Established 2025 · Project SLK Ltd.

Where Artificial Intelligence Meets Clinical Reality

The SLK Research Institute conducts applied research at the intersection of emergency medicine and AI, translating clinical insight into technology that works where it matters most.

8+ SCI Publications
35K+ Patient Records
3 Research Domains
Scroll to explore
01

About the Institute

The Project SLK Research Institute for AI Medical Innovation is the dedicated research arm of Project SLK Ltd., focused on the systematic study of AI applications in clinical medicine.

Grounded in real-world emergency department data and frontline clinical experience, our work spans post-cardiac arrest syndrome (PCAS) prognostication, automated ED triage and severity classification, and AI-driven clinical decision support systems — all designed to be practical, validated, and deployable.

Our findings are published in SCI/SCIE-indexed international journals and directly inform Project SLK's product pipeline, including the Compact Emergency Unit (CEU), creating a virtuous cycle between rigorous research and real-world implementation.

"For AI to truly serve underserved communities, it must be built not as a laboratory model but as a tool that functions in the field."
— From the Institute's founding statement
02

Research Areas

🧠

Post-Cardiac Arrest Syndrome

Developing multimodal AI models for neurological outcome prediction after cardiac arrest, leveraging the multicenter KORHN registry with temporal clinical features, biomarkers, and neurophysiological data.

Neuroprognostication Multimodal ML BRAIN Score
🏥

Emergency Department AI

Building prediction models from 35,000+ ED encounters for automated severity classification, undertriage detection, and adverse outcome prediction in discharged patients, with emphasis on explainability.

Undertriage Detection ED Severity Explainable AI
📦

Compact Emergency Unit

Conducting the technical design, validation, and health-economic modeling for AI-powered compact emergency care units deployable in medically underserved regions.

CEU Telemedicine Health Equity
03

Selected Publications

2026
Distinct Coagulation Phenotypes in Post-Cardiac Arrest Syndrome: A Latent Class Analysis
Journal of Clinical Medicine (SCI)
Published
2026
Distinct Trajectories of Consciousness Recovery After Cardiac Arrest
Medicina (SCIE)
Published
2026
Multimodal Neuroprognostication in Post-Cardiac Arrest Syndrome Using Machine Learning
Diagnostics (SCIE)
Published
2026
Temporal Multimodal Prediction of Neurological Outcomes in Post-Cardiac Arrest Patients
Scientific Reports (SCI)
Under Review
2026
Neutrophil-to-Lymphocyte Ratio Trajectories and Neurological Outcomes in PCAS
Resuscitation Plus (SCIE)
Under Review
2026
Beyond Binary Cutoffs: Explainable AI for Urolithiasis Diagnosis on Non-Contrast CT
Diagnostics (SCIE)
Under Review
2026
Compact Emergency Unit: A Simulation-Based Validation Study
Healthcare (SCIE)
Under Review
2025
Beyond Vital Signs: Machine Learning for Undertriage Detection in the Emergency Department
AI (MDPI)
Under Review
04

Research Team

SL
Sohee Lee
Director
AI & Machine Learning Specialist
Core algorithm design
& technology development lead
JL
Jee Yong Lim, MD
CRO · Clinical Research Lead
Clinical Assistant Professor
Dept. of Emergency Medicine
Seoul St. Mary's Hospital,
The Catholic University of Korea
YK
Youngjin Kim
CEO
Industrial facility design
& construction specialist
AI-optimized space planning
JS
Jaekwang Shin
CFO
Professor, Seokyeong University
Data analytics & education
Financial strategy & grants
05

Research Infrastructure

🏥 Clinical Data

Access to the Catholic Medical Center (CMC) Clinical Data Warehouse spanning 8 hospitals, alongside the multicenter KORHN cardiac arrest registry — providing large-scale, real-world clinical datasets.

🔬 Key Collaborations

Seoul St. Mary's Hospital Department of Emergency Medicine, Korean Hypothermia Network (KORHN), and the College of Medicine at The Catholic University of Korea.

💻 Technology Stack

Python & R-based ML pipelines, XGBoost / LightGBM / deep learning architectures, and Explainable AI (SHAP) frameworks for transparent, clinically interpretable models.

Collaboration & Inquiries

We welcome opportunities in collaborative clinical AI research, data analytics partnerships, and industry–academia engagement.

research@projectslk.com