| K-MIMIC: a nationwide Korean multi-institutional Multimodal intensive care dataset |
|
Young-Gon Kim1,2,3, Jongho Shin1, Sul Mui Won4, Sang-Min Lee5,6, Ho Geol Ryu5,7,8, Geonhee Lee1,9, Wookyung Kim1,9, Dai-Jin Kim10,11, Taehoon Ko10,12,13, Tong Min Kim10, Il-Woo Song14, SuEun Jung14, Jun Wan Lee15,16, Jeong-Ho Hong17,18, Jong-Yeup Kim19,20, Da Hye Moon21, Won-Yeon Lee22, Woo Hyun Cho23,24, Yoon Mi Shin25,26, Soomin Jo27,28, Byoung Jun Lee29, Minjae Yoon30, Borim Ryu31, Jin-Heon Jeong32, Seung Yong Park33,34, Soung sil Choi35, Taeyun Kim36, Hyung-Chul Lee3,7,8, Eui Kyu Chie4,37 |
1Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Republic of Korea
2Department of Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea
3Healthcare AI Research Institute, Seoul National University Hospital, Seoul, Republic of Korea
4Department of Radiation Oncology, Seoul National University Hospital, Seoul, Republic of Korea
5Department of Critical Care Medicine, Seoul National University Hospital, Seoul, Republic of Korea
6Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea
7Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea
8Department of Anesthesiology and Pain Medicine, Seoul National University Hospital, Seoul, Republic of Korea
9Interdisciplinary Program of Medical Informatics, Seoul National University, Seoul, Republic of Korea
10Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
11Department of Psychiatry, College of Medicine, The Catholic University of Korea, Seoul St. Mary’s Hospital, Seoul, Republic of Korea
12Department of Medical Sciences, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
13CMC Institute for Basic Medical Science, The Catholic Medical Center of the Catholic University of Korea, Seoul, Republic of Korea
14Big Data Science Team, ezCaretech Co., Ltd., Seoul, Republic of Korea
15Department of Cardiovascular Thoracic Surgery, Chungnam National University Hospital, Daejeon, Republic of Korea
16Center for Critical Care Medicine, Chungnam National University Hospital, Daejeon, Republic of Korea
17Department of Neurology, Keimyung University Dongsan Hospital, Keimyung University School of Medicine, Daegu, Republic of Korea
18Department of Medical Informatics, Keimyung University School of Medicine, Daegu, Republic of Korea
19Department of Otorhinolaryngology–Head & Neck Surgery, College of Medicine, Konyang University, Daejeon, Republic of Korea
20Department of Biomedical Informatics, College of Medicine, Konyang University, Daejeon, Republic of Korea
21Department of Pulmonology, Kangwon National University Hospital, Chuncheon, Republic of Korea
22Department of Internal Medicine, Yonsei University Wonju Severance Christian Hospital Yonsei University Wonju College of Medicine, Wonju, Republic of Korea
23Division of Allergy, Pulmonary and Critical Care Medicine, Department of Internal Medicine, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Yangsan, Republic of Korea
24Department of Internal Medicine, School of Medicine, Pusan National University, Yangsan, Republic of Korea
25Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Chungbuk National University Hospital, Cheongju, Republic of Korea
26Department of Internal Medicine, Chungbuk National University College of Medicine, Cheongju, Republic of Korea
27Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Dongguk University Ilsan Hospital, Goyang, Republic of Korea
28Department of Internal Medicine, Graduate School, Dongguk University, Seoul, Republic of Korea
29Division of Pulmonary, Allergy and Critical Care Medicine, Department of Internal Medicine, Veterans Health Service Medical Center, Seoul, Republic of Korea
30Division of Cardiology, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
31Center for Data Science, Biomedical Research Institute, Seoul Metropolitan Government–Seoul National University Boramae Medical Center, Seoul, Republic of Korea
32Department of Intensive Care Medicine & Neurology, Dong-A University Hospital, Busan, Republic of Korea
33Division of Respiratory, Allergy and Critical Care Medicine, Chonbuk National University Hospital, Jeonju, Republic of Korea
34Department of Internal Medicine, Chonbuk National University Medical School, Jeonju, Republic of Korea
35Division of Cardiothoracic Surgery, Bundang Jesaeng Hospital, Seongnam, Republic of Korea
36Department of Critical Care Medicine, Seongnam Citizens Medical Center, Seongnam, Republic of Korea
37Department of Radiation Oncology, Seoul National University College of Medicine, Seoul, Republic of Korea |
Corresponding author:
Hyung-Chul Lee, Tel: +82-2-2072-0723,
Email: vital@snu.ac.kr
Eui Kyu Chie, Tel: +82-2072-3705,
Email: ekchie93@snu.ac.kr
|
|
Received: 25 August 2025 • Revised: 18 December 2025 • Accepted: 8 January 2026 |
|
|
| Abstract |
Background
Recent advancements in critical care have highlighted the need for comprehensive, multimodal datasets to support clinical decision-making and advancing artificial intelligence (AI) research. However, such datasets are scarce in Asia. We developed the Korean Multi-Institutional Multimodal Intensive Care (K-MIMIC) dataset by integrating structured electronic medical records (EMRs), high-resolution bio-signals, and medical imaging from multiple hospitals in Korea.
Methods
This retrospective multicenter study collected intensive care unit (ICU) data from 278,274 patients admitted to 71 ICUs across 10 hospitals between 2001 and 2023. The data modalities included structured EMRs, physiological waveforms, and imaging studies. Data extraction followed standardized protocols and de-identification procedures in compliance with the Korean Health Data Utilization Guidelines. Multimodal linkage was achieved at the patient level to enable temporal trajectory analysis.
Results
The K-MIMIC dataset contains 287,274 ICU admissions from 241,805 unique patients, including 22,588 bio-signal files and 496,999 imaging studies, primarily chest X-rays aligned with EMRs. Nearly 47% of ICU admissions originated in the emergency department (ED). Elderly patients (65–90 years old) constituted the largest age group. Fifteen thousand, five hundred forty-eight patients had EMR data linked with both bio-signals and imaging, enabling full multimodal analyses.
Conclusions
The K-MIMIC is the first large-scale, multicenter, multimodal ICU dataset in Asia to provide a robust resource for critical care research, including AI-based prediction, monitoring, and longitudinal outcome studies. The dataset demonstrates the feasibility of secure and standardized ICU data integration across diverse institutions.
|
| Key Words:
Artificial intelligence; Critical illness; Databases; Diagnostic imaging; Intensive care units; Multimodal imaging |
|
PDF Links
Full text via DOI
Download Citation
