A5015785293- Hemodynamic Monitoring and Therapy
- Cardiac, Anesthesia and Surgical Outcomes
- Anesthesia and Sedative Agents
- Non-Invasive Vital Sign Monitoring
- Acute Kidney Injury Research
- Airway Management and Intubation Techniques
- Artificial Intelligence in Healthcare and Education
- Liver Disease and Transplantation
- Pituitary Gland Disorders and Treatments
- Machine Learning in Healthcare
- Respiratory Support and Mechanisms
- Blood Pressure and Hypertension Studies
- Organ Transplantation Techniques and Outcomes
- Intensive Care Unit Cognitive Disorders
- Liver Disease Diagnosis and Treatment
- Tracheal and airway disorders
- Anesthesia and Neurotoxicity Research
- Cardiac Arrest and Resuscitation
- Heart Rate Variability and Autonomic Control
- Traumatic Brain Injury and Neurovascular Disturbances
- ECG Monitoring and Analysis
- Taxation and Compliance Studies
- Technology Adoption and User Behaviour
- Telomeres, Telomerase, and Senescence
- Animal Genetics and Reproduction
Seoul National University
2012-2025
Seoul National University Hospital
2016-2025
New Generation University College
2020-2025
National University College
2020-2024
Pain and Rehabilitation Medicine
2017-2024
Monash University
2024
Korea University Medical Center
2020-2022
Inha University
2015-2020
Barro Colorado Island
2019
Korea University
2012-2018
Abstract The current anaesthesia information management system (AIMS) has limited capability for the acquisition of high-quality vital signs data. We have developed a Vital Recorder program to overcome disadvantages AIMS and support research. Physiological data surgical patients were collected from 10 operating rooms using Recorder. basic equipment used patient monitor, machine, bispectral index (BIS) monitor. Infusion pumps, cardiac output monitors, regional oximeter, rapid infusion device...
Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were have better predictive ability than the classic statistical analysis. We compared performance of that logistic regression analysis predict AKI transplantation. reviewed 1211 patients and preoperative intraoperative anesthesia surgery-related variables obtained. The primary outcome was postoperative defined by acute network criteria....
Machine learning approaches were introduced for better or comparable predictive ability than statistical analysis to predict postoperative outcomes. We sought compare the performance of machine with that logistic regression acute kidney injury after cardiac surgery. retrospectively reviewed 2010 patients who underwent open heart surgery and thoracic aortic Baseline medical condition, intraoperative anesthesia, surgery-related data obtained. The primary outcome was (AKI) defined according...
Abstract In modern anesthesia, multiple medical devices are used simultaneously to comprehensively monitor real-time vital signs optimize patient care and improve surgical outcomes. However, interpreting the dynamic changes of time-series biosignals their correlations is a difficult task even for experienced anesthesiologists. Recent advanced machine learning technologies have shown promising results in biosignal analysis, however, research development this area relatively slow due lack...
Abstract Background The discrepancy between predicted effect-site concentration and measured bispectral index is problematic during intravenous anesthesia with target-controlled infusion of propofol remifentanil. We hypothesized that total would be more accurately by a deep learning approach. Methods Long short-term memory the feed-forward neural network were sequenced to simulate pharmacokinetic pharmacodynamic parts an empirical model, respectively, predict intraoperative combined use...
Predicting in-hospital cardiac arrest in patients admitted to an intensive care unit (ICU) allows prompt interventions improve patient outcomes. We developed and validated a machine learning-based real-time model for predictions using electrocardiogram (ECG)-based heart rate variability (HRV) measures. The HRV measures, including time/frequency domains nonlinear were calculated from 5 min epochs of ECG signals ICU patients. A light gradient boosting (LGBM) algorithm was used develop the...
Abstract Continuous, comfortable, convenient (C3), and accurate blood pressure (BP) measurement monitoring are needed for early diagnosis of various cardiovascular diseases. To supplement the limited C3 BP existing cuff-based technologies, though they may achieve reliable accuracy, cuffless such as pulse transit/arrival time, wave analysis, image processing, have been studied to obtain measurement. One recent innovative machine-learning artificial intelligence-based technologies that can...
Abstract Background A real-time model for predicting short-term mortality in critically ill patients is needed to identify at imminent risk. However, the performance of needs be validated various clinical settings and ethnicities before its application. In this study, we aim develop an ensemble machine learning using routinely measured variables a single academic institution South Korea. Methods We developed deep light gradient boosting models. Internal validation was performed last two...
