准教授
篠崎 智大
Associate Professor
SHINOZAKI, Tomohiro
- 生物統計情報学コース
研究テーマ
- 生物統計学、疫学理論、因果推論
- 区分：
- 学環所属（基幹・流動教員）
- Biostatistics and bioinformatics course
Research Theme
- Biostatistics, Epidemiologic theory and Causal inference
- Position:
- III Faculty (Core & Mobile)
- 略歴
2009年3月 東京大学医学部健康科学・看護学科 卒業
2011年3月 東京大学大学院医学系研究科公共健康医学専攻専門職学位課程 修了
2012年4月 東京大学大学院医学系研究科健康科学・看護学専攻博士後期課程中途 退学
2012年5月 東京大学大学院情報学環／学際情報学府 助教
2012年11月 東京大学大学院医学系研究科 助教（配置換）
2019年4月 東京理科大学工学部情報工学科 講師
2023年4月 東京理科大学工学部情報工学科 准教授
2025年7月 東京大学大学院情報学環 准教授- 主要業績
- Researchmap: https://
researchmap.jp/she-knows-a-key
- Biography
Dr. Tomohiro Shinozaki is a biostatistician and associate professor at the Interfaculty Initiative in Information Studies, the University of Tokyo. He earned his Bachelor of Health Sciences (2009), Master of Public Health (2011), and Ph.D. in Health Sciences (2016), all from the University of Tokyo.
He began his academic career in 2012 as an assistant professor in both the Interfaculty Initiative in Information Studies and the Graduate School of Medicine at the University of Tokyo, where he specialized in biostatistics and epidemiology. He later held a faculty position in the Department of Information and Computer Technology at Tokyo University of Science from 2019 to 2025, serving as lecturer and then associate professor.
His research focuses on statistical methods for clinical, epidemiologic, and health sciences research, particularly causal inference in observational studies. His methodological interests include target trial emulation, marginal structural models, and causal survival analysis. He is actively engaged in collaborative research with clinicians and epidemiologists, and has authored numerous peer-reviewed publications.
研究テーマ：セミパラメトリック構造モデル、観察研究におけるバイアス、時間依存性曝露、動的治療レジメン、標的学習、最小限仮定によるリーン推測、標的試験エミュレーション、媒介分析
臨床・疫学・健康科学研究のデザインおよびデータ解析の方法論を追求する生物統計学を土台として、因果推論（causal inference）を中心とした理論研究と、臨床家や疫学者との協同を通した実証研究に取り組んでいます。医療者・疫学者・政策立案者との科学的な合意形成を目指す方法論として、理論的整合性に加えて、現実への接地を重視した統計的アプローチの開発・整理・実装を研究課題とします。
Research Theme: Semiparametric structural models; Biases in observational studies; Time-varying exposures; Dynamic treatment regimes; Targeted learning; Assumption-lean inference; Target trial emulation; Mediation; Mediation analyses
Building on biostatistics, which provides methodological foundations for study design and data analysis in clinical, epidemiologic, and health sciences research, I pursue both theoretical works centered on causal inference and empirical studies in close collaboration with clinicians and epidemiologists. My research focuses on developing, refining, and implementing statistical approaches that facilitate scientific consensus among healthcare professionals, epidemiologists and policymakers. These approaches emphasize not only theoretical coherence but also a strong grounding in real-world settings.