AI Researcher at AITRICS · PhD Student in Digital Health at SAIHST, Sungkyunkwan University · Co-founder & CEO of BreathYou
_{Clinical time-series deep learning · Medical AI regulation (SaMD) · Respiratory digital health}

I'm a PhD student in Digital Health at SAIHST, Sungkyunkwan University, advised by Prof. Byung-Jae Lee, and an AI Researcher at AITRICS. In 2025 I co-founded BreathYou, a digital health startup focused on allergy and respiratory AI that turns parts of this research into products clinicians can use.

My work sits between machine learning research and clinical deployment — how a model becomes a medical device, how it's trained, how it's validated, and how it earns regulatory trust. At AITRICS, I contributed to a cardiac arrest early-warning system that was approved by Korea's MFDS as an AI medical device, and I'm now leading the product development of an AKI prediction model I developed, with the same goal of MFDS approval. For my doctoral research, I work with longitudinal pulmonary function data from Samsung Medical Center, building time-series models that better capture how respiratory health changes over time.

• Clinical time-series deep learning — Transformers for longitudinal pulmonary function trajectories, early-warning prediction (sepsis, cardiac arrest, AKI), and robust label engineering
• Medical AI regulation (SaMD) — lessons from MFDS-approved and FDA-cleared systems; prospective external validation and real-world monitoring
• Respiratory digital health — Korean-specific reference equations, a multimodal respiratory foundation model, and CDSS for pulmonary function decline
• Signal-level physiology — HRV / ECG, EMG, and multimodal affective computing

• 🫁 DeepBreath CDSS — predicting pulmonary function decline trajectories from longitudinal PFT data (BreathYou)
• 📝 MediPipe — OCR / NLP pipeline for medical record structuring (BreathYou)
• 🩺 AKI prediction model — leading product development toward MFDS approval (AITRICS)
• 🫀 Transformer-based cardiac arrest & sepsis prediction for general wards, with a focus on prospective validation

A full, maintained list lives on my homepage and Google Scholar.

🌟 Featured — representative work   K. H. Lee†, D. Yoon†, H. Lim, K.-B. Lee*, Y. K. Lee*. Deep learning models for acute kidney injury prediction: multi-center external validation and evaluation under simulated continuous monitoring conditions. npj Digital Medicine, 2026. [DOI]
_{† equal contribution · * corresponding authors}

• K. H. Lee, C.-H. Cho, A. Y. Kim, H. J. Jeon, S. Byun. Deep learning-based stress detection from RR intervals in major depressive disorder, panic disorder, and healthy individuals. Frontiers in Psychiatry, 2025.
• K. H. Lee, S. Hahn, H. Lim, K.-B. Lee, Y. K. Lee. Development of a Labeling Algorithm for Early Prediction of Acute Kidney Injury. Studies in Health Technology and Informatics, 2025.
• K. H. Lee, H. Choo, S. Hong, S. Hong, K.-B. Lee, H. Cho. Relationship between In-Hospital Sepsis Prediction Score and Prevalence of Community-Onset Sepsis. Applied Medical Informatics, 2024.
• N. Kang, K. H. Lee, S. Byun, J.-Y. Lee, D.-C. Choi, B.-J. Lee. Novel AI-based technology to diagnose asthma using methacholine challenge tests. Allergy, Asthma & Immunology Research, 2024.
• K. H. Lee, S. Byun. Age prediction in healthy subjects using RR intervals and HRV: a deep learning pilot. Applied Sciences, 2023.
• K. H. Lee, J. Y. Min, S. Byun. EMG-based classification of hand and finger gestures using artificial neural networks. Sensors, 2021.

• ETRI Director's Award (Top 7) — Human Understanding AI Paper Competition, 2022 — Multimodal Attention-based Korean emotion recognition (RoBERTa + Wav2vec 2.0)
• Excellence Award — OCR AI Training Data Hackathon (NIA), 2021 — CRAFT-based OCR annotation system for pharmaceuticals
• Grand Prize — Medical Information Analysis Expert Advanced Course (Asan Medical Center), 2021 — Real-time intraoperative BIS prediction from EEG

I'm always happy to talk with people working on clinical AI, medical device development, SaMD regulatory pathways, or respiratory health — feel free to reach out.

📍 Suwon, Gyeonggi-do, Republic of Korea  ·  ✉️ lkh256 [at] breathyou [dot] care