning, medical education, disease screening, patient engagement, and informed decision-making. His current projects include responsible AI for clinical training and patient-centered informed consent, as well as multimodal large language model-based virtual patients for neurological and psychiatric disorders.

He has published widely across medical AI, digital health, social computing, and human-AI interaction. His representative work includes studies on simulated patient systems powered by LLM-based AI agents, large language models in biomedical and health informatics, AI applications in psychiatry, multimodal deep learning for Parkinson’s disease detection, and social media-based analyses of public health information and online discourse. His interdisciplinary scholarship reflects a broader goal: to translate advances in artificial intelligence into trustworthy, scalable, and clinically meaningful tools for mental health and neuropsychiatric care.

Leo also leads a cross-disciplinary research group, in Psychiatry and AI (PsyAI), dedicated to medical AI and digital health research in psychiatry. Through this group, he leads collaborative work that connects AI methodology, clinical psychiatry, digital health, and responsible innovation, with the aim of improving early detection, personalized intervention, clinical training, and patient-centered communication in real-world healthcare settings.

1. Best Paper Award, International Conference on Mechatronics, Robotics, and Artificial Intelligence (2025)
2. SIGIR Student Travel Award, Association for Computing Machinery (2023)
3. Azure Credit Award, Microsoft Azure (2023)
4. AWS Computing Award, NeuraIPS BigANN Competition (2023)
5. Wiley Top Downloaded Article Award, John Wiley & Sons, Inc. (2021)

1. Chen S, Gao M, Sasse K, Hartvigsen T, Anthony B, Fan L, Aerts H, Gallifant J, Bitterman DS. When helpfulness backfires: LLMs and the risk of false medical information due to sycophantic behavior. NPJ Digital Medicine. 2025;8(1):605-. doi:10.1038/s41746-025-02008-z.
2. Sun J, Lu T, Shao X, Han Y, Xia Y, Zheng Y, Wang Y, Li X, Ravindran A, Fan L, Fang Y, Zhang X, Ravindran N, Wang Y, Liu X, Lu L. Practical AI application in psychiatry: Historical review and future directions. Molecular Psychiatry. 2025;30(9):4399-4408. doi:10.1038/s41380-025-03072-3.
3. Li X, Fan L, Wu H, Chen K, Yu X, Che C, Cai Z, Niu X, Cao A, Ma X. Enhancing autism spectrum disorder early detection with parent-child dyads block-play protocol and attention-enhanced hybrid deep learning framework. Engineering Applications of Artificial Intelligence. 2025;148:110430. doi:10.1016/j.engappai.2025.110430.
4. Yu H, Zhou J, Li L, Chen S, Gallifant J, Shi A, Sun J, Li X, He J, Hua W, Jin M, Chen G, Zhou Y, Li Z, Gupte T, Chen ML, Azizi Z, Dou Q, Yan BP, Xing Y, Zhang Y, Assimes TL, Bitterman DS, Ma X, Lu L, Fan L. Simulated patient systems powered by large language model-based AI agents offer potential for transforming medical education. Communications Medicine. 2025;6(1):27-. doi:10.1038/s43856-025-01283-x.
5. Lin S, Hua W, Wang Z, Jin M, Fan L, Zhang Y. EmojiPrompt: Generative prompt obfuscation for privacy-preserving communication with cloud-based LLMs. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Association for Computational Linguistics; 2025:12342–12361. doi:10.18653/v1/2025.naacl-long.614. (Conference Paper)
6. Hua W, Zhu K, Li L, Fan L, Jin M, Lin S, Xue H, Li Z, Wang J, Zhang Y. Disentangling logic: The role of context in large language model reasoning capabilities. In: Findings of the Association for Computational Linguistics: ACL 2025. Association for Computational Linguistics; 2025:19219–19242. doi:10.18653/v1/2025.findings-acl.983. (Conference Paper)
7. Fan L, Li L, Ma Z, Lee S, Yu H, Hemphill L. A bibliometric review of large language models research from 2017 to 2023. ACM Transactions on Intelligent Systems and Technology. 2024;15(5):91. doi:10.1145/3664930.
8. Fan L, Li L, Hemphill L. Toxicity on social media during the 2022 mpox public health emergency: Quantitative study of topical and network dynamics. Journal of Medical Internet Research. 2024;26(1):e52997. doi:10.2196/52997.
9. Li L, Ma Z, Fan L, Lee S, Yu H, Hemphill L. ChatGPT in education: A discourse analysis of worries and concerns on social media. Education and Information Technologies. 2024;29(9):10729-10762. doi:10.1007/s10639-023-12256-9.
10. Lv C, Fan L, Li H, Ma J, Jiang W, Ma X. Leveraging multimodal deep learning framework and a comprehensive audio-visual dataset to advance Parkinson’s detection. Biomedical Signal Processing and Control. 2024;95:106480. doi:10.1016/j.bspc.2024.106480.
11. LI L, FAN L, Atreja S, Hemphill L. “HOT” ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media. ACM Transactions on the Web. 2024;18(2):30. doi:10.1145/3643829.
12. Yu H, Fan L, Li L, Zhou J, Ma Z, Xian L, Hua W, He S, Jin M, Zhang Y, Gandhi A, Ma X. Large language models in biomedical and health informatics: A review with bibliometric analysis. Journal of Healthcare Informatics Research. 2024;8(4):658-711. doi:10.1007/s41666-024-00171-8.
13. Fan L, Hua W, Li L, Ling H, Zhang Y. NPHardEval: Dynamic benchmark on reasoning ability of large language models via complexity classes. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics; 2024:4092-4114. doi:10.18653/v1/2024.acl-long.225. (Conference Paper)
14. Lin S, Hua W, Li L, Chang CJ, Fan L, Ji J, Hua H, Jin M, Luo J, Zhang Y. BattleAgent: Multi-modal dynamic emulation on historical battles to complement historical analysis. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics; 2024:172–181. doi:10.18653/v1/2024.emnlp-demo.18. (Conference Paper)
15. Fan L, Lafia S, Li L, Yang F, Hemphill L. DataChat: Prototyping a conversational agent for dataset search and visualization. Proceedings of the Association for Information Science and Technology. 2023;60(1):586-591. doi:10.1002/pra2.820.
16. Yu H, Fan L, Gilliland AJ. Disparities and resilience: Analyzing online health information provision, behaviors and needs of LBGTQ plus elders during COVID-19. BMC Public Health. 2022;22(1):2338-. doi:10.1186/s12889-022-14783-5.
17. Lafia S, Fan L, Thomer A, Hemphill L. Subdivisions and crossroads: Identifying hidden community structures in a data archive’s citation network. Quantitative Science Studies. 2022;3(3):694-714. doi:10.1162/qss_a_00209.
18. Fan L, Yin Z, Yu H, Gilliland AJ. Using machine learning to enhance archival processing of social media archives. Journal on Computing and Cultural Heritage. 2022;15(3). doi:10.1145/3547146.
19. Fan L, Yu H, Gilliland AJ. #StopAsianHate: Archiving and analyzing Twitter discourse in the wake of the 2021 Atlanta Spa Shootings. Proceedings of the Association for Information Science and Technology. 2021;58(1):440-444. doi:10.1002/pra2.475.
20. Fan L, Yu H, Yin Z. Stigmatization in social media: Documenting and analyzing hate speech for COVID-19 on Twitter. Proceedings of the Association for Information Science and Technology. 2020;57(1):e313. doi:10.1002/pra2.313.