BEAR Lab at NCC-GCSP focuses on developing AI models to enhance precision medicine. Our research explores the intersection of AI, pulsatile physiological signals, and genomic data to improve patient risk prediction and personalized treatment strategies. 

• AI Model Development: Designing advanced AI models for biomedical data analysis.

• Physiological Signal Processing: Cleansing, synthesizing, and generating pulsatile physiological signals for patient risk assessment and prognosis prediction.

• Genomic Data Analysis: Predicting risk scores and clustering genes using genomic data and patient survival information.

• Personalized Cancer Treatment: Developing AI-driven approaches for tailored treatment strategies in cancer patients.

Our research integrates machine learning, deep learning, and statistical modeling to derive clinically meaningful insights.

By collaborating with leading medical institutions, we aim to bridge the gap between AI innovation and real-world healthcare applications.

Hello, I'm Junetae Kim, and I'd like to share a bit about my journey and current endeavors.

Academic and Professional Background:

• Undergraduate Studies: I began with a Bachelor's degree in Business Administration from Hanyang University, which laid the groundwork for my interest in strategic and analytical thinking.​

• Doctoral Research: I pursued a Ph.D. in Management Engineering with a focus on Management Information Systems (MIS) at KAIST. During this period, I applied artificial intelligence (AI) for disease prediction, enhancing early detection and personalized treatment strategies.​

• Industry Experience: Post-Ph.D., I joined Samsung Electronics, where I had the opportunity to work on innovative projects. Notably, I developed semiconductor market forecasting models utilizing BERT, a cutting-edge natural language processing technique.​

• Current Role: Presently, I serve as an Associate Professor in the Department of Public Health & AI at the National Cancer Center Graduate School of Cancer Science and Policy (NCC-GCSP). I played a pivotal role in establishing the AI major within our department, aiming to integrate artificial intelligence into cancer science.​

Research Interests:

My research focuses on integrating domain-knowledge of pulsatile physiological signals (such as arterial blood pressure, electrocardiograms, photoplethysmograms) and genetic data with deep learning. I am particularly interested in Bayesian deep learning, which incorporates uncertainty estimation into AI models, enhancing their reliability in clinical settings. Additionally, I explore generative AI techniques to create synthetic biomedical data. This interdisciplinary approach aims to enhance our understanding and treatment of cancer.

While I am still learning and growing in this field, I aspire to go beyond simply applying existing AI techniques to healthcare. I try to develop principled and thoughtful algorithms that can help address the unmet needs of real clinical problems.

Engagement in Mentorship:

Despite my academic and professional commitments, I remain actively involved in hands-on coding. Collaborating closely with students and researchers, I emphasize practical coding skills and problem-solving. Additionally, I support individuals from non-scientific or non-engineering backgrounds in transitioning into the AI field, drawing from my diverse experiences to provide tailored guidance.

I believe that in a rapidly evolving field like AI, where not only algorithms but also tools and frameworks are constantly advancing, meaningful advising may come from firsthand engagement with those tools. Just as a surgeon cannot effectively teach residents without practicing surgery themselves, I find it essential to keep coding alongside my students and research colleagues. Through this shared technical journey, I aim to grow together with them—not just as a supervisor, but as a fellow learner and collaborator.