Statistical Learning Across Biomedicine

SLAB

The foundation, the floor, the framework.

전북대학교 통계학과 · Department of Statistics · Jeonbuk National University

Scroll

"We don't just remove variability.
We model it."

Most people think statistics is about computing averages. It's not.

Data varies. Always. The real question is: what model best explains that variability? A mean tells you where the center is — but a good statistical model tells you how and why observations differ, across brains, across images, across populations, and with what uncertainty.

That's the question driving everything we do.

Foundation

Statistical Methodology

Floor

Biomedical Imaging & Clinical AI

Framework

Population Health & Epidemiology

Foundation

01 — Statistical Methodology

Building methods
from the ground up.

We develop novel statistical methods for complex, real-world data. Generalized fiducial inference offers a new framework for uncertainty quantification. Dynamic network clustering captures how connections evolve over time — in social, biological, and brain networks.

Methods are not just tools. They are the structure that makes scientific inference possible.

Fiducial Inference Uncertainty Quantification Dynamic Networks Brain Connectivity R / Python Packages

Students will learn

Statistical method development end-to-end
Network analysis & graph theory
R/Python package development
Simulation study design

Floor

02 — Biomedical Imaging & Clinical AI

Medical imaging
meets statistical rigor.

We develop and evaluate statistical and AI-based methods for medical image analysis — spanning CT, MRI, fMRI, and DTI. From pulmonary CT modeling to neuroimaging pipelines, we ensure that clinical AI systems are validated with the rigor they deserve.

If the model says something, we ask: can we trust it?

CT / MRI / fMRI / DTI Neuroimaging GLMM · GEE DL Reproducibility Survival Analysis

Students will learn

Medical image data preprocessing & analysis
GLMM, GEE, Cox PH, competing risks
DL model evaluation & reproducibility
Neuroimaging analysis pipelines

Framework

03 — Population Health & Epidemiology

Data that connects
diet to disease.

Using large-scale population surveys including KNHANES, we investigate how dietary patterns — including Korean traditional foods — relate to chronic disease outcomes. Complex survey design requires careful statistical handling, and we specialize in getting it right.

From nutritional epidemiology to chronic disease risk, we connect individual-level data to population-level inference.

KNHANES Complex Survey Design Nutritional Epidemiology K-Food GLM · Logistic

Students will learn

Complex survey data analysis
Large-scale public data (KNHANES, 건보)
Epidemiological study design
Logistic / Poisson regression, GLM

People

Our Team

PI

Members

Alumni

황승용 (Seungyong Hwang)

Assistant Professor · Department of Statistics, Jeonbuk National University

Experience

Senior Biostatistician GRAIL, Inc., Menlo Park, CA

2022 — 2024

Postdoctoral Fellow, Department of Genetics Stanford University, Stanford, CA

2020 — 2022

Education

Ph.D. in Biostatistics University of California, Davis Advisors: Prof. Thomas C.M. Lee & Prof. Jie Peng

Email Google Scholar GitHub LinkedIn CV

김남윤(Namyoon Kim)

Undergraduate student

Machine Learning for Healthcare

홍성지(Seongji Hong)

Master student

N/A

·

Publications

Research Output

Published

Under Review

In Preparation

SCIE Co-Author

Gochujang attenuates colorectal cancer by promoting colonic SCFA utilization and GPCR expression despite limited recovery of microbial diversity

Baek J, Kim J, Jeong D, Hwang S, Donohoe D, Han A

SCIE Co-Author

CNNeoPP: a large language model-enhanced deep learning pipeline for personalized neoantigen prediction and liquid biopsy applications

Cai Y, Chen R, Song M, Wang L, Huo Z, Yang D, Zhang S, Gao S, Hwang S, Bai L, Lv Y, Cui Y, Zhang X

SCIE Co-Author

Contextualized biomedical language processing enhances ICU survival prediction

Chen R, Cai Y, Zhang S, Huo Z, Song M, Li W, Yang D, Hwang S, Bai L, Han F, Zhang X

SCIE First Author

Estimating fiber orientation distribution with application to study brain lateralization using HCP D-MRI data

Hwang S, Lee T, Paul D, Peng J

SCIE Co-First Author

Diagnostic Accuracy of Magnetic Resonance Imaging Features and Tumor-to-Nipple Distance for Nipple-Areolar Complex Involvement: A Systematic Review and Meta-Analysis

Byon J, Hwang S, Choi E, Choi H

SCIE First Author

Generalized Fiducial Inference for Threshold Estimation in Dose-Response and Regression Settings

Hwang S, Lai C, Lee T

SCIE Co-Author

Simultaneous detection of multiple change points and community structures in time series of networks

Cheung RCY, Aue A, Hwang S, Lee T

First Author Under Review

Estimating Spatially-Smoothed Fiber Orientation Distribution from Diffusion-MRI Experiments

Hwang S et al.

First Author Under Review

Hierarchical Clustering in time-evolving dynamic networks

Hwang S et al.

First Author Under Review

A Weighted Approach for Single Cutoff Selection in Survival Analysis

Hwang S et al.

First Author Under Review

Rethinking Statistics Education in the Age of Generative AI: The DRIP Framework

Hwang S et al.

News & Updates

Latest from S-LAB

2026 · 05

Invited Talk at 한국데이터정보과학회

Presented D-MRI processing and brain lateralization research.

Teaching

Courses

STAT · Undergraduate

통계적 사고와 사회 (Statistical Thinking and Society)

An introduction to statistical thinking for non-majors. Learn how data shapes decisions in everyday life.

STAT · Undergraduate

R 프로그래밍 (R Programming)

Introduction to statistical computing using R - datan manipulation, visualization and statistical analysis

STAT · Undergraduate

생명과학자료분석 (Statistical Analysis for Life Science)

Statistical methods for life sciences, clinical trial design, and SAS-based analysis.

STAT · Undergraduate

응용통계학 (Applied Statistics)

Generalized linear models including logistic regression, Poisson regression, and model diagnostics using R.

STAT · Graduate

생물통계학 (Advanced Biostatistics)

Graduate-level biostatistics. Emphasizes application to real biomedical data.

Join Us

We welcome students and researchers with curiosity about statistical methodology and its applications. If any of our research areas interest you, feel free to reach out.

MS / PhD Students

Strong interest in statistics or biomedical research. R or Python experience is a plus.

Undergraduate Research Assistants

JBNU undergraduates looking to gain hands-on research experience.

Collaborators

Clinicians, epidemiologists, or researchers with data and statistical questions.

Get in touch →

Resources