Dong Wook Kim
연세대학교 의과대학 · 의학
Dong Wook Kim 교수의 연구실은 종양학, 특히 구강 평면세포암과 소세포폐암의 생존 예측 및 유전적 기반 연구에 중점을 두고 있습니다. 머신러닝 기반의 생존 예측 모델(예: DeepSurv, 랜덤 서바이벌 포레스트)을 활용한 정밀의료 기반의 암 예후 분석과 함께, 소득 수준, 당뇨병 등 사회경제적 요인과 기저질환의 영향을 고려한 구강건강 연구도 진행하고 있습니다. 또한 어린이의 신장 볼륨 측정을 위한 초음파 자동 측정 기술 개발 및 임상 응용 방안에 대해서도 연구를 확장하고 있습니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
The Cox proportional hazards model commonly used to evaluate prognostic variables in survival of cancer patients may be too simplistic to properly predict a cancer patient's outcome since it assumes that the outcome is a linear combination of covariates. In this retrospective study including 255 patients suitable for analysis who underwent surgical treatment in our department from 2000 to 2017, we applied a deep learning-based survival prediction method in oral squamous cell carcinoma (SCC) pati
These observations suggest that initial fasting and fluid restriction are not essential for the KD and that the tolerability of this treatment may be improved. These data support our intention to conduct a formal, prospective, randomized trial comparing 2 forms of the KD.
In a rapidly increasing Korean population, the lower socioeconomic groups as well as individuals with DM were significantly more likely to present with periodontitis.
Abstract: The discovery of recurrent alterations in genes encoding transcription regulators and chromatin modifiers is one of the most important recent developments in the study of the small cell lung cancer (SCLC) genome. With advances in models and analytical methods, the field of SCLC biology has seen remarkable progress in understanding the deregulated transcription networks linked to the tumor development and malignant progression. This review will discuss recent discoveries on the roles of
The unpredictable change in the rotational axis of the tibia and its broad variability after rotating platform mobile bearing TKA may provide a warning against the use of a fixed landmark for establishing tibial rotational alignment.
In this study, we aimed to develop a new automated method for kidney volume measurement in children using ultrasonography (US) with image pre-processing and hybrid learning and to formulate an equation to calculate the expected kidney volume. The volumes of 282 kidneys (141 subjects, <19 years old) with normal function and structure were measured using US. The volumes of 58 kidneys in 29 subjects who underwent US and computed tomography (CT) were determined by image segmentation and compared to
