Instructor Spotlight: Chuan Hong, PhD
Chuan Hong, PhD, is an assistant professor of biostatistics and bioinformatics at Duke University, where she bridges the worlds of statistics, artificial intelligence, and clinical medicine. Guided by a fascination with uncertainty, her work explores how statistical and AI methods can make health care prediction more reliable, fair, and impactful.
Please share some about your background and what led you to the field of biostatistics/bioinformatics?
My path to biostatistics and biomedical informatics, and eventually to AI in health care, has always been guided by a fascination with uncertainty. I’m drawn to fields where the answers are rarely clear, where complexity is inherent, and yet decisions must still be made. Health care embodies that tension. What captivates me about AI isn’t just its capacity to automate, but its potential to reason through ambiguity, learn from imperfect data, and uncover the blind spots in how we think. In this space, the unknown isn’t a flaw, it’s the frontier.
What is your current research or professional focus?
My current research focuses on developing statistical and AI methods to make clinical prediction more reliable, fair, and useful. I lead projects on cardiovascular risk prediction, electronic health record (EHR) phenotyping, and the development and evaluation of emerging AI tools in clinical practice. Across these areas, a common thread is improving calibration, fairness, and translation from algorithms to bedside impact.
Which course(s) do you teach in the program?
At Duke, I teach BIOSTAT 707: Statistical Methods for Learning and Discovery, a course that introduces students to the foundations of machine learning with a focus on biomedical applications.
What do you most enjoy about teaching this course?
What I enjoy most is watching students shift from simply applying methods to truly understanding the logic behind them : when to use them, why they work, and how to adapt them to new problems. My goal isn’t for students to memorize formulas or follow step-by-step recipes, but to learn how to think: to reason through uncertainty, ask the right questions, and continue learning independently long after the course ends. The field is changing fast: the real challenge isn’t just mastering today’s tools, it’s learning how to approach tomorrow’s.
What do you enjoy most about working with Duke MB students?
Working with Duke MB students is one of the most rewarding parts of my role, not just because I get to teach, but because I continue to learn alongside them. Their passion for learning constantly inspires me.
In many ways, they make me better: more thoughtful as an instructor, more reflective as a researcher, and more aware of the responsibility. That sense of responsibility, in turn, sharpens my own discipline, reminding me to stay rigorous, honest, and open-minded in how I teach and practice science.
What advice do you give students for getting the most out of your class?
My advice to students is simple: stay curious and embrace uncertainty.
What is something students might be surprised to learn about you?
Students might be surprised to learn that I’m a student pilot in training. Outside of work, I’ve always been drawn to forms of adventure that balance freedom with discipline. Whether I’m flying a small aircraft or driving along an open highway with no fixed destination, I value the sense of deliberate control and the quiet mental space it creates for clear thinking.
What fascinates me about flight training is how closely it resembles training a machine learning model. In both cases, progress begins in uncertainty and unfolds through repetition, feedback, and gradual refinement. Over time, I’ve come to realize that in learning how to train models, we also learn how to train ourselves: with discipline, patience, and a structured approach to continuous improvement.