Welcome to join this lecture and learn how data science and AI technologies can help advance medical research and clinical care toward a smarter future!

📌“This lecture will introduce the advantages of classification and regression tree (CART) models in terms of interpretability, and examine why their predictive accuracy has long lagged behind that of black-box models such as random forests, neural networks, and gradient boosting. Traditional tree models are limited to splits on a single variable and produce constant predictions at each terminal node; while these features enhance interpretability, they also constrain performance. With the recent emphasis on explainable AI, there has been renewed interest in improving model accuracy while preserving interpretability. This lecture will present the GUIDE algorithm, which integrates linear splits and linear models within nodes to overcome these limitations, achieving predictive performance comparable to or even better than that of black-box models while maintaining model transparency. In addition, this approach can help explain how variables are utilized in black-box models, serving as an interpretable alternative. For clinical practitioners, such models can enhance the accuracy of clinical prediction and risk assessment while maintaining transparency and traceability in decision-making, thereby supporting more trustworthy smart healthcare applications.

 📅 Lecture Information

▪️ Topic: A Decision Tree Approach to Explainable AI Models

▪️ Speaker: Wei-Yin Loh (Professor, Department of Statistics, University of Wisconsin–Madison)

▪️ Date & Time: May 28, 2026 (Thursday), 12:10–13:30

▪️ Venue: Room IR630, 6th Floor, International Academic Research Building, Kaohsiung Medical University

▪️ Registration Link: https://forms.gle/zfEKCjjna6t1b9KQ8

▪️ Registration Deadline: Until 12:00 PM, May 26, 2026 (Tuesday); online registration only

▪️ Format: Hybrid (On-site: 60 participants; Online: unlimited)

▪️ Organizer: Biomedical Artificial Intelligence Academy of KMU, Department of Artificial Intelligence in Medicine of KMU

▪️ Note: ☕ Lunch will be provided for on-site participants. Everyone is welcome to join!

※ This lecture is eligible for KMU faculty growth credits. Participants must complete both sign-in/out and the satisfaction survey to receive credit points.

We look forward to your participation!