Hyerim Kim
서울대학교 의예과 · 의학
이 교수의 연구실은 심층 학습 기반의 의료 데이터 분석을 핵심으로 하며, 영양 섭취와 만성질환 간의 복합적 연관성을 분류하고 예측하는 데 초점을 맞추고 있습니다. 특히 고혈압, 비만, 당뇨병, 고지혈증 등 대사질환의 위험도를 정밀하게 예측하기 위한 딥뉴럴네트워크(DNN) 모델 개발이 주요 연구 과제입니다. 또한, 약물에 의한 알레르기 반응이나 간세포암과 같은 질환의 분자 기전 규명을 위한 분자생물학적 연구도 병행하고 있습니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
Few studies have been conducted to classify and predict the influence of nutritional intake on overweight/obesity, dyslipidemia, hypertension and type 2 diabetes mellitus (T2DM) based on deep learning such as deep neural network (DNN). The present study aims to classify and predict associations between nutritional intake and risk of overweight/obesity, dyslipidemia, hypertension and T2DM by developing a DNN model, and to compare a DNN model with the most popular machine learning models such as l
The hepatitis B viral X protein (HBx) is a multifunctional protein that plays a role in the activation of the NF-kappaB signaling pathway. In this study, we demonstrate that HBx up-regulates expression of TANK-binding kinase-1 (TBK1) at the transcriptional level. Increased levels of TBK1 protein then induce the phosphorylation of NF-kappaB p65 at serine 536. Because TBK1 is up-regulated by HBx as part of its promotion of NF-kappaB activation, it is possible that increased TBK1 levels play a role
The interstitial pneumonia pattern on the day 7 chest radiograph has a high specificity for predicting BPD or death and can be utilized to select high-risk preterm infants who will benefit from potentially preventive interventions against BPD.
Photoreduction of <TEX>$CO_2$</TEX> into hydrocarbon fuels on the surface of photocatalyst is one of the breakthroughs in the field of photocatalysis. At present various approaches have been investigated with the aim of increasing the <TEX>$CO_2$</TEX> conversion efficiency. The reactor for photoconversion of <TEX>$CO_2$</TEX> plays a vital role in experimental setup. In this work an attempt was made to testify a newly designed the photoreactor for conversion of <TEX>$CO_2$</TEX> into useful pro
Although allergic reactions are not rare complications in drug use, anaphylaxis or anaphylactoid reactions to some widely used drugs can embarrass clinicians because anaphylaxis is not easily diagnosed at the time of the event and treatment is unfamiliar to many. Lidocaine is a very popular drug in dental procedures and anaphylactoid reaction to it has been rarely reported. Clinicians who use lidocaine daily should, however, be aware of the possibility of anaphylaxis after its use. Once it occur
Few studies classified and predicted hypertension using blood pressure (BP)-related determinants in a deep learning algorithm. The objective of this study is to develop a deep learning algorithm for the classification and prediction of hypertension with BP-related factors based on the Korean Genome and Epidemiology Study-Ansan and Ansung baseline survey. We also investigated whether energy intake adjustment is adequate for deep learning algorithms. We constructed a deep neural network (DNN) in w
Tuffier line is a common landmark for spinal anesthesia. The 10th rib line has been suggested as a new landmark to predict the intervertebral levels. We evaluated the accuracy of these 2 anatomic landmarks for identifying the L4-L5 intervertebral space using ultrasonography in elderly patients with hip fracture.Seventy-nine elderly patients scheduled for hip fracture surgery under spinal anesthesia were included. In the lateral decubitus position with the fracture side up, the L4-L5 intervertebr
Retinitis pigmentosa (RP) is an outer retinal degenerative disease that can lead to photoreceptor cell death and profound vision loss. Although effective regulation of intraretinal inflammation can slow down the progression of the disease, an efficient anti-inflammatory treatment strategy is still lacking. This study reports the fabrication of a hyaluronic acid-based inflammation-responsive hydrogel (IRH) and its epigenetic regulation effects on retinal degeneration. The injectable IRH was desig
The aim of this study was to evaluate the effectiveness of cricoid and paralaryngeal force for oesophageal entrance occlusion during induction of anaesthesia. Seventy-four patients were included in this randomised, crossover study. The relative position of the glottis and outer anteroposterior diameter of the upper oesophageal entrance were assessed at baseline, after the application of 30 N cricoid and paralaryngeal force, and after induction of anaesthesia. The occlusion rate of the oesophagea