Research

Research Overview

Our research aims to advance next-generation medical intelligence by integrating artificial intelligence, computational science, and multimodal biomedical data. We focus on developing innovative methodologies that enable early diagnosis, prognosis prediction, and personalized treatment of complex diseases. 

By working at the intersection of computer science, medical imaging, neuroscience, and data science, our lab conducts data-driven translational research that bridges fundamental algorithms and real-world clinical applications. Our ultimate goal is to transform large-scale biomedical data into actionable knowledge and digital biomarkers that support clinical decision-making and improve patient outcomes. 

Computational Science for Biomedicine

We develop advanced computational frameworks at the intersection of computer science, applied mathematics, and biomedical engineering. Our research addresses fundamental challenges in modeling complex biological systems and enables scalable solutions for personalized and precision medicine. 

Multimodal Biomedical Data for Medical AI

We analyze large-scale, heterogeneous biomedical data—including brain MRI, medical imaging, physiological signals, and clinical records—using high-performance computing and AI. Our work focuses on integrating multimodal data to uncover hidden patterns and mechanisms underlying neurological and psychiatric disorders. 

Machine Learning for Medical AI

We are creating high-throughout software for early detection, prediction and diagnosis of diseases, identification of new biomarkers and targets, and personalized interventions and therapies using machine learning.

We design novel machine learning and deep learning algorithms for:

• Early detection and diagnosis of diseases

• Disease progression modeling and prognosis prediction

• Generative modeling (e.g., diffusion, multimodal foundation models)

• Discovery of digital biomarkers and therapeutic targets

Our research emphasizes robustness, interpretability, and clinical applicability of AI systems.

Translational AI & Digital Biomarkers

We develop AI-driven solutions that translate research into clinical impact. This includes building predictive models and automated medical report generation systems that assist clinicians in diagnosis and decision-making, particularly in brain disorders and complex diseases. 

Science as a Service (AI for Open Science)

We build scalable, cloud-based platforms for sharing biomedical datasets, models, and tools. By enabling reproducible research and collaborative environments, we accelerate scientific discovery and lower barriers to advanced AI-driven healthcare solutions. 

Vision

We envision a future where AI-powered multimodal medical intelligence enables:

• Early and precise diagnosis of diseases

• Predictive and preventive healthcare

• Personalized treatment strategies

Our lab strives to lead the convergence of AI, brain science, and digital healthcare to address critical challenges in an aging society and next-generation medicine.

Active Projects

• 치료저항성 우울증에서 반복 경두개자기자극술 세타 버스트 자극 프로토콜의 유효성, 안정성 검증 및 치료효과 예측을 위한 전향적 무작위 배정 다기관 임상연구, 연구자주도 임상연구지원, 한국보건산업진흥원, 보건복지부, 2025-2027

• 학습자의 정서적 요인이 학습에 미치는 영향, 융복합 국제공동연구, 경희대학교, 2025-2026

• 미래 응급의료 멀티모달 인공지능 모델 연구, 글로벌 AI 프론티어랩, SW컴퓨팅산업원천기술개발, 정보통신기획평가원, 2024-2028

• 멀티레벨/멀티모달 인공지능 기반 미래 응급의료체계 실현 기술 개발 및 창의적 혁신 미래 인재 양성, 대학 ICT 연구센터, 정보통신기획평가원, 2024-2031

• 경희대학교 메타버스융합대학원 (참여), 정보통신기획평가원, 과학기술정보통신부, 2024-2029

• 경희대학교 지능웨어 융합 교육연구단 (참여), BK21 혁신인재양성사업, 한국연구재단, 과학기술정보통신부, 2024-2027

• 경희대학교 소프트웨어중심대학 (참여), 정보통신창의인재양성, 정보통신기획평가원, 과학기술정보통신부, 2023-

• 경희대학교 실감미디어 컨소시엄 사업단 (참여), 디지털 신기술 인재양성 혁신융합대학사업, 한국연구재단, 교육부, 2021-2026