Risk Prediction of Diabetic Nephropathy via Interpretable Feature Extraction from EHR Using Convolutional Autoencoder
Katsuki, T.; Ono, M.; Koseki, A.; Kudo, M.; Haida, K.; Kuroda, J.; Makino, M.; Yanagiya, R.; Suzuki, A.
Studies in Health Technology and Informatics 247: 106-110
2018
ISSN/ISBN: 1879-8365 PMID: 29677932 Document Number: 696585
This paper describes a technology for predicting the aggravation of diabetic nephropathy from electronic health record (EHR). For the prediction, we used features extracted from event sequence of lab tests in EHR with a stacked convolutional autoencoder which can extract both local and global temporal information. The extracted features can be interpreted as similarities to a small number of typical sequences of lab tests, that may help us to understand the disease courses and to provide detailed health guidance. In our experiments on real-world EHRs, we confirmed that our approach performed better than baseline methods and that the extracted features were promising for understanding the disease.