Nan Liu, Duke-NUS
@nliulab
Translating AI into healthcare through ethical and trustworthy machine learning; Editorial Board @npjDigitalMed.
The widespread use of #GenAI technologies (e.g. #ChatGPT) has drawn attention to potential #ethical issues. We developed Transparent Reporting of Ethics for Generative AI (#TREGAI) checklist for thorough assessment of ethical considerations in #GenAI research. #AI @LancetDigitalH

Delighted to share our latest opinion piece in @CellCellPress #Patterns. We highlight why #interpretability and #transparency are essential—not just for building trust in #health #AI, but as the foundation for #fairness, #privacy, and #reliability. doi.org/10.1016/j.patt…

🚀𝗕𝗿𝗶𝗱𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗚𝗮𝗽 𝗶𝗻 𝗔𝗜 𝗙𝗮𝗶𝗿𝗻𝗲𝘀𝘀 𝗳𝗼𝗿 𝗛𝗲𝗮𝗹𝘁𝗵𝗰𝗮𝗿𝗲: 𝗞𝗲𝘆 𝗜𝗻𝘀𝗶𝗴𝗵𝘁𝘀 𝗮𝗻𝗱 𝗔𝗰𝘁𝗶𝗼𝗻𝘀 We did a scoping review to highlight critical gaps and actionable strategies for advancing clinical #AI #fairness. @npjDigitalMed @dukenus

NEW Review: Generative #ArtificialIntelligence and ethical considerations in health care: a scoping review and ethics checklist. @EricTopol Read it here: buff.ly/4dh7erT
🌏 Advancing international partnership for governing generative #AI (#GenAI) models in #medicine and #healthcare. We introduce POLARIS-GM initiative: a scenario-based, consensus-driven framework for GenAI #governance and #regulation. @NatureMedicine nature.com/articles/s4159…

[New Study] Leveraging AI and Transfer Learning to Enhance Outcome Prediction for Out-of-Hospital Cardiac Arrest in Diverse Settings: Insights from the Pan-Asian Resuscitation Outcomes Study medrxiv.org/content/10.110… #AI #Healthcare #OHCA
I will be speaking at the @UCSF #AI Seminar Series. My talk will focus on the #implementation of health AI and the balance between #innovation, patient #safety, and #ethical considerations. A big thank you to Prof. @Jean_J_Feng for the kind invitation. #DukeNUS
Next @UCSF AI Seminar series is this Thursday, May 8 - with Dr. Nan Liu @nliulab - AI Implementation in Healthcare: Balancing Innovation, Patient Safety and Ethical Considerations. Register docit.ucsf.edu/events/ai-semi… @UCSF_DOCIT @UCSFDOM
We are entering a new era of #medical #education with advances in #AI, especially generative AI (#GenAI). These innovations have the potential to transform how we train healthcare professionals, addressing global workforce shortages. papers.ssrn.com/sol3/papers.cf…
Just arrived in #Yokohama for #CHI2025! No paper this year—here to soak in ideas and learn. Always up for a chat on #HCI, especially in #healthcare, #AI #fairness, #equity, and #bias. Feel free to DM! @acm_chi


𝘀𝗲𝗲𝗕𝗶𝗮𝘀: 𝗔 𝗖𝗼𝗺𝗽𝗿𝗲𝗵𝗲𝗻𝘀𝗶𝘃𝗲 𝗧𝗼𝗼𝗹 𝗳𝗼𝗿 𝗔𝘀𝘀𝗲𝘀𝘀𝗶𝗻𝗴 𝗮𝗻𝗱 𝗩𝗶𝘀𝘂𝗮𝗹𝗶𝘇𝗶𝗻𝗴 𝗔𝗜 𝗙𝗮𝗶𝗿𝗻𝗲𝘀𝘀 Paper: lnkd.in/gwkmT3ik Code: lnkd.in/g-F-UdFF #seeBias #AI #Fairness #Bias #R #Toolbox #DukeNUS

How can generative AI and large language models be used to mitigate medication-related harm? We conducted a review to address this question. nature.com/articles/s4174… #GenAI #AI #LLM #Medication #Drug #Healthcare #Medicine #DukeNUS

Our Transparent Reporting of Ethics for Generative AI (#TREGAI) checklist was featured by Channel NewsAsia. lnkd.in/gbdddUEE #AI #GenAI #Ethics #Healthcare #DukeNUS #DAISI

Generative #AI (GenAI) is revolutionizing healthcare, but it faces challenges. Retrieval-Augmented Generation (#RAG) is a possible approach to enhance #GenAI's reliability, reduce biases, and offer more personalized, evidence-based care. nature.com/articles/s4440…
Leveraging anatomical constraints with uncertainty for pneumothorax segmentation - Yuan - Health Care Science - Wiley Online Library onlinelibrary.wiley.com/doi/10.1002/hc…
Federated Learning in Healthcare: A Benchmark Comparison of Engineering and Statistical Approaches for Structured Data Analysis | Health Data Science spj.science.org/doi/10.34133/h…
Transdisciplinary perspectives for health systems science | New Journal accepting submissions now: npj Health Systems. @Nature @AMIAinformatics @HIMSS #healthsystem #systemscience @McWilliamsSBMI @UTHealthHouston nature.com/articles/s4440…
JUST PUBLISHED: Federated Learning in Healthcare: A Benchmark Comparison of Engineering and Statistical Approaches for Structured Data Analysis Click here to read the latest free, Open Access article from Health Data Science: spj.science.org/doi/10.34133/h…
Cognitive biases in clinical decision-making lead to diagnostic errors. Our study shows that #LLMs, through a multi-agent framework, can help re-evaluate and correct misconceptions, enhancing diagnostic accuracy. jmir.org/2024/1/e59439/ #AI #Healthcare #Diagnostics #MedTech

🌍Collaborative Assessment for Responsible and Ethical AI Implementation (CARE-AI)—a novel tool designed to guide the ethical deployment of AI-based prediction models in clinical settings. nature.com/articles/s4159… #AI #AIEthics #ethics #DukeNUS

BREAKING: Assoc Prof Liu Nan and Senior Research Fellow Ning Yilin from #DukeNUS Centre for Quantitative Medicine led a global consortium to review ethical discussions on #healthcare generative #AI applications. Read more: duke-nus.edu.sg/newshub/media-…