Biography. See-Kiong Ng (PhD, Carnegie Mellon University) is Professor at the School of Computing, National University of Singapore (NUS), Deputy Director of the NUS Institute of Data Science, and Director of Talent at AI Singapore. His research is driven by a long-standing passion for uncovering insights from data and using AI to solve important real-world problems. He began his cross-disciplinary career in the 1990s as one of the early pioneers in bioinformatics, applying data mining and machine learning to help biologists better understand genomics and the human body. Since then, he has extended these approaches to a wide range of complex, data-rich domains, including smart cities, social media, e-commerce, and other real-world systems, authoring more than 200 research publications across multiple disciplines. His current research focuses on developing AI systems that are both safe and useful, with the goal of enabling AI to contribute meaningfully to society and improve human well-being.

Abstract.
Human health unfolds continuously, whereas current healthcare systems observe it only intermittently—through episodic clinical encounters and retrospective assessments. At the same time, people increasingly reveal aspects of their lived experience through online communities, wearable devices, and interactions with AI systems. This shift opens three complementary opportunities for population health: sensing, through extracting meaningful signals from digital traces; supporting, through human-centred interactions with healthcare theory-grounded AI; and simulating, by generating controlled representations of patients and societies when real-world observations are scarce. Using population mental health as a case study, the first part of this talk examines how signals from digital platforms can be interpreted through psychotherapy-informed methods, including schema therapy and Socratic questioning. These studies show how AI should move beyond surface-level language patterns towards more interpretable cognitive signals to augment human counsellors and enable population-level analyses. The second part turns from sensing to simulating situations that are difficult, rare, or ethically challenging to sample. I present two case studies: stochastic steering for the fine-grained simulation of cognitively impaired patients, and multilingual agent-based world modelling for social science. Our central thesis is that AI can expand the evidence base for population mental health by increasing our observational bandwidth through digital interaction and our counterfactual bandwidth through simulation. Realising this potential, however, requires careful integration of AI with psychological theory and empirical calibration, as well as responsible governance to ensure that generated plausibility is never mistaken for human reality.

Biography. Dr. Nan Liu is Director of the Duke-NUS AI + Medical Sciences Initiative (DAISI) and Co-Director of the SingHealth Duke-NUS AI in Medicine Institute (AIMI). He is an Associate Professor at Duke-NUS Medical School, and an Adjunct Associate Professor in the Department of Biostatistics and Bioinformatics at Duke University, USA. Currently, he leads the Digital Medicine Lab. His research focuses on ethical and responsible artificial intelligence with applications in healthcare and medicine. Dr. Liu has received research grants from the National Medical Research Council and the National Research Foundation. He was recognized as one of the world’s top 2% scientists by Stanford University and Elsevier. Dr. Liu has also served as an editor for many prestigious journals, including NPJ Digital Medicine and PLOS Medicine.

Abstract.
As AI continues to transform the healthcare landscape, it is essential to balance innovation with patient safety and ethical responsibility. This talk will explore the challenges and opportunities of integrating AI in healthcare, focusing on the importance of patient safety, the ethics of AI, and the limitations of emerging technologies. It will also address ethical guidelines and considerations that must be followed, along with practical strategies for the safe and responsible use of AI in healthcare. The aim is to provide a comprehensive understanding of how to implement AI in ways that benefit patients while maintaining safety and ethical integrity..

Biography. Dr. Aparna Taneja is a researcher with the AI for Social Good team in Google Research India. Her current research focus is to drive innovation in AI to achieve real-world social impact. Her team collaborates with NGOs in public health, conservation, and agriculture. One of her team's ongoing collaborations is with the NGO ARMMAN, whose mission is to improve maternal and child health outcomes in underserved communities in India. Her earlier projects involved improving search quality on Google Maps and using satellite imagery for applications in remote sensing. Prior to Google, she was a postdoctoral researcher at Disney Research Zurich. She completed her PhD with the Computer Vision and Geometry Group at ETH Zurich and her bachelor's degree in Computer Science from the Indian Institute of Technology Delhi.

Abstract.
The widespread availability of cell phones has enabled non-profits to deliver critical health information to their beneficiaries in a timely manner. This project assists non-profits that employ automated messaging programs to deliver timely preventive care information to beneficiaries (new and expecting mothers) during pregnancy and after delivery. Unfortunately, a key challenge in such information delivery programs is that a significant fraction of beneficiaries drop out of the program. Yet, non-profits often have limited health-worker resources (time) to place crucial service calls for live interaction with beneficiaries to prevent such engagement drops. To assist non-profits in optimizing this limited resource, we developed a Restless Multi-Armed Bandits (RMABs) system. The RMAB system was evaluated in collaboration with an NGO via a real-world service quality improvement study and showed a 30% reduction in engagement drops. This model was eventually deployed by the NGO and served over 350K women so far.