Kyoto University School of Public Health

Biostatistics and Data Science

face1Shigeyuki Matsui, Ph.D.

HOMEPAGE

The department aims to contribute to health sciences, through creating and practicing effective statistical and machine learning methods to solve important data science problems from a wide spectrum of biomedical researches.

Our department is carrying out many methodological researches on statistics and machine learning in biomedicine, including design and analysis of clinical trials and observational studies. The faculty members are also engaged in many medical research projects and continuously bridging statistical design and analysis to a wide variety of data science problems encountered in these projects. This also enables them to provide graduate students with the good practice of data science. Our graduates are expected to have leadership careers as researchers and practitioners in academic data science departments or data centers, government, and industry (hopefully, in the nation).

In response to many inquiries from overseas, we expect that candidate students from overseas will have, at least, a sufficient level of knowledge of statistics, machine learning theory and methodology, and programming skills. We welcome those who are expected to bring new possibilities to our department (especially in methodological research of biostatistics and machine learning), not those who just want to learn from us. We also assume that students will be able to secure their own academic and living expenses. Those considering applying to our doctoral program are required to submit in advance a detailed research plan that has been prepared based on a thorough literature review.

Research and Education

Our laboratory’s research themes are the design and data analysis of medical studies involving human subjects.
Some of the current methodological research themes are:

  • Analysis of heterogeneity in treatment effects in self-control and factorial studies
  • Adaptive clinical trial design and estimation of treatment effects
  • Selective reasoning after data-driven events
  • Active learning and adaptive experimental design in drug dose finding
  • Leveraging external control using transfer learning
  • Hierarchical and latent structure modeling of brain imaging data
  • Bayesian information borrowing meta-analysis using similar study sets
  • Evaluating the reliability and clinical usefulness of personalized medicine, including AI medicine

In addition to the methodological research mentioned above, we are also conducting many collaborative research projects with researchers in various disease areas (practicing data science in medicine and healthcare).

Recent Publications

  1. Seno K, Igeta M, Matsui K, Dimon T, Matsui S. Statistical and machine learning methods for phase I dose-finding design. In Handbook of Statistics in Clinical Oncology, 4th Edition. (eds. J. Crowley, A. Hoering, M. Othus), CRC Press, in press, 2025.
  2. Matsui S, Igeta M. Phase II and III clinical trial designs for precision medicine. In Handbook of Statistics in Clinical Oncology, 4th Edition. (eds. J. Crowley, A. Hoering, M. Othus), CRC Press, in press, 2025.
  3. Emoto R, Igeta M, Matsui K, Ishii K, Takamura T, Matsui S. Evaluating treatment-effect modifiers using data from randomized two-sequence, two-period crossover clinical trials: Application to a diabetes study. Journal of the Royal Statistical Society, Series C, in press, 2025.
  4. Emoto R, Nishikimi M, Shoaib M, Hayashida K, Nishida K, Kikutani K, Ohshimo S, Matsui S, Shime N, Iwami T. Prediction of prehospital change of the cardiac rhythm from nonshockable to shockable in out-of-hospital patients with cardiac arrest: A post hoc analysis of a nationwide, multicenter, prospective registry. Journal of the American Heart Association 2022; 11(12): e025048.
  5. Emoto R, Kawaguchi A, Takahashi K, Matsui S. Effect-size estimation using semiparametric hierarchical mixture models in disease-association studies with neuroimaging data. Computational and Mathematical Methods in Medicine 2020; Article ID 7482403.
  6. Matsui S, Crowley J. Biomarker-stratified phase III clinical trials: Enhancement with a subgroup-focused sequential design. Clin Cancer Res 2018; 24(5): 994-1001.
  7. Matsui S, Noma H, Qu P, Sakai Y, Matsui K, Heuck C, Crowley J. Multi-subgroup gene screening using semi-parametric hierarchical mixture models and the optimal discovery procedure: Application to a randomized clinical trial in multiple myeloma. Biometrics 2018; 74(1): 313-320.
  8. Toshiro Tango and Shigeyuki Matsui (eds.). Clinical Trial Encyclopedia. Asakura Shoten, 2023.
  9. Tango, T. and Matsui, S. (eds.). New Edition: Handbook of Medical Statistics. Asakura Shoten, 2018.
  10. Matsui S, Buyse M, Simon R. (eds). Design and Analysis of Clinical Trials for Predictive Medicine. CRC Press, 2015.

Biostatistics and Data Science

Shigeyuki Matsui (Professor)
Kota Matsui (Associate Professor)
Ryo Emoto (Designated Lecturer)
Kazuki Nishida (Assistant Professor)
URL: http://kbsd.med.kyoto-u.ac.jp/english/