We present the INSPIRE dataset, a publicly available research dataset in perioperative medicine, which includes approximately 130,000 surgical operations at an academic institution South Korea over ten-year period between 2011 and 2020. This comprehensive patient characteristics such as age, sex, American Society of Anesthesiologists physical status classification, diagnosis, procedure code, department, type anaesthesia. The also vital signs operating theatre, general wards, intensive care...
The thin film synthesis and characterization of room temperature ferromagnetic semiconductor (In1−xFex)2O3−σ are reported. high thermodynamic solubility, up to 20%, Fe ions in the In2O3 is demonstrated by a combinatorial phase mapping study where lattice constant decreases almost linearly as doping concentration increases. Extensive structural, magnetic magneto-transport including anomalous Hall effect studies on samples consistently point source magnetism within host rather than from an...
The synthesis and magnetic properties of (In1−xFex)2O3−σ bulk ceramics with Cu co-doping are reported. Magnetic Fe ions found to have high thermodynamic solubility (up 20%) in the In2O3 host compound. lattice constant decreases almost linearly as doping concentration increases indicating incorporation into lattice. samples annealed under Ar reduced atmosphere were be ferromagnetic, Curie temperature is around 750K. extensive structural studies rule out possibility that observed magnetism...
n-3 Polyunsaturated fatty acids (PUFAs) are known to protect the cardiovascular system and improve blood pressure control. These important dietary constituents converted into bioactive metabolites, but their role in regulation of is unclear. In particular, functions cytochrome P450 (CYP) metabolites PUFAs remain virtually unexplored. this study, we examined effects docosahexaenoic acid (DHA) on large-conductance calcium-activated potassium (BK) channel activities coronary arterial smooth...
MicroRNAs (miRNAs) play a critical role in determining the differentiation fate of pluripotent stem cells and germ mammals. However, mechanism(s) miRNA-mediated posttranscriptional regulation with regard to lineage specification chick development require further investigation. Therefore, we conducted miRNA expression profiling explore specific signatures undifferentiated blastoderm primordial (PGCs). We identified seven miRNAs that are highly expressed 10 PGCs. In this study, miR-302a...
Accurate prediction of postoperative mortality is important for not only successful patient care but also information-based shared decision-making with patients and efficient allocation medical resources. This study aimed to create a machine-learning model 30-day after non-cardiac surgery that adapts the manageable amount clinical information as input features validated against multi-centered rather than single-centered data. Data were collected from 454,404 over 18 years age who underwent...
The Hypotension Prediction Index (HPI) was recently introduced and clinically validated in different surgical conditions. This prospective observational study evaluated HPI's performance living donor liver transplant recipients under the hypothesis that HPI would be inferior to previously reported predictability major surgery due characteristics of transplantation.Twenty adult patients undergoing transplantation were enrolled. monitored during with attending anesthesiologist blinded HPI....
Nontyphoid Salmonella (NTS) isolates lead to not only self-limited, acute gastrointestinal infections, but also bacteraemia with or without extraintestinal focal infections (EFIs). The risk factors associated EFIs in adults NTS were clearly elucidated.In a medical center southern Taiwan, patients aged > = 18 years between January 1999 and June 2005 included for analysis.Of 129 patients, 51 (39.5%) complicated EFIs. most common EFI was mycotic aneurysm, followed by pleuropulmonary spinal...
Acute hypotension after reperfusion of the liver graft occurs frequently during transplantation. A randomized, prospective trial was performed to test effects epinephrine and phenylephrine pretreatments for attenuating postreperfusion syndrome (PRS). Ninety-three adult recipients were randomly allocated receive an intravenous bolus 10 μg epinephrine, 100 phenylephrine, or normal saline (the control group) at time reperfusion. The occurrence PRS, use vasoactive drugs, postoperative courses...
Visual Abstract Export Background and objectives High BP variability may cause AKI because of inappropriate kidney perfusion. This study aimed to investigate the association between intraoperative postoperative in patients who underwent noncardiac surgery. Design, setting, participants, & measurements We performed a cohort adults undergoing surgery hospitals South Korea. studied three cohorts using following recording windows for BP: discovery cohort, 1-minute intervals; first validation...
In this article, we present a real-time electroencephalogram (EEG) based depth of anesthesia (DoA) monitoring system in conjunction with deep learning framework, AnesNET. An EEG analog front-end (AFE) that can compensate ±380-mV electrode DC offset using coarse digital servo loop is implemented the proposed system. The EEG-based MAC, EEGMAC, introduced as novel index to accurately predict DoA, which designed for applying patients anesthetized by both volatile and intravenous agents. protocol...