Presentation | 2021-01-28 Consideration about Learning Scheme with Outlier Detection in Training Data for Prediction Model of Medication Effect Using Recurrent Neural Networks Yoshitomo Sakuma, Takumi Kobayashi, Chika Sugimoto, Ryuji Kohno, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, the application of machine learning to the medical and healthcare field has attracted attention. In particular, assisting general anesthesia during surgery and remote management of insulin administration for diabetic patients are research subjects that are attracting attention as applications of machine learning. In previous research, we have also proposed a method for predicting the dosing effect of anesthetics using a recurrent neural network (RNN), which is one of the methods of machine learning. However, if RNNs are learned using outliers (artifacts) included in vital data due to other vital, prediction accuracy is decreased. Therefore, in this study, we consider an outlier detection method for training data to realize dependable prediction the effect of medication on the human body using RNN. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Machine Learning / Prediction Model / Neural Network / Outlier Detection |
Paper # | MICT2020-27,MBE2020-32 |
Date of Issue | 2021-01-21 (MICT, MBE) |
Conference Information | |
Committee | MBE / MICT |
---|---|
Conference Date | 2021/1/28(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Takashi Watanabe(Tohoku Univ.) / Eisuke Hanada(Saga Univ.) |
Vice Chair | Ryuhei Okuno(Setsunan Univ.) / Hirokazu Tanaka(Hiroshima City Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) |
Secretary | Ryuhei Okuno(Akita-noken) / Hirokazu Tanaka(Kobe Univ.) / Daisuke Anzai(Yokohama National Univ.) |
Assistant | Akihiro Karashima(Tohoku Inst. of Tech.) / Jun Akazawa(Meiji Univ. of Integrative Medicine) / Keita Saku(Kyushu Univ.) / Kai Ishida(KISTEC) / Kento Takabayashi(Okayama Pref. Univ.) |
Paper Information | |
Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Healthcare and Medical Information Communication Technology |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Consideration about Learning Scheme with Outlier Detection in Training Data for Prediction Model of Medication Effect Using Recurrent Neural Networks |
Sub Title (in English) | |
Keyword(1) | Machine Learning |
Keyword(2) | Prediction Model |
Keyword(3) | Neural Network |
Keyword(4) | Outlier Detection |
1st Author's Name | Yoshitomo Sakuma |
1st Author's Affiliation | Yokohama National University(Yokohama National Univ.) |
2nd Author's Name | Takumi Kobayashi |
2nd Author's Affiliation | Yokohama National University(Yokohama National Univ.) |
3rd Author's Name | Chika Sugimoto |
3rd Author's Affiliation | Yokohama National University(Yokohama National Univ.) |
4th Author's Name | Ryuji Kohno |
4th Author's Affiliation | Yokohama National University(Yokohama National Univ.) |
Date | 2021-01-28 |
Paper # | MICT2020-27,MBE2020-32 |
Volume (vol) | vol.120 |
Number (no) | MICT-348,MBE-349 |
Page | pp.pp.28-33(MICT), pp.28-33(MBE), |
#Pages | 6 |
Date of Issue | 2021-01-21 (MICT, MBE) |