Y
Yamashita Yasuho
Researcher at Hitachi
Publications - 6
Citations - 343
Yamashita Yasuho is an academic researcher from Hitachi. The author has contributed to research in topics: Logistic regression & Linear model. The author has an hindex of 1, co-authored 6 publications receiving 91 citations.
Papers
More filters
Journal ArticleDOI
The PD-1 expression balance between effector and regulatory T cells predicts the clinical efficacy of PD-1 blockade therapies.
Shogo Kumagai,Yosuke Togashi,Takahiro Kamada,Eri Sugiyama,Hitomi Nishinakamura,Yoshiko Takeuchi,Kochin Vitaly,Kota Itahashi,Yuka Maeda,Shigeyuki Matsui,Takuma Shibahara,Yamashita Yasuho,Takuma Irie,Ayaka Tsuge,Shota Fukuoka,Akihito Kawazoe,Hibiki Udagawa,Keisuke Kirita,Keiju Aokage,Genichiro Ishii,Takeshi Kuwata,Kenta Nakama,Masahito Kawazu,Toshihide Ueno,Naoya Yamazaki,Koichi Goto,Masahiro Tsuboi,Hiroyuki Mano,Toshihiko Doi,Kohei Shitara,Hiroyoshi Nishikawa +30 more
TL;DR: A biomarker based on PD-1 positivity of effector and regulatory T cells in the tumor microenvironment that accurately predicts the effectiveness of checkpoint blockade in patients is developed.
Posted ContentDOI
Deep learning generates custom-made logistic regression models for explaining how breast cancer subtypes are classified
Takuma Shibahara,Chisa Wada,Yamashita Yasuho,Kazuhiro Fujita,Masamichi Sato,Atsushi Okamoto,Yoshimasa Ono +6 more
TL;DR: An explainable deep learning model called a point-wise linear model, which uses meta-learning to generate a custom-made logistic regression for each sample, and it was found that the point- Wise linear model used genes relevant to the cell cycle-related pathways.
Patent
Data analysis apparatus, data analysis method, and data analysis program
TL;DR: In this paper, a data analysis apparatus (300) executes: a selection process selecting a first variable group that is a trivial feature variable group contributing to prediction and a second feature data group other than the first feature variable groups from a set of feature variables; an operation process operating a first regularization coefficient related to a first weight parameter group corresponding to the first variable groups in such a manner that the loss function is larger, and operating a second regularization coefficients related to second weight parameter groups corresponding to second feature variables group in such an operation.
Patent
Time series data analysis apparatus, time series data analysis method and time series data analysis program
TL;DR: In this paper, the authors propose a time series data analysis apparatus that generates first internal data on the basis of first feature quantity data groups, a first internal parameter, and a first learning parameter.
Posted Content
A point-wise linear model reveals reasons for 30-day readmission of heart failure patients.
TL;DR: This is the first study on a deep-learning approach to explaining decisions behind readmission predictions and it provides an automatic patient stratification to explain cohorts of readmitted patients.