A5034752551- Marine and coastal plant biology
- Acute Ischemic Stroke Management
- Algal biology and biofuel production
- Stroke Rehabilitation and Recovery
- Axon Guidance and Neuronal Signaling
- Seaweed-derived Bioactive Compounds
- Food Quality and Safety Studies
- Polar Research and Ecology
- Cardiovascular Health and Disease Prevention
- Topic Modeling
- Hippo pathway signaling and YAP/TAZ
- Context-Aware Activity Recognition Systems
- Cerebrovascular and Carotid Artery Diseases
- Fungal Plant Pathogen Control
- Marine Biology and Ecology Research
- Medical Research and Treatments
- Zebrafish Biomedical Research Applications
- Bluetooth and Wireless Communication Technologies
- Distributed and Parallel Computing Systems
- Scoliosis diagnosis and treatment
- Regional Development and Environment
- Pediatric health and respiratory diseases
- Heat shock proteins research
- Medical Imaging and Analysis
- Agriculture, Soil, Plant Science
Yonsei University
2016-2025
Korea University
2023-2024
Seoul National University
2005-2024
Gyeonggi Research Institute
2024
National Institute of Fisheries Science
2010-2023
Korea Advanced Institute of Science and Technology
2023
Severance Hospital
2022
Chungnam National University Hospital
2022
LG Chem (South Korea)
2021
LG (South Korea)
2021
The advance of deep learning has made huge changes in computer vision and produced various off-the-shelf trained models. Particularly, Convolutional Neural Network (CNN) been widely used to build image classification model which allow researchers transfer the pre-trained for other classifications. We propose a method detect breast cancer using histopathology images based on Google's Inception v3 were initially non-medical images. pilot study shows feasibility detection with AUC 0.93.
Abstract We investigated whether cognitive decline could be explained by resting-state electroencephalography (EEG) biomarkers measured in prefrontal regions that reflect the slowing of intrinsic EEG oscillations. In an aged population dwelling a rural community (total = 496, males 165, females 331), we estimated global using Mini-Mental State Examination (MMSE) and parameters at Fp1 Fp2 eyes-closed state. Using tertile split method, subjects were classified as T3 (MMSE 28–30, N 162), T2...
Bayesian network is an increasingly popular method in modeling uncertain and complex problems, because its interpretability often more useful than plain prediction. To satisfy the core requirement medical research to obtain interpretable prediction with high accuracy, we constructed inference engine for post-stroke outcomes based on classifiers. The system that was trained data of 3,605 patients acute stroke forecasts functional independence at 3 months mortality 1 year after stroke. Feature...
We introduce a Feasible Artificial Intelligence with Simple Trajectories for Predicting Adverse Catastrophic Events (FAST-PACE) solution preparing immediate intervention in emergency situations. FAST-PACE utilizes concise set of collected features to construct an artificial intelligence model that predicts the onset cardiac arrest or acute respiratory failure from 1 h 6 prior its occurrence. Data trajectory 29,181 patients intensive care units two hospitals includes periodic vital signs,...
Subtle abnormal motor signs are indications of serious neurological diseases. Although deficits require fast initiation treatment in a restricted time, it is difficult for nonspecialists to detect and objectively assess the symptoms. In clinical environment, diagnoses decisions based on grading methods, including National Institutes Health Stroke Scale (NIHSS) score or Medical Research Council (MRC) score, which have been used measure weakness. Objective various environments necessitated...
Introduction: The link between arterial stiffness, measured by estimated pulse wave velocity (ePWV), and outcomes following endovascular treatment (EVT) is unclear. Hypothesis: This study aimed to determine whether ePWV predicts post-EVT outcome in patients with acute ischemic stroke. Methods: was a secondary analysis of the OPTIMAL-BP trial, which enrolled 302 EVT from 19 stroke centers Korea June 18, 2020 November 28, 2022. calculated using regression equation based on age mean blood...
BACKGROUND The link between arterial stiffness, measured by estimated pulse wave velocity (ePWV), and outcomes following endovascular thrombectomy (EVT) has not been tested. This study aimed to determine whether ePWV predicts post‐EVT outcome in patients with acute ischemic stroke. METHODS was a secondary analysis of the OPTIMAL‐BP (Outcome Patients Treated With Intraarterial Thrombectomy–Optimal Blood Pressure Control) trial, which enrolled 302 EVT from 19 stroke centers South Korea June...
Emergency medical service (EMS) occurs in a high-pressure and error-prone environment, where paramedics must provide prompt decisions care while recording information with limited time, incomplete data, restricted resources, competing priorities. The EMS requires cooperative workflows between patients or caregivers, centers the community. In conventional EMS, they have difficulties obtaining causes of emergencies personal histories, which are important for rapid proper response. We analyzed...
A machine learning technique for identifying hidden coronary artery disease (CAD) might be useful. We developed and validated models to predict patients with CAD assess long-term outcomes in acute ischemic stroke.Multidetector CT was performed without a known history of CAD. Primary were defined as having any degree obstructive (≥50% stenosis). Demographic variables, risk factors, laboratory results, Trial ORG 10172 Acute Stroke Treatment classification, NIH Scale score, blood pressure,...
Medical concentric tubes have recently been designed using auxetic structures with negative Poisson's ratios to reduce undesirable snapping instability and improve mechanical performance. Despite the vast range of stiffness levels, prior designs were restricted relatively simple geometries like square or triangular holes. Here, we present a novel free-form optimization for designing bending torsional tubular multi-objective Bayesian (MBO) method. The initial dataset hole shapes is generated...
We recently reported that the phosphotyrosine-binding (PTB) domain of Anks family proteins binds to EphA8, thereby positively regulating EphA8-mediated signaling pathways. In current study, we identified a potential role for SAM domains in EphA signaling. found directly bind ubiquitin, suggesting regulate degradation ubiquitinated receptors. Consistent with Cbl ubiquitin ligases Eph receptors, our results revealed ligase c-Cbl induced ubiquitination and EphA8 upon ligand binding....
Temperature is one of the major environmental factors that affect distribution, growth rate, and life cycle intertidal organisms, including red algae. In an effort to identify genes involved in high-temperature tolerance Porphyra, we generated 3,979 expression sequence tags (ESTs) from gametophyte thalli P. seriata Kjellm. under normal conditions conditions. A comparison ESTs two cDNA libraries allowed us high temperature response (HTR) genes, which are induced or up-regulated as result...
The benefits of thrombolytic treatment are time-dependent. We developed a smartphone application that aids stroke patient self-screening and hospital selection, may also decrease arrival time.The was for iPhone Android smartphones. Map data the were adopted from open map. For registration, web page (http://stroke119.org) using PHP MySQL.The Stroke 119 includes screening tool real-time information on nearby hospitals provide treatment. It provides symptoms, treatment, prescribed actions when...