RnDCircle Logo
류승호 연구실
성균관대학교 의학과
류승호 교수
기본 정보
연구 분야
프로젝트
논문
구성원

류승호 연구실

성균관대학교 의학과 류승호 교수

류승호 연구실은 산업역학과 예방의학을 기반으로 건강검진 및 코호트 데이터를 활용해 심혈관질환·암·폐질환 등의 위험요인을 규명하고, 유방촬영·흉부 X선·CT 같은 의료영상과 혈액마커를 결합한 인공지능 기반 예측모델 및 이미지 바이오마커를 개발하며, 국가 바이오 빅데이터와 정밀의학 연구를 통해 다질환 통합 위험평가와 맞춤형 예방전략 수립을 목표로 하는 보건의료 연구를 수행하고 있다.

대표 연구 분야
연구 영역 전체보기
산업역학 및 예방의학 기반 만성질환 위험평가 thumbnail
산업역학 및 예방의학 기반 만성질환 위험평가
연구 성과 추이
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.

5개년 연도별 논문 게재 수

183총합

5개년 연도별 피인용 수

2,620총합
주요 논문
3
논문 전체보기
1
article
|
인용수 0
·
2024
Prognostic implication of right ventricular - pulmonary arterial coupling in patients with non-valvular atrial fibrillation
Do Yeon Kim, Seungho Ryu, Jae‐Won Jang, S. H. Shin
IF 35.6 (2024)
European Heart Journal
Abstract Background The clinical importance of right ventricular (RV) - pulmonary arterial (PA) coupling has been reported in various cardiac diseases such as right heart failure, pulmonary hypertension, and valvular dysfunction. However, there is limited data on patients with non-valvular atrial fibrillation (AF). We aim to investigate whether RV-PA uncoupling affects the clinical outcome in patients with non-valvular AF. Methods A total of 807 consecutive patients with non-valvular AF who underwent echocardiography (mean age 70 ± 12 years, 39% female) were included. We excluded patients with significant (at least moderate degree) valvular diseases, left ventricular ejection fraction (LVEF) <50%, cardiac implantable electronic devices, previous cardiac surgery, and poor echocardiographic image for RV analysis. RV-PA coupling was assessed by the ratio of RV global longitudinal strain (GLS) to PA systolic pressure (PASP), and decreased RV-PA coupling was defined as less than 0.52 %/mmHg based on on the receiver operating characteristic analysis. The primary outcome was the composite of all-cause death and hospitalization for heart failure. Results Over a mean of 4.7 ± 3.5 years of follow-up, 178 (22%) patients had experienced primary outcomes. Among them, 107 (13%) patients were hospitalized for HF and 90 (11%) patients died. Patients with decreased RV-PA coupling were older (73 ± 11 vs. 68 ± 12 years, p<0.001), had a higher prevalence of females (51 vs. 33%, p<0.001) and diabetes (33 vs. 23%, p=0.003), lower left ventricular ejection fraction (60 ± 5 vs. 61 ± 5%, p=0.011), higher E/e’ (14 ± 5 vs. 11 ± 4, p<0.001), larger left atrial volume index (78 ± 37 vs. 62 ± 22 ml/m2, p<0.001) and larger RV end-systolic area (11 ± 4 vs. 10 ± 3 cm2/m2, p=0.001) compared to those with preserved RV-PA coupling. In multivariate Cox regression analysis, decreased RV-PA coupling was associated with worse clinical outcomes even after adjusting for age, diabetes, E/e’, and RV end-systolic area (Hazard ratio [HR] 1.50, 95% Confidence interval [CI] 1.09 – 2.07, p=0.014) (Figure 1). Conclusions In patients with non-valvular AF, RV-PA coupling was associated with clinical outcome, suggesting that it may provide additional information for predicting future cardiovascular risk in this population.
https://doi.org/10.1093/eurheartj/ehae666.495
Medicine
Cardiology
Internal medicine
Atrial fibrillation
2
article
|
bronze
·
인용수 23
·
2024
Human papillomavirus infection and cardiovascular mortality: a cohort study
Hae Suk Cheong, Yoosoo Chang, Yejin Kim, Min‐Jung Kwon, Yoosun Cho, Bomi Kim, Eun‐Jeong Joo, Young Ho Bae, Chanmin Kim, Seungho Ryu
IF 35.6 (2024)
European Heart Journal
In this cohort study of young and middle-aged Korean women, at low risks for CVD mortality, those with HR-HPV infection had higher death rates from CVD, specifically ASCVD and IHD, with a more pronounced trend in obese individuals.
https://doi.org/10.1093/eurheartj/ehae020
Medicine
Hazard ratio
Proportional hazards model
Internal medicine
Cohort
Confounding
Cohort study
Mortality rate
Cervical cancer
HPV infection
3
article
|
인용수 1
·
2022
Robust artificial intelligence-powered imaging biomarker based on mammography for risk prediction of breast cancer.
Eun Kyung Park, Hyeonsoo Lee, Minjeong Kim, Ki Hwan Kim, Hyeonseob Nam, Yoosoo Chang, Seungho Ryu
IF 45.3 (2022)
Journal of Clinical Oncology
10533 Background: Accurate risk assessment allows the precise personalized screening of breast cancer. Conventional statistical risk models have been used that estimate the probability of breast cancer incidence with patient demographics, detailed personal and family history. The purpose of this study was to investigate the feasibility of the AI-powered Imaging Biomarker in mammography (IBM) which was developed to predict the risk of future breast cancer beyond the mammographic breast density. Methods: We trained and developed the deep learning risk model, the AI-powered IBM, using a total of 36,955 examinations from 21,438 patients, who underwent at least one mammogram using Hologic or Siemens machines and pathology-confirmed breast cancer outcomes. To discover the feasibility of the AI-powered IBM, mammograms and various clinical information including pathology-confirmed breast cancer outcomes were collected, which were only used for external validation. C-indices and receiver operating characteristic (ROC) curves for 1- to 5-year outcomes were obtained. We compared 5-year ROC area under the curves (AUCs) of our AI-powered IBM and statistical risk models including the Tyrer-Cuzick model and the Gail model, which were most commonly used and widely known, using DeLong’s test. Results: A total of 16,894 mammograms were collected for external validation, of which 4,002 were followed by a cancer diagnosis within 5 years. Our AI-powered IBM obtained C-index of 0.758, and the model demonstrated the risk of breast cancer with AUC of 0.895 (95% CI: 0.880, 0.909) at 1-year, 0.839 (0.824, 0.852) at 2-year, 0.807 (0.794, 0.819) at 3-year, 0.783 (0.7947, 0.819) at 4-year. The 5-year AUC of our AI-powered IBM was 0.808 (0.792, 0.822). Our AI-powered IBM showed significantly higher 5-year AUC than the Gail model (AUC: 0.572, P< 0.001) and the Tyrer-Cuzick model (0.569, P< 0.001). Conclusions: A deep learning AI-powered IBM using mammograms has a substantial potential to advance toward the robust risk prediction of breast cancer over conventional risk models. This approach for risk stratification of breast cancer might be feasible to improve personalized screening programs.
https://doi.org/10.1200/jco.2022.40.16_suppl.10533
Medicine
Breast cancer
Mammography
Receiver operating characteristic
Biomarker
Cancer
Breast imaging
Risk assessment
Medical physics
Oncology
최신 정부 과제
18
과제 전체보기
1
2025년 2월-2028년 2월
|231,055,000
AI 기반 흉부 영상(X선, CT) 및 혈액마커(SERS)를 활용한 폐기능 예측 및 폐질환 사망 위험 평가
본 연구의 최종 목표는 저선량 흉부CT 또는 흉부 X선 영상을 기반으로, 폐 관련 혈액 마커(SERS) 패턴과 융합하여 고성능 폐기능 예측모델을 개발하는 것임. 이를 기반으로 폐질환 사망 위험을 평가하고, 위험도에 따른 분류를 제시하여 고위험군에 대한 체계적 관리 및 예방 전략을 수립하고자 함● 목표 1. 저선량 흉부 CT 데이터를 활용하여 폐기능 및 흡연...
흉부영상
폐기능
예측
폐질환 사망
인공지능
2
2024년 9월-2028년 12월
|143,000,000
일반 국민참여자 (건강인) 대상 국가 통합 바이오 빅데이터 구축 연구
최종목표: 5년간 일반 국민참여자 총 33,150 모집 및 임상정보 생산, 검체 채취세부목표: - 참여자 동의를 기반으로 검체 (혈액, 소변, 조직)를 확보 - 임상 및 유전체 데이터, 공공 데이터 등을 수집, 생산 - 데이터뱅크 구축 및 연계
예방의학
역학
빅데이터
임상 연구 방법론
3
2024년 9월-2028년 12월
|1,123,500,000
일반 국민참여자 (건강인) 대상 국가 통합 바이오 빅데이터 구축 연구
최종목표: 5년간 일반 국민참여자 총 33,150 모집 및 임상정보 생산, 검체 채취세부목표: - 참여자 동의를 기반으로 검체 (혈액, 소변, 조직)를 확보 - 임상 및 유전체 데이터, 공공 데이터 등을 수집, 생산 - 데이터뱅크 구축 및 연계
예방의학
역학
빅데이터
임상 연구 방법론

주식회사 디써클

대표 장재우,이윤구서울특별시 강남구 역삼로 169, 명우빌딩 2층 (TIPS타운 S2)대표 전화 0507-1312-6417이메일 info@rndcircle.io사업자등록번호 458-87-03380호스팅제공자 구글 클라우드 플랫폼(GCP)

© 2026 RnDcircle. All Rights Reserved.