Article
Machine learning for effectively avoiding overfitting is a crucial strategy for the genetic prediction of polygenic psychiatric phenotypes.
Translational psychiatry - 17 Aug 2020
Takahashi Yuta, Ueki Masao, Tamiya Gen, Ogishima Soichi, Kinoshita Kengo, Hozawa Atsushi, Minegishi Naoko, Nagami Fuji, Fukumoto Kentaro, Otsuka Kotaro, Tanno Kozo, Sakata Kiyomi, Shimizu Atsushi, Sasaki Makoto, Sobue Kenji, Kure Shigeo, Yamamoto Masayuki, Tomita Hiroaki
Abstract excerpt
The accuracy of previous genetic studies in predicting polygenic psychiatric phenotypes has been limited mainly due to the limited power in distinguishing truly susceptible variants from null variants and the resulting overfitting. A novel prediction algorithm, Smooth-Threshold Multivariate Genetic Prediction (STMGP), was applied to improve the genome-based prediction of psychiatric phenotypes by decreasing...
Read the complete abstract on PubMedTopics
Share this publication in a Topic to start or enrich a Post.