Dr Joshua Tan | Singapore General Hospital

Dr Joshua Tan Kuan
Associate Consultant
Health Services Research Unit
Singapore General Hospital

Dr. Joshua Tan is an Associate Consultant at the Health Services Research Unit, Singapore General Hospital, where he works at the intersection of public health, data science, and health services research. He holds a Bachelor of Medicine from the NUS Yong Loo Lin School of Medicine and a Master of Science in Public Health from the London School of Hygiene and Tropical Medicine.

Joshua’s work focuses on making sense of big data to improve health services delivery. He has experience translating artificial intelligence and advanced analytics into real-world clinical and operational impact. His research includes predictive models for hospital utilisation, population health analytics dashboards, feature engineering of clinical variables, and the use of large language models to extract clinically meaningful information from unstructured medical notes. In addition, he leads SGH’s Impact and Health Technology Assessment unit, where he evaluates the clinical, economic, and system-level value of new health technologies.

Previously, Joshua served as Deputy Chief Resident of the National Preventive Medicine Residency Programme. He has worked across various public healthcare institutions and the Ministry of Health, Singapore, and has authored numerous scientific and policy papers.

Bridging frontline clinical realities with data-driven innovation, Joshua is passionate about helping everyday clinicians understand how AI can support better decision-making, reduce administrative burden, and improve patient care—making the practice of clinical medicine more fulfilling.

Session:

Symposium 2
Beyond the Black Box: Unlocking real value of AI and Big Data for the Everyday Clinician
17 April 2026, 1100 - 1230, Room L1-S3, Academia

Presenting Title:

Big Data and AI Clinical Decision Making at the Population Level
Artificial intelligence (AI) and machine learning (ML) hold great promise for improving clinical decision-making in healthcare—but real-world value depends on being grounded in a meaningful use case, reliable data, and actionable workflows. This lecture presents a practical approach to moving from “AI hype” to operational impact, drawing on recently published research identifying patients at risk of prolonged length of stay and high healthcare utilization—challenges that are difficult for population health teams to address consistently at scale.

We begin by drawing on clinical cognition: what minimum signals do clinicians rely on, and what implicit heuristics guide judgment? We then examine why “big data” matters—not as an end in itself, but as a means to establish robustness and generalizability across time, sites, and patient subgroups, while confronting missingness, bias, and imperfect labels.

Next, we experiment with models: test diverse algorithms, exploring how the behave, weighing the advantages and disadvantages. Crucially, we go beyond headline metrics by interrogating model outputs. Finally, we discuss explainability, safety, governance, and the reality of adoption: success requires iterative build–measure–learn cycles shaped by stakeholder needs. Participants will leave with a decision-focused framework for developing, evaluating, and implementing ML to support trustworthy population-level care.

Return to Speakers